DOI: 10.3897/jucs.166567

Authors: Sava Stanisic, Borislav Djordjevic, Branislav Belotic, Olga Ristic, Ivan Tot, Kristina Zivanovic, Dimitrije Kolasinac

Abstract: he orchestration of microservices in distributed cloud environments poses significant challenges due to the heterogeneous nature of cluster nodes and dynamic workload patterns. Traditional scheduling strategies in Kubernetes often fail to optimize latency-sensitive applications effectively. This paper proposes a latency-aware orchestration framework that integrates reinforcement learning techniques to dynamically schedule and migrate microservices across heterogeneous Kubernetes clusters. The proposed approach leverages a deep Q-network (DQN) agent trained to minimize end-to-end response times while balancing resource utilization and avoiding service-level objective (SLO) violations. Experiments conducted on a hybrid testbed comprising virtual and physical nodes demonstrate that the reinforcement learning-based scheduler reduces latency by up to 25% compared to default Kubernetes scheduling policies. The results highlight the potential of intelligent orchestration methods to enhance performance in complex cloud-native deployments.

HTML

PDF

DOI: 10.3897/jucs.152399

Authors: Abdelhady Naguib, Abdulaziz Shehab

Abstract: The importance of localization algorithms is due to their uses in various wireless sensor network applications. A single anchor movement can be used to aid in localization to reduce the cost of using multiple anchors or equipping sensor nodes with GPS units, but the main challenge here is choosing the best path of movement while avoiding potential obstacles. This paper proposes a path planning algorithm called Square Spiral with Obstacle Avoidance (SQSPOA) which allows a mobile anchor node to track an optimal path while broadcasting its current coordinates to the unknown sensor nodes. During its movement, the mobile anchor node faces many obstacles that may hinder its mobility; but as a result of the superiority of the proposed algorithm the mobile anchor can avoid these obstacles while still broadcasting its coordinates to sensor nodes. The performance of the proposed algorithm was evaluated at the presence of variable-sized obstacles and was compared with recent path planning algorithms. Simulation results proved the superiority of the proposed algorithm with respect to localization error, percent of localized sensor node and trajectory length.

HTML

PDF

DOI: 10.3897/jucs.130529

Authors: Moulay Youssef Ichahane, Noureddine Assad, Hassan Ouahmane

Abstract: The diagnosis of rheumatoid arthritis (RA) diagnosis demands precise detection methods due to its complex symptomatology. This study presents a novel hybrid diagnostic framework that is the first to integrates Case-Based Reasoning (CBR) with deep learning and introduce three key innovations: (i) a dual-pathway architecture that combine electronic health records with imaging analysis, (ii) an Enhanced Clustering-Based K-nearest neighbors (ECB KNN) model for optimal feature selection, and (iii) a dynamic K-means clustering approach for handling class imbalance. We evaluated our framework using two comprehensive datasets: MIMIC-IV-Hosp, containing clinical data and MIMIC-CXR containing 377,110 chest X-ray images. The model employs a VGG16-based CNN for radiological feature extraction, with a particular focus on pulmonary manifestations, which is combined with our ECB KNN algorithm for patient-specific clinical data analysis. Using five-fold cross-validation, our framework is shown to achieve superior performance metrics (precision: 0.90-0.95, recall: 0.89-0.93, F1-score: 0.91) compared to baseline methods (traditional CNN: precision 0.82, recall 0.79; standard CBR: precision 0.85, recall 0.83). This significant improvement in diagnostic accuracy demonstrates the potential of our framework in terms of enhancing early RA detection and clinical decision support. The architecture of the model architecture is designed to allow for extensibility to other rheumatic conditions, thereby offering a comprehensive solution for multi-disease diagnosis in rheumatology.

HTML

PDF

DOI: 10.3897/jucs.139707

Authors: Chaimae Moumouh, José A. García-Berná, Begoña Moros, Juan M. Carrillo de Gea, Mohamed Yassin Chkouri, José L. Fernández-Alemán

Abstract: The impact of technology on improving health and well-being of individuals is remarkable. EHealth boosts the transition from paper-based health records to Electronic Health Records (EHRs). The use of EHRs can lead to improve quality of care, costs and time. In eHealth systems the health data is stored in digital form, and can be exchanged or accessed securely by authorised users. It is worth noting that medical data is considered very confidential information. However, the privacy and security of medical data remains a critical issue. Any leak or breach in security can lead to serious privacy damages for patients. Despite the safeguards, training courses and the consciousness on keeping data safe, the human error continues to be a problem. The main purpose of this paper is to present a bibliometric overview on the academic research related to privacy and security in EHRs. For this purpose, the papers of this study were searched in the Scopus. A period of 24 years was considered for selecting the papers. The information gathered in the database identified a total of 3,077 publications. Some key findings revealed that in the year 2015 the highest number of publications was produced. The Harvard Medical School was the most prolific institution with 2.44% papers from the total number of publications. A total of 97.21% of the documents were written in English. Finally, the results provided in this manuscript allowed us to make a picture on the current relevance in academic literature on privacy and security in EHRs.

HTML

PDF

DOI: 10.3897/jucs.141277

Authors: Kausthav Pratim Kalita, Debojit Boro, Dhruba Kumar Bhattacharyya

Abstract: Purpose: Big data applications enable organizations to derive actionable insights that inform strategic decision making and enhance operational efficiency in real time. Hadoop’s architecture features a distributed file system that stores voluminous data across multiple machines within a cluster. However, the management and control of access to this data can be viewed as centralized, as Hadoop relies on a central coordination system to manage tasks and resources across the cluster.Design / methodology / approach: To address the limitation in Hadoop, this paper proposes integrating blockchain technology to establish strict authentication procedures through smart contracts, enabling controlled access to the Hadoop platform. The proposed platform allows organizations to access Hadoop clusters through participation in a blockchain network, enabling efficient data storage mechanisms and model training capabilities.Findings: The performance of this integrated system is evaluated through simulations leveraging Ethereum based smart contracts. The findings suggest that implementing appropriate indexing mechanisms and hashing techniques can enable sufficient access control, thereby facilitating controlled access to Hadoop clusters. The paper presents the simulation results in terms of execution cost and execution time.Originality/value: This paper addresses the identified need for a transparent and reliable access control system that leverages blockchain’s smart contracts to enable controlled and restricted access to Hadoop clusters.

HTML

PDF

DOI: 10.3897/jucs.154672

Authors: Aleksandar Velinov, Aleksandra Mileva, Simon Volpert, Sebastian Zillien, Steffen Wendzel

Abstract: Network steganography has existed for several decades and it uses network traffic and network protocols as carriers for embedding secret messages in a stealthy manner. Quick UDP Internet Connections (QUIC) is a novel secure and reliable transport layer network protocol that is encapsulated in the User Datagram Protocol (UDP) and utilizes the Transport Layer Security Version 1.3 (TLSv1.3) standard. In addition, Hypertext Transfer Protocol Version 3 (HTTP/3) employs QUIC. In this paper, we present a systematic analysis of the covert channels that can be found in QUIC. Twenty novel covert channels are identified by applying the latest covert channel pattern based taxonomy, and an analysis of their transmission rate, undetectability, and robustness is presented, together with suggested countermeasures. A single covert channel is implemented as a proof of concept tool and is appropriately evaluated.

HTML

PDF

DOI: 10.3897/jucs.147898

Authors: Gustavo Lazarotto Schroeder, Wesllei Felipe Heckler, Rosemary Francisco, Jorge Luis Victória Barbosa

Abstract: Smartphone use has increased globally and has become essential in daily life. Although benefits exist, concerns arise about the negative effects of prolonged hyperconnectivity. The excessive use of smartphones combined with demographic and mental health related risk factors can lead to problematic smartphone use (PSU). PSU is characterized as the compulsive use of smartphones that disrupts an individual’s daily life, work, and relationships. Considering this scenario, the present paper proposes OntoKratos as an ontology designed to detect and prevent PSU. The ontology enables inferences, such as determining the individual’s mental health and PSU state, inferring context information, identifying PSU demographic and emotional risk factors, and suggesting interventions. OntoKratos includes 89 classes, 43 object properties, 35 data properties, and 1,113 axioms. Evaluations performed through a simulated dataset demonstrated the ontology’s effectiveness regarding PSU identification and interventions for PSU behaviors. Ontology’s rules allowed the definition of accurate axioms, improving the correct classification and inference of eight instantiated individuals. This study presents the first ontology for PSU identification and intervention suggestions on PSU behaviors. OntoKratos allows to identify and assist individuals by considering mental health and PSU status, inferring potential PSU risk factors, and providing tailored intervention suggestions to cope with PSU.

HTML

PDF

DOI: 10.3897/jucs.140979

Authors: Kadir Ileri, M. Şamil Balcı, Adem Dalcalı

Abstract: Energy harvesting is an effective solution, especially in scenarios with low power requirements, using sources such as magnetic fields, vibrations, and wind. This study focuses on predicting harvested power of toroidal electromagnetic energy harvesters using various machine learning methods, including Least Absolute Shrinkage and Selection Operator (Lasso), Adaptive Boosting (AdaBoost), K-Nearest Neighbors (KNN), Decision Tree (DT), Random Forest, Gradient Boosting Machine (GBM), Extreme Gradient Boosting (XGBoost), and Light Gradient Boosting Machine (LightGBM). To enhance the performance of these models, Artificial Bee Colony (ABC) optimization has been applied. The experiments were conducted using 1,300 trials across seven toroidal cores with varying sizes and magnetic permeabilities. During each experiment, the line current was varied between 0–100 A, and the resulting induced voltage and current were recorded. These measurements were used to create a comprehensive dataset named the Toroidal-Energy-Harvesting Dataset, enabling accurate power prediction. The performance of the machine learning models was assessed using statistical metrics, including R², MSE, MAE, and RMSE. Among the evaluated models, the ABC-optimized XGBoost (ABC-XGBoost) demonstrated the highest performance, achieving an R² value of 0.9993, an MSE of 247.1, an MAE of 9.8, and an RMSE of 15.7, indicating superior accuracy and minimal error. The comparative analysis clearly shows that proposed ABC-XGBoost outperformed the other models, making it the most effective solution for accurate power prediction in the Toroidal-Energy-Harvesting Dataset.

HTML

PDF

DOI: 10.3897/jucs.150679

Authors: Stefan Lengauer, Lin Shao, Hossein Miri, Michael Bedek, Cordula Kupfer, Maria Zangl, Bettina Kubicek, Barbara Dienstbier, Klaus Jeitler, Cornelia Krenn, Thomas Semlitsch, Carolin Zipp, Dietrich Albert, Andrea Siebenhofer, Tobias Schreck

Abstract: The effective and targeted provision of health information to consumers, specifically tailored to their needs and preferences, is indispensable in healthcare. With access to appropriate health information and adequate understanding, consumers are more likely to make informed and healthy decisions, become more proficient in recognizing symptoms, and potentially experience improvements in the prevention or treatment of their medical conditions. Most of today’s health information, however, is provided in the form of static documents. In this paper, we present a novel and innovative visual health information system based on adaptive document visualizations. Depending on the users’ information needs and preferences, the system can display its content with document visualization techniques at different levels of detail, aggregation, and visual granularity. Users can navigate using content organization along sections or automatically computed topics, and choose abstractions from full texts to word clouds. Our first contribution is a formative user study which demonstrated that the implemented document visualizations offer several advantages over traditional forms of document exploration. Informed from that, we identified a number of crucial aspects for further system development. Our second contribution is the introduction of an interaction provenance visualization which allows users to inspect which content, in which representation, and in which order has been received. We show how this allows to analyze different document exploration and navigation patterns, useful for automatic adaptation and recommendation functions. We also define a baseline taxonomy for adapting the document presentations which can, in principle, be leveraged by the observed user patterns. The interaction provenance view, furthermore, allows users to reflect on their exploration and inform future usage of the system.

HTML

PDF

DOI: 10.3897/jucs.137699

Authors: Wolfram Luther, Ashot Harutyunyan

Abstract: This article presents an extensive literature review on the importance of fairness in society, science, the world of work and leisure, with a focus on healthcare. Depending on the application area, fairness criteria and metrics play a major role in evaluation, classification, and allocation. Different approaches to a general definition of algorithmic fairness for individuals or groups are considered, and their measures from the perspective of the concerned sciences and requirements for the decision-making processes are also formulated. There are many reasons for the lack of fairness: inadequate data quality or low model performance, differences in understanding, competing standards, inappropriate measures in selection, classification and decision-making, lack of accuracy or performance of algorithms paired with insufficient communication, interaction or collaboration of stakeholders. The requirements are illustrated using the example of medical risk prediction tools, e.g., the individual and familial risk for the occurrence of pathogenic variants in BRCA1 (BReast CAncer 1) or BRCA2 genes with impact on early breast cancer (BC) and ovarian cancer (OC) disease, and the 5-year risk that an individual with ocular hypertension will develop Primary Open Angle Glaucoma (POAG), the leading global cause of irreversible blindness.

HTML

PDF

DOI: 10.3897/jucs.152864

Authors: Claudio Alvarez, Andres Carvallo, Gustavo Zurita

Abstract: As student cohorts grow, real-time case-based learning discussions generate increasing volumes of textual data, intensifying the orchestration load teachers must manage. Reviewing and providing feedback on student responses promptly becomes increasingly challenging, demanding efficient methods to assist educators in selecting relevant contributions to steer classroom discussions. This study proposes a low-footprint natural language processing (NLP) approach that leverages small-scale models running on commodity hardware, avoiding the computational overhead and cost associated with large language models. Our system, integrated into EthicApp, a collaborative learning platform, employs pre-trained language models such as the Universal Sentence Encoder (USE) and Bidirectional Encoder Representations from Transformers for Spanish (BETO), along with traditional text-mining techniques like Term Frequency-Inverse Document Frequency (TF-IDF). Through expert evaluations, we found that BETO exhibited superior performance in identifying relevant student responses but required GPU acceleration. At the same time, USE provided an efficient alternative that outperformed TF-IDF and remained feasible for CPU-based execution. Additionally, the methods showed a tendency—most notably BETO—to select longer responses, which, rather than introducing selection bias, was interpreted as an indicator of deeper student engagement. No significant semantic bias was found, ensuring a fair representation of students’ perspectives. Our findings suggest that low-footprint NLP can effectively reduce teacher orchestration load, enabling more targeted feedback without requiring extensive computational resources.

HTML

PDF

DOI: 10.3897/jucs.140463

Authors: Daniel Spiekermann

Abstract: The evolution of modern data centers from traditional hardware-based infrastructures to highly virtualized environments has introduced new complexities in network traffic analysis. Virtual networks, characterized by dynamic changes in both overlay and underlay architectures, necessitate sophisticated methods for accurate anomaly detection and network analysis. This paper investigates the real-world behaviour of network traffic within virtualized environments, identifying the key factors that impact packet dynamics, including VM operations, multi-tenancy, user customization, and hardware adjustments. By defining the frequency and nature of these events, this research provides further details for the creation of accurate packet generation tools. These tools must simulate the dynamic characteristics of virtual networks, enabling reliable and realistic synthetic data generation. The research explains the need for enhanced packet generation methodologies to provide valid training and testing data for digital investigations, anomaly detection, and network simulations. As a result, this paper emphasizes the importance of developing accurate synthetic network traffic that mirrors real-world conditions and provides a valid basement for traffic analysis in virtual networks.

HTML

PDF

DOI: 10.3897/jucs.137544

Authors: Igor Tomičić, Petra Grd, Andrija Bernik

Abstract: This paper presents a comprehensive analysis of the integration of artificial intelligence (AI) into threat intelligence (TI) systems, focusing on its potential to enhance cybersecurity operations. The paper presents an extensive literature review, covering the current state of AI applications in TI, including machine learning, deep learning, and natural language processing for automating threat detection, classification, and analysis. It outlines the core functions of AI in TI, such as threat detection, correlation, prediction, and automated response, and introduces a detailed taxonomy categorizing AI techniques based on their roles in enhancing TI processes. Additionally, the paper proposes a conceptual workflow for AI-powered TI, illustrating how AI can streamline data collection, threat analysis, and incident response. A roadmap for future research is further provided, highlighting key areas for development, including explainable AI, federated learning, and edge computing. This work contributes to the field by offering a structured framework for integrating AI into TI and identifying critical challenges and future directions in AI-driven cybersecurity.

HTML

PDF

DOI: 10.3897/jucs.167412

Authors: Yanling Chen

Abstract: In this paper, we show the problem of two-party privacy-preserving record linkage (PPRL) can be seen as an identification problem in Information Theory. We propose to apply the identification codes that are designed for identification via channels to the problem of PPRL, due to their advantage in the performance analysis, especially on a quantitative evaluation of the privacy. Note that for the PPRL, linkage quality is typically evaluated experimentally, whilst for privacy, there are so far no commonly accepted privacy measures available that allow an objective evaluation. Our approach of identification code provides an objective evaluation on both linkage quality and privacy based on parameters of employed identification codes.

HTML

PDF

DOI: 10.3897/jucs.164654

Authors: Wolfram Luther, A. J. Han Vinck

Abstract: This volume presents a conference paper selection from the 4th Workshop on Collaborative Technologies and Data Science in Smart City Applications (CODASSCA 2024): Data Science and Reliable Machine Learning, held in Yerevan, Armenia, October 3-6, 2024, https://codassca2024.aua.am/. The special issues guest editors invited five groups of authors from Armenia, Chile, Germany, the UK, and the USA to submit enlarged versions of their CODASSCA 2024 papers There was also a J.UCS open call so that any author could submit papers on the highlighted subjects. The invitation to review the 16 contributions received was accepted by 16 experts, and, after three rounds, seven articles were finally accepted for publication in the special issue.

HTML

PDF

DOI: 10.3897/jucs.129692

Authors: Pedro Henrique Dias Valle, Elisa Yumi Nakagawa

Abstract: Context: Software systems have become increasingly large and complex, and are required in several critical domains, including Industry 4.0, the military, smart cities, and transportation. Consequently, the architectural design of these systems becomes considerably complicated, in addition to requiring interoperability among diverse systems that sometimes comprise them. Problem: Although many interoperability architectural solutions exist, software architects have struggled to comprehend, analyze, and select the most suitable ones to solve their problems. Objective: This work provides a catalog of the main interoperability architectural solutions (patterns, styles, tactics, and approaches) for addressing the four levels of interoperability (namely, technical, syntactic, semantic, and organizational) to resolve interoperability issues in software systems. Method: 65 studies found systematically in the scientific literature were deeply examined and provided evidence to define our catalog, which comprises interoperability issues and architectural solutions to address these problems. Results: As a contribution, this catalog could help software architects better decide which architectural solutions could solve each interoperability issue in their integration projects.

HTML

PDF

DOI: 10.3897/jucs.128779

Authors: Carlos Goetz, Rodrigo Simon Bavaresco, Wesllei Felipe Heckler, Gustavo Lazarotto Schroeder, Rafael Kunst, Jorge Luis Victória Barbosa

Abstract: Stress is a mental disorder responsible for impacting the industry through psychosomatic illnesses, loss of productivity, and accidents caused by stressful workplaces. Conversely, the literature indicates that fostering mental well-being among workers can boost motivation and performance while alleviating symptoms of stress. The fourth industrial revolution incorporated technologies into work that allowed the automation of processes and control of environments. The fifth revolution introduced the application of research and innovation aimed at a human-centered consciousness, enabling the advancement of mental health through sensors and wearables. Despite advancements in stress classification technologies, there remain opportunities for further research into identifying stress motivators within industrial work environments. In this sense, this paper proposes an ontology to identify stressors considering personal and environmental data, allowing knowledge generation related to work stressors for mitigating the problem. The methodology utilized in this ontology development consisted of seven stages and two evaluation phases. The findings addressed four key questions related to competency as outlined in the model. The results revealed potential stressful scenarios, including the timing of occurrence, shared locations, environmental factors, and identifying groups experiencing moments of stress. This study presents as a scientific contribution the first ontology to address the identification of work-related stressors in the industrial environment.

HTML

PDF

DOI: 10.3897/jucs.122380

Authors: Maroua Benleulmi, Ibtissem Gasmi, Nabiha Azizi, Nilanjan Dey

Abstract: Recommender systems have a pivotal function in delivering customized and pertinent suggestions to clients on the basis of their preferences and activities. The present paper presents a thorough overview of deep learning-based recommender systems, explores their application to enhance performance, and overcomes limitations. The survey encompasses fundamental models of recommender systems; moreover, it also delves into key deep learning models. This discussion focuses on the effective integration of deep learning techniques into recommender systems. Real-world applications highlight the effectiveness of these approaches in capturing complex and nonlinear patterns from large-scale data. This paper concludes by reflecting on challenges encountered in this research field and outlines potential future directions, offering valuable insights for academics and professionals in the field of recommender systems based on deep learning.

HTML

PDF

DOI: 10.3897/jucs.150345

Authors: Francisco J. Quesada-Real, Francisco Moya-Pérez, Mercedes Rodriguez-Garcia, Bapi Dutta

Abstract: Tendering processes aim to provide transparency in the trade of services or goods but often fall short, leading to corruption and loss of trust. The emergence of Distributed Ledger Technologies (DLTs), such as blockchain, has prompted research into their application for enhancing transparency in tendering. However, adopting DLT usually incurs extra costs, network fees, and high carbon footprints. This paper conducts a Multi-Criteria Decision Making (MCDM) process to select the most suitable DLT for tendering processes. As a result, a novel tendering process based on IOTA is proposed, which improves transparency, ensures ecological sustainability, and avoids extra costs. The IOTA-based approach also fosters collaboration between human and computer capabilities in selecting the tender winner. Our method is compared with existing approaches, demonstrating the highest transparency.

HTML

PDF

DOI: 10.3897/jucs.150833

Authors: Manuel J. Barranco, Raciel Yera, Francisco J. Martínez

Abstract: In recent years, food recommendation systems have garnered significant attention from internet users seeking diets that are both appealing and health-promoting. For individuals managing chronic conditions such as diabetes, personalized food recommendations that consider both individual preferences and nutritional requirements could potentially yield substantial benefits in maintaining an appropriate dietary regimen. Even though previous research works have been covered the problem of food recommendation for the diabetes domain, they suffer from an insufficient use of the corresponding domain knowledge, and from a deficient management of user preferences in this process. This study then presents a novel preference-based food recommendation framework specifically adapted for patients with diabetes, and that mitigates such previous gaps. Experimental findings suggest that within this context, a balance can be achieved between appealing and health promotion, resulting in nutritionally appropriate menus that simultaneously align with users’ preferences.

HTML

PDF

DOI: 10.3897/jucs.150597

Authors: Juan Carlos Leyva López, Omar Alejandro Reyna Gutiérrez

Abstract: Customer-oriented marketing is a strategy that aims to recommend the right product(s) to the right customer(s). It is low-cost, low-risk, and profit-driven. It typically involves two components: customers and products. One of the critical challenges of targeted marketing is identifying products with potential market value for customers. In this paper, we studied an instance of this general problem. This paper finds the k-most preferable products (k-MPP) from a set of products under study to be offered to a customer for targeted marketing. We model the k-MPP problem as a multicriteria ranking problem and propose an algorithmic framework for customer-oriented marketing. Our framework utilizes a multicriteria outranking approach to solve the k-MPP problem. The framework's effectiveness is demonstrated by conducting a case study to find the k-most preferable restaurants for a customer in a Mexican city.

HTML

PDF

DOI: 10.3897/jucs.120860

Authors: Francisco Dominguez-Mateos, Vincent O’Brien, James Garland, Ryan Furlong, Daniel Palacios-Alonso

Abstract: In deep metric learning (DML) high-level input data are represented in a lower-level representation (embedding) space, such that samples from the same class are mapped close together, while samples from disparate classes are mapped further apart. In this lower-level representation, only a single inference sample from each known class is required to accurately discriminate between classes. To this end, embeddings trained for a specific task may contain additional feature information which can be used to go a level deeper into the discrimination task, i.e. allowing for feature sub-discrimination. This study takes an embedding trained to discriminate faces (identities) and uses the inherent feature information within the embedding to differentiate several attributes such as gender, age, and skin tone, without any additional training. This study is split into two cases; intra class discrimination where all the embeddings considered are from the same identity/in-dividual but with minor attributes such as beard/beardless, glasses/without glasses and emotions; and extra class discrimination where the embeddings represent different identities/people with more prominent attributes such as male/female, pale/dark tone, young/older. In the intra class sub-discriminant scenario, the inference process distinguishes common attributes and several artefacts of different identities, achieving 90.0% and 76.0% accuracy for beards and glasses, respectively. The system can also perform extra class sub-discrimination with a high accuracy rate, notably 99.3%, 99.3% and 94.1% for gender, skin tone, and age, respectively. To sum up, this work investigates the sub-discriminative capabilities of DML models by clustering discriminative features evident within the structure of DML embeddings.

HTML

PDF

DOI: 10.3897/jucs.115121

Authors: Mehtap Ülker, A. Bedri Özer

Abstract: With the development of deep learning techniques, many models have been proposed for abstractive text summarization. However, the problem of summarizing source documents while preserving their integrity persists due to token restrictions and the inability to adequately extract semantic word relations between different sentences. To overcome this problem, a fine-tuning BART-based model was proposed, which generates a scientific summary by selecting important words contained in the text in the input document. The input text consists of terminology and keywords from the source document. The proposed model is based on the working principle of graph-based methods. Thus, the proposed model can summarize the source document with as few words as possible that are relevant to the content. The proposed model was compared with baseline models and the results of human evaluation. The experimental results demonstrate that the proposed model outperforms the baseline methods with a 37.60 ROUGE-L score.

HTML

PDF

DOI: 10.3897/jucs.115016

Authors: Aluizio Haendchen Filho, Adson Marques da Silva Esteves, Hércules Antonio do Prado, Edilson Ferneda, André Luis Alice Raabe

Abstract: The high dropout rate in Information Technologies courses is a relevant problem in many countries, mainly because of the increasing demand for professionals in this sector. Usually, high dropout rates in these courses are related to difficulties in algorithms and programming subjects. Content recommendation systems are proposed to mitigate this problem, employing adaptive learning environments that facilitate the learning process. This study presents a content recommendation system that uses learning paths to group students and provide personalized recommendations based on peers' progress. The work follows the many efforts of group-based recommendation systems reported in the literature. The system uses intelligent agents and clustering algorithms to implement the recommendation system and was evaluated by submitting the simulation results to the judgment of human experts who significantly agreed with them. This initiative could make programming teaching more adaptive, using the groups' knowledge. Facilitating learning is one of the key issues to reduce dropout rates and resolve the shortage of labor in the technological area in Portuguese-speaking countries.

HTML

PDF

DOI: 10.3897/jucs.112725

Authors: Edward Kai Fung Dang, Robert Wing Pong Luk, Qing Li

Abstract: Traditional information retrieval models mostly adopt a term independence assumption and are based on single terms or unigrams. Past efforts have attempted to go beyond this assumption, such as by using contiguous terms (i.e. word n-grams) or terms appearing in proximity. One such approach employs pseudo-relevance feedback (PRF) in an extended BM25 model, with an expanded query containing bigrams and proximity word pairs besides unigrams. However, the benefit of this approach over the traditional unigram PRF remains inconclusive. We speculate the uncertain effectiveness of bigram PRF in this past work is due to: (1) The new bigrams obtained from the expanded query may be formed by pairing unigrams drawn from different documents. These are potentially noise instead of relevant concepts; (2) The collection statistics of n-grams needed to calculate the document ranking functions, such as their document frequency, is not available in retrieval. Only estimates of these quantities are used instead. We suggest that these issues may be overcome by extracting word n-grams as single units in query expansion, and employing a document index that contains both unigrams and word n-grams. We demonstrate the approach for the case of bigram PRF in an extended BM25. Retrieval experiments are conducted on a range of standard test collections. For the majority of tested collections, the difference between values of the evaluation metrics (Mean Average Precision and the precision-oriented NDCG@20) obtained by our bigram PRF and the unigram PRF baseline is not statistically significant. Thus, our bigram PRF fails to improve over unigram PRF robustly across collections. An analysis of our results reveals ‘query drift’ due to bigram query expansion terms that represent too-broad topics as a cause for the failure of our approach.

HTML

PDF

DOI: 10.3897/jucs.113095

Authors: Ujwala Thakur, Ankit Vidyarthi, Amarjeet Prajapati

Abstract: Recognizing and understanding human activities in real-time videos is a challenging task due to the complex nature of video data and the need for efficient and accurate analysis. This research pioneers a breakthrough in video activity recognition by introducing a robust framework leveraging the power of a stacked Bidirectional Long Short-Term Memory (Bi-LSTM) and Gated Recurrent Unit (GRU) architecture, harmonized within a fusion-based deep model. The stacked Bi-LSTM-GRU model capitalizes on its dual recurrent architecture, capturing nuanced temporal dependencies within video sequences. The fusion-based deep architecture synergizes spatial and temporal features, enabling the model to discern intricate patterns in human activities. To further enhance the discriminative power of the model, we introduce a fusion module in the proposed deep architecture. The fusion module integrates multi-modal features extracted from different levels of the network hierarchy, allowing for a more comprehensive representation of video activities. We demonstrate the efficacy of our approach through rigorous experimentation on UCF50, UCF101, and HMDB51 datasets. In experiments on the UCF50 dataset, our model achieves an accuracy of 97.01% and 95.86% on training and validation sets respectively, showcasing its proficiency in discerning activities across a diverse range of scenarios. The evaluation extends to the UCF101 dataset, where the proposed approach achieves a competitive accuracy of 97.62% and 96.93% on training and validation sets, surpassing previous benchmarks by a margin of approx 1%. Further-more, on the challenging HMDB51 dataset, the model demonstrates a robust accuracy of 89.71%and 88.88% on training and validation sets, solidifying its efficacy in intricate action recognition tasks.

HTML

PDF

DOI: 10.3897/jucs.116174

Authors: Farhad Lotfi, Branka Rodić, Aleksandra Labus, Zorica Bogdanović

Abstract: Background: Anxiety among students has become a fairly major problem. In the current era, Machine Learning (ML) can be used as a quick technology to predict students' anxiety with the high-level accuracy. Objectives: This research aims to predict university students' anxiety by using supervised learning algorithms with providing pertinent feedback. Methods: A total of 231 students from the University of Belgrade filled out the standard questionnaire called the State-Trait Anxiety Inventory (STAI). In addition, deeper information related to students’ anxiety like physical activity, Grade Point Average (GPA), and smoking cigarettes were collected. The Linear Regression algorithm was chosen to examine STAI using Python. Results: Linear regression as an appropriate algorithm was exploited for this purpose. The accuracy metric obtained by using the Mean Absolute Error (MAE), was 7.86 for state anxiety and 5.68 for trait anxiety. In addition, the Mean Squared Error (MSE) has also been calculated with state anxiety at 7.80, and trait anxiety at 9.66. Moreover, to find the factor with the highest impact after training, a regression analysis method (LASSO) was used. K-Nearest Neighbour (KNN) algorithm also checked the accuracy of training by overfitting and underfitting. Conclusion: The purpose of this study was the analysis of anxiety factors with the highest impact as well as the analysis of the STAI by linear regression to improve a smart healthcare model by discovering an acceptable output with the highest accuracy.

HTML

PDF

DOI: 10.3897/jucs.110173

Authors: Darwin Alulema, Maximiliano Paredes-Velasco, Ricardo de Arriba Lasso

Abstract: Teaching technical content in science and engineering requires the development of high-level competencies such as analytical and critical thinking skills, and is perceived by students as a difficult subject to understand. One way to help students learn this type of content is through the use of scaffolding, which dynamically regulates and adjusts learning according to the student’s needs. Although the use of scaffolding has already been applied in different educational contexts, so far there are no studies analysing its impact on students’ emotions and perception. In this paper we propose the LESCA system, which performs adaptive content feedback through scaffolding. The main hypothesis of this article is that the use of this tool together with teacher scaffolding improves the acquisition of content at higher cognitive levels and improves the student’s emotional state during learning. An experience has been carried out with 36 students of Industrial Electronics and Robotics Associate Degree with a pre-post design, where one group of students did not use the tool and another one did. The findings indicate that knowledge acquisition at the higher levels of Bloom’s taxonomy improved after the use of technological scaffolding and that this acquisition improved significantly when incorporating teacher scaffolding. On the other hand, students who performed the tasks with the system experienced significantly less anxiety and despair than students who did not use it. In addition, it has been found that students perceive teacher scaffolding to be significantly more useful than technological scaffolding.

HTML

PDF

DOI: 10.3897/jucs.105363

Authors: G.V.Vidya Lakshmi, S. Gopikrishnan

Abstract: Data in the Internet of Things (IoT) domain may be missing due to connectivity errors, environmental extremes, sensor malfunctions, and human errors. Despite the many approaches for imputing missing values, the most significant difficulty in terms of imputation precision or compute complexity for larger missing sub-sequences in uni-variate series is still being explored. This work introduced IMD-MP (Imputation of Missing Data using Matrix Profile), a new technique that improves imputation accuracy for big data analysis in IoT applications based on spatial-temporal correlations using a novel distance metric Matrix Profile Distance (MPD). Our method preserves spatial correlation by grouping the sensors present in the network (using grouping algorithm-GA) to impute the missing data of the failed sensor node. After grouping, similar sensor nodes to the failed sensor node are identified using the Node Similarity Algorithm (NSF). From its similar sensor data, a certain number of sub-sequences that are most similar to the one preceding the failed node’s missing values are gathered. These sub-sequences heights are optimized to ensure temporal correlation in the imputed data. To find the optimal imputation sequence, the current research uses MPD and similarity scores. Numerical findings using sensor data from real-time environmental mon-itoring and Intel data sets demonstrate the algorithm’s effectiveness compared to other benchmarks.

HTML

PDF

DOI: 10.3897/jucs.106979

Authors: George Marsicano, Edna Dias Canedo, Glauco V. Pedrosa, Cristiane S. Ramos, Rejane M. da C. Figueiredo

Abstract: Digital transformation in public administration needs to be accompanied by more dynamic and intelligent strategies, which effect cultural change. Inspired by the business culture of startups, in 2021 the Brazilian government created the StartUp GOV.BR program to develop and accelerate the development of digital transformation projects within the Federal Government. This program aims to make digital transformation processes more proactive and flexible and generate more profitable operations. In this work, we investigated the perception of ICT practitioners (members of startups) about the program and the issues that surround it. Our goal was to identify relations, potentialities and restrictions of this program to contribute to outlining growth strategies, as well as the assets and capabilities needed to successfully transform digital public services in a startup-based environment. For this purpose, we conducted 23 focus groups with up to 12 people, totaling 175 participants. Then, we fully transcribed and qualitatively analyzed the data from each of the focus groups based on Grounded Theory. As a result, we developed maps of relationships between categories, along with narratives that help explain and understand the members’ perception of the StartUp GOV.BR program. We also listed 34 points for improvement and 62 actions to be taken to improve the program. The results achieved in this work can contribute to a research agenda of initiatives towards the Digital Transformation of public services in governments around the world combining innovative digital strategies based on the perspective of professionals.

HTML

PDF

DOI: 10.3897/jucs.112790

Authors: Florian Skopik, Arndt Bonitz, Daniel Slamanig, Markus Kirschner, Wolfgang Hacker

Abstract: Military field operations place high demands on information and communication technology (ICT) devices, both in terms of reliability and security. These requirements include robustness against environmental influences such as vibrations, water, and humidity as well as protection against physical attacks and cyber-attacks. Attempts to compromise a device must be detected immediately, and if necessary, trigger automated countermeasures such as alarms, partial deactivation or emergency wiping of all data. In this work, we specifically focus on cyber security issues and aim to deliver a concept for a device that can be used in multiple security domains, isolating mission-specific data from each other without the risk of data spillover. For that purpose, we outline a high-level concept for a resilient single device concept that is able to withstand common intrusion attempts. We identify threat agents, misuse cases and the risks of a single device concept for multiple security domains and evaluate the most pressing issues. Based on the identified risks, we determine additional mitigation measures and discuss their applicability. We foresee our work to provide valuable insights into the requirements on and design decisions of highly secure mobile device solutions.

HTML

PDF

DOI: 10.3897/jucs.111677

Authors: André Fernandes, João Cruz, Miguel Mira da Silva, Rúben Pereira

Abstract: Organizations are under increasing pressure to comply with various rules, standards, and policies in today’s regulatory environment. Compliance controls are put in place to avoid legal or regulatory violations, which could lead to severe penalties, loss of reputation, and financial damages. However, these controls may have similar scopes and objectives, resulting in duplicated work and unnecessary costs for the organizations. To address this issue, researchers carry out the mapping and integration of these standards to avoid duplication, streamline compliance efforts, and identify best practices. Our work aims to improve the State-of-the-Art by exploring the main benefits and problems resulting from these processes, as well as identifying methods or artifacts that can be reused in the future. We focus on the fields of Risk, Security, and Business Continuity, as these are critical areas where compliance is crucial for organizations. Through our research, we have found that current methods of generating mapping artifacts are not only cumbersome to execute but also ineffective, as they output a single artifact without the reasoning behind it.

HTML

PDF

DOI: 10.3897/jucs.104838

Authors: Yilena Pérez-Almaguer, Edianny Carballo-Cruz, Yailé Caballero-Mota, Raciel Yera

Abstract: Recommender systems (RSs) are a relevant kind of artificial intelligence-based systems focused on providing users with the information that best fit their preferences and needs in a search space overloaded of possible options. Specifically, group recommender systems (GRSs) are a special type of RS centered on recommending items that are consumed in groups and not individually, being TV program and touristic packages key examples of such items. The current work is focused on proposing a content-based group recommendation approach (CB-GRS) contextualized to the restaurant recommendation domain. In contrast to previous content-based group recommendation models, the proposal incorporates novel stages such as restaurants feature imputation, the generation of a virtual group profile, the use of feature weighting, and the automatic selection of the most appropriate aggregation approach for composing group recommendations. The proposal is evaluated in an original recommendation scenario, related to restaurant from Havana City in Cuba, where several restaurant attributes are identified for applying the proposed CB-GRS approach. The experimental protocol evaluates individually each component of the proposal, evidencing their importance as part of the whole framework. Furthermore, the comparison with previous works has been also developed. The proposed approach can be applied in other recommendation scenarios, and in addition, the developed experimental protocol is generalizable for the evaluation of further content-based individual and group recommendation approaches in the tourism domain.

HTML

XML

PDF

DOI: 10.3897/jucs.104093

Authors: Bashar Alshouha, Jesus Serrano-Guerrero, David Elizondo, Francisco P. Romero, Jose A. Olivas

Abstract: The capability of offering patient-centered healthcare services involves knowing the consumer needs. Many of these needs can be conveyed through opinions about services that can be found on social networks. The consumers/patients can express their complains, satisfaction, frustration, etc. in terms of feelings and emotions toward those services; for that reason, it is pivotal to accurately detect them. There are many recent techniques to detect sentiments or emotions, but one of the most promising is transfer learning. This allows adapting a model originally trained for a task to a different one by fine-tuning. Following this idea, the primary objective of this research is to study whether several pre-trained language models can be adapted to a task such as patient emotion detection in an efficient manner. For this purpose, seven clinical and biomedical pre-trained models and four domain-general models have been adapted to detect multiple emotions. These models have been tuned using a dataset consisting of real patient opinions which convey several emotions per opinion. The experiments carried out state the domain-specific pre-trained models outperform the domain-general ones. Particularly, Clinical-Longformer obtained the best scores, 98.18% and 95.82% in terms of accuracy and F1-score, respectively. Analyzing the patient feedback available on social networks may provide valuable knowledge about consumer sentiments and emotions, especially for healthcare managers. This information can be very interesting for purposes such as assessing the quality of healthcare services or designing patient-centered services.

HTML

XML

PDF

DOI: 10.3897/jucs.103738

Authors: Yunwu Xu, Yan Li

Abstract: The objective of this work is to improve the existing Wireless Sensor Network coverage optimization method. The pigeon-inspired optimization algorithm was first evaluated, and its shortcomings were noted. The pigeon-inspired optimization method was then enhanced with the good point set, Yin-Yang optimization algorithm, and opposition-based learning. To test the improved algorithm, five representative standard functions were chosen: sphere function (f1), Rosenbrock function (f2), Levy function (f3), Schwefel function (f4), and Levy function N.13 (f5). The algorithm's speed of convergence may be determined by the first two functions, which are unimodal. The final three functions, which are multimodal, can extract several local optimal values from the local optimum. In comparison with other known algorithms, the improved Yin-Yang PIO algorithm showed the highest optimization accuracy and stability. Three sets of experiments were performed to optimize the WSN coverage with different parameters. The first series of experiments suggest that Yin–Yang PIO has the best optimization effect, with a coverage rate of 99.51% (10.22% higher with PIO and 6.41% higher compared with PSO). The second and third series of experiments show that Yin-Yang PIO significantly increased the WSN coverage ratio, up to 99.9%. The algorithm can be applied to optimize WSN coverage in various environments. Future research can extend the research scope to include other optimization problems in IoT.

HTML

XML

PDF

DOI: 10.3897/jucs.104938

Authors: Valdicélio Santos, Michel S. Soares

Abstract: Among the difficulties in developing software-intensive systems are the necessity of managing and controlling data that must be held for decades, as well as describing the needs and concerns of a variety of stakeholders. Therefore, one cannot neglect a good Software Engineering practice which is to develop software-intensive systems based on solid software architecture. However, the processes related to the software architecture of software-intensive systems are often considered only from a low level of abstraction. A recent architectural Standard, the ISO/IEC/IEEE 42020, defines 6 clauses for the architecture process, among them the Architecture Conceptual-ization process is the subject of this study. Considering that the ISO/IEC/IEEE 42020 has only recently been published, given the importance of establishing a well-defined software architecture, and considering the difficulties of understanding an architectural Standard, this work proposes a framework, and then the design and further evaluation of a web-based application to support soft-ware architects in using the activities and tasks of the Architecture Conceptualization clause based on the framework described. The ArchConcept was designed to address the high-level abstraction of the Standard ISO/IEC/IEEE 42020 and can be useful for software architects who want to follow ISO/IEC/IEEE 42020’s recommendation and achieve high-quality results in their work of software architecture conceptualization. A qualitative evaluation employing a questionnaire was carried out to obtain information about the perceptions of professionals regarding the ArchConcept, according to the Technology Acceptance Model (TAM). As ArchConcept is focused on activities of Archi-tecture Conceptualization, which is one of the early stages of a software project, the results found could be evidence of the short time dedicated to the initial phases of projects and their consequences.regarding the ArchConcept, according to the Technology Acceptance Model (TAM). As ArchConcept is focused on the early stages of the project (Architecture Conceptualization), the results found in this work could be evidence of the short time dedicated to the initial phase of projects and their consequences.

HTML

XML

PDF

DOI: 10.3897/jucs.97822

Authors: Herminia Beatriz Parra de Gallo, Marcela Vegetti

Abstract: This paper shows the research conducted to respond to a continuous requirement of justice regarding the application of scientifically supported forensic tools. Considering ontological engineering as the appropriate framework to respond to this requirement, the article presents OntoFoCE (Spanish abbreviation for Ontology for Electronic Mail Forensics), a specific ontology for the forensic analysis of emails. The purpose of this ontology is to help the computer expert in the validation of an email presented as judicial evidence. OntoFoCE is the fundamental component of the ObE Forensics (Ontology-based Email Forensics) tool. Although there are numerous forensic tools to analyze emails, the originality of the one proposed here lies in the implementation of semantic technologies to represent the traceability of the email transmission process. From that point on, it is possible to provide answers to the items of digital evidence subject to the expert examination. These answers make it possible to support these evidence items in the forensic analysis of an email and to guarantee the gathering of scientifically and technically accepted results that are valid for justice. Thus, the research question that is tried to be answered is: Is it possible to apply ontological engineering as a scientific support to design and develop a forensic tool that allows automatic answers to the evidence items subject to the expert examination in the forensic analysis of emails?

HTML

XML

PDF

DOI: 10.3897/jucs.101550

Authors: Anita Herrera, Ángel Arroyo, Alfredo Jiménez, Álvaro Herrero

Abstract: The analysis of Artificial Intelligence techniques and models used in the tourism sector provides insightful information for the management and innovation of this industry. In this paper, we conduct a comprehensive review of the different techniques and models, in regards to Artificial Intelligence when applied to the tourism industry. Specifically, we present a categorization of Artificial Intelligence applications used in different areas of tourism. The results allow to recognize valid studies and useful tools for the activation and growth of the tourism sector, an industry that represents a significant increase in the Gross Domestic Product of various economies and supports the development of life conditions for their inhabitants. Artificial Intelligence applications generate more personalized travel experiences, improve the efficiency of tourism services and strengthen the tourism competitiveness of the destination.

HTML

XML

PDF

DOI: 10.3897/jucs.112556

Authors: Nelson Baloian, Jonathan Frez, José A. Pino, Cristóbal Fuenzalida, Sergio Peñafiel, Belisario Panay, Gustavo Zurita, Horacio Sanson

Abstract: We present a methodology to handle the problem of planning sales goals. The methodology supports the retail manager to carry out simulations to find the most plausible goals for the future. One of the novel aspects of this methodology is that the analysis is based not on current sales levels, as most previous works do, but on those in the future, making a more precise and accurate analysis of the situation. The work presents the solution for a scenario using three sales performance indicators: foot traffic, conversion rate and ticket mean value for sales, but it explains how it can be generalized to more indicators. The contribution of this work is in the first place a framework, which consists of a methodology for performing sales planning, then, an algorithm, which finds the best prediction model for a particular store, and finally, a tool, which helps sales planners to set realistic sales goals based on the predicted sales. First we present the method to choose the best indicator prediction model for each retail store and then we present a tool which allows the retail manager estimate the improvements on the indicators in order to attain a desired sales goal level; the managers may then perform several simulations for various scenarios in a fast and efficient way. The developed tool implementing this methodology was validated by experts in the subject of administration of retail stores yielding good results.

HTML

XML

PDF

DOI: 10.3897/jucs.112797

Authors: Lorenz Gillner, Ekaterina Auer

Abstract: In this paper, we describe the requirements for traceable open-source data retrieval in the context of computation of BRCA1/2 mutation probabilities (mutations in two tumor-suppressor genes responsible for hereditary BReast or/and ovarian CAncer). We show how such data can be used to develop a Dempster-Shafer model for computing the probability of BRCA1/2 mutations enhanced by taking into account the actual age of a patient or a family member in an appropriate way even if it is not known exactly. The model is compared with PENN II and BOADICEA (based on undisclosed data), two established platforms for this purpose accessible online, as well as with our own previous models. A proof-of-concept implementation shows that set-based techniques are able to provide better information about mutation probabilities, simultaneously highlighting the necessity for ground truth data of high quality.

HTML

XML

PDF

DOI: 10.3897/jucs.113266

Authors: Kosuke Sasaki, Zhen He, Tomoo Inoue

Abstract: Distance learning has been expanding. Learner engagement is particularly important in project-based learning (PBL), but the interaction between teacher and learner and the understanding of learner status, including engagement, is not easy. This study aims to support teacher-learner communication based on learner engagement for remote PBL. In this paper, we propose the use of video activity reports by learners to estimate and understand learner engagement and to demonstrate its feasibility on the basis of the relationship between verbal and nonverbal information that can be obtained from video activity reports and learner engagement. Analysis of 232 video activity reports submitted by eight graduate students while working on remote research-based PBLs reveals that learner engagement decreases (1) when the report contained negative words, (2) when filled pauses were frequent or long, and (3) when silent pauses were infrequent or short. Furthermore, the feasibility of an AI-based support system is demonstrated through the design and implementation of a prototype.

HTML

XML

PDF

DOI: 10.3897/jucs.112604

Authors: Kheir Eddine Daouadi, Yaakoub Boualleg, Oussama Guehairia

Abstract: Nowadays, hate speech detection from Arabic tweets attracts the attention of many researchers. Numerous systems and techniques have been proposed to address this classification challenge. Nonetheless, three major limits persist: the use of deep learning models with an excess of hyperparameters, the reliance on hand-crafted features, and the requirement for a huge amount of training data to achieve satisfactory performance. In this study, we propose Contextual Deep Random Forest (CDRF), a hate speech detection approach that combines contextual embedding and Deep Random Forest. From the experimental findings, the Arabic contextual embedding model proves to be highly effective in hate speech detection, outperforming the static embedding models. Additionally, we prove that the proposed CDRF significantly enhances the performance of Arabic hate speech classification.

HTML

XML

PDF

DOI: 10.3897/jucs.112523

Authors: Claudio Gutiérrez-Soto, Patricio Galdames, Daniel Navea

Abstract: Social networks such as Twitter provide thousands of terabytes per day, which can be exploited to find relevant information. This relevant information is used to promote marketing strategies, analyze current political issues, and track market trends, to name a few examples. One instance of relevant information is finding cyclic behavior patterns (i.e., patterns that frequently repeat themselves over time) in the population. Because trending topics on Twitter change rapidly, efficient algorithms are required, especially when considering location and time (i.e., the specific location and time) during broadcasts. This article presents an efficient algorithm based on association rules to find cyclical patterns on Twitter, considering the inherent spatio-temporal attributes of data. Using a Hash Table enhances the efficiency of this algorithm, called HashCycle. Notably, HashCycle does not use minimum support and can detect patterns in a single run over a sequence. The processing times of HashCycle were compared to the Apriori (which is a well-known and widely used on diverse platforms) and Projection-based Partial Periodic Patterns (PPA) algorithms (which is one of the most efficient algorithms in terms of processing times). Empirical results from two spatio-temporal databases (a synthetic data set and one based on Twitter) show that HashCycle has more efficient processing times than two state-of-the-art algorithms: Apriori and PPA.

HTML

XML

PDF

DOI: 10.3897/jucs.112577

Authors: Wolfram Luther, Gregor Schiele

Abstract: This volume presents a selection of invited papers from the 3rd Workshop on Collaborative Technologies and Data Science in Smart City Applications (CODASSCA 2022): From Data to Information and Knowledge, held in Yerevan, Armenia, August, 23-25, and further articles from a free call for papers JUCS-CODASSCA-2023 published by Easychair. The workshop continues the cooperation between the University of Duisburg‐Essen (UDE) and the American University of Armenia (AUA) funded by the German Academic Exchange Service (DAAD) and the German Research Foundation (DFG). The workshop took place together with a one-week summer school on the topic Enhancements of Deep Learning for Intelligent Applications and the Connected Society.

HTML

XML

PDF

DOI: 10.3897/jucs.97170

Authors: Layse Santos Souza, Michel S. Soares

Abstract: A smart city is an urban centre that integrates a variety of solutions to improve infrastructure performance and achieve sustainable urban development. Urban roads are a crucial infrastructure highly demanded by citizens and organisations interested in their deployment, performance, and safety. Urban traffic signal control is an important and challenging real-world problem that aims to monitor and improve traffic congestion. The deployment of traffic signals for vehicles or pedestrians at an intersection is a complex activity that changes constantly, so it is necessary to establish rules to control the flow of vehicles and pedestrians. Thus, this article describes the joint use of the SmartCitySysML, a profile proposed by the authors, with TCPN (Timed Coloured Petri Nets) to refine and formally model SysML diagrams specifying the internal behaviour, and then verify the developed model to prove behavioural properties of an urban traffic signal control system.

HTML

XML

PDF

DOI: 10.3897/jucs.98674

Authors: Rasha R. Atallah, Ahmad Sami Al-Shamayleh, Mohammed A. Awadallah

Abstract: Facial recognition is a procedure of verifying a person's identity by using the face, which is considered one of the biometric security methods. However, facial recognition methods face many challenges, such as face aging, wearing a face mask, having a beard, and undergoing plastic surgery, which decreases the accuracy of these methods.This study evaluates the impact of plastic surgery on face recognition models. The motivation for conducting the research in that aspect is because plastic surgery treatments do not only change the shape and texture of any face but also have increased rapidly in this era. This paper proposes a model based on an artificial neural network with model-agnostic meta-learning (ANN-MAML) for plastic surgery face recognition. This study aims to build a framework for face recognition before and after undergoing plastic surgery based on an artificial neural network. Also, the study seeks to clarify the collaboration between facial plastic surgery and facial recognition software to determine the issues. The researchers evaluated the proposed ANN-MAML's performance using the HDA dataset. The experimental results show that the proposed ANN-MAML learning model attained an accuracy of 90% in facial recognition using Rhinoplasty (Nose surgery) images, 91% on Blepharoplasty surgery (Eyelid surgery) images, 94% on Brow lift (Forehead surgery) images, as well as 92% on Rhytidectomy (Facelift) images. Finally, the results of the proposed model were compared with the baseline methods by the researchers, which showed the superiority of the ANN-MAML over the baselines.

HTML

XML

PDF

DOI: 10.3897/jucs.94067

Authors: Luis P. Prieto, Gerti Pishtari, Yannis Dimitriadis, María Jesús Rodríguez-Triana, Tobias Ley, Paula Odriozola-González

Abstract: Recent advances in machine learning and natural language processing have the potential to transform human activity in many domains. The field of learning analytics has applied these techniques successfully to many areas of education but has not been able to permeate others, such as doctoral education. Indeed, doctoral education remains an under-researched area with widespread problems (high dropout rates, low mental well-being) and lacks technological support beyond very specialized tasks. The inherent uniqueness of the doctoral journey may help explain the lack of generalized solutions (technological or otherwise) to these challenges. We propose a novel approach to apply the aforementioned advances in computation to support doctoral education. Single-case learning analytics defines a process in which doctoral students, researchers, and computational elements collaborate to extract insights about a single (doctoral) learner's experience and learning process. The feasibility and added value of this approach are demonstrated using an authentic dataset collected by nine doctoral students over a period of at least two months. The insights from this exploratory proof-of-concept serve to spark a research agenda for future technological support of doctoral education, which is aligned with recent calls for more human-centred approaches to designing and implementing learning analytics technologies.

HTML

XML

PDF

DOI: 10.3897/jucs.91399

Authors: Mohammad Kchouri, Norharyati Harum, Hussein Hazimeh, Ali Obeid

Abstract: Falling is a critical issue for disabled people, and it leads to potentially serious injuries and death. Smart fall detection is a technology that depends on sensors and auxiliary devices that seek to improve the quality of life and enhance the lifestyle of disabled people. So far, the most widely used fall prediction methods collect data from inertial measurement unit (IMU) sensors. In addition, they use thresholds to identify falls based on artificial experiences or machine learning (ML) algorithms. Nonetheless, these approaches still require extensive classification and calibration. In this paper, we suggest a new technique to detect falls by combining Fuzzy Logic (FL) and Support Vector Machine (SVM). The FL model is built by using a fuzzy membership function along with the input dataset to obtain the intermediate output. Because combining these two algorithms is not an easy task, we leverage SVM with a kernel comprised of a fuzzy membership function and thus build a new model known as FSVM. Besides, the hyperplane of the SVM is used as the separating plane to replace the traditional threshold method for detecting falling Activities of Daily Living (ADLs) on a comprehensive dataset containing simulated falling ADLs, non-falling ADLs, and scripted ADLs, including falling ADLs and unscripted ADLs performed by volunteers with our designed device. The results show that no false-positive rate had been triggered, and 100% specificity was achieved for ADL. An overall accuracy of about 99.87% in detecting the fall function was obtained. Furthermore, the overall sensitivity of 100% with no false negative rate obtained was achieved by implementing the proposed method. The attained results validate that our introduced method can effectively learn from features extracted from a multiphase fall model.

HTML

XML

PDF

DOI: 10.3897/jucs.98824

Authors: Jaeyoung Yang, Sooin Kim, Sangwoo Lee, Won-gyum Kim, Donghoon Kim, Doosung Hwang

Abstract: The increased usage of the internet and ICT has posed a significant challenge to protect copyrighted content due to advanced image forgery techniques that make image authentication extremely difficult. The aim of this paper is to establish a binary classification method for determining copyright images from copyright-free ones. A deep hashing model is introduced for an image authentication system, which uses deep learning-based perceptual hashing. Hash codes from a deep hashing model trained with a copyright image dataset are used to identify images. The deep learning model is able to learn features that represent the implicit meaning or structural information of an image. The copyright dataset, which lacks class labels, is trained with deep hashing models with self-supervision. The proposed model is based on an autoencoder or variational autoencoder model and is improved by including convolutional filters, residual blocks, and vision transformer blocks. Experimental results show that the proposed model performs a one-to-one mapping with most stored images and can retrieve related images using image features in hash collisions. The model can find the query image among the top 5 images with comparable hash codes. The results indicate that the proposed deep hashing approach is robust and applicable.

HTML

XML

PDF

DOI: 10.3897/jucs.96013

Authors: Monika Lamba, Seema Verma, Pardeep Kumar

Abstract: Safety has become the primary concern for the air transportation system nowadays primarily due to increasing air traffic throughout the world. Various regulatory bodies have been maintaining enormous amount of aviation accidental data repositories. This past data is highly complex because of its many temporal and geographical components along with multiple variables. To be able to analyze this past data, there is always a need of user friendly and GUI based System. This article has proposed an intelligent vision-based decision-making system for the exploration of past aviation accidents and incidents dataset. The proposed visual query-based model is capable to analyse the major factors like flight phases, human factors, weather conditions and faulty components in particular aircraft models which are responsible for those unsafe events and may claim life of many passengers who are traveling and crew personnels. This model enables the users to express “what” visuals should be created instead of “how” to create them. Various case studies conducted through visual queries have proved that the system will be highly able to improve situational awareness regarding flight conditions to the crew members and air traffic controllers along with aviation authorities so that they are able to take timely decisions and deciding on what kind of training staff members need to reduce the consequences of such accidents and incidents.

HTML

XML

PDF

DOI: 10.3897/jucs.97112

Authors: Vimal Dwivedi, Mubashar Iqbal, Alex Norta, Raimundas Matulevičius

Abstract: Blockchain governs inter-organizational business processes and enables decentralized autonomous organizations (DAO) with governance capabilities via smart contracts (SC). Due to the programmer’s lack of prior knowledge of the contract domain, SCs are ambiguous and error-prone. Several works, i.e., SPESC, Symboleo, and SmaCoNat, exist to support the legally-binding SCs. The aforementioned SCLs present intriguing approaches to building legally-binding SCs but either lack domain completeness, or are intended for non-collaborative business processes. In our previous work, we address the above-mentioned shortcomings of the XML-based smart-legal-contract markup language (SLCML), in which blockchain developers focus on the contractual workflow rather than the syntax specifics. However, SLCML, as a blockchain-independent formal specification language, is not evaluated to determine its applicability, usefulness, and usability for establishing legally-binding SCs for workflow enactment services (WES) to automate and streamline the business processes within connected organizations. In accordance with this, we formally implement the SLCML and propose evaluation approaches, such as running case and lab experiments, to demonstrate the SLCML’s generality and applicability for developing legally-binding SCs. Overall, the results of this work ascertain the applicability, usefulness, and usability of the proposed SLCML for establishing legally-binding SCs for WES.

HTML

XML

PDF

DOI: 10.3897/jucs.85610

Authors: Achraf Boumhidi, Abdessamad Benlahbib, El Habib Nfaoui

Abstract: Reputation generation systems are decision-making tools used in different domains including e-commerce, tourism, social media events, etc. Such systems generate a numerical reputation score by analyzing and mining massive amounts of various types of user data, including textual opinions, social interactions, shared images, etc. Over the past few years, users have been sharing millions of tweets related to cryptocurrencies. Yet, no system in the literature was designed to handle the unique features of this domain with the goal of automatically generating reputation and supporting investors’ and users’ decision-making. Therefore, we propose the first financially oriented reputation system that generates a single numerical value from user-generated content on Twitter toward cryptocurrencies. The system processes the textual opinions by applying a sentiment polarity extractor based on the fine-tuned auto-regressive language model named XLNet. Also, the system proposes a technique to enhance sentiment identification by detecting sarcastic opinions through examining the contrast of sentiment between the textual content, images, and emojis. Furthermore, other features are considered, such as the popularity of the opinions based on the social network interactions (likes and shares), the intensity of the entity’s demand within the opinions, and news influence on the entity. A survey experiment has been conducted by gathering numerical scores from 827 Twitter users interested in cryptocurrencies. Each selected user assigns 3 numerical assessment scores toward three cryptocurrencies. The average of those scores is considered ground truth. The experiment results show the efficacy of our model in generating a reliable numerical reputation value compared with the ground truth, which proves that the proposed system may be applied in practice as a trusted decision-making tool.

HTML

XML

PDF

DOI: 10.3897/jucs.93533

Authors: Kashif Mehboob Khan, Warda Haider, Najeed Ahmed Khan, Darakhshan Saleem

Abstract: The amount of data is increasing rapidly as more and more devices are being linked to the Internet. Big data has a variety of uses and benefits, but it also has numerous challenges associated with it that are required to be resolved to raise the caliber of available services, including data integrity and security, analytics, acumen, and organization of Big data. While actively seeking the best way to manage, systemize, integrate, and affix Big data, we concluded that blockchain methodology contributes significantly. Its presented approaches for decentralized data management, digital property reconciliation, and internet of things data interchange have a massive impact on how Big data will advance. Unauthorized access to the data is very challenging due to the ciphered and decentralized data preservation in the blockchain network. This paper proposes insights related to specific Big data applications that can be analyzed by machine learning algorithms, driven by data provenance, and coupled with blockchain technology to increase data trustworthiness by giving interference-resistant information associated with the lineage and chronology of data records. The scenario of record tampering and big data provenance has been illustrated here using a diabetes prediction. The study carries out an empirical analysis on hundreds of patient records to perform the evaluation and to observe the impact of tampered records on big data analysis i.e diabetes model prediction. Through our experimentation, we may infer that under our blockchain-based system the unchangeable and tamper-proof metadata connected to the source and evolution of records produced verifiability to acquired data and thus high accuracy to our diabetes prediction model.

HTML

XML

PDF

DOI: 10.3897/jucs.90346

Authors: Seyedeh Mahsa Mirhoseini-Moghaddam, Mohammad Reza Yamaghani, Adel Bakhshipour

Abstract: In this study, a combined system of electronic nose (e-nose) and computer vision was developed for the detection of adulteration in extra virgin olive oil (EVOO). The canola oil was blended with the pure EVOO to provide adulterations at four levels of 5, 10, 15, and 20%. Data collection was carried out using an e-nose system containing 13 metal oxide gas sensors, and a computer vision system. Applying principal component analysis (PCA) on the e-nose-extracted features showed that 93% and 92% of total data variance was covered by the three first PCs generated from Maximum Sensor Response (MSR), Area Under Curve (AUC) features, respectively. Cluster analysis verified that the pure and impure EVOO samples can be categorized by e-nose properties. PCA-Quadratic Discriminant Analysis (PCA-QDA) classified the EVOOs with an accuracy of 100%. Multiple Linear Regression (MLR) was able to estimate the adulteration percentage with the R2 of 0.8565 and RMSE of 2.7125 on the validation dataset. Moreover, factor analysis using Partial Least Square (PLS) introduced the MQ3 and TGS2620 sensors as the most important e-nose sensors for EVOO adulteration monitoring. Application of Response Surface Methodology (RSM) on RGB, HSV, L*,a*, and b* as color parameters of the EVOO images revealed that the color parameters are at their optimal state in the case up to 0.1% of canola impurity, where the obtained desirability index was 97%. Results of this study demonstrated the high capability of e-nose and computer vision systems for accurate, fast and non-destructive detection of adulteration in EVOO and detection of food adulteration may be more reliable using these artificial senses.

HTML

XML

PDF

DOI: 10.3897/jucs.86563

Authors: Uma Priya D, P. Santhi Thilagam

Abstract: In recent years, the increased use of smart devices and digital business opportunities has generated massive heterogeneous JSON data daily, making efficient data storage and management more difficult. Existing research uses different similarity metrics and clusters the documents to support the above tasks effectively. However, extant approaches have focused on either structural or semantic similarity of schemas. As JSON documents are application-specific, differently annotated JSON schemas are not only structurally heterogeneous but also differ by the context of the JSON attributes. Therefore, there is a need to consider the structural, semantic, and contextual properties of JSON schemas to perform meaningful clustering of JSON documents. This work proposes an approach to cluster heterogeneous JSON documents using the similarity fusion method. The similarity fusion matrix is constructed using structural, semantic, and contextual measures of JSON schemas. The experimental results demonstrate that the proposed approach outperforms the existing approaches significantly.

HTML

XML

PDF

DOI: 10.3897/jucs.78240

Authors: Qusai Y. Shambour, Mosleh M. Abualhaj, Ahmad Adel Abu-Shareha

Abstract: Recent years have witnessed a rapid explosion of online information sources about restaurants, and the selection of an appropriate restaurant has become a tedious and time-consuming task. A number of online platforms allow users to share their experiences by rating restaurants based on more than one criterion, such as food, service, and value. For online users who do not have enough information about suitable restaurants, ratings can be decisive factors when choosing a restaurant. Thus, personalized systems such as recommender systems are needed to infer the preferences of each user and then satisfy those preferences. Specifically, multi-criteria recommender systems can utilize the multi-criteria ratings of users to learn their preferences and suggest the most suitable restaurants for them to explore. Accordingly, this paper proposes an effective multi-criteria recommender algorithm for personalized restaurant recommendations. The proposed Hybrid User-Item based Multi-Criteria Collaborative Filtering algorithm exploits users’ and items’ implicit similarities to eliminate the sparseness of rating information. The experimental results based on three real-word datasets demonstrated the validity of the proposed algorithm concerning prediction accuracy, ranking performance, and prediction coverage, specifically, when dealing with extremely sparse datasets, in relation to other baseline CF-based recommendation algorithms.

HTML

XML

PDF

DOI: 10.3897/jucs.79494

Authors: Robert Ehrensperger, Clemens Sauerwein, Ruth Breu

Abstract: Digital transformation impacts longstanding business models and enables enterprises to create new ones. This transformation leads to increased competition that forces enterprises to compete, not only between companies but also between the entire supply chain and business networks. The emerging concept of digital business ecosystems (DBE) allows enterprises to concentrate on network co-creation and co-evolution of bundled services and products across enterprise boundaries. This exploratory study introduces a maturity model derived from existing DBEs. Based on employing a design science methodology, we reviewed 22 scientific publications, interviewed 28 senior experts from practice and derived a maturity model from the results. We applied the maturity model through an online survey to 29 DBEs from different industry sectors and compared it with 22 maturity assessment approaches from other domains. The maturity model enables researchers to compare and assess existing DBEs and helps practitioners to identify areas for improvement in the collaboration within DBEs.

HTML

XML

PDF

DOI: 10.3897/jucs.86891

Authors: Aurora Polo-Rodríguez, Pietro Dionisio, Francesco Agnoloni, Ana Perandrés Gómez, Cristiano Paggetti, Lucía González López, Alfonso Cruz Lendínez, Macarena Espinilla-Estévez, Javier Medina-Quero

Abstract: Active ageing is a multidimensional process for achieving the potential quality of life and meaning in the life cycle. In the context of the Andalusian region in Spain, where the majority of the population is over 60 years old and lives in rural areas, it has become a key challenge. That is why the European projects within the Framework Programme for Research and Innovation, such as Pharaon - Pilots for Active and Healthy Ageing, promote technologies adapted by and for our elders. In the case of the Andalusian pilot, part of this project, we have selected a social network adapted to them, enabling them to communicate with the community at home and share their experiences. In addition, to improve their physical fitness, a device to count active minutes and steps is included, which provides users and caregivers with a visible and objective metric of daily health status. The technology has been evaluated following a well-defined methodology, which is described in this work to promote the deployment of technology in large-scale pilots. A specific architecture (Information System for Active Ageing in Andalusia - ISA3) and the components evaluated within a common ecosystem (Pharaon Project) are presented.

HTML

XML

PDF

DOI: 10.3897/jucs.79905

Authors: Fatemeh Farnaghi-Zadeh, Mohsen Rahmani, Maryam Amiri

Abstract: Feature selection plays an important role as a preprocessing step for pattern recognition and machine learning. The goal of feature selection is to determine an optimal subset of relevant features out of a large number of features. The neighborhood discrimination index (NDI) is one of the newest and the most efficient measures to determine distinguishing ability of a feature subset. NDI is computed based on a neighborhood radius (E). Due to the significant impact of E on NDI, selecting an appropriate value of E for each data set might be challenging and very time-consuming. This paper proposes a new approach based on targEt PointS To computE neIgh- borhood relatioNs (EPSTEIN). At first, all the data points are sorted in the descending order of their density. Then, the highest density data points are selected as many as the number of classes. To determine the neighborhood relations, the circles centered on the target points are drawn and the points inside or on the circles are considered to be neighbors. In the next step, the significance of each feature is computed and a greedy algorithm selects appropriate features. The performance of the proposed approach is compared to both the commonest and newest methods of feature selection. The experimental results show that EPSTEIN could select more efficient subsets of features and improve the prediction accuracy of classifiers in comparison to the other state-of-the-art methods such as Correlation-based Feature Selection (CFS), Fast Correlation-Based Filter (FCBF), Heuris- tic Algorithm Based on Neighborhood Discrimination Index (HANDI), Ranking Based Feature Inclusion for Optimal Feature Subset (KNFI), Ranking Based Feature Elimination (KNFE) and Principal Component Analysis and Information Gain (PCA-IG).

HTML

XML

PDF

DOI: 10.3897/jucs.81681

Authors: Ghazala Hcini, Imen Jdey, Hela Ltifi

Abstract: Malaria is a huge public health concern around the world. The conventional method of diagnosing malaria is for qualified technicians to visually examine blood smears for parasite-infected red blood cells under a microscope. This procedure is ineffective. It takes time and requires the expertise of a skilled specialist. The diagnosis is dependent on the individual performing the examination’s experience and understanding. This article offers a new and robust deep learning model for automatically classifying malaria cells as infected or uninfected. This approach is based on a convolutional neural network (CNN). It improved by the regularization method on a publicly available dataset which contains 27, 558 cell images with equal instances of parasitized and uninfected cells from the National Institute of health. The performance of our proposed model is 99.70% of accuracy and 0.0476 loss value.

HTML

XML

PDF

DOI: 10.3897/jucs.79777

Authors: Raoua Abdelkhalek, Imen Boukhris, Zied Elouedi

Abstract: Recommender Systems (RSs) are considered as popular tools that have revolutionized the e-commerce and digital marketing. Their main goal is predicting the users’ future preferences and providing accessible and personalized recommendations. However, uncertainty can spread at any level throughout the recommendation process, which may affect the results. In fact, the ratings given by the users are often unreliable. The final provided predictions itself may also be pervaded with uncertainty and doubt. Obviously, the reliability of the predictions cannot be fully certain and trustworthy. For the system to be effective, recommendations must inspire trust in the system and provide reliable and credible recommendations. The user may speculate about the uncertainty pervaded behind the given recommendation. He could tend to a reliable recommendation offering him a global overview about his preferences rather than an inappropriate one that contradicts his activities and objectives. While such imperfection cannot be ignored, traditional RSs are rarely able to deal with the uncertainty spreading around the prediction process, which may affect the credibility, the transparency and the trustworthiness of the current RS. Thus, in this paper, we opt for the uncertain framework of the belief function theory (BFT), which allows us to represent, quantify and manage imperfect evidence. By using the BFT, the users’ preferences and the interactions between the neighbors can be represented under uncertainty. Evidence from different information sources can then be combined leading to more reliable results. The proposed approach is a hybrid evidential movie RS that uses different data sources and delivers a personalized user-interface allowing a global overview of the possible future preferences. This representation would increase the users’ confidence towards the system as well as their satisfaction. Experiments are performed on MovieLens and their additional features provided by the Internet Movie Database (IMDb) and Rotten Tomatoes. The new approach achieves promising results compared to traditional approaches in terms of MAE, NMAE and RMSE. It also reaches interesting Precision, Recall and F-measure values of respectively, 0.782, 0.792 and 0.787.

HTML

XML

PDF

DOI: 10.3897/jucs.94162

Authors: Zhiling Yang

Abstract: Natural Language Processing (NLP) is an efficient method for enhancing educational outcomes. In educational settings, implementing NLP entails starting the learning process through natural acquisition. English teaching and learning have received increased attention from the relevant education departments as an integral aspect of the new curriculum reform. The environment of English teaching and learning is undergoing extraordinary changes as a result of the constant improvement and extension of teaching level and scale, as well as the growth of Internet information technology. As a result, the current research aims to look into techniques for efficiently using AI (artificial intelligence) apps to teach and learn English from the perspective of university students. This research can measure the levels as well as effectiveness of the employment of AI applications for teaching English based on deep learning techniques. There, the NLP based language enhancement has been carried out using Character-level recurrent neural network with back Propagation neural network (Cha_RNN_BPNN) based classification. With the help of this DL (deep learning) technique, it is possible to use AI methods to assist teachers in analysing and diagnosing students' English learning behaviour, replacing teachers in part to answer students' questions in a timely manner, and automatically grading assignments during the English teaching process. Experimental analysis shows Word Perplexity, Flesch-Kincaid (F-K) Grade Level for Readability, Cosine Similarity for Semantic Coherence, gradient change of NN, validation accuracy, and training accuracy of the proposed technique.

HTML

XML

PDF

DOI: 10.3897/jucs.94134

Authors: Loveleen Kumar, Manish Jain

Abstract: Image superresolution (SR) is the process of enlarging and enhancing a low-resolution image. Image superresolution helps in industrial image enhancement, classification, detection, pattern recognition, surveillance, satellite imaging, medical diagnosis, image analytics, etc. It is of utmost importance to keep the features of the low-resolution image intact while enlarging and enhancing it. In this research paper, a framework is proposed that works in three phases and generates superresolution images while keeping low-resolution image features intact and reducing image blurring and artifacts. In the first phase, image enlargement is done, which enlarges the low-resolution image to the 2x/4x scale using two standard algorithms. The second phase enhances the image using an AI-empowered Generative adversarial network (GAN). We have used a GAN with dual generators and named it EffN-GAN (EfficientNet-GAN). Fusion is done in the last phase, wherein the final improved image is generated by fusing the enlarged image and GAN output image. The fusion phase helps in reducing the artifacts. We have used the DIV2K dataset to train the GAN and further tested the results on the images of Set5, Set14, B100, Urban100, Manga109 datasets with ground truth of size 224x224x3. The obtained results were compared with the state-of-the-art superresolution approach based on important image quality parameters, namely, Peak signal-to--to-noise ratio (PSNR), Structural similarity index (SSIM), Visual information fidelity (VIF) image quality parameters. The results show that the proposed framework for generating super-resolution images from 2x/4x resolution downgraded images improves the aforementioned mentioned image quality parameters significantly.

HTML

XML

PDF

DOI: 10.3897/jucs.94161

Authors: Abhishek Kumar, Abdul Khader Jilani Saudagar, Mohammed AlKhathami, Badr Alsamani, Muhammad Badruddin Khan, Mozaherul Hoque Abul Hasanat, Ankit Kumar

Abstract: Virtual Reality (VR) has made considerable gains in the consumer and professional markets. As VR has progressed as a technology, its overall usefulness for educational purposes has grown. On the other hand, the educational field struggles to keep up with the latest innovations, changing affordances, and pedagogical applications due to the rapid evolution of technology. Therefore, many have elaborated on the potential of virtual reality (VR) in learning. This research proposes a novel techniques customized curriculum for medical students and recommendations for their learning process based on deep learning techniques. Here the data has been collected based on the pre-historic performance of the student and their current requirement and these data have been created as a dataset. Then this has been processed for analysis based on CAD system integrated with deep learning techniques for creating a customized curriculum. Initially this data has been processed and analysed to remove missing and invalid data. Then these data were classified for creation of the curriculum using a gradient decision tree integrated with naïve Bayes. From this, the customized curriculum has been generated. Based on this customized curriculum, the learning approach recommendation has been carried out using the fuzzy rules integrated knowledge-based recommendation system. The experimental results of the proposed technique have been carried out with an accuracy of 98%, specificity of 82%, F-1 score of 79%, information overload of 75%, and precision of 81%.

HTML

XML

PDF

DOI: 10.3897/jucs.94133

Authors: Ashok Kumar Saini, Roheet Bhatnagar, Devesh Kumar Srivastava

Abstract: Machine learning is a branch of computer science concerned with developing algorithms & models capable of ‘learning through data and iterations’. Deep learning simulates the structure and function of human organs and diseases using artificial neural networks with more than one hidden layer. The primary purpose of this work is to develop and test computer vision and machine learning algorithms for classifying Huanglongbing (HLB)-infected, healthy, and unhealthy leaves and fruits of the citrus plant. The images were segmented using a normalized graph cut, and texture information was extracted using a co-occurrence matrix. The collected attributes were used for classification and support vector machine (SVM), and deep learning methods were employed. When rating the classification outcomes, the accuracy of the classification and the number of false positives and false negatives were considered. The result shows that Deep Learning could create categories up to 96.8% of HLB-infected leaves and fruits. Despite a broad variance in intensity from leaves collected in North India, this method suggests it could be beneficial in diagnosing HLB.

HTML

XML

PDF

DOI: 10.3897/jucs.94132

Authors: Vijay Krishna Pallaw, Kamred Udham Singh

Abstract: The network’s convenience has created a copyright dilemma for some multimedia works. Nowadays, every healthcare system relies on digital medical images for diagnosis. These medical images are transmitted through communication channels, so there is a risk of tampering and copyright violation. A digital watermarking system can ensure and guarantee that tampering and copyright violation are prevented. This study presents a nonblind digital watermarking approach to X-ray medical images based on Contourlet transform (C.T.) and Slantlet Transform (SLT). Since the two-dimensional signals are represented flexibly by contourlet transforms, the contour plot can be used efficiently to represent curves and smooth contours. At the same time, the SLT has better time-localization & smoothness properties. The maximum energy of an image is conceived in the LL band if SLT transform are employed. Therefore, the LL band is used to entrench the watermark. The additive quantization method has been used to entrench the watermark. The efficiency of our scheme is assessed by different quality parameters and compared with several existing schemes. The results of the experiment show that the proposed scheme performs better and has the ability to resist several attacks.

HTML

XML

PDF

DOI: 10.3897/jucs.94160

Authors: Xin Ma

Abstract: Higher vocational education is a self-contained method of higher education that is aligned with global productivity and economic development. Its goal is to develop talented workers who contribute significantly to the economy and industry. Teaching analysis, teaching strategy, teaching practice, and assessment are all part of the course design process in high vocational education. Teaching assessment is one of the most effective methods for improving the quality of course teaching among teaching processes. This research proposes novel techniques in English teaching based on artificial intelligence for course selection based on students' feedback. Here, the dataset has been collected based on the students’ feedback on courses for Higher Vocational Education in English teaching. This dataset has been processed to remove invalid data, missing values, and noise. The processed data features have been dimensionality reduction integrated with K-means neural network. And the extracted features have been classified with higher accuracy using recursive elimination-based convolutional neural network. Based on this feedback data classification, recommendation for courses in Higher Vocational Education in English teaching has been suggested. The experimental analysis shows various students' feedback dataset validation and training in terms of accuracy of 96%, precision of 92%, recall of 93%, RMSE of 68%, and computational time of 65%.

HTML

XML

PDF

DOI: 10.3897/jucs.94127

Authors: Lalan Kumar, Kamred Udham Singh

Abstract: Watermarking is a valuable technique for verifying medical images obtained through the internet for diagnosis. There is a greater need for security in medical pictures with ever- increasing security risks. This research presented a Finite Ridgelet Transform (FRT)-Hessenberg based watermarking scheme in medical images. The suggested paradigm is divided into two stages. Before watermark insertion, FRT is applied to medical images. The coefficients are combined into blocks of 4 x 4 and each block is decomposed using Hessenberg decomposition. The second column of the Q matrix is used to insert the watermark using the additive quantization technique. The results obtained from our experiment have given good visual quality of the watermarked images. The high PSNR value 53.6121 and NC value 1.0 show that our scheme is performing better. Moreover, the performance of our scheme is robust against several attacks. The consequences of this result imply that the anticipated scheme is effective for medical image watermarking.

HTML

XML

PDF

DOI: 10.3897/jucs.94155

Authors: V D Ambeth Kumar, Vijayakumar Varadarajan, Mukesh Kumar Gupta, Joel J. P. C Rodrigues, Neha Janu

Abstract: We proposed the idea of editing a special issue that would compile the fruitful research that resulted from the stimulating discussions that occurred during the workshop that was held during the 5th International Conference on Intelligent Computing, Chennai on 25th & 26th March 2022. The objective of this special issue is to call for high-quality papers covering the latest data analytic concepts and technologies of big data and artificial intelligence. This special issue serves as a forum for researchers across the globe to discuss their work and recent advances in this field. The best papers from Artificial intelligence and Big Data Analytics (BAM) in the domains of Product, Finance, Health, and Environment were invited, peer-reviewed. The best high-quality papers were selected based on the innovativeness and relevance of the theme. The amount of data being generated and stored in various fields such as education, energy, environment, healthcare, fraud detection, and traffic is increasing exponentially in the modern era of Big Data. Simultaneously, there is a significant paradigm shift in business and society worldwide due to rapid advancements in fields such as artificial intelligence, machine learning, deep learning, and data analytics. This creates significant challenges for decision-making and the potential for transformation in areas such as the economy, government, and industry. Artificial Intelligence tools, techniques, and technologies, in conjunction with Big Data, improve the predictive power of the systems created and allow the government, public, and private sectors to discover new patterns and trends, as well as improve public values such as accountability, safety, security, and transparency to enable better decision-making, policies, and governance. They also have a wide range of capabilities to perform complex tasks that humans cannot. They could be used to collect, organize, and analyze large, diverse data sets to discover patterns and trends that address a variety of problems related to the development of the economy, such as identifying new sources of revenue, expanding the customer base for business, product reviews, and promotion, disease prediction and prevention, climatic variation prediction, and the provision of energy solutions. The wide variety of subject areas discussed at the 5th International Conference on Intelligent Computing is reflected in the seven accepted papers presented in the following section.

HTML

XML

PDF

DOI: 10.3897/jucs.85648

Authors: Marloes Vredenborg, Daan Sutmuller, Mariëlle den Hengst-Bruggeling, Judith Masthoff

Abstract: In homicide investigations, the growing availability of data results in an increasing amount of information and Persons of Interest (PoIs) that can be collected and incorporated during an investigation. This might result in information overload and increased tunnel vision during a homicide investigation. In this paper, we designed a system to support homicide investigations in such a way that it reduces information overload and tunnel vision. For evaluation purposes, we built a prototype that was filled with a fictional homicide investigation. A user study indicated that criminal investigators experienced a significantly low level of information overload and tunnel vision using the prototype. Moreover, the results showed acceptable usability and verbal statements indicated a largely positive attitude towards the prototype. This research clearly shows the opportunity to use interface design artefacts to support the prevention of information overload and tunnel vision.

HTML

XML

PDF

DOI: 10.3897/jucs.78884

Authors: Banani Ghose, Zeenat Rehena, Leonidas Anthopoulos

Abstract: The level of air pollution in smart cities plays a critical role in the community’s health and quality of life. Thus, air pollution forecasting would be beneficial and would guide citizens in avoiding exposure to dangerous emissions. The air health of a place can be diagnosed by close observation of the AQI (Air Quality Index) of that place. Moreover, the AQI of a place may have some influence on the pollutant concentration of the neighboring places. To address this issue, this work introduces a hybrid deep learning framework that is able to predict the values of a corresponding metric: AQI of smart cities. As a part of this work, two algorithms are proposed. The first one replaces the missing values in the dataset and the second one formulates the influence of the nearby places’ pollutant concentrations on the air quality of a particular place. A deep learning-based forecasting model is also proposed by combining 1D-CNN and Bi-GRU. To test the applicability of the framework, a large-scale experiment is carried out with the real-world dataset collected from New South Wales, Australia. Experimental results validate that the proposed framework provides a stable forecasting result, it confirms that the AQI of a place gets affected by the pollutant concentration of the nearby places and the comparison of forecasting result with the existing state of the art models shows that the proposed model outperforms the other models.

HTML

XML

PDF

DOI: 10.3897/jucs.72590

Authors: Jesus Serrano-Guerrero, Bashar Alshouha, Francisco P. Romero, Jose A. Olivas

Abstract: Online opinions/reviews contain a lot of sentiments and emotions that can be very useful, especially, for Internet suppliers which can know whether their services/products are meeting their customers’ expectations or not. To detect these sentiments and emotions, most applications resort to lexicon-based approaches. The major issue here is that most well-known emotion lexicons have been developed for English language; nevertheless, in other languages such as Arabic, there are fewer available tools, and many times, the quality of them is poor.The goal of this study is to compare the performance of two different types of algorithms, shallow machine learning-based and deep learning-based, when dealing with emotion detection in Arabic language. To improve the performance of the algorithms, two lexicons, which were originally developed in other languages and translated into Arabic language, have been used to add emotional features to different information models used to represent opinions. All approaches have been tested using the dataset SemEval 2018 Task 1: Affect in Tweets and the dataset LAMA+DINA. The semantic approaches outperform the classical algorithms, that is, the information provided by the lexicons clearly improves the results of the algorithms. Particularly, the BiLSTM algorithm outperforms the rest of the algorithms using word2vec. On the contrary to other languages, the best results were obtained using the NRC lexicon.

HTML

XML

PDF

DOI: 10.3897/jucs.80625

Authors: Derya Yiltas-Kaplan

Abstract: Software-defined networking (SDN) has emerged as a solution to the cumbersome structures of classical computer networks. It separates control and data planes to give independence to devices with respect to either traffic routing or network management. The two isolated planes communicate with each other via the help of software modules, which are located in an SDN controller, such as Floodlight, NOX, or Ryu. In this study, Floodlight is used and an SDN topology with 20 switches is constructed with Python code in Mininet. All algorithms have been coded with Java. The default routing algorithm in Floodlight is Dijkstra’s algorithm. Four different network optimization algorithms, namely Bellman-Ford, Ford-Fulkerson, Auction, and Dual Ascent algorithms, are utilized in ordinary network routing instead of Dijkstra’s algorithm. None of these four algorithms were used in SDN before and network implementations using Ford-Fulkerson, Auction, or Dual Ascent algorithms were scarce in the literature. The results are analyzed with multiple types of normalization on a new user interface communicating with Floodlight part via HTTP requests. There has not been a user interface that performs the same operations in Floodlight. In the future, this study may possibly be improved with considering normalization processes based on various proportions among the metric values and accounting the computational time of the algorithms.

HTML

XML

PDF

DOI: 10.3897/jucs.77793

Authors: Igor Tomicic, Markus Schatten, Vadym Shkarupylo

Abstract: This paper proposes an open ontology for self-sustainable human settlements in an effort to set the common language for modelling self-sustainable systems and address the issues regarding heterogeneity of physical devices, protocols, software components, data and message formats and other relevant factors, which proved to be unavoidable in implementations of smart systems in the domain of self-sustainability, smart homes, Internet of things, smart energy management systems, demand side systems, and related areas of research and engineering. Although the existing body of research is showing significant results in related, specialized research areas, currently there is no common formal language available which would bring the diversity of such research efforts under a single umbrella and thus enhance and integrate such efforts, which is often pointed out by the researchers in related fields. This paper discuses self- sustainable systems and associated areas, argues the need for the ontology development, presents its scope, development methodology, domain’s architecture and metamodel, and finally the proposed ontology itself, implemented in an open OWL format.

HTML

XML

PDF

DOI: 10.3897/jucs.67953

Authors: Julio Cesar Vale Neves, Luiz Enrique Zarate, Mark Alan Junho Song

Abstract: Due to the high complexity of real problems, a considerable amount of research that deals with high volumes of information has emerged. The literature has considered new applications of data analysis for high dimensional environments in order to manage the difficulty in extracting knowledge from a database, especially with the increase in social and professional networks. Tri- adic Concept Analysis (TCA) is a technique used in the applied mathematical area of data analysis. Its main purpose is to enable knowledge extraction from a context that contains objects, attributes, and conditions in a hierarchical and systematized representation. There are several algorithms that can extract concepts, but they are inefficient when applied to large datasets because the compu- tational costs are exponential. The objective of this paper is to add a new data structure, binary decision diagrams (BDD), in the TRIAS algorithm and retrieve triadic concepts for high dimen- sional contexts. BDD was used to characterize formal contexts, objects, attributes, and conditions. Moreover, to reduce the computational resources needed to manipulate a high-volume of data, the usage of BDD was implemented to simplify and represent data. The results show that this method has a considerably better speedup when compared to the original algorithm. Also, our approach discovered concepts that were previously unachievable when addressing high dimensional contexts.

HTML

XML

PDF

DOI: 10.3897/jucs.76535

Authors: Stefano Masneri, Ana Domínguez, Mikel Zorrilla, Mikel Larrañaga, Ana Arruarte

Abstract: Augmented reality is a technology that enhances human perception with additional, artificially generated sensory inputs. This creates new experiences enriching human vision by combining natural with digital elements. Augmented reality development dates back to the early sixties but it is only in the last decade, thanks to improvements to hardware and software, when it has begun to be rapidly incorporated in several fields, including education. This study presents a systematic review of the literature on the use of augmented reality applications in primary and secondary schools, with a specific focus on collaborative, multi-user and interactive applications. The aim of the study is to investigate the characteristics of such applications, the processes that led to their adoption, and their effectiveness in enhancing the learning experience. This study synthesises a set of 100 publications from 2015 to 2020 and performs a qualitative analysis of their content. The review describes the current state of the art in research in augmented reality for education and provides future research lines, as well as trends for the future of such applications in educational settings, analysing the relevance of the multi-user interaction challenge within the augmented reality ecosystem.

HTML

XML

PDF

DOI: 10.3897/jucs.69711

Authors: Nahia Ugarte, Mikel Larrañaga, Ana Arruarte

Abstract: Recommender Systems provide users with content or products they are interested in. The main purpose of Recommender Systems is to find, among the vast amount of information that is available or advertised on the Internet, content that meets the user’s needs i.e., a product or content that satisfies his or her wishes. These systems are being used more and more in many of the services of our daily lives. In this paper, a systematic mapping review that explores the use of Rec- ommender Systems in formal learning stages is presented. The paper analyzes what kinds of items the Recommender Systems suggest, who the users that receive the recommendations are, what kinds of information the Recommender Systems use to carry out the recommendation process, the algorithms and techniques the Recommender Systems employ and, finally, how the Recommender Systems have been evaluated. The results obtained in the review will make it possible to iden- tify not only the current situation in this field but also some of the challenges that are still to be faced.

HTML

XML

PDF

DOI: 10.3897/jucs.69377

Authors: Sedef Demirci, Seref Sagiroglu

Abstract: Social media platforms have become popular news sources thanks to their immense popularity and high speed of information dissemination. Using these platforms is essential for news organizations and journalists to track and discover news in digital journalism age. However, the abundance of meaningless data and the lack of organization on these platforms make it difficult to reach valuable news for journalists. In this paper, we create the first public dataset containing large number of real-world Turkish news tweets belonging to different news categories, to the best of our knowledge. We propose an artificial intelligence-based two-step approach to assist journalists for accessing the news shared by various sources on social media under the relevant categories like politics (elections, riots, etc.), health (pandemic, covid-19, etc.), etc. via a single platform by reducing the possibility of overlooking needed information. In the first step, we propose a machine learning based novel model for collecting and categorizing news posts on social media. We implement several traditional machine learning and deep learning based algorithms and evaluate their classification performance in terms of accuracy, precision, recall, and F1 score. In the second step, we develop a software tool, named TwitterBulletin, which automatically retrieves Turkish news tweets and groups them under news categories in real time by using the CNN classifier which achieves the best performance in the first step. The results show that the overall accuracy rate of TwitterBulletin is reasonably high and satisfactory despite the challenge of classifying short tweets.

HTML

XML

PDF

DOI: 10.3897/jucs.80750

Authors: Dagmara Łapczyńska, Konrad Łapczyński, Anna Burduk, Jose Machado

Abstract: The paper deals with a production scheduling process, which is a problematic and it requires considering a lot of various factors while making the decision. Due to the specificity of the production system analysed in the practical example, the production scheduling problem was classified as a Job-shop Scheduling Problem (JSP). The production scheduling process, especially in the case of JSP, involves the analysis of a variety of data simultaneously and is well known as NP-hard problem. The research was performed in partnership with a company from the automotive industry. The production scheduling process is a task that is usually performed by process engineers. Thus, it can often be affected by mistakes of human nature e.g. habits, differences in experience and knowledge of engineers (their know-how), etc. The usage of heuristic algorithms was proposed as the solution. The chosen methods are genetic and greedy algorithms, as both of them are suitable to resolve a problem that requires analysing a lot of data. The paper presents both approaches: practical and theoretical aspects of the usefulness and effectiveness of genetic and greedy algorithms in a production scheduling process.

HTML

XML

PDF

DOI: 10.3897/jucs.80743

Authors: Mariusz Topolski, Marcin Beza

Abstract: Feature engineering is a branch of science that provides tools to support, for example, the preparation of feature spaces for a pattern recognition task. The present work focuses on the problem of feature extraction. The proposed model is based on the mechanisms of PCA principal component analysis. It fills a gap in the implementation of feature extraction by looking for spaces that best discriminate between classes. This was realized by rotating the features according to the centroids of the classes. In addition, a measure of their consistency was determined which allows precise estimation of the number of features for a particular component. Four experiments were conducted in this study. The first two were done on synthetic datasets, while the next two were conducted on ten real datasets. The synthetic data allowed to determine the characteristics depending on the percentage of informative features, the number of input features, the level of imbalance and the number of output components in the extraction task. The obtained results showed that the developed solution allows for a more precise extraction, thus increasing the quality of classification. Moreover, it was shown that the method based on class centroids allows to construct efficient ensembles of classifiers.

HTML

XML

PDF

DOI: 10.3897/jucs.69069

Authors: Mahmut Ünver, Atilla Ergüzen, Erdal Erdal

Abstract: Information technologies have invaded every aspect of our lives. Distance education was also affected by this phase and became an accepted model of education. The evolution of education into a digital platform has also brought unexpected problems, such as the increase in internet usage, the need for new software and devices that can connect to the Internet. Perhaps the most important of these problems is the management of the large amounts of data generated when all training activities are conducted remotely. Over the past decade, studies have provided important information about the quality of training and the benefits of distance learning. However, Big Data in distance education has been studied only to a limited extent, and to date no clear single solution has been found. In this study, a Distributed File Systems (DFS) is proposed and implemented to manage big data in distance education. The implemented ecosystem mainly contains the elements Dynamic Link Library (DLL), Windows Service Routines and distributed data nodes. DLL codes are required to connect Learning Management System (LMS) with the developed system. 67.72% of the files in the distance education system have small file size (<=16 MB) and 53.10% of the files are smaller than 1 MB. Therefore, a dedicated Big Data management platform was needed to manage and archive small file sizes. The proposed system was designed with a dynamic block structure to address this shortcoming. A serverless architecture has been chosen and implemented to make the platform more robust. Moreover, the developed platform also has compression and encryption features. According to system statistics, each written file was read 8.47 times, and for video archive files, this value was 20.95. In this way, a framework was developed in the Write Once Read Many architecture. A comprehensive performance analysis study was conducted using the operating system, NoSQL, RDBMS and Hadoop. Thus, for file sizes 1 MB and 50 MB, the developed system achieves a response time of 0.95 ms and 22.35 ms, respectively, while Hadoop, a popular DFS, has 4.01 ms and 47.88 ms, respectively.

HTML

XML

PDF

DOI: 10.3897/jucs.74230

Authors: Luca Calderoni, Dario Maio, Paolo Palmieri

Abstract: In this paper we compare two probabilistic data structures for association queries derived from the well-known Bloom filter: the shifting Bloom filter (ShBF), and the spatial Bloom filter (SBF). With respect to the original data structure, both variants add the ability to store multiple subsets in the same filter, using different strategies. We analyse the performance of the two data structures with respect to false positive probability, and the inter-set error probability (the probability for an element in the set of being recognised as belonging to the wrong subset). As part of our analysis, we extended the functionality of the shifting Bloom filter, optimising the filter for any non-trivial number of subsets. We propose a new generalised ShBF definition with applications outside of our specific domain, and present new probability formulas. Results of the comparison show that the ShBF provides better space efficiency, but at a significantly higher computational cost than the SBF.

HTML

XML

PDF

DOI: 10.3897/jucs.67593

Authors: Florencia Vega, Guillermo Rodríguez, Fabio Rocha, Rodrigo Pereira dos Santos

Abstract: Agile Methods propose an approach for developing software based on an iterative and incremental life cycle model, in which needs and solutions evolve through collaboration between multi-functional and self-organized teams. As such, agile practices in work teams are gaining much momentum. To meet the demanding level of projects, agile software development also has to keep up with several challenges. In this context, software industry has chosen to use several tools to ease development and communication between different teams’ members. However, these tools generate overwhelming volumes of data that hamper decision-making by project managers. To address this issue, we present Scrum Watch, a tool-based approach that focuses on generating, through cloud-based technologies, graphic elements and reports that assist project managers with information to support decision making. Results obtained from an undergraduate Systems Engineering course through a capstone project confirm the feasibility of the proposed approach, which exploits the benefits of the availability and visualization of process and product metrics.

HTML

XML

PDF

DOI: 10.3897/jucs.71645

Authors: Roberto Cavicchioli, Riccardo Martoglia, Micaela Verucchi

Abstract: Exposing city information to dynamic, distributed, powerful, scalable, and user-friendly big data systems is expected to enable the implementation of a wide range of new opportunities; however, the size, heterogeneity and geographical dispersion of data often makes it difficult to combine, analyze and consume them in a single system. In the context of the H2020 CLASS project, we describe an innovative framework aiming to facilitate the design of advanced big-data analytics workflows. The proposal covers the whole compute continuum, from edge to cloud, and relies on a well-organized distributed infrastructure exploiting: a) edge solutions with advanced computer vision technologies enabling the real-time generation of “rich” data from a vast array of sensor types; b) cloud data management techniques offering efficient storage, real-time querying and updating of the high-frequency incoming data at different granularity levels. We specifically focus on obstacle detection and tracking for edge processing, and consider a traffic density monitoring application, with hierarchical data aggregation features for cloud processing; the discussed techniques will constitute the groundwork enabling many further services. The tests are performed on the real use-case of the Modena Automotive Smart Area (MASA).

HTML

XML

PDF

DOI: 10.3897/jucs.76983

Authors: Abdelhalim Hadjadj, Khaled Halimi

Abstract: The integration of the Internet of Things (IoT) technology and artificial intelligence has become essential in many aspects of daily life since the expansion of the communications and information field. Healthcare is one area that urgently needs to benefit from these technologies to keep up with the dramatic evolution of communications for contemporary human life. IoT, through wearable devices, provides real-time data related to the measurement of a person’s vital signs of health. However, for this data to become more relevant and valuable, it needs to be linked to other domains. Public transport is a domain related to the daily activity of people who take advantage of the IoT to provide exemplary transport services whose quality of service can greatly affect people’s health. The integration of these two domains offers many benefits, especially when providing services adapted to passengers’ health status, making them safer and healthier. This paper proposes an approach based on an IoT architecture using Semantic Web technologies; it aims to integrate health monitoring in public transport, provide passengers with quality transport services, and ensure continuous health monitoring. The use of Semantic Web technologies overcomes the lack of interoperability due to the heterogeneity of data collected by different devices and generated by two different domains. An experimental study was conducted, and the proposed approach’s results were compared with those obtained by the evaluation of a physician. The results show that the approach is effective and should allow passengers to benefit from appropriate transport services that better match their health status.

HTML

XML

PDF

DOI: 10.3897/jucs.77153

Authors: Nelson Baloian, Daniel Biella, Wolfram Luther, José Pino, Daniel Sacher

Abstract: This paper presents a survey of innovative concepts and technologies involved in virtual museums (ViM) that shows their advantages and disadvantages in comparison with physical museums. We describe important lessons learned during the creation of three major virtual museums between 2010 and 2020 with partners at universities from Armenia, Germany, and Chile. Based on their categories and features, we distinguish between content-, communication- and collaboration-centric museums with a special focus on learning and co-curation. We give an overview of a generative approach to ViMs using the ViMCOX metadata format, the curator software suite ViMEDEAS, and a comprehensive validation and verification management. Theoretical considerations include exhibition design and new room concepts, positioning objects in their context, artwork authenticity, digital instances and rights management, distributed items, private museum and universal access, immersion, and tour and interaction design for people of all ages. As a result, this survey identifies different approaches and advocates for stakeholders’ collaboration throughout the life cycle in determining the ViM's direction and evolution, its concepts, collection type, and the technologies used with their requirements and evaluation methods. The paper ends with a brief perspective on the use of artificial intelligence in ViMs.

HTML

XML

PDF

DOI: 10.3897/jucs.76602

Authors: Amit Kumar, Sonali Agarwal

Abstract: Social capital is an asset earned by people through their social connections. One of the motivations among developers to contribute to open source development and maintenance tasks is to earn social capital. Recent studies suggest that the social capital of the project has an impact on the sustained participation of the developers in open source software (OSS). One way to improve the social capital of the project is to help the developers in connecting with their peers. However, to the best of our knowledge, there is no prior research which attempts to predict future collaborations among developers and establish the significance of these collaborations on improving the social capital at the project level. To address this research gap, in this paper, we model the past collaborations among developers on version control system (VCS) and issue tracking system (ITS) as homogeneous and heterogeneous developer social network (DSN). Along with the novel path count based features, defined on proposed heterogeneous DSN, multifaceted proximity features are used to generate a feature set for machine learning classifiers. Our experiments performed on 5 popular open source projects (Spark, Kafka, Flink, WildFly, Hibernate) indicate that the proposed approach can predict the future collaborations among developers on both the platforms i.e. VCS as well as ITS with a significant accuracy (AUROC up to 0.85 and 0.9 for VCS and ITS respectively). A generic metric- recall of gain in social capital is proposed to investigate the efficacy of these predicted collaborations in improving the social capital of the project. We also concretised this metric on various measures of social capital and found that collaborations predicted by our approach have significant potential to improve the social capital at project level (e.g. Recall of gain in cohesion index up to 0.98 and Recall of gain in average godfather index up to 0.99 for VCS). We also showed that structure of collaboration network has an impact on the accuracy and usefulness of predicted collaborations. Since the past research suggests that many newcomers abandon the open source project due to social barriers which they face after joining the project, our research outcomes can be used to build the recommendation systems which might help to retain such developers by improving their social ties based on similar skills/interests.

HTML

XML

PDF

DOI: 10.3897/jucs.65918

Authors: Hamda Slimi, Ibrahim Bounhas, Yahya Slimani

Abstract: Fake news has invaded social media platforms where false information is being propagated with malicious intent at a fast pace. These circumstances required the development of solutions to monitor and detect rumor in a timely manner. In this paper, we propose an approach that seeks to detect emerging and unseen rumors on Twitter by adapting a pre-trained language model to the task of rumor detection, namely RoBERTa. A comparison against content-based characteristics has shown the capability of the model to surpass handcrafted features. Experimental results show that our approach outperforms state of the art ones in all metrics and that the fine tuning of RoBERTa led to richer word embeddings that consistently and significantly enhance the precision of rumor recognition.

HTML

XML

PDF

DOI: 10.3897/jucs.66979

Authors: José Monteiro, Maria Bernando, Mafalda Ferreira, Tânia Rocha

Abstract: In democratic countries, government websites became an important channel for interaction with the public administration in the last few years. Nevertheless, several issues have an impact on the way users access to content and information. Lack of accessibility and usability or, in the broad sense, lack of concern with user needs, can still be found in many government websites. To address the problem, a previous literature review on e-government information delivery attributes was performed. Based on this review, a large set of attributes related to quality was obtained to evaluate these dimensions in the context of e-government. The purpose of this study is to better understand which of these attributes are the most valued, in the users’ perspective, for evaluating content delivered by government websites. A qualitative approach was adopted, using Focus Group interviews as a strategy to obtain data and Thematic Analysis to analyze such data. The main results highlighted the attributes related to content delivery, interaction, and emotional aspects. User Experience, accessibility, and usability were prioritized by Focus Group participants.

HTML

XML

PDF

DOI: 10.3897/jucs.66714

Authors: Andrea Lezcano Airaldi, Jorge Andres Diaz-Pace, Emanuel Irrazábal

Abstract: Data-driven storytelling helps to communicate facts, easing comprehension and decision making, particularly in crisis settings such as the current COVID-19 pandemic. Several studies have reported on general practices and guidelines to follow in order to create effective narrative visualizations. However, research regarding the benefits of implementing those practices and guidelines in software development is limited. In this article, we present a case study that explores the benefits of including data visualization best practices in the development of a software system for the current health crisis. We performed a quantitative and qualitative analysis of sixteen graphs required by the system to monitor patients' isolation and circulation permits in quarantine due to the COVID-19 pandemic. The results showed that the use of storytelling techniques in data visualization contributed to an improved decision-making process in terms of increasing information comprehension and memorability by the system stakeholders.

HTML

XML

PDF

DOI: 10.3897/jucs.69750

Authors: Abdelouafi Ikidid, Abdelaziz El Fazziki, Mohammed Sadgal

Abstract: Artificial technologies are rapidly becoming one of the most powerful and popular technologies for solving complicated problems involving distributed systems. Nevertheless, their potential for application to advanced artificial transportation systems has not been sufficiently explored. This paper presents a traffic optimization system based on agent technology and fuzzy logic that aims to manage road traffic, prioritize emergency vehicles, and promote collective modes of transport in smart cities. This approach aims to optimize traffic light control at a signalized intersection by acting on the length and order of traffic light phases in order to favor priority flows and fluidize traffic at an isolated intersection and for the whole multi-intersection network, through both inter- and intra-intersection collaboration and coordination. Regulation and prioritization decisions are made on real-time monitoring through cooperation, communication, and coordination between decentralized agents. The performance of the proposed system is investigated by implementing it in the AnyLogic simulator, using a section of the road network that contains priority links. The results indicate that our system can significantly increase the efficiency of the traffic regulation system.

HTML

XML

PDF

DOI: 10.3897/jucs.74166

Authors: Armando Cruz, Hugo Paredes, Leonel Morgado, Paulo Martins

Abstract: Virtual worlds, particularly those able to provide a three-dimensional physical space, have features that make them suitable to support collaborative activities. These features distinguish virtual worlds from other collaboration tools, but current taxonomies of the field of Computer-Supported Cooperative Work do not account for several distinctive features of virtual worlds, namely those related with non-verbal communication. We intended to find out how the use of an avatar, gestures, spatial sounds, etc., influence collaboration in order to be able to include non-verbal communication in taxonomies of the field Computer-Supported Cooperative Work. Several cases of collaboration in virtual worlds are analysed, to find the impact of these non-verbal characteristics of virtual worlds. We proposed adding the concept of Presence to taxonomies of Computer-Supported Cooperative Work and contribute with guidance for future taxonomy development that includes it as a new dimension. This new dimension of Presence is subdivided into "avatar" and "physical space" subdimensions. In turn, these are divided into "physical appearance", "gestures, sounds and animations" and "focus, nimbus and aura"; "environment" and "objects / artefacts". This new taxonomy-development proposal may contribute to inform better design of virtual worlds in support of cooperative work.

HTML

XML

PDF

DOI: 10.3897/jucs.72314

Authors: Svatopluk Stolfa, Jakub Stolfa, Petr Simonik, Tomas Mrovec, Tomas Harach

Abstract: The paper is based on an experimental study at VSB TUO Ostrava with a DEMOCAR vehicle that simulates a real car with sensor fusion concept and a vehicle gateway to send and coordinate commands to ECUs to realize and manage autonomous driving. In this experimental study of autonomous driving vehicles control, a HARA (Hazard and Risk Analysis, ISO 26262:2018) has been done on vehicle level and strategies have been defined and implemented to manage safety situations where the car lateral control shall be hand over to a driver when in HAD 2 mode. The issue is that the switching to safe state shall not be done immediately but the vehicle has to stay in safe driving mode – fail-operational up to 4 seconds until a driver can take over. The UECE and other relevant studies show that it can take up to 6 seconds if driver/operator is not in the flow (HAD 3) and up to the 2 seconds when driver is in the flow (HAD 1). The paper makes assumptions and proposals about vehicle lateral control strategy to ensure the smooth take- over of the car by driver and its impact on control software development architectures.

HTML

XML

PDF

DOI: 10.3897/jucs.72333

Authors: Masao Ito

Abstract: There is no standard method for describing the Operational Design Domain (ODD) in automated driving vehicles. There are many elements in the operating domain, including the external environment, and it is necessary to connect them with the internal state of the automated driving system. Its content ultimately requires the user's understanding. The description method of this ODD is summarised from the aspect of safety. Consistency with standards and guidelines will also be considered.

HTML

XML

PDF

DOI: 10.3897/jucs.70326

Authors: Mathieu Briland, Fabrice Bouquet

Abstract: False data injection is an attack in which an attacker injects fabricated data into a system with the objective to change the behaviour and the decision-making of the system. Many industrial data-based devices are vulnerable to such attacks, this work presents an approach for testing False Data Injection Attack. This approach uses a Domain-Specific Language to generate altered data with two objectives, to provide sophisticated attacks scenarios to increase the resilience of vulnerable systems against False Data Injection Attack and to train detection tools.

HTML

XML

PDF

DOI: 10.3897/jucs.70330

Authors: Sara Qassimi, El Hassan Abdelwahed

Abstract: Research on digital cultural heritage has raised the importance of providing visitors with relevant assistance before and during their visits. With the advent of the social web, the cultural heritage area is affected by the problem of information overload. Indeed, a large number of available resources have emerged coming from the social information systems (SocIS). Therefore, visitors are swamped with enormous choices in their visited cities. SocIS platforms use the features of collaborative tagging, named folksonomy, to commonly contribute to the management of the shared resources. However, collaborative tagging uses uncontrolled vocabulary which semanti- cally weakens the description of resources, consequently decreases their classification, clustering, thereby their recommendation. Therefore, the shared resources have to be pertinently described to ameliorate their recommendations. In this paper, we aim to enhance the cultural heritage visits by suggesting semantically related places that are most likely to interest a visitor. Our proposed approach represents a semantic graph-based recommender system of cultural heritage places through two steps; (1) constructing an emergent semantic description that semantically augments the place and (2) effectively modeling the emerging graphs representing the semantic relatedness of similar cultural heritage places and their related tags. The experimental evaluation shows relevant results attesting the efficiency of the proposed approach.

HTML

XML

PDF

DOI: 10.3897/jucs.70369

Authors: Xabier Larrucea, Micha Moffie, Dan Mor

Abstract: Since the emergence of GDPR, several industries and sectors are setting informatics solutions for fulfilling these rules. The Health sector is considered a critical sector within the Industry 4.0 because it manages sensitive data, and National Health Services are responsible for managing patients’ data. European NHS are converging to a connected system allowing the exchange of sensitive information cross different countries. This paper defines and implements a set of tools for extending the reference architectural model industry 4.0 for the healthcare sector, which are used for enhancing GDPR compliance. These tools are dealing with data sensitivity and data hiding tools A case study illustrates the use of these tools and how they are integrated with the reference architectural model.

HTML

XML

PDF

DOI: 10.3897/jucs.68384

Authors: Fabian Honegger, Yuan Feng, Matthias Rauterberg

Abstract: Adequate use of multimodal stimuli plays a crucial role in help forming the sense of presence within a virtual environment. While most of the presence research attempts to engage more sensory modalities to induce a higher sense of presence, this paper investigates the relevance of each sensory modality and different combinations on the subjective sense of presence using a specifically designed scenario of a passive experience. We chose a neutral test scenario of “waiting at a train station while a train is passing by” to avoid the potential influence of story narrative on mental presence and replicated realistic multimodal stimuli that are highly relevant to our test setting. All four stimuli - visual, auditory, vibration, and draught - with 16 possibilities of combinations were systematically evaluated with 24 participants. The evaluation was performed on one crucial aspect of presence – “realness” to reflect user presence in general. The perceived realism value was assessed using a scalometer. The findings of main effects indicate that the auditory stimuli had the most significant contribution in creating the sense of presence. The results of interaction effects suggest the impact of draught stimuli is significant in relation to other stimuli - visual and auditory. Also, the gender effects revealed that the sense of presence reported by female participants is influenced by more factors than merely adding more sensory modalities.

HTML

XML

PDF

DOI: 10.3897/jucs.67701

Authors: Timothy Read, Agnes Kukulska-Hulme, Elena Barcena, John Traxler

Abstract: An extensive literature exists on how to help students learn languages. The learning process is particularly challenging since it combines different types of knowledge and skills into a dual process of comprehension and production, using both oral and written modalities. Networked technology has led to the emergence of different types of learning that can be applied to languages. In this article three of these types are highlighted as being particularly useful for language learning, as can be seen by their impact in the literature, namely mobile, open and social learning. After an analysis of each one, a proposal is made to combine them into a single framework called Mobile Open Social Learning for Languages (or MOSL4L). It is subsequently characterized using Activity Theory and some suggestions are made for establishing a rubric that could enable language learning scenarios to be analyzed in terms of the constituent parts that define their nature and enable the causal relations with learning to be highlighted.

HTML

XML

PDF

DOI: 10.3897/jucs.67046

Authors: Marcelo Aires Vieira, Elivaldo Lozer Fracalossi Ribeiro, Daniela Barreiro Claro, Babacar Mane

Abstract: With the growth of cloud services, many companies have begun to persist and make their data available through services such as Data as a Service (DaaS) and Database as a Service (DBaaS). The DaaS model provides on-demand data through an Application Programming Inter- face (API), while DBaaS model provides on-demand database management systems. Different data sources require efforts to integrate data from different models. These model types include unstructured, semi-structured, and structured data. Heterogeneity from DaaS and DBaaS makes it challenging to integrate data from different services. In response to this problem, we developed the Data Join (DJ) method to integrate heterogeneous DaaS and DBaaS sources. DJ was described through canonical models and incorporated into a middleware as a proof-of-concept. A test case and three experiments were performed to validate our DJ method: the first experiment tackles data from DaaS and DBaaS in isolation; the second experiment associates data from different DaaS and DBaaS through one join clause; and the third experiment integrates data from three sources (one DaaS and two DBaaS) based on different data type (relational, NoSQL, and NewSQL) through two join clauses. Our experiments evaluated the viability, functionality, integration, and performance of the DJ method. Results demonstrate that DJ method outperforms most of the related work on selecting and integrating data in a cloud environment.

HTML

XML

PDF