Latest Articles from JUCS - Journal of Universal Computer Science Latest 19 Articles from JUCS - Journal of Universal Computer Science https://lib.jucs.org/ Fri, 29 Mar 2024 18:02:56 +0200 Pensoft FeedCreator https://lib.jucs.org/i/logo.jpg Latest Articles from JUCS - Journal of Universal Computer Science https://lib.jucs.org/ Transfer Learning with EfficientNetV2S for Automatic Face Shape Classification https://lib.jucs.org/article/104490/ JUCS - Journal of Universal Computer Science 30(2): 153-178

DOI: 10.3897/jucs.104490

Authors: Petra Grd, Igor Tomičić, Ena Barčić

Abstract: The classification of human face shapes, a pivotal aspect of one’s appearance, plays a crucial role in diverse fields like beauty, cosmetics, healthcare, and security. In this paper, we present a multi-step methodology for face shape classification, harnessing the potential of transfer learning and a pretrained EfficientNetV2S neural network. Our approach comprises key phases, including preprocessing, augmentation, training, and testing, ensuring a comprehensive and reliable solution. The preprocessing step involves precise face detection, cropping, and image scaling, laying a solid foundation for accurate feature extraction. Our methodology utilizes a publicly available dataset of female celebrities, comprising five face shape classes: heart, oblong, oval, round, and square. By augmenting this dataset during training, we magnify its diversity, enabling better generalization and enhancing the model’s robustness. With the EfficientNetV2S neural network, we employ transfer learning, leveraging pretrained weights to optimize accuracy, training speed, and parameter size. The result is a highly efficient and effective model, which outperforms state-of-the-art approaches on the same dataset, boasting an outstanding overall accuracy of 96.32%. Our findings demonstrate the efficiency of our approach, proving its potential in the field of face shape classification. The success of our methodology holds promise for various applications, offering valuable insights into beauty analysis, cosmetic recommendations, and personalized healthcare.

HTML

XML

PDF

]]>
Research Article Wed, 28 Feb 2024 16:00:02 +0200
Dimensionality Reduction for Hierarchical Multi-Label Classification: A Systematic Mapping Study https://lib.jucs.org/article/91309/ JUCS - Journal of Universal Computer Science 30(1): 130-150

DOI: 10.3897/jucs.91309

Authors: Raimundo Osvaldo Vieira, Helyane Bronoski Borges

Abstract: Hierarchical multi-label classification problems typically deal with datasets with many attributes and labels, which can negatively impact the classifier performance. The application of dimensionality reduction methods can significantly improve the performance of classifiers. Dimensionality reduction can be performed by feature extraction or feature selection, according to the problem domain and datasets characteristics. This work carried out a systematic literature mapping to identify the approaches and techniques of dimensionality reduction that have been used in hierarchical multi-label classification tasks. Searches were performed on 7 important databases for the Computer Science field. From a list of 184 retrieved papers, 12 were selected for analysis, from which it was possible to determine a general overview of studies conducted from 2010 to 2022. It was identified that feature selection was the most frequent reduction method, with filter approach standing out. In addition, it was detected that most of the works used tree hierarchical structure. As its main outcome, this paper presents the state of the art of dimensionality reduction problem for hierarchical multi-label classification, indicating trends and research issues in the field.

HTML

XML

PDF

]]>
Research Article Sun, 28 Jan 2024 16:00:07 +0200
OBLEA: A New Methodology to Optimise Bluetooth Low Energy Anchors in Multi-occupancy Location Systems https://lib.jucs.org/article/96878/ JUCS - Journal of Universal Computer Science 29(6): 627-646

DOI: 10.3897/jucs.96878

Authors: José L. López Ruiz, Ángeles Verdejo Espinosa, Alicia Montoro Lendínez, Macarena Espinilla Estévez

Abstract: Nowadays, it is becoming increasingly important to understand the multiple configuration factors of BLE anchors in indoor location systems. This task becomes particularly crucial in the context of activity recognition in multi-occupancy smart environments. Knowing the impact of the configuration of BLE anchors in an indoor location system allows us to distinguish the interactions performed by each inhabitant in a smart environment according to their proximity to each sensor. This paper proposes a new methodology, OBLEA, that determines the optimisation of Bluetooth Low Energy (BLE) anchors in indoor location systems, considering multiple BLE variables to increase flexibility and facilitate transferability to other environments. Concretely, we present a model based on a data-driven approach that considers configurations to obtain the best performing configuration with a minimum number of anchors. This methodology includes a flexible framework for the indoor space, the architecture to be deployed, which considers the RSSI value of the BLE anchors, and finally, optimisation and inference for indoor location. As a case study, OBLEA is applied to determine the location of ageing inhabitants in a nursing home in Alcaudete, Jaén (Spain). Results show the extracted knowledge related to the optimisation of BLE anchors involved in the case study.

HTML

XML

PDF

]]>
Research Article Wed, 28 Jun 2023 12:00:06 +0300
Automated video game parameter tuning with XVGDL+ https://lib.jucs.org/article/75357/ JUCS - Journal of Universal Computer Science 28(12): 1282-1311

DOI: 10.3897/jucs.75357

Authors: Jorge Ruiz Quiñones, Antonio J. Fernández Leiva

Abstract: Usually, human participation is required in order to provide feedback during the game tuning or balancing process. Moreover, this is commonly an iterative process in which play-testing is required as well as human interaction for gathering all important information to improve and tune the game components’ specification. In this paper, a mechanism is proposed to accelerate this process and reduce significantly the costs of it, contributing with a solution to perform the game parameter tuning and game balancing using search algorithms and artificial intelligence (AI) techniques. The process is executed in a fully automated way, and just requires a game specification written in a particular video game description language. Automated play-testing, and game’s feedback information analysis, are related to perform game parameters’ tuning and balancing, leading to offer a solution for the problem of optimizing a video game specification. Recently, XVGDL, a new language for specifying video games which is based on the eXtensible Markup Language (XML), has been presented. This paper uses XVGDL+, an extension of this lan- guage that incorporates new components to specify, within the video game specification, desirable goals or requirements to be evaluated after each game execution. A prototypical implementation of a Game Engine (termed XGE+) was also presented. This game engine not only enables the execution of an XVGDL+ game specification but also provides feedback information once the game has finished.The paper demonstrates that the combination of XVGDL+ with XGE+ offers a powerful mechanism for helping solving game AI research problems, in this case, the game tuning of video game parameters, with respect to initial optimization goals. These goals, as one of the particularities of the proposal presented here, are included within the game specification, minimizing the input of the process.As a practical proof of it, two experiments have been conducted to optimize a game specification written in XVGDL via a hill climbing local search method, in a fully automated way.

HTML

XML

PDF

]]>
Research Article Wed, 28 Dec 2022 10:00:00 +0200
Fastener Classification Using One-Shot Learning with Siamese Convolution Networks https://lib.jucs.org/article/70484/ JUCS - Journal of Universal Computer Science 28(1): 80-97

DOI: 10.3897/jucs.70484

Authors: Canan Tastimur, Erhan Akin

Abstract: Deep Learning has been widely used in image-based applications such as object classification, object detection, and object recognition in recent years. Classifying highly similar objects is a very difficult problem. It is difficult to classify datasets in this situation where object similarity between classes and differences between classes are high. In this study, Siamese Convolution Neural Network, which is a similarity measurement-based network, has been practiced to classify 6 types of screws, 5 types of nuts, and 7 types of bolts that are very similar to each other. In addition, this neural network formed with the One-Shot Learning technique is trained. Thanks to the OSL technique, there is no need to use large data sets. Also, there is no need to use large amounts of data from each class. Adding a new class to be classified is also made easier by the use of the OSL technique. The performance results of the proposed method are manifested in detail in the article.

HTML

XML

PDF

]]>
Research Article Fri, 28 Jan 2022 10:30:00 +0200
15-Puzzle Problem Solving with the Artificial Bee Colony Algorithm Based on Pattern Database https://lib.jucs.org/article/65202/ JUCS - Journal of Universal Computer Science 27(6): 635-645

DOI: 10.3897/jucs.65202

Authors: Adem Tuncer

Abstract: The N-puzzle problem is one of the most classical problems in mathematics. Since the number of states in the N-puzzle is equal to the factorial of the number of tiles, traditional algorithms can only provide solutions for small-scale ones, such as 8-puzzle. Various uninformed and informed search algorithms have been applied to solve the N-puzzle, and their performances have been evaluated. Apart from traditional methods, artificial intelligence algorithms are also used for solutions. This paper introduces a new approach based on a meta-heuristic algorithm with a solving of the 15-puzzle problem. Generally, only Manhattan distance is used as the heuristic function, while in this study, a linear conflict function is used to increase the effectiveness of the heuristic function. Besides, the puzzle was divided into subsets named pattern database, and solutions were obtained for the subsets separately with the artificial bee colony (ABC) algorithm. The proposed approach reveals that the ABC algorithm is very successful in solving the 15-puzzle problem.

HTML

XML

PDF

]]>
Research Article Mon, 28 Jun 2021 10:00:00 +0300
Forecasting Air Travel Demand for Selected Destinations Using Machine Learning Methods https://lib.jucs.org/article/68185/ JUCS - Journal of Universal Computer Science 27(6): 564-581

DOI: 10.3897/jucs.68185

Authors: Murat Firat, Derya Yiltas-Kaplan, Ruya Samli

Abstract: Over the past decades, air transportation has expanded and big data for transportation era has emerged. Accurate travel demand information is an important issue for the transportation systems, especially for airline industry. So, “optimal seat capacity problem between origin and destination pairs” which is related to the load factor must be solved. In this study, a method for determining optimal seat capacity that can supply the highest load factor for the flight operation between any two countries has been introduced. The machine learning methods of Artificial Neural Network (ANN), Linear Regression (LR), Gradient Boosting (GB), and Random Forest (RF) have been applied and a software has been developed to solve the problem. The data set generated from The World Bank Database, which consists of thousands of features for all countries, has been used and a case study has been done for the period of 2014-2019 with Turkish Airlines. To the best of our knowledge, this is the first time that 1983 features have been used to forecast air travel demand in the literature within a model that covers all countries while previous studies cover only a few countries using far fewer features. Another valuable point of this study is the usage of the last regular data about the air transportation before COVID-19 pandemic. In other words, since many airline companies have experienced a decline in the air travel operation in 2020 due to COVID-19 pandemic, this study covers the most recent period (2014-2019) when flight operation performed on a regular basis. As a result, it has been observed that the developed model has forecasted the passenger load factor by an average error rate of 6.741% with GB, 6.763% with RF, 8.161% with ANN, and 9.619 % with LR.

HTML

XML

PDF

]]>
Research Article Mon, 28 Jun 2021 10:00:00 +0300
Detection of Cyberattacks Traces in IoT Data https://lib.jucs.org/article/24139/ JUCS - Journal of Universal Computer Science 26(11): 1422-1434

DOI: 10.3897/jucs.2020.075

Authors: Vibekananda Dutta, Michał Choraś, Marek Pawlicki, Rafał Kozik

Abstract: Artificial Intelligence plays a significant role in building effective cybersecurity tools. Security has a crucial role in the modern digital world and has become an essential area of research. Network Intrusion Detection Systems (NIDS) are among the first security systems that encounter network attacks and facilitate attack detection to protect a network. Contemporary machine learning approaches, like novel neural network architectures, are succeeding in network intrusion detection. This paper tests modern machine learning approaches on a novel cybersecurity benchmark IoT dataset. Among other algorithms, Deep AutoEncoder (DAE) and modified Long Short Term Memory (mLSTM) are employed to detect network anomalies in the IoT-23 dataset. The DAE is employed for dimensionality reduction and a host of ML methods, including Deep Neural Networks and Long Short-Term Memory to classify the outputs of into normal/malicious. The applied method is validated on the IoT-23 dataset. Furthermore, the results of the analysis in terms of evaluation matrices are discussed.

HTML

XML

PDF

]]>
Research Article Sat, 28 Nov 2020 00:00:00 +0200
Mobile Agents for Detecting Network Attacks Using Timing Covert Channels https://lib.jucs.org/article/22648/ JUCS - Journal of Universal Computer Science 25(9): 1109-1130

DOI: 10.3217/jucs-025-09-1109

Authors: Jędrzej Bieniasz, Monika Stępkowska, Artur Janicki, Krzysztof Szczypiorski

Abstract: This article addresses the problem of network attacks using steganographic techniques based on the manipulation of time relationships between IP packets. In the study, an efficient method to detect such attacks is presented. The proposed algorithm is based on the Change Observation Theory, and employs two types of agents: base and flying ones. The agents observe the time parameters of the network traffic, using proposed meta-histograms and trained machine learning algorithms, in the node where they were installed. The results of experiments using various machine learning algorithm are presented and discussed. The study showed that the Random Forest and MLP classifiers achieved the best detection results, yielding an area under the ROC curve (AUC) above 0.85 for the evaluation data. We showed a proof-of-concept for an attack detection method that combined the classification algorithm, the proposed anomaly metrics and the mobile agents. We claim that due to a unique feature of self-regulation, realized by destroying unnecessary agents, the proposed method can establish a new type of multi-agent intrusion detection system that can be applied to a wider group of IT systems.

HTML

XML

PDF

]]>
Research Article Sat, 28 Sep 2019 00:00:00 +0300
Hybrid Stochastic GA-Bayesian Search for Deep Convolutional Neural Network Model Selection https://lib.jucs.org/article/22617/ JUCS - Journal of Universal Computer Science 25(6): 647-666

DOI: 10.3217/jucs-025-06-0647

Authors: Waseem Rawat, Zenghui Wang

Abstract: In recent years, deep convolutional neural networks (DCNNs) have delivered notable successes in visual tasks, and in particular, image classification related applications. However, they are sensitive to the selection of their architectural and learning hyperparameters, which impose an exponentially large search space on modern DCNN models. Traditional hyperparameter selection methods include manual model tuning, grid, or random search but these require expert domain knowledge or are computationally burdensome. On the other hand, Bayesian optimization and evolutionary inspired techniques have surfaced as viable alternatives to the hyperparameter problem. In this work, an alternative automated system that combines the advantages of evolutionary processes and state-of-the-art Bayesian optimization is proposed. Specifically, the search space is first partitioned into separate discrete-architectural, and continuous and categorical learning parameter subspaces, which are then efficiently traversed by a stochastic genetic search applied to the former, combined with a genetic-Bayesian search of the latter. Several sequential experiments on prominent image classification tasks reveal that the proposed method results in overall classification accuracy improvements over several well-established techniques, and significant computational costs reductions compared to brute force computation.

HTML

XML

PDF

]]>
Research Article Fri, 28 Jun 2019 00:00:00 +0300
Detection of Potholes Using a Deep Convolutional Neural Network https://lib.jucs.org/article/23529/ JUCS - Journal of Universal Computer Science 24(9): 1244-1257

DOI: 10.3217/jucs-024-09-1244

Authors: Lim Suong, Kwon Jangwoo

Abstract: Poor road conditions like cracks and potholes can cause inconvenience to passengers, damage to vehicles, and accidents. Detecting those obstacles has become relevant due to the rise of the autonomous vehicle. Although previous studies used various sensors and applied different image processing techniques, performance is still significantly lacking, especially when compared to the tremendous leaps in performance with computer vision and deep learning. This research addresses this issue with the help of deep learning-based techniques. We applied the You Only Look Once version 2 (YOLOv2) detector and propose a deep convolutional neural network (CNN) based on YOLOv2 with a different architecture and two models. Despite a limited amount of learning data and the challenging nature of pothole images, our proposed architecture is able to obtain a significant increase in performance over YOLOv2 (from 60.14% to 82.43% average precision).

HTML

XML

PDF

]]>
Research Article Fri, 28 Sep 2018 00:00:00 +0300
Sustaining Continuous Collaborative Learning Flows in MOOCs: Orchestration Agent Approach https://lib.jucs.org/article/23442/ JUCS - Journal of Universal Computer Science 24(8): 1034-1051

DOI: 10.3217/jucs-024-08-1034

Authors: Ishari Amarasinghe, Davinia Hernández-Leo, Kalpani Manathunga, Anders Jonsson

Abstract: Collaborative learning spaces deployed in Massive Open Online Courses (MOOCs) provide productive social learning opportunities. However, sustaining collaboration in these spaces is challenging. This paper provides a classification of MOOCs participants based on their behavior in a structured collaborative learning space. This analysis leads to requirements for new technological interventions to orchestrate collaborative learning flows in MOOCs. The paper proposes the design of an intelligent agent to address these requirements and reports a study which shows that the intervention of the proposed orchestration agent in a MOOC facilitates to maintain continuous yet meaningful collaboration learning flows.

HTML

XML

PDF

]]>
Research Article Tue, 28 Aug 2018 00:00:00 +0300
Towards an Extended Model of Conceptual Representations in Formal Ontologies: A Typicality-Based Proposal https://lib.jucs.org/article/23021/ JUCS - Journal of Universal Computer Science 20(3): 257-276

DOI: 10.3217/jucs-020-03-0257

Authors: Marcello Frixione, Antonio Lieto

Abstract: In this paper we propose a possible solution for the problem of the computational representation of non-classical concepts (i.e. concepts that cannot be characterized in terms of necessary and sufficient conditions) in the field of formal ontologies. In particular, taking into account empirical evidences coming from cognitive psychology, according to which concept representation is not a unitary phenomenon, we suggest that a similar approach to the representation of conceptual knowledge could be useful also in the field of ontology based technologies. Finally we propose, in a linked open data perspective, conceptual spaces as a suitable framework for developing some aspects of the presented proposal.

HTML

XML

PDF

]]>
Research Article Sat, 1 Mar 2014 00:00:00 +0200
Design Considerations for Application Selection and Control in Multi-user Public Displays https://lib.jucs.org/article/23949/ JUCS - Journal of Universal Computer Science 19(17): 2526-2542

DOI: 10.3217/jucs-019-17-2526

Authors: Constantin Taivan, Rui José, Bruno Silva, Ivan Elhart, Jorge Cardoso

Abstract: Urban spaces are increasingly embedded with various types of public digital displays. Many of these displays can be subject to multi-user interactions and support a broad range of applications. A fundamental implication emerging from the interactive nature of those applications is that users should have access to appropriate selection and control techniques that would allow them to drive the way applications are shown and used in the respective environment. Such techniques should enable each user to reason and express intentions about the system behavior, while also dealing with concurrent requests from multiple users in a way that is fair and clear. In this study, we aim to inform the definition of novel techniques for application selection and control in pervasive display environments that can address the above challenges. Drawing inspiration from traditional GUI interaction concepts we developed and deployed a public display system that supports multiple applications and is able to receive explicit content presentation requests from multiple viewers. Based on the experiment observations and interviews with the participants, we reached a set of design considerations for future pervasive displays environments that are open to third party applications providers and allow the audience to influence content presentation.

HTML

XML

PDF

]]>
Research Article Fri, 1 Nov 2013 00:00:00 +0200
Ambient Intelligence: Beyond the Inspiring Vision https://lib.jucs.org/article/29704/ JUCS - Journal of Universal Computer Science 16(12): 1480-1499

DOI: 10.3217/jucs-016-12-1480

Authors: Rui José, Helena Rodrigues, Nuno Otero

Abstract: Ambient Intelligence (AmI) has emerged in the past 10 years as a multidisciplinary field within ubiquitous computing, attracting considerable research, funding and public attention and leading to many research groups, and conferences specifically focused on Ambient Intelligence topics. From its conception, AmI has always been a field strongly driven by a particular vision of how ICT technologies would shape our future. This has given the AmI vision, essentially as proposed by ISTAG, an excessively central role in shaping the field and setting its research agenda. We argue that this inspiring vision should no longer be the main driver for AmI research and that we should now re-interpret its role in the background of 10 years of research. In this paper, we reflect on what it means for AmI to move behind its foundational vision and we identify a number of emerging trends around some of its core concepts, more specifically the notion of intelligence, the system view and the requirements process. The main motivation is to search for alternative research directions that may be more effective in delivering today the essence of the AmI vision, even if they mean abandoning some of the currently prevailing approaches and assumptions. Overall, these trends provide a more holistic view of AmI and may represent important contributions for bringing this field closer to realisation, delivery and real social impact.

HTML

XML

PDF

]]>
Research Article Mon, 28 Jun 2010 00:00:00 +0300
A Neural Network Based Vehicle Classification System for Pervasive Smart Road Security https://lib.jucs.org/article/29373/ JUCS - Journal of Universal Computer Science 15(5): 1119-1142

DOI: 10.3217/jucs-015-05-1119

Authors: Naixue Xiong, Jing He, Jong Park, Donald Cooley, Yingshu Li

Abstract: Pervasive smart computing environments make people get accustomed to convenient and secure services. The overall goal of this research is to classify vehicles along the I215 freeway in Salt Lake City, USA. This information will be used to predict future roadway needs and the expected life of a roadway. The classification of vehicles will be performed by a synthesis of multiple sets of features. All feature sets have not yet been determined; however, one such set will be the reduced wavelet transform of the image of a vehicle. In order to use such a feature, it is necessary that the image be normalized with respect to size, position, and so on. For example, a car in the right most lane in an image will appear smaller than one in the left most lane, because the right most lane is closest to the camera. Likewise, a vehicle’s size will vary depending on where in a lane its image is captured. In our case, the image capture area for each lane is approximately 100 feet of roadway. A goal of this paper is to normalize the image of a vehicle so that regardless of its lane or position in a lane, the features will be approximately the same. The wavelet transform itself will not be used directly for recognition. Instead, it will be input to a neural network and the output of the neural network will be one element of the feature set used for recognition.

HTML

XML

PDF

]]>
Research Article Sun, 1 Mar 2009 00:00:00 +0200
Complexity Analysis of Ontology Integration Methodologies:a Comparative Study https://lib.jucs.org/article/29347/ JUCS - Journal of Universal Computer Science 15(4): 877-897

DOI: 10.3217/jucs-015-04-0877

Authors: Trong Duong, Geun-Sik Jo, Jason Jung, Ngoc Nguyen

Abstract: Most previous research on ontology integration has focused on similarity measure-ments between ontological entities, e.g., lexicons, instances, schemas and taxonomies, resulting in high computational costs of considering all possible pairs between two given ontologies. In this paper, we propose a novel approach to reducing computational complexity in ontology integration. Thereby, we address the importance and types of concepts, for priority matching anddirect matching between concepts, respectively. Identity-based similarity is computed, to avoid comparisons of all properties related to each concept, while matching between concepts. Theproblem of conflict in ontology integration has initially been explored on the instance-level and concept-level. This is useful to avoid many cases of mismatching.

HTML

XML

PDF

]]>
Research Article Sat, 28 Feb 2009 00:00:00 +0200
SemanticMiner - Ontology-Based Knowledge Retrieval https://lib.jucs.org/article/28064/ JUCS - Journal of Universal Computer Science 9(7): 682-696

DOI: 10.3217/jucs-009-07-0682

Authors: Eddie Moench, Mike Ullrich, Hans-Peter Schnurr, Jürgen Angele

Abstract: During the analysis of knowledge processes in enterprises it often turns out that simple access to existing enterprise knowledge which is covered in documents is not possible. To enable access to a companys document and data stocks Information Retrieval (IR) technologies play a central role. In the following we describe the underlying theory of the SemanticMiner system, including methods and technologies as well as continuing approaches to obtain Knowledge Retrieval (KR) by dint of semantic technologies.

HTML

XML

PDF

]]>
Research Article Mon, 28 Jul 2003 00:00:00 +0300
Imperfect Information Flow of Agents Communication in Arrow Logic https://lib.jucs.org/article/27441/ JUCS - Journal of Universal Computer Science 3(11): 1266-1281

DOI: 10.3217/jucs-003-11-1266

Authors: Yoshihiko Murakawa, Satoshi Tojo

Abstract: This paper formalizes the communication of agents with modal operators in arrow logic. A communication between agents consists of an agent's utterance and the other agent's perception, thus, both of the utterance and the perception are regarded as parts of a communication channel between agents. Information is regarded as a propositional content of a sentence. An information channel where information flows can be considered to be a program, in the sense that it gets an utterance as an input and puts an output to be a perception of some agent. In the real situations, th ere are so called miscommunications. Thus, the communication channel as a program may add some noise on information indeterministically. We implement the noises are some modal operators on information. We try to formalize the communication channels in arrow logic. In that, we especially pay attention to the following three problems: channel bottleneck, unreliable channel, and reverse information. This paper's contribution is two-fold. First, we formalize the theory of information flow, based on situation semantics, in terms of arrow logic. Secondly, we propose the theory of communication channels between agents by using arrow logic, where, classical modal operators like knowledge, belief, and perception are distributed on various places on the communication channel. We discuss the satisfiability and the applicability of our formalization, using the test principles by Barwise on this information flow model.

HTML

XML

PDF

]]>
Research Article Fri, 28 Nov 1997 00:00:00 +0200