Latest Articles from JUCS - Journal of Universal Computer Science Latest 32 Articles from JUCS - Journal of Universal Computer Science https://lib.jucs.org/ Thu, 28 Mar 2024 12:03:26 +0200 Pensoft FeedCreator https://lib.jucs.org/i/logo.jpg Latest Articles from JUCS - Journal of Universal Computer Science https://lib.jucs.org/ Low-sample classification in NIDS using the EC-GAN method https://lib.jucs.org/article/85703/ JUCS - Journal of Universal Computer Science 28(12): 1330-1346

DOI: 10.3897/jucs.85703

Authors: Marko Zekan, Igor Tomičić, Markus Schatten

Abstract: Numerous advanced methods have been applied throughout the years for the use in Network Intrusion Detection Systems (NIDS). Among these are various Deep Learning models, which have shown great success for attack classification. Nevertheless, false positive rate and detection rate of these systems remains a concern. This is mostly because of the low-sample, imbalanced nature of realistic datasets, which make models challenging to train.Considering this, we applied a novel semi-supervised EC-GAN method for network flow classifi- cation of CIC-IDS-2017 dataset. EC-GAN uses synthetic data to aid the training of a supervised classifier on low-sample data. To achieve this, we modified the original EC-GAN to work with tabular data. In our approach, WCGAN-GP is used for synthetic tabular data generation, while a simple deep neural network is used for classification. The conditional nature of WCGAN-GP diminishes the class imbalance problem, while GAN itself solves the low-sample problem. This approach was successful in generating believable synthetic data, which was consequently used for training and testing the EC-GAN.To obtain our results, we trained a classifier on progressively smaller versions of the CIC-DIS-2017 dataset, first via a novel EC-GAN method and then in the conventional way, without the help of synthetic data. We then compared these two sets of results with another author’s results using accuracy, false positive rate, detection rate and macro F1 score as metrics. Our results showed that supervised classifier trained with EC-GAN can achieve significant results even when trained on as little as 25% of the original imbalanced dataset.

HTML

XML

PDF

]]>
Research Article Wed, 28 Dec 2022 10:00:00 +0200
Traffic Optimization with Software-Defined Network Controller on a New User Interface https://lib.jucs.org/article/80625/ JUCS - Journal of Universal Computer Science 28(6): 648-669

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

]]>
Research Article Tue, 28 Jun 2022 10:00:00 +0300
Toward a Fuzzy-based Approach for Computational Load Offloading of IoT Devices https://lib.jucs.org/article/24143/ JUCS - Journal of Universal Computer Science 26(11): 1455-1474

DOI: 10.3897/jucs.2020.077

Authors: Lelio Campanile, Mauro Iacono, Fiammetta Marulli, Michele Mastroianni, Nicola Mazzocca

Abstract: Technological development and market expansion offer an increased availability of resources and computing power on IoT nodes at affordable cost. The edge computing paradigm allows keeping locally on the edge of the network a part of computing, while keeping all advantages of the cloud and adding support for privacy, real-time and network resilience. This can be further improved in IoT applications by exibly harvesting resources on IoT nodes, by moving part of the computing tasks related to data from the edge server to the nodes, raising the abstraction level of the data aspects of the architecture and potentially enabling larger IoT networks to be efficiently deployed and managed, in a stand-alone logic or as a component of edge architecture. Anyway, an e_cient energy management mechanism is needed for battery powered IoT networks, the most exible implementations, that dynamically balances task allocation and execution in order to In this paper we present a fuzzy logic based power management strategy for IoT subsystem that aims at maximizing the duration of the network by locally migrating part of the computing tasks between nodes. As our goal is to enable the deployment of semi-autonomic large IoT networks, our proposal does not rely on external resources for migration control and operates on a local basis to ensure scalability: at the best of our knowledge, this differentiates our proposal with respect to similar solutions available in literature.

HTML

XML

PDF

]]>
Research Article Sat, 28 Nov 2020 00:00:00 +0200
On Machine Learning Approaches for Automated Log Management https://lib.jucs.org/article/22639/ JUCS - Journal of Universal Computer Science 25(8): 925-945

DOI: 10.3217/jucs-025-08-0925

Authors: Ashot Harutyunyan, Arnak Poghosyan, Naira Grigoryan, Narek Hovhannisyan, Nicholas Kushmerick

Abstract: We address several problems in intelligent log management of distributed cloud computing applications and their machine learning solutions. Those problems concern various tasks on characterizing data center states from logs, as well as from related or other quantitative metrics (time series), such as anomaly and change detection, identification of baseline models, impact quantification of abnormalities, and classification of incidents. These are highly required jobs to be performed by today's enterprise-grade cloud management solutions. We describe several approaches and algorithms that are validated to be effective in an automated log analytics combined with analytics from time series perspectives. The paper introduces novel concepts, approaches, and algorithms for feasible log-plus-metric-based management of data center applications in the context of integration of relevant technology products in the market.

HTML

XML

PDF

]]>
Research Article Wed, 28 Aug 2019 00:00:00 +0300
Dynamic Estimation of Temporary Failure in SoC FPGAs for Heterogeneous Applications https://lib.jucs.org/article/23789/ JUCS - Journal of Universal Computer Science 24(12): 1776-1799

DOI: 10.3217/jucs-024-12-1776

Authors: J. Kokila, N. Ramasubramanian, Ravindra Thamma

Abstract: Recent processors are shrinking in size due to the advancement of technology. Reliability is an important design parameter along with power, cost, and performance. The processors need to be fault tolerant to counter reliability challenges. This work proposes a dynamic thermal and voltage management (DTVM) system which ensures a reasonable level of fault tolerance. The fault tolerance system (FTS) identifies and subsequently can forecast temporary failures at run-time. The temporary failures are dynamically estimated on SoC FPGAs for a class of heterogeneous applications. The dynamic priority scheduling based on absolute deadline is adopted to improve the nature of FTS. Experimental results indicate that the failure rate reduces by 7.2% with the variation of 2% and 12% in temperature and voltage respectively.

HTML

XML

PDF

]]>
Research Article Fri, 28 Dec 2018 00:00:00 +0200
Feature Selection for Black Hole Attacks https://lib.jucs.org/article/23124/ JUCS - Journal of Universal Computer Science 22(4): 521-536

DOI: 10.3217/jucs-022-04-0521

Authors: Muneer Yassein, Yaser Khamayseh, Mai Abujazoh

Abstract: The security issue is essential and more challenging in Mobile Ad-Hoc Network (MANET) due to its characteristics such as, node mobility, self-organizing capability and dynamic topology. MANET is vulnerable to different types of attacks. One of possible attacks is black hole attack. Black hole attack occurs when a malicious node joins the network with the aim of intercepting data packets which are exchanged across the network and dropping them which affects the performance of the network and its connectivity. This paper proposes a new dataset (BDD dataset) for black hole intrusion detection systems which contributes to detect the black hole nodes in MANET. The proposed dataset contains a set of essential features to build an efficient learning model where these features are selected carefully using one of the feature selection techniques which is information gain technique J48 decision tree, Naïve Bayes (NB) and Sequential Minimal Optimization (SMO) classifiers are learned using training data of BDD dataset and the performance of these classifiers is evaluated using a learning machine tool Weka 3.7.11. The obtained performance results indicate that using the proposed dataset features succeeded in build an efficient learning model to train the previous classifiers to detect the black hole attack.

HTML

XML

PDF

]]>
Research Article Fri, 1 Apr 2016 00:00:00 +0300
Generating an Excerpt of a Service Level Agreement from a Formal Definition of Non-Functional Aspects Using OWL https://lib.jucs.org/article/23028/ JUCS - Journal of Universal Computer Science 20(3): 366-384

DOI: 10.3217/jucs-020-03-0366

Authors: Mariam Rady

Abstract: If we take a look at current cloud computing services, the only quality guarantee they provide are vague Service Level Agreements(SLA). In this paper we modelled some non-functional aspects in an ontology and used this ontology as a knowledge base to generate an excerpt from a service contract. We concentrate in this excerpt on availability as it is one of the most discussed attributes in current Service Level Agreements.

HTML

XML

PDF

]]>
Research Article Sat, 1 Mar 2014 00:00:00 +0200
A Comparison of Five Programming Languages in a Graph Clustering Scenario https://lib.jucs.org/article/23016/ JUCS - Journal of Universal Computer Science 19(3): 428-456

DOI: 10.3217/jucs-019-03-0428

Authors: Martin Stein, Andreas Geyer-Schulz

Abstract: The recent rise of social networks fuels the demand for efficient social web services,whose performance strongly benefits from the availability of fast graph clustering algorithms. Choosing a programming language heavily affects multiple aspects in this domain, such as run-time performance, code size, maintainability and tool support. Thus, an impartial comparison can provide valuable insights that are also useful for software development in general. This article in-vestigates the languages C++, Java, C#, F# and Python (as well as its close variant Cython) in a controlled scenario: In each language, a graph clustering task is implemented and executed. Thepaper introduces the problem to be solved and gives an overview over the different characteristics of the languages. After a detailed description of the testing environment, we report runtime,memory and code size results and discuss them with respect to the characteristics mentioned before. The findings indicate C++ as the fastest language for the challenge at hand, but they alsoshow that Java, C# and F# come close under some circumstances. Furthermore, it becomes clear that the amount of code can be significantly reduced with modern languages like Python or F#.

HTML

XML

PDF

]]>
Research Article Fri, 1 Feb 2013 00:00:00 +0200
The Method of Logistic Optimization in E-commerce https://lib.jucs.org/article/23544/ JUCS - Journal of Universal Computer Science 18(10): 1238-1258

DOI: 10.3217/jucs-018-10-1238

Authors: Robert Bucki, Petr Suchánek

Abstract: Rapidly changing business environment requires new approaches and methods for supporting management systems in all types of companies. Modern companies doing business use e-commerce systems by default. One of the key areas of e-commerce systems is logistics and the supply chain. The optimal way to ensure the success of logistics and supply chains is to use the methods of modeling and simulation based on appropriate models and especially its mathematical representation. In this paper, authors highlight the customer-oriented model of the e-commerce system and deal with logistic optimization and simulations. As an example, a sample logistic structure which requires the adequate control approach is presented. This is realized by means of heuristic algorithms which are responsible for meeting the set criterion. Moreover, the criteria to either maximize the production output or minimize the lost flow capacity of the logistic system or minimize the tool replacement criterion are introduced. Equations of state are given in order to represent the flow of material through the logistic system.

HTML

XML

PDF

]]>
Research Article Mon, 28 May 2012 00:00:00 +0300
Optimizations for Risk-Aware Secure Supply Chain Master Planning https://lib.jucs.org/article/29534/ JUCS - Journal of Universal Computer Science 15(15): 3019-3037

DOI: 10.3217/jucs-015-15-3019

Authors: Axel Schröpfer, Florian Kerschbaum, Christoph Schütz, Richard Pibernik

Abstract: Supply chain master planning strives for optimally aligned production, warehousing and transportation decisions across a multiple number of partners. Its execution in practice is limited by business partners' reluctance to share their vital business data. Secure Multi-Party Computation (SMC) can be used to make such collaborative computations privacy-preserving by applying cryptographic techniques. Thus, computation becomes acceptable in practice, but the performance of SMC remains critical for real world-sized problems. We assess the disclosure risk of the input and output data and then apply a protection level appropriate for the risk under the assumption that SMC at lower protection levels can be performed faster. This speeds up the secure computation and enables significant improvements in the supply chain.

HTML

XML

PDF

]]>
Research Article Tue, 1 Sep 2009 00:00:00 +0300
A Heuristic Approach for the Automatic Insertion of Checkpoints in Message-Passing Codes https://lib.jucs.org/article/29524/ JUCS - Journal of Universal Computer Science 15(14): 2894-2911

DOI: 10.3217/jucs-015-14-2894

Authors: Gabriel Rodríguez, María Martín, Patricia González, Juan Touriño

Abstract: Checkpointing tools may be typically implemented at two different abstraction levels: at the system level or at the application level. The latter has become a more popular alternative due to its flexibility and the possibility of operating in different environments. However, application-level checkpointing tools often require the user to manually insert checkpoints in order to ensure that certain requirements are met (e.g. forcing checkpoints to be taken at the user code and not inside kernel routines). The approach presented in this work is twofold. First, a spatial coordination protocol for checkpointing parallel SPMD applications is proposed, based on forcing checkpoints to be taken at the same places in the application code by all processes. Thus, global consistency is achieved without adding any new runtime communications or piggybacked data, and without the need to use specific fault-tolerant message-passing implementations. Second, the paper also introduces a compilation technique for the automatic insertion of checkpoints using the spatial coordination protocol, based on a static analysis of communications and a heuristic analysis of computational load. These analyses can also be used to achieve automatic checkpoint insertion in approaches based on classical protocols, such as uncoordinated checkpointing or distributed snapshots.

HTML

XML

PDF

]]>
Research Article Sat, 1 Aug 2009 00:00:00 +0300
Transmission Latency based Network Friendly Tree for Peer-to-Peer Streaming https://lib.jucs.org/article/29460/ JUCS - Journal of Universal Computer Science 15(9): 2011-2025

DOI: 10.3217/jucs-015-09-2011

Authors: Ting Peng, Qinghua Zheng, Yinli Jin

Abstract: In Peer-to-Peer(P2P) streaming system, the multicasting tree construction method influences considerably on network load. Under current available strategies, network resources are not used economically, or network resource friendship and the flexibility can't be approached thoroughly. With the increasing application of Internet, network infrastructure itself becomes a precious resource, which should be performed effectively. In our implementation, network transmission delay between the peers is detected, used as practical performance metrics of the P2P streaming system. According to the metrics, network friendly tree is provided as overlay multicasting tree construction strategy for P2P streaming system. In this strategy, additional transmission delays are minimized as new peers enter. The simulation experiment presents that the proposed strategy network friendly tree works better than other contrasts. And the transmission performance improves significantly at minor additional cost.

HTML

XML

PDF

]]>
Research Article Fri, 1 May 2009 00:00:00 +0300
Cooperation Enforcement in a Highly Dynamic Mobile Ad Hoc Network https://lib.jucs.org/article/29371/ JUCS - Journal of Universal Computer Science 15(5): 1090-1118

DOI: 10.3217/jucs-015-05-1090

Authors: Yao Ho, Ai Ho, Kien Hua, Fei Xie

Abstract: Operations of mobile ad hoc networks rely on the collaboration of participating nodes to route data for each other. This standard approach using a fixed set of nodes for each communication link cannot cope with high mobility due to a high frequency of link breaks. A recent approach based on virtual routers has been proposed to address this problem. In this new environment, virtual routers are used for forwarding data. The functionality of each virtual router is provided by the mobile devices currently within its spatial proximity. Since these routers do not move, the communication links are much more robust compared to those of the conventional techniques. In this paper, we investigate techniques to enforce collaboration among mobile devices by identify and punish misbehaving users in supporting the virtual router functionality. Simulation results based on various system configurations are given. They indicate that the proposed technique is effective.

HTML

XML

PDF

]]>
Research Article Sun, 1 Mar 2009 00:00:00 +0200
Agent Migration: Framework for Analysis https://lib.jucs.org/article/29352/ JUCS - Journal of Universal Computer Science 15(4): 941-966

DOI: 10.3217/jucs-015-04-0941

Authors: Dariusz Król, Aleksander Lupa

Abstract: A lot of work is devoted to analysing architectures for coordinating the behaviour of individual agents. However, providing agents with abilities to migrate continues to be a highly challenging problem. We propose a novel multi-agent framework, called Agent-based Migration (AM). We begin by defining the principal objective, which is the migration phenomenon applied, in our case, to distributed calculation of prime numbers. We present the AM architecture in detail. Then, we introduce different types of migration and the communication scheme. We also conduct a set of experiments in two environments: 4 heterogeneous computers and 45 (almost) homogeneous computers. Specifically, we are looking for a way to find optimal configurations for migration in both environments. The conclusion from this work is that introducing propagation to a system in a form of agent migration in both networks could considerably decrease the execution time according to used algorithms and established assumptions.

HTML

XML

PDF

]]>
Research Article Sat, 28 Feb 2009 00:00:00 +0200
An Optimization of CDN Using Efficient Load Distribution and RADS Caching Algorithm https://lib.jucs.org/article/29145/ JUCS - Journal of Universal Computer Science 14(14): 2329-2342

DOI: 10.3217/jucs-014-14-2329

Authors: Yun Na, Sarvar Abdullaev, Franz I. S. Ko

Abstract: Nowadays, while large-sized multimedia objects are becoming very popular throughout the Internet, one of the important issues appears to be the acceleration of content delivery network (CDN) performance. CDN is a web system that delivers the web cached objects to the client and accelerates the web performance. Therefore the performance factor for any CDN is vital factor in determining the quality of services. The performance improvement can be achieved through load balancing technique, so the server load could be distributed to several clustered groups of machines and processed in parallel. Also the performance of CDN heavily depends on caching algorithm which is used to cache the web objects. This study investigates a method that improves the performance of delivering multimedia content through CDN while using RADS algorithm for caching large-sized objects separately from small-sized ones. We will also consider the efficient distribution of requests outgoing from local servers in order to balance the CDN load. This method uses various types of factors such as CPU processing time, I/O access time and Task Queue between nearby servers. At the end of the paper, we will see the experimental results derived from implementing the proposed optimization technique and observe how it could contribute to the effectiveness of CDN.

HTML

XML

PDF

]]>
Research Article Mon, 28 Jul 2008 00:00:00 +0300
Guaranteeing Seamless Mobility with User Redials and Automatic Handover Retrials https://lib.jucs.org/article/29076/ JUCS - Journal of Universal Computer Science 14(10): 1597-1624

DOI: 10.3217/jucs-014-10-1597

Authors: Jose Gimenez-Guzman, M. Domenech-Benlloch, Vicent Pla, Vicente Casares-Giner, Jorge Martinez-Bauset

Abstract: In communication systems that guarantee seamless mobility of users across service areas, repeated attempts occur as a result of user behavior but also as au- tomatic retries of blocked requests. Both phenomena play an important role in the system performance and therefore should not be ignored in its analysis. On the other hand, an exact Markovian model analysis of such systems has proven to be infeasible and resorting to approximate techniques is mandatory. We propose an approximate methodology which substantially improves the accuracy of existing methods with a negligible increase of the computational time from the human point of view. A numer- ical evaluation of the model is carried out to investigate the impact on performance of the parameters related to the retry phenomena. As a result, some useful guidelines for setting up the automatic retries are provided. Finally, we also show how our model can be used to obtain a tight performance approximation in the case where reattempts have a deterministic nature.

HTML

XML

PDF

]]>
Research Article Wed, 28 May 2008 00:00:00 +0300
Structural Performance Evaluation of Multi-Agent Systems https://lib.jucs.org/article/29036/ JUCS - Journal of Universal Computer Science 14(7): 1154-1178

DOI: 10.3217/jucs-014-07-1154

Authors: Dariusz Król, Michał Zelmozer

Abstract: This paper is dedicated to the issue of structural performance of multi-agent platforms. Due to the wide range of all available architectures, we have concentrated only on Java RMI implementations. The main goal of this paper consists of two parts. The first one is to investigate and develop the performance metrics to enable evaluation of distributed systems without reorganization of the running system. The second part is the programming verification of two considered Java RMI multi-agent solutions: Aglets and Jade. We have examined the defined metrics in many experiments with different network and environment configurations to provide experimental evidence that these metrics are adequate in variety of conditions.

HTML

XML

PDF

]]>
Research Article Tue, 1 Apr 2008 00:00:00 +0300
A Normal Copula Model for the Economic Risk Analysis of Correlated Failures in Communications Networks https://lib.jucs.org/article/30045/ JUCS - Journal of Universal Computer Science 14(5): 786-799

DOI: 10.3217/jucs-014-05-0786

Authors: Maurizio Naldi, Giuseppe Acquisto

Abstract: The reliability of a communications network is often evaluated without taking into account the economic consequence of failures. Here a new approach is proposed to assess the economic consequences of failures as a figure of merit of reliable networks. For this purpose a partition of the network operator's market into service basins is proposed, which includes the presence of correlation between the subsystems needed to serve different service basins as well as within the same service basin. A simulation algorithm, based on the Cross-Entropy method, is fully described to evaluate the probability that the economic loss exceeds a given threshold. An application of the method to a simple scenario is finally reported.

HTML

XML

PDF

]]>
Research Article Sat, 1 Mar 2008 00:00:00 +0200
Approximation to a Behavioral Model for Estimating Traffic Aggregation Scenarios https://lib.jucs.org/article/29000/ JUCS - Journal of Universal Computer Science 14(5): 731-744

DOI: 10.3217/jucs-014-05-0731

Authors: Alberto Garcia, Klaus Hackbarth

Abstract: This article provides a comparison among different methods for estimating the aggregation of Internet traffic resulting from different users, network-access types and corresponding services. Some approximate models usually used as isolated methods are combined with a temporally scaled ON-OFF model with binomial approximations. The aggregation problem is solved using a new form of parameterization based on the composition of the source traffic accordingly to the concrete characteristics of the users, the accesses and the services. This is a new concept, called CASUAL, included within an overall network planning methodology for the design and dimensioning of Next Generation Internet.

HTML

XML

PDF

]]>
Research Article Sat, 1 Mar 2008 00:00:00 +0200
Passive Estimation of Quality of Experience https://lib.jucs.org/article/28990/ JUCS - Journal of Universal Computer Science 14(5): 625-641

DOI: 10.3217/jucs-014-05-0625

Authors: Denis Collange, Jean-Laurent Costeux

Abstract: Quality of Experience (QoE) is a promising method to take into account the users' needs in design ing, monitoring and manag ing networks. However, there is a challenge in finding a quick and simple way to estimate th e QoE due to the diversity of needs , habits and customs. We propose a new empirical method to approximate it automatically from passive network measurements and we compare its pros and cons with usual techniques. We apply it, as an example , on ADSL traffic traces to estimate the QoE dependence on the loss rate for the most used applications . We analyze more precisely the correlations between packet losses and some traffic characteristics of TCP connections, the duration, the sizes and the inter-arrival. We define different thresholds on the loss rate for network management. A nd we propose a notion of sensitiveness to compare these correlations on different applications.

HTML

XML

PDF

]]>
Research Article Sat, 1 Mar 2008 00:00:00 +0200
Performance Evaluation and Limitations of a Vision System on a Reconfigurable/Programmable Chip https://lib.jucs.org/article/28759/ JUCS - Journal of Universal Computer Science 13(3): 440-453

DOI: 10.3217/jucs-013-03-0440

Authors: José Fernández-Pérez, Francisco Sánchez-Fernández, Ricardo Carmona-Galán

Abstract: This paper presents a survey of the characteristics of a vision system implemented in a reconfigurable/programmable chip (FPGA). System limitations and performance have been evaluated in order to derive specifications and constraints for further vision system synthesis. The system hereby reported has a conventional architecture. It consists in a central microprocessor (CPU) and the necessary peripheral elements for data acquisition, data storage and communications. It has been designed to stand alone, but a link to the programming and debugging tools running in a digital host (PC) is provided. In order to alleviate the computational load of the central microprocessor, we have designed a visual co-processor in charge of the low-level image processing tasks. It operates autonomously, commanded by the CPU, as another system peripheral. The complete system, without the sensor, has been implemented in a single reconfigurable chip as a SOPC. The incorporation of a dedicated visual co-processor, with specific circuitry for low-level image processing acceleration, enhances the system throughput outperforming conventional processing schemes. However, time-multiplexing of the dedicated hardware remains a limiting factor for the achievable peak computing power. We have quantified this effect and sketched possible solutions, like replication of the specific image processing hardware.

HTML

XML

PDF

]]>
Research Article Wed, 28 Mar 2007 00:00:00 +0300
A Dynamically and Partially Reconfigurable Implementation of the IDEA Algorithm Using FPGAs and Handel-C https://lib.jucs.org/article/28753/ JUCS - Journal of Universal Computer Science 13(3): 407-418

DOI: 10.3217/jucs-013-03-0407

Authors: José Granado-Criado, Miguel A. Vega-Rodríguez, Juan Sánchez-Pérez, Juan Gómez-Pulido

Abstract: Nowadays, the information security has achieved a great importance, both when information is sent through a non-secure network (as the Internet) and when data are stored in massive storage devices. The cryptographic algorithms are used in order to guarantee the security of data sent or stored. A lot of research is being done in order to improve the performance of the current cryptographic algorithms, including the use of FPGAs. In this work we present an implementation of the IDEA cryptographic algorithm using reconfigurable hardware (FPGAs). In addition, in order to improve the performance of the algorithm, partial and dynamic reconfiguration has been used to implement our final circuit. This fact allows us to obtain a very high encryption speed (14.757 Gb/s), getting better results than those found in the literature.

HTML

XML

PDF

]]>
Research Article Wed, 28 Mar 2007 00:00:00 +0300
Internet Path Behavior Prediction via Data Mining: Conceptual Framework and Case Study https://lib.jucs.org/article/28742/ JUCS - Journal of Universal Computer Science 13(2): 287-316

DOI: 10.3217/jucs-013-02-0287

Authors: Leszek Borzemski

Abstract: In this paper we propose an application of data mining methods in the prediction of the availability and performance of Internet paths. We deploy a general decision-making method for advising the users in further usage of Internet path at particular time and date. The method is based on the clustering and tree classification data mining techniques. The usefulness of our method for prediction the Internet path behavior has been confirmed in real-life experiment. The active Internet measurements were performed to gather the end-to-end latency and packet routing information. The knowledge gathered has been analyzed using a professional data mining package via neural clustering and decision tree algorithms. The results show that the data mining can be efficiently used for the purpose of the forecasting the network behavior. We propose to build a network performance monitoring and prediction service based on proposed data mining procedure. We address our approach especially to the non-networkers of such networking frameworks as Grid and overlay networks who want to schedule their network activity but who want to be left free from networking issues to concentrate on their work.

HTML

XML

PDF

]]>
Research Article Wed, 28 Feb 2007 00:00:00 +0200
Our Experiences with Optimizations in Sun's Java Just-In-Time Compilers https://lib.jucs.org/article/28632/ JUCS - Journal of Universal Computer Science 12(7): 788-810

DOI: 10.3217/jucs-012-07-0788

Authors: Anderson Faustino da Silva, Vitor Costa

Abstract: Modern Java Compilers, such as Sun's HotSpot compilers, implement a number of optimizations, ranging from high-level program transformations to low-level architecure dependent operations such as instruction scheduling. In a Just-in-Time (JIT) environment, the impact of each optimization must be weighed against its cost in terms of total runtime. Towards better understanding the usefulness of individual optimizations, we study the main optimizations available on Sun HotSpot compilers for a wide range of scientific and non-scientific benchmarks, weighing their cost and benefits in total runtime. We chose the HotSpot technology because it is state of the art and its source code is available.

HTML

XML

PDF

]]>
Research Article Fri, 28 Jul 2006 00:00:00 +0300
The Design of the YAP Compiler: An Optimizing Compiler for Logic Programming Languages https://lib.jucs.org/article/28631/ JUCS - Journal of Universal Computer Science 12(7): 764-787

DOI: 10.3217/jucs-012-07-0764

Authors: Anderson Faustino da Silva, Vitor Costa

Abstract: Several techniques for implementing Prolog in a efficient manner have been devised since the original interpreter, many of them aimed at achieving more speed. There are two main approaches to efficient Prolog implementation: (1) compilers to bytecode and then interpreting it (emulators) or (2) compilers to native code. Emulators have smaller load/compilation time and are a good solution for their simplicity when speed is not a priority. Compilers are more complex than emulators, and the difference is much more acute if some form of code analysis is performed as part of the compilation, which impacts development time. Generation of low level code promises faster programs at the expense of using more resources during the compilation phase. In our work besides using an mixed execution mode, we design an optimizing compiler that using type feedback profiling, dynamic compilation and dynamic deoptimization for improving the performance of logic programming languages.

HTML

XML

PDF

]]>
Research Article Fri, 28 Jul 2006 00:00:00 +0300
Secure Service Discovery based on Trust Management for ad-hoc Networks https://lib.jucs.org/article/28594/ JUCS - Journal of Universal Computer Science 12(3): 340-356

DOI: 10.3217/jucs-012-03-0340

Authors: Celeste Campo, Florina Almenares, Daniel Díaz, Carlos García-Rubio, Andrés López

Abstract: In ad-hoc networks, mobile devices communicate via wireless links without the aid of any fixed networking infrastructure. These devices must be able to discover services dynamically and share them safely, taking into account ad-hoc net-works requirements such as limited processing and communication power, decentralised management, and dynamic network topology, among others. Legacy solutions fail in addressing these requirements. In this paper, we propose a service discovery protocol with security features, the Secure Pervasive Discovery Protocol. SPDP is a fully distributed protocol in which services offered by devices can be discovered by others, without a central server. It is based on an anarchy trust model, which provides location of trusted services, as well as protection of confidential information, secure communications, or access control.

HTML

XML

PDF

]]>
Research Article Tue, 28 Mar 2006 00:00:00 +0300
An Experimental Evaluation of JAVA JIT Technology https://lib.jucs.org/article/28447/ JUCS - Journal of Universal Computer Science 11(7): 1291-1309

DOI: 10.3217/jucs-011-07-1291

Authors: Anderson Faustino da Silva, Vitor Costa

Abstract: Interpreted languages are widely used due to ease to use, portability, and safety. On the other hand, interpretation imposes a significance overhead. Just­in­ Time (JIT) compilation is a popular approach to improving the runtime performance of languages such as Java. We compare the performance of a JIT compiler with a traditional compiler and with an emulator. We show that the compilation overhead from using JIT is negligible, and that the JIT compiler achieves better overall performance, suggesting the case for aggresive compilation in JIT compilers.

HTML

XML

PDF

]]>
Research Article Thu, 28 Jul 2005 00:00:00 +0300
Time Costs in Actor Computations https://lib.jucs.org/article/28413/ JUCS - Journal of Universal Computer Science 11(6): 850-873

DOI: 10.3217/jucs-011-06-0850

Authors: Michele Santo, Franco Frattolillo

Abstract: Actor programs give rise to computation structures that evolve dynamically and unpredictably both in shape and size. Therefore, their execution times cannot be statically determined. This paper describes an approach to the problem of estimating time costs of actor programs. The approach takes into account the constraints imposed both by the semantics and implementation of the model. In particular, implementation constraints can be captured and exploited to drastically reduce the number of computations generable by the program, thus simplifying the execution time evaluation. Moreover, execution times are expressed in a parametric form by using a variant of the LogP model able to synthetically characterize the target hardware/software platform.

HTML

XML

PDF

]]>
Research Article Tue, 28 Jun 2005 00:00:00 +0300
Data Distribution Specification for High Performance Computing https://lib.jucs.org/article/27815/ JUCS - Journal of Universal Computer Science 7(8): 736-753

DOI: 10.3217/jucs-007-08-0736

Authors: Hans Zima

Abstract: High performance computing (HPC) architectures are specialized machines which can reach their peak performance only if they are programmed in a way which exploits the idiosyncrasies of the architecture. An important feature of most such architectures is a physically distributed memory, resulting in the requirement to take data locality into account independent of the memory model offered to the user. In this paper we discuss various ways for managing data distribution in a program, comparing in particular the low-level message-passing approach to that in High Performance Fortran (HPF) and other high performance languages. The main part of the paper outlines a method for the specification of data distribution semantics for distributed-memory architectures and clusters of SMPs. The paper concludes with a discussion of open issues and references to future work.

HTML

XML

PDF

]]>
Research Article Tue, 28 Aug 2001 00:00:00 +0300
Performance of Switch Blocking on Multithreaded Architectures https://lib.jucs.org/article/27719/ JUCS - Journal of Universal Computer Science 6(10): 928-947

DOI: 10.3217/jucs-006-10-0928

Authors: K. Gopinath, M. K. Narasinhan

Abstract: Block multithreaded architectures tolerate large memory and synchronization latencies by switching contexts on every remote-memory-access or on a failed synchronization request. We study the performance of a waiting mechanism called switch-blocking where waiting threads are disabled (but not unloaded) and signalled at the completion of the wait in comparison with switch_spinning where waiting threads poll and execute in a round-robin fashion. We present an implementation of switch-blocking on a cycle-by-cycle simulator for Alewife (a block multithreaded machine) for both remote memory accesses and synchronization operations and discuss results from the simulator. Our results indicate that while switch-blocking almost always has better performance than switch-spinning, its performance is similar to switch-spinning under heavy lock contention. Support for switch-blocking for remote memory accesses may be appropriate in the future due to their strong interactions with synchronization operations.

HTML

XML

PDF

]]>
Research Article Sat, 28 Oct 2000 00:00:00 +0300
Transformational Approaches to the Specification and Verification of Fault-Tolerant Systems: Formal Background and Classification https://lib.jucs.org/article/27603/ JUCS - Journal of Universal Computer Science 5(10): 668-692

DOI: 10.3217/jucs-005-10-0668

Authors: Felix Gärtner

Abstract: Proving that a program suits its specification and thus can be called correct has been a research subject for many years resulting in a wide range of methods and formalisms. However, it is a common experience that even systems which have been proven correct can fail due to physical faults occurring in the system. As computer programs control an increasing part of todays critical infrastructure, the notion of correctness has been extended to fault tolerance, meaning correctness in the presence of a certain amount of faulty behavior of the environment. Formalisms to verify fault-tolerant systems must model faults and faulty behavior in some form or another. Common ways to do this are based on a notion of transformation either at the program or the specification level. We survey the wide range of formal methods to verify fault-tolerant systems which are based on some form of transformation. Our aim is to classify these methods, relate them to one another and, thus, structure the area. We hope that this might faciliate the involvement of researchers into this interesting field of computer science.

HTML

XML

PDF

]]>
Research Article Thu, 28 Oct 1999 00:00:00 +0300
Distributed Caching in Networked File Systems https://lib.jucs.org/article/27131/ JUCS - Journal of Universal Computer Science 1(6): 399-409

DOI: 10.3217/jucs-001-06-0399

Authors: Artur Klauser, Reinhard Posch

Abstract: Changing relative performance of processors, networks, and disks makes it necessary to reconsider algorithms using these three resources. As networks get faster and less congested topologies emerge, it becomes important to use network resources more aggressively to obtain good performance. Substitution of local disk accesses by accesses to remote memory can lead to better balanced resource usage and thus to faster systems. In this work we address the issue of file caching in a networked file system configuration. Distributed block-level in-memory caches are considered. We show that carefully constructed distributed concepts can lead to lower server load and better overall system performance than centralized concepts. Oversimplification, although aimed at gaining performance for single components, may deteriorate overall performance as a result of unbalanced resource usage.

HTML

XML

PDF

]]>
Research Article Wed, 28 Jun 1995 00:00:00 +0300