Computer Science https://journals.agh.edu.pl/csci <p><img style="float: left; margin-right: 15px; margin-bottom: 5px;" src="https://journals.agh.edu.pl/public/site/images/admin/computer.jpg" alt="" />The Computer Science Journal (ISSN: 1508-2806; e-ISSN: 2300-7036) is a quarterly published by the AGH University of Krakow Poland since 1999.<br />We publish original papers concerning theoretical and applied computer science problems. The main areas of interest of the journal are theoretical aspects of computer science, soft computing, HPC, cloud and distributed processing and simulation, multimedia systems and computer graphics, and natural language processing.</p> <p>Please note: we don't have any article processing charges, our journal is non-profit. The journal is indexed by Web of Science and SCOPUS.</p> <p> </p> <p> </p> <p><strong>Web of Science Impact Factor = 0.5</strong></p> <p><strong>Scopus Quartile = 3 (32nd - the highest percentile in SCOPUS)</strong></p> <!-- <p> </p> <p>Our journal is indexed in the following services: <a href="http://scholar.google.com">Google Scholar</a>, <a href="http://search.labs.crossref.org/">CrossRef metadata search</a>, <a href="http://www.doaj.org">Directory of Open Access Journals</a>, <a href="http://www.openarchives.org">Open Archives Initiative</a>, <a href="http://fbc.pionier.net.pl/owoc/">Digital Libraries Federation</a>, <a href="http://baztech.icm.edu.pl/">BazTech</a>, <a href="http://indexcopernicus.com/">Index Copernicus</a>, <a href="http://ulrichsweb.serialssolutions.com/login">Ulrich's Periodicals Directory</a>, <a href="http://www.ebscohost.com/">EBSCOhost Applied Sciences</a>, <a href="http://dblp.uni-trier.de/db/journals/aghcs/index.html">DBLP</a>, <a href="https://dbh.nsd.uib.no/publiseringskanaler/erihplus/periodical/info?id=490585">ERIH PLUS</a>, <strong><a href="https://www.scopus.com/sourceid/21100826268?origin=resultslist">SCOPUS</a> and Emerging Sources Citation Index - part of Clarivate Web of Science</strong>.</p> <p>This is an open access journal in accordance with the <a href="http://www.soros.org/openaccess/read.shtml">BOAI</a>definition of open access. The content of the journal is freely available according to the <a href="https://creativecommons.org/licenses/by/4.0/">Creative Commons License Attribution 4.0 International (CC BY 4.0)</a></p> <p><a href="http://journals.agh.edu.pl/csci/about/submissions#onlineSubmissions"><strong>SUBMISSION PAGE DIRECT LINK</strong></a></p> <p>Please note:</p> <ul> <li><strong>We do not apply any Article Processing Charges. Our journal is a fully non-profit endeavour.</strong></li> <li>The journal is Open Access (also free of charges).</li> <li>First Author of the accepted paper receives one complimentary hardcopy.</li> <li>We accept PDF or DOC/DOCX manuscripts for review.</li> <li>For final typesetting we strongly prefer Latex/Bibtex. If the authors of the accepted paper are unable to prepare the paper in Latex it will be translated to Latex - for the cost of likely significant delay in publishing. </li> <li>You may use our <a href="https://www.overleaf.com/latex/templates/computer-science-journal-agh-template/tbmvnvhdzjny">Overleaf template</a> to prepare your paper.</li> <li>We review Survey papers - but only if the authors cite in their paper 3 recent papers by themselves, devoted to the area of the survey. We do not accept nor review surveys authored by non-experts.</li> <li>The paper submitted to our journal is expected to be 15-20 pages long.</li> <li>You are free to publish the early version of the paper in Arxiv, Research Gate and similar websites - but the paper should be updated with the final version, after the paper is accepted and published.</li> <li>We speed up the publication process by publishing early birds versions of the paper (with DOI).</li> <li>The submitted paper should follow typical guidelines for scientific publications - see for example this <a href="https://cs.stanford.edu/people/widom/paper-writing.html">Tutorial</a> by Jennifer Widom.</li> <li>We are using <a href="http://www.ithenticate.com">IThenticate</a> to prevent (self)plagiarism.</li> <li>You can check our position at <a href="https://www.scimagojr.com/journalsearch.php?q=21100826268&amp;tip=sid&amp;clean=0">Scimago Journal &amp; Country Rank</a>.</li> </ul> --> AGH University of Krakow, Faculty of Computer Science en-US Computer Science 1508-2806 Sentiment-aware Enhancements of PageRank-based Citation Metric, Impact Factor, and H-index for Ranking the Authors of Scholarly Articles https://journals.agh.edu.pl/csci/article/view/6042 <p>Heretofore, the only way to evaluate an author has been frequency-based citation metrics. However, citations with a neutral sentiment possibly can not be considered in the same light as those expressing a positive or negative sentiment. We present sentiment-enhanced alternatives to three conventional metrics namely Impact Factor, H-index, and PageRank-based index. The proposal studies the impact of the proposed metrics on the ranking of authors. We experimented with two datasets, collectively comprising almost 20,000 citation sentences. The evaluation of the proposed metrics revealed a significant impact of sentiments on author ranking, evidenced by a weak Kendall coefficient for the Author Impact Factor and H-index. However, the PageRank-based metric showed a moderate to strong correlation, perhaps due to its prestige-based attributes. Furthermore, a remarkable Rank-biased deviation exceeding 28% was seen in all cases, indicating a stronger rank deviation in top-ordered ranks.</p> Shikha Gupta Animesh Kumar Copyright (c) 2024 Computer Science https://creativecommons.org/licenses/by/4.0 2024-06-24 2024-06-24 25 2 10.7494/csci.2024.25.2.6042 Explainable Spark-based PSO Clustering for Intrusion Detection https://journals.agh.edu.pl/csci/article/view/5891 <p>Given the exponential growth of available data in large networks, the existence of rapid, transparent and explainable intrusion detection systems has become of high necessity to effectively discover attacks in such huge networks. To deal with this challenge, we propose a novel explainable intrusion detection system based on Spark, Particle Swarm Optimization (PSO) clustering and eXplainable Artificial Intelligence (XAI) techniques. Spark is used as a parallel processing model for the effective processing of large-scale data, PSO is integrated for improving the quality of the intrusion detection system by avoiding sensitive initialization and premature convergence of the clustering algorithm and finally, XAI techniques are used to enhance interpretability and explainability of intrusion recommendations by providing both micro and macro explanations of detected intrusions. Experiments are conducted on several large collections of real datasets to show the effectiveness of the proposed intrusion detection system in terms of explainability, scalability and accuracy. The proposed system has shown high transparency in assisting security experts and decision-makers to understand and interpret attack behavior.</p> chiheb eddine Ben ncir Mohamed Aymen Ben Haj kacem Mohammed Alatas Copyright (c) 2024 Computer Science https://creativecommons.org/licenses/by/4.0 2024-06-24 2024-06-24 25 2 10.7494/csci.2024.25.2.5891 Detection of Credit Card Fraud with Optimized Deep Neural Network in Balanced Data Condition https://journals.agh.edu.pl/csci/article/view/5967 <p>Due to the huge number of financial transactions, it is almost impossible for humans to manually detect fraudulent transactions. In previous work, the datasets are not balanced and the models suffer from overfitting problems. In this paper, we tried to overcome the problems by tuning hyperparameters and balancing the dataset by hybrid approach using under-sampling and over-sampling techniques. In this study, we have observed that these modifications are effective to get better performance in comparison to the existing models. The MCC score is considered an important parameter in binary classification since it ensures the correct prediction of the majority of positive data instances and negative data instances. So, we emphasize on MCC score and our method achieved MCC score of 97.09%, which is far more (16 % approx.) than other state of art methods. In terms of other performance metrics, the result of our proposed model is also improved significantly.</p> Nirupam Shome Devran Dey Sarkar Richik Kashyap Rabul Hussain Lasker Copyright (c) 2024 Computer Science https://creativecommons.org/licenses/by/4.0 2024-06-24 2024-06-24 25 2 10.7494/csci.2024.25.2.5967 Clustering for Clarity: Improving Word Sense Disambiguation through Multilevel Analysis https://journals.agh.edu.pl/csci/article/view/5844 <p><span dir="ltr" role="presentation">In natural language processing, a critical activity known as word sense disam</span><span dir="ltr" role="presentation">biguation (WSD) seeks to ascertain the precise meaning of an ambiguous word</span><br role="presentation"><span dir="ltr" role="presentation">in context. Traditional methods for WSD frequently involve supervised learn</span><span dir="ltr" role="presentation">ing methods and lexical databases like WordNet. However, these methods fall</span><br role="presentation"><span dir="ltr" role="presentation">short in managing word meaning complexity and capturing fine-grained differ</span><span dir="ltr" role="presentation">ences. In this paper, for increasing the precision and granularity of word sense</span><br role="presentation"><span dir="ltr" role="presentation">disambiguation we proposed multilevel clustering method that goes deeper in </span><span dir="ltr" role="presentation">the nested levels as locate groups of linked context words and categorize them</span><br role="presentation"><span dir="ltr" role="presentation">according to their word meanings. With this method, we can more effectively </span><span dir="ltr" role="presentation">manage polysemy and homonymy as well as detect minute differences in mean</span><span dir="ltr" role="presentation">ing.</span>&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; <span dir="ltr" role="presentation">An actual investigation of the</span> <span dir="ltr" role="presentation">SemCor</span> <span dir="ltr" role="presentation">corpus demonstrates the perfor</span><span dir="ltr" role="presentation">mance score of multilevel clustering in WSD. This proposed method successfully</span><br role="presentation"><span dir="ltr" role="presentation">separated clusters and groups context terms according to how semantically re</span><span dir="ltr" role="presentation">lated they are, producing improved disambiguation outcomes. A more detailed</span><br role="presentation"><span dir="ltr" role="presentation">knowledge of word senses and their relationships may be obtained thanks to </span><span dir="ltr" role="presentation">the clustering process, which makes it possible to identify smaller clusters in</span><span dir="ltr" role="presentation">side larger clusters. The outcomes demonstrate how multilevel clustering may </span><span dir="ltr" role="presentation">enhance the granularity and accuracy of WSD. Our solution overcomes the </span><span dir="ltr" role="presentation">drawbacks of conventional approaches and provides a more fine-grained repre</span><span dir="ltr" role="presentation">sentation of word senses by combining clustering algorithms.</span></p> shivkishan dubey Copyright (c) 2024 Computer Science https://creativecommons.org/licenses/by/4.0 2024-06-24 2024-06-24 25 2 10.7494/csci.2024.25.2.5844 Finding The Inverse of A Polynomial Modulo in The Ring Z[X] Based on The Method of Undetermined Coefficients https://journals.agh.edu.pl/csci/article/view/5740 <p><span dir="ltr" role="presentation">This paper presents the theoretical foundations of finding the inverse of a poly</span><span dir="ltr" role="presentation">nomial modulo in the ring</span> <span dir="ltr" role="presentation">Z</span><span dir="ltr" role="presentation">[</span><span dir="ltr" role="presentation">x</span><span dir="ltr" role="presentation">]</span> <span dir="ltr" role="presentation">based on the method of undetermined coeffi</span><span dir="ltr" role="presentation">cients. The use of the latter makes it possible to significantly reduce the time </span><span dir="ltr" role="presentation">complexity of calculations avoiding the operation of finding the greatest com</span><span dir="ltr" role="presentation">mon divisor. An example of calculating the inverse of a polynomial modulo in </span><span dir="ltr" role="presentation">the ring</span> <span dir="ltr" role="presentation">Z</span><span dir="ltr" role="presentation">[</span><span dir="ltr" role="presentation">x</span><span dir="ltr" role="presentation">]</span> <span dir="ltr" role="presentation">based on the proposed approach is given. Analytical expressions </span><span dir="ltr" role="presentation">of the time complexities of the developed and classical methods depending on </span><span dir="ltr" role="presentation">the degrees of polynomials are built. The graphic dependence of the complexity </span><span dir="ltr" role="presentation">of performing the operation of finding the inverse of a polynomial in the ring </span><span dir="ltr" role="presentation">Z</span><span dir="ltr" role="presentation">[</span><span dir="ltr" role="presentation">x</span><span dir="ltr" role="presentation">]</span> <span dir="ltr" role="presentation">is presented, which shows the advantages of the method based on unde</span><span dir="ltr" role="presentation">termined coefficients.</span> <span dir="ltr" role="presentation">It is found that the efficiency of the developed method </span><span dir="ltr" role="presentation">increases logarithmically with an increase in the degrees of polynomials.&nbsp;</span></p> Ruslan Shevchuk Ihor Yakymenko Mikolaj Karpinski Inna Shylinska Mykhailo Kasianchuk Copyright (c) 2024 Computer Science https://creativecommons.org/licenses/by/4.0 25 2 10.7494/csci.2024.25.2.5740 Quantum Inspired Chaotic Salp Swarm Optimization for Dynamic Optimization https://journals.agh.edu.pl/csci/article/view/5289 <p>Many real-world problems are dynamic optimization problems that are unknown beforehand. In practice, unpredictable events such as the arrival of new jobs, due date changes, and reservation cancellations, changes in parameters or constraints make the search environment dynamic. Many algorithms are designed to deal with stationary optimization problems, but these algorithms do not face dynamic optimization problems or manage them correctly. Although some of the optimization algorithms are proposed to deal with the changes in dynamic environments differently, there are still areas of improvement in existing algorithms due to limitations or drawbacks, especially in terms of locating and following the previously identified optima. With this in mind, we studied a variant of SSA known as QSSO, which is integrating the principles of quantum computing. An attempt is made to improve the overall performance of standard SSA to deal with the dynamic environment effectively by locating and tracking the global optima for DOPs. This work is an extension of the proposed new algorithm QSSO, known as the Quantum-inspired Chaotic Salp Swarm Optimization (QCSSO) Algorithm, which is detailing the various approaches taken into consideration while solving DOPs. A chaotic operator is employed with quantum computing to respond to change and guarantee to increase individual searchability by improving population diversity and the speed at which the algorithm converges. We experimented by evaluating QCSSO on a well-known generalized dynamic benchmark problem (GDBG) provided for CEC 2009, followed by a comparative numerical study with well-regarded algorithms. As promised, the introduced QCSSO is discovered, and a rival algorithm for DOPs.</p> Sanjai Pathak Ashish Mani Mayank Sharma Amlan Chatterjee Copyright (c) 2024 Computer Science https://creativecommons.org/licenses/by/4.0 25 2 10.7494/csci.2024.25.2.5289