https://vfast.org/journals/index.php/VTCS/issue/feedVAWKUM Transactions on Computer Sciences2024-03-05T21:32:15+05:00Dr. Sher Afzal Khanvtcs@vfast-iccass.orgOpen Journal Systems<p>The <em><strong>(Virtual AWK and Unified Modeling) <em><strong>VAWKUM</strong></em> Transactions on Computer Sciences </strong></em>(VTCS) is a biannually peer-reviewed scientific journal that publishes high-quality research in all areas of computer science and its applications. he journal is indexed in several major databases, including HEC in category Y. </p> <p>ISSN: 2308-8168 (Online), 2411-6335 (Print)</p> <p>Editor in Chief: Prof. Sher Afzal Khan, Abdul Wali Khan University Mardan</p> <p><strong><span style="text-decoration: underline;"><span class="csspropertycolor" style="box-sizing: inherit; color: red; font-family: Consolas, Menlo, 'courier new', monospace; font-size: 15px; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; background-color: #ffffff; text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial;">Important Links </span></span></strong></p> <p><a href="https://vfast.org/journals/index.php/VTCS/user/register"><button class="pkpButton"> REGISTER</button></a> <a href="https://vfast.org/journals/index.php/VTCS/about/submissions"><button class="pkpButton"> SUBMISSION</button></a> <a href="https://vfast.org/journals/index.php/VTCS/about/editorialTeam"><button class="pkpButton">EDITORIAL TEAM </button></a> <a href="https://vfast.org/files/VAWKUM.zip"><button class="pkpButton">LATEX TEMPLATE</button></a></p> <ol> <li><a href="https://hjrs.hec.gov.pk/index.php?r=site%2Fresult&id=1021785#journal_result">HEC Category Y</a></li> <li><a href="https://www.worldcat.org/title/vawkum-transaction-on-computer-sciences/oclc/858007042&referer=brief_results">Worldcat</a></li> <li><a href="http://pastic.gov.pk/periodicaldetails.aspx?ID=211">Pastic.gov.pk</a></li> <li><a href="http://www.journaltocs.ac.uk/index.php?action=search">JournalTOCS</a></li> <li><a href="http://journaldatabase.info/journal/issn2308-8168">Academic Journals Database</a></li> <li><a href="https://catalogue-bibliotheque.sciencespo.fr/discovery/fulldisplay/alma991006835630305808/33USPC_SPO:SPO">Sciences Po</a></li> <li><a href="http://www.sudoc.abes.fr/cbs/xslt/DB=2.1/SET=1/TTL=1/CMD?ACT=SRCHA&IKT=1016&SRT=RLV&TRM=VAWKUM">Sudoc</a></li> <li><a href="https://www.journalguide.com/journals/vawkum-transaction-on-computer-sciences">Journal Guide</a></li> <li><a href="https://portal.issn.org/resource/ISSN/2308-8168%23">ISSN + ROA</a>D </li> <li><a href="http://ulrichsweb.serialssolutions.com/login">Ulrich’s Periodicals Directory/ProQuest</a></li> <li><a href="http://www.oalib.com/journal/14016/1%23.X6ZbE2gza00">Oalib Open Access Library</a></li> <li> <a href="http://sfx.princeton.edu:9003/sfx_pul/az?param_textSearchType_save=startsWith&param_perform_save=searchTitle&param_letter_group_script_save=&param_chinese_checkbox_save=0&param_starts_with_browse_save=0&param_sid_save=b2d32284a5f202b8c792b440b6535c2f&param_lang_save=eng&param_type_save=textSearch&param_chinese_checkbox_type_save=Pinyin&param_current_view_save=table&param_letter_group_save=&param_langcode_save=en&param_jumpToPage_save=&param_services2filter_save=getFullTxt&param_pattern_save=vawkum&param_type_value=textSearch&param_jumpToPage_value=&param_pattern_value=VAWKUM+Transaction+on+Computer+Sciences&param_textSearchType_value=startsWith&param_starts_with_browse_value=0&not_first_load_indicator=1&param_ui_control_scripts_value=&param_chinese_checkbox_value=0">Princeton University USA Librar</a>y</li> <li><a href="http://mperio.ru/resursy-otkrytogo-dostupa/v/">World of Periodicals</a></li> <li><a href="https://www.base-search.net/Search/Results?lookfor=VFAST&name=&oaboost=1&newsearch=1&refid=dcbasen">BASE: Bielefeld Academic Search Engine</a></li> <li><a href="https://core.ac.uk/search?q=%22VFAST%20Transactions%20%22&repository=13733&from_Year=2013&to_Year=2020&page=3">COnnecting REpositories (CORE)</a></li> <li><a href="https://app.dimensions.ai/discover/publication?search_mode=content&search_text=VAWKUM&search_type=kws&search_field=full_search&and_facet_source_title=jour.1156513">Dimensions</a> </li> <li><a href="http://journalseeker.researchbib.com/view/issn/2308-8168">Research Bible</a></li> </ol>https://vfast.org/journals/index.php/VTCS/article/view/1722Semi-Automated Approach for Evaluation of Software Defect Management Process using ML Approach2024-02-17T23:29:05+05:00Adeel Mannanadeel.mannan@hamdard.eduRohail Qamarrohailqamar@cloud.neduet.edu.pkSaadia Arshadsaadia@cloud.neduet.edu.pk<p>Evaluation of the software development process is crucial for enhancing software production and product quality inside a company. Traditional methods that rely on manual qualitative evaluations (such as artifact inspection) are flawed because they are (i) time-consuming, (ii) hampered by authority limits, and (iii) frequently subjective. This research introduces a unique machine learning-based semi-automated method for software process assessment to get over these constraints. We specifically frame the issue as a sequence classification challenge that can be resolved using machine learning methods. We develop a new quantitative indicator to impartially assess the effectiveness and quality of a software process based on the framework. We use it to assess the defect management procedure used in four actual industrial software projects in order to verify the effectiveness of our methodology. Our empirical findings demonstrate the effectiveness and potential of our technique in offering a reliable, quantitative assessment of software process.</p>2024-03-07T00:00:00+05:00Copyright (c) 2024 VAWKUM Transactions on Computer Scienceshttps://vfast.org/journals/index.php/VTCS/article/view/1706Educational Data Mining in Outcome-Based Education: An Analysis of Predictive Models for Program Learning Outcome Attainment2024-01-10T18:25:37+05:00Dua Aghaduaagha2@gmail.comAreej Fatemah Meghjiareej.fatemah@faculty.muet.edu.pkSania Bhattisania.bhatti@faculty.muet.edu.pkMariam Memonmariam.jawaid@faculty.muet.edu.pk<p>Outcome-based Education (OBE) is a student-centered strategy that focuses on students' performance in terms of knowledge, skills, and attitude to address academic gaps. Educational Data Mining (EDM) utilizes artificial intelligence and machine learning to analyze student data and boost academic achievements. Experimenting with student academic data of 397 first-year students of Mehran University of Engineering and Technology, covering nine courses and spanning two semesters, this research proposes a prediction mechanism to help anticipate student academic outcomes at an early stage during their university degree. The aim of this research is threefold. First, an exploration of EDM-based classification to predict OBE-based Program Learning Outcome (PLO) attainment. Second, the investigation of imbalanced class distribution and the benefits of using the Synthetic Minority Over-Sampling Technique on educational data. Third, a comprehensive performance evaluation of eleven classifiers is explored in this research. The evaluation entailed the use of accuracy, Kappa, recall, and precision to assess classifier performance on both balanced and unbalanced class distributions. Although several classifiers were found to be competent in handling educational data for OBE-PLO prediction, the Random Forest exhibited superior performance with an accuracy of 76.88% and a Kappa score of 0.727.</p>2023-12-31T00:00:00+05:00Copyright (c) 2024 VAWKUM Transactions on Computer Scienceshttps://vfast.org/journals/index.php/VTCS/article/view/1692Detection of Malware Attacks using Artificial Neural Network2023-12-18T20:10:16+05:00Humza Ranahumza.rana99@gmail.comMinhaj Ahmad Khanminhajbzu2@gmail.com<p><strong>Malware attacks are increasing rapidly as the technology continues to become prevalent. These attacks have become extremely difficult to detect as they continuously change their mechanism for exploitation of vulnerabilities in software. The conventional approaches to malware detection become ineffective due to a large number of varying patterns and sequences, thereby requiring artificial intelligence-based approaches for the detection of malware attacks. In this paper, we propose an artificial neural network-based model for malware detection. Our proposed model is generic as it can be applied to multiple datasets. We have compared our model with different machine-learning approaches. The experimentation results show that the proposed model can outperform other well-known approach as it achieves 99.6\% , 98.9\% and 99.9\% accuracy on the Windows API call dataset, Top PE Imports Dataset and Malware Dataset, respectively.</strong></p>2023-12-31T00:00:00+05:00Copyright (c) 2024 VAWKUM Transactions on Computer Scienceshttps://vfast.org/journals/index.php/VTCS/article/view/1685Transforming data from the image to the text domain: benign versus malignant micro-calcification classification2023-12-27T23:45:44+05:00Zobia Suhailzobia.suhail@pucit.edu.pkReyer Zwiggelaarrrz@aber.ac.uk<p>In this paper we present a new approach for the classification of benign and malignant micro-calcification clusters by transforming data from the image to the text domain. A string representation is extracted from binary micro-calcification segmentation images. We extracted two different features from the strings and combined different machine learning techniques towards benign versus malignant classification. We evaluated our proposed method on the DDSM database and experimental results indicates a Classification Accuracy equal to 92%.</p> <p> </p>2023-12-31T00:00:00+05:00Copyright (c) 2024 VAWKUM Transactions on Computer Scienceshttps://vfast.org/journals/index.php/VTCS/article/view/1663An Empirical Evaluation of Data Integrity Algorithm Performance in Non-Relational Document Databases2023-11-16T13:04:55+05:00Mujeeb-ur-Rehman Jamalimujeebjamali@usindh.edu.pkNajma Imtiaz Alinajma.channa@usindh.edu.pkImtiaz Ali Brohiimtiaz.brohi@guch.edu.pkMuhammad Umar Muradumarmurad.11@gmail.comYasir Nawazyasir.memon@usindh.edu.pkUswa UroojUswasiddiqui26@gmail.com<p>Non-relational document databases are a type of NoSQL databases, are gaining popularity owing to their flexibility, scalability, and performance. Document databases provide some distinct security issues. One of the most difficult security challenges is that they are frequently built to be extremely accessible. This can make them more vulnerable to assault if suitable security measures are not taken. Users of database can access data with weak authentication or authorization. Another issue is that they store data in a semi-structured or unstructured format. This makes it difficult to create and execute security safeguards. It may be difficult to detect and secure sensitive data that is kept. Document databases are certain data integrity problems. In this research work, we have developed Big Document DBCrypto’s architecture under which Middle ware provides users to use symmetric cryptography with any hashing algorithm or asymmetric cryptography with digital signatures to ensure data integrity.</p>2023-12-08T00:00:00+05:00Copyright (c) 2023 VAWKUM Transactions on Computer Scienceshttps://vfast.org/journals/index.php/VTCS/article/view/1655Detection of Questions from Text Data Using LSTM-Deep Learning Model2023-11-06T15:21:19+05:00Nadir Hussainnadirhussain.gu@outlook.comDr. Sheikh Muhammad Saqibsaqibsheikh414@gmail.comHamza Arifhamzaarif1441@gmail.comMuhammad Usman Gurmaniusmankhangurmani@gmail.com<p>This paper discusses the importance of detecting questions in textual data for various applications in natural language processing (NLP), such as question answering and chatbot creation. The proposed approach employs long short-term memory (LSTM) models to accurately identify questions by leveraging the sequential nature of language.<br />The paper highlights that LSTM models address challenges like ambiguous language and varying sentence structures. They allow the model to learn from sequential patterns, crucial for understanding the intent behind the text. The preprocessing steps, including tokenization, embedding, and padding, are detailed to prepare the data for training and testing. The study investigates the impact of hyperparameters like hidden layers, hidden states, and optimizer choice on the LSTM algorithm’s performance. In experiments on benchmark datasets, the proposed LSTM-based approach consistently outperforms conventional machine learning models, achieving a remarkable accuracy of 99.25% on the test dataset. The paper concludes by suggesting future directions, including applying<br />the approach to other NLP tasks like named entity recognition, sentiment analysis, and text classification. Further optimization for specific datasets or domains is also encouraged. Overall, this research contributes to robust question detection models in NLP, with potential applications in various fields.</p> <p> </p>2024-03-05T00:00:00+05:00Copyright (c) 2024 VAWKUM Transactions on Computer Scienceshttps://vfast.org/journals/index.php/VTCS/article/view/1654Advancements in News Article Classification: Approaches in Machine Learning and Deep Learning across Sports, Entertainment, Politics, Business, and Weather Domains2023-11-02T21:06:48+05:00Saima Ramzanfouzia.jabeen@sbbwu.edu.pkFouzia Jabeen -fouzia.jabeen@sbbwu.edu.pkZafar -saimaramzan870@gmail.comShah -saimaramzan870@gmail.com<p><em>The classification of news articles is a crucial technology for processing news information, aiding in the organization of information. It is challenging to classify news due to the continuous emergence of news that requires processing. The modern technological era has reshaped traditional lifestyles in various domains. Similarly, the medium of publishing news and events has experienced rapid growth with the advancement of Information Technology. In this research, news article classification is organized into five selected domains: sports, entertainment, politics, business, and weather news. The classification involves both common and uncommon approaches, along with datasets based on Machine Learning and Deep Learning techniques. Furthermore, the evaluation incorporates various metrics such as precision, recall, and accuracy to compare approaches across the selected five news domains with datasets. To narrow the focus, we limited the news categorization to a few domains (sports, entertainment, politics, business, and weather) to facilitate a better understanding of a large amount of data through concise content. We recommend our work to individuals interested in extending and building upon my research over time.</em></p>2023-12-28T00:00:00+05:00Copyright (c) 2023 VAWKUM Transactions on Computer Scienceshttps://vfast.org/journals/index.php/VTCS/article/view/1627User-Centric Context-Aware Location-Based Service for ATM’s Users2023-11-14T19:54:44+05:00Abdul Rehman Balocharehman.baloch@usindh.edu.pkKamran Taj Pathankamran.taj@usindh.edu.pkAzhar Ali Shahazhar.shah@usindh.edu.pkMujeeb-ur-Rehman Jamalimujeebjamali@usindh.edu.pkMuhammad Ali Balochmuhammadbaloch@aydin.edu.tr<p>The article discusses a context-aware system designed to help Automated Teller Machine (ATM) users quickly locate a working ATM with cash. Many people rely on ATMs for quick cash withdrawals, but often waste time searching for a working machine. The proposed system takes into account the user’s environmental context, such as their activity, the availability of cash in the ATM, the on/off status of the machine, and the presence of a line or crowd at the ATM booth. The objective of the system is to enhance the ATM locator according to the user’s specific needs, utilizing advanced features to recommend the best option for ATM customers based on their current situation. This user-centric approach aims to provide a more efficient and effective system for ATM users.</p>2023-12-06T00:00:00+05:00Copyright (c) 2023 VAWKUM Transactions on Computer Scienceshttps://vfast.org/journals/index.php/VTCS/article/view/1602Public data security using Ethereum Smart Contract2023-09-18T19:24:49+05:00Mehak Ziamehakzia.ranaa@gmail.comMuhammad Kamrankamranabidhiraj@gmail.comDr. Naeem Aslamnaeemaslam@nfciet.edu.pkMuhammad Fuzailfuzail@nfciet.edu.pk<p>Smart contracts, a unique form of blockchain technology, enable financial transactions on the Ethereum blockchain. However, the blockchain paradigm's decentralized structure raises security concerns and has been linked to significant financial losses. Contrary to typical financial entities, Ethereum lacks centralized controls to solve these challenges. These problems have been addressed and Ethereum's security has been enhanced by symbolic execution, which has grown to be a well-known technique for guaranteeing programme integrity. The security of the blockchain can be improved more efficiently by using this method to assess Ethereum's security and identify areas that require the attention of security experts.</p>2023-11-23T00:00:00+05:00Copyright (c) 2023 VAWKUM Transactions on Computer Scienceshttps://vfast.org/journals/index.php/VTCS/article/view/1591Classification of Call Transcriptions2023-09-23T16:02:29+05:00Sulman Malikmscsf16m017@pucit.edu.pkMuhammad Idreesidrees@pucit.edu.pkHafiz Muhammad Danishdanish@uet.edu.pkAshfaq Ahmadashfaqch@gmail.comSalman Khalidsalmank888@gmail.comSaadia Shahzadsaadia.shahzad@pucit.edu.pk<p>Multi-labeled call transcription classification is essential for public and private sector organizations, as they spend a lot of time and workforce manually classifying phone call queries. Implementing a machine learning-based auto classifier can effectively assist in this task, especially by reducing the time and resources required. The<br />paper proposes an efficient call transcription classifier that not only reduces manpower but also saves time significantly. The first step in transcript cleaning involves several essential processes, such as converting the transcript to lowercase, applying word embedding techniques, and removing numbers, punctuation, and stopwords. The second step involves designing the model to incorporate four separate classifiers, each trained<br />independently. Each classifier consists of a bi-directional LSTM layer, an embedding layer, and three subsequent dense layers. These dense layers use the ReLU as an activation function, and softmax as a final layer. The experimental results demonstrate that all four classifiers have achieved precision, recall, and F1-score greater than 80%. In conclusion, we conduct a comparative analysis of the results against existing studies, demonstrating<br />that our model has exhibited superior performance.</p>2023-10-07T00:00:00+05:00Copyright (c) 2023 VAWKUM Transactions on Computer Scienceshttps://vfast.org/journals/index.php/VTCS/article/view/1587Formal Modeling and Analysis of Air Traffic Control System Using Petri Nets2023-09-08T17:00:01+05:00Muhammad Ilyas Fakhirfakhir@gcu.edu.pkAmber Razzaqamber9522@gmail.comAsad Raza Kazmiarkazmi@gcu.edu.pkAwais Qasimawais@gcu.edu.pk<p><em>Air traffic control (ATC) system in airports is one of the most complex systems due to the huge number of requirements in the framework of air traffic management. The incessant increase in air traffic over the past few decades, so it is more challenging for ATC System to manage flow of the aircraft using one runway. To organize and expedite the flow of<br />air traffic, we proposed a formal model of ATC using two runways by Hierarchical timed Color Petri Net. HTCPN is appropriate to present complex reactive system. ATC assign landing and taking over runways according to the first-come-first-served (FCFS) approach. CPN tool is used for simulation and analysis of proposed model. Space state analysis is<br />performed to check the behavior of model like boundedness, liveness and dead lock properties etc. Performance analysis is conducted to check accuracy of model.</em></p>2023-11-01T00:00:00+05:00Copyright (c) 2023 VAWKUM Transactions on Computer Scienceshttps://vfast.org/journals/index.php/VTCS/article/view/1582The Quality Analysis of Food and Vegetable from Image Processing2023-08-23T17:34:57+05:00Abdul Khalique Balochak.balouch94@gmail.comProf Dr. Ali Okatanaliokatan@aydin.edu.trMujeeb-ur-Rehman Jamalimujeebjamali@usindh.edu.pkNadeem Ahmed Kanasronadeem.kanasro@usindh.edu.pkMuhammad Ali Balochmuhammadbaloch@aydin.edu.trAsad Ali Jamaliasadjamali15@gmail.com<p class="Defafult2">The quality analysis of food and vegetable from image is hot topic now a day, where researchers make them better then pervious findings through different technique and methods. In this research we have review the literature, and find gape from them, and suggest better proposed approach, design the algorithm, developed a software to measure the quality from images, where accuracy of image show better results, and compare the results with Perouse work done so for. The Application we use an open-source dataset and python language with tensor flow lite framework. In this research we focus to sort food and vegetable from image, in the images, the application can sort and make them grading after process the images; it could create less errors them human base sorting errors by manual grading. Digital pictures datasets were created. The collected images arranged by classes. The classification accuracy of the system was about 94%. As fruits and vegetables play important role in our day to day life, the quality of fruits and vegetables is needed in evaluating agricultural produce, customer always buy good quality fruits and vegetables. This document is about quality detection of fruit and vegetables using images. Most of customers suffering due to unhealthy foods and vegetables by suppliers so there is no proper quality measurement level followed by hotel managements. I have developed an application to measure the quality of the fruits and vegetables by using images, it will tell you how is your fruits and vegetables are fresh or rotten. A large number of algorithms have been used in this project, including digital images, ResNet, VGG16, CNN and Transfer Learning grading feature extraction. This application used an open source dataset of images and language used python, and designs a framework of system.</p>2023-10-10T00:00:00+05:00Copyright (c) 2023 VAWKUM Transactions on Computer Scienceshttps://vfast.org/journals/index.php/VTCS/article/view/1521Encryption Techniques and Algorithms to Combat Cybersecurity Attacks: A Review2023-07-11T06:41:53+05:00Shuaib Ahmed Wadhoshoaib.qau09@gmail.comAreej Fatemah Meghjiareej.fatemah@faculty.muet.edu.pkAun Yichietaunyc@utar.edu.myRoshan Kumarroshan.nih@gmail.comFarhan Bashir Shaikhfarhan.shaikh@usindh.edu.pkThe danger of cyber-attacks is constant in the current digital environment. The necessity for effective security actions are more crucial than ever before due to the increasingly complex nature of cybersecurity attacks. Using encryption approaches and algorithms is one of the best ways to secure more sensitive data from cyber-attacks. In order to effectively defend against cybersecurity assaults, this research study attempts to give an analysis of the function that encryption methods and approaches serve. We investigate various encryption algorithms and techniques, their advantages and disadvantages, and their applications. In addition, we investigate the difficulties of encryption and the potential solutions to these difficulties.2023-06-30T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTCS/article/view/1494Test Driven Development and Its Impact on Program Design and Software Quality: A Systematic Literature Review2023-07-11T06:30:17+05:00Dua Aghaduaagha2@gmail.comRashida Sohailrashdakhanzada@gmail.comAreej Fatemah Meghjiareej.fatemah@faculty.muet.edu.pkRamsha Qaboolioramshaqaboolio@gmail.comSania Bhattisania.bhatti@faculty.muet.edu.pk<span>Test-Driven Development (TDD) is a methodology in software development that necessitates tests to be written before to the production code. This approach can be used in any software development paradigm that involves writing code, including Agile, Scrum, XP, and Lean. This research paper surveys the impact of TDD on software development with a specific focus on its effects on code coverage, productivity, internal and external software quality, and the affective reactions associated with TDD. The paper also identifies potential challenges and drawbacks of implementing TDD, such as increased overhead and time consumption, a learning curve for developers, and difficulty in testing certain types of code. The studies’ results suggest that TDD can improve code coverage, and code quality, reduce defects, increase productivity and developer satisfaction, improve internal and external software quality, and ultimately lead to higher customer satisfaction. </span>2023-06-24T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTCS/article/view/1493W-rank: A keyphrase extraction method for webpage based on linguistics and DOM-base features2023-07-11T06:30:16+05:00Himat Shahshafiqueawan925@gmail.comDr. Shafique AhmedShafique.awan@bbsul.edu.pkAnwar Ali Sathioshafiqueawan925@gmail.comDr Asadullah Burdishafiqueawan925@gmail.com<p><strong><em>Th</em></strong><strong><em>is paper addresses the problem of an automatic keyphrase extraction for a webpage text. Our method is unsupervised, and we call it W-rank. In our method, first we extract the text of a webpage and tokenize into three different candidate words list: unigram ,bigrams and noun phrases. Then we assign score to all words based on their individual appearance in linguistic and DOM-based feature sets. In the final step, we rank these candidate words using score and select top 5 keyphrase from each list and combine them as a final keyphrases for a given webpage. We focus more on the relevancy of keyphrases to its content using linguistic features. We compare our method with other methods using precision, recall and f-score. The experimental result shows, W-rank improves the performance of our previous method D-rank and outperforms other state of art methods.</em></strong></p>2023-05-30T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTCS/article/view/1491Robot Assist Sign Language Recognition for Hearing Impaired Persons Using Deep Learning2023-07-11T06:30:16+05:00Kashaf khan2k20mscs113@nfciet.edu.pkDr. Naeem Aslam2k20mscs113@nfciet.edu.pkKamran Abid2k20mscs113@nfciet.edu.pkSafa Munir2k20mscs113@nfciet.edu.pkThe adoption of Sign Language Communication (SLC) systems has become more significant in closing the interaction between the deaf society and the world of hearing people. In this study, researchers aim to contribute to this field by developing a system that helps sign language users communicate through BERT approaches based on deep learning frameworks as well as NLP. Accurate recognition of sign language is critical for SLC systems to work well. Deep learning models are effective in identifying sign language with high accuracy. This study aims to determine the most suitable DL model for identifying sign language and assess the impact of incorporating Natural Language Processing (NLP) techniques in generating frequent and accurate responses in SLC systems. The NLP model will be developed as an optimum return mechanism to generate frequent responses. This research includes testing three different deep learning models: MLP, CNN, and RestNet50v2 to recognize sign language gestures. Restnet50v2 outscored the other two approaches with a 0.97% perfection. As said earlier, the system also generates automated responses using the NLP BERT model, with an overall accuracy of 0.8% and a BLEU score of 0.83%. This method has a way to enhance interaction among the deaf community via the use of technology, opening new avenues for developing intelligent chatbots that can better understand nonverbal communication. Further research can be done to expand its functionality to recognize a broader range of sign language gestures and improve the user interface. Overall, this study demonstrates how technology can enhance the ways of people with deafness or hearing loss by addressing communication barriers.2023-06-19T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTCS/article/view/1489The Impact of COVID-19 on E-Learning: Context-Based Sentiment Analysis Discourse Using Text Mining2023-07-11T06:30:16+05:00Aqsa Rehman2k20mscs121@nfciet.edu.pkNaeem Aslamaqsa.rehman1995@gmail.comKamran Abidaqsa.rehman1995@gmail.comMuhammad Fuzailaqsa.rehman1995@gmail.comAsif-Ur- Rehmanaqsa.rehman1995@gmail.comFinding the most dominant and pertinent user opinions on a certain topic is crucial to the sentiment analysis success factor. During the pandemic lockdowns around the world, the suspension of academic institutions leads to an exceptional increase in distance education. Academic institutions closed their campuses immediately to mitigate the effects of COVID-19 and prevent its pervasive spread, and educational activities were shifted to online platforms. The effectiveness of online education is a significant topic of interest for both students and their parents, especially in terms of how students and teachers perceive it and how technologically viable it is in a range of social circumstances. Before such a wide adoption of e-learning is possible, these issues must be analyzed from multiple perspectives. The present research aims to evaluate the efficacy of e-learning by examining individuals' perceptions of it. Opinions can be found on websites such as Instagram, Facebook, Twitter, etc. As social media has recently emerged as a significant means of communication. This study addresses factors connected to a significant change in the educational system. 200,000 tweets were gathered from Twitter to evaluate the opinions of Twitter users who were taking part in online learning. This study adopts VADER to analyze the subjectivity and polarity score of tweets, a topic model was also created using the LDA algorithm to determine the themes that were talked about on Twitter the most. The models have been constructed and evaluated using Word2Vec to capture the semantic relationships between words and LSTM and RNN sequential model for sentiment analysis. This study measured the efficiency of a sentiment analysis model using the accuracy metric, the conducted experiments reveal that the proposed hybrid model achieves an overall accuracy of 96.3%. The results also indicate a significant negative impact of the Covid-19 pandemic on individuals' emotions, with 64.4% of the analyzed tweets displaying negative sentiments. These findings provide valuable insights into the relationship between global events and individual emotions on social media platforms.2023-05-27T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTCS/article/view/1474Evaluation of Safe Landing Site Detection Methods for Unmanned Aerial Vehicles2023-07-11T06:30:17+05:00Hamid Ghoushamidghous@gmail.comMubasher H. Malikmubasher@isp.edu.pkDania Majeeddaniamajeed@isp.edu.pkFathima Nuzha Mohamedfatima_lewis1@gmail.comAyesha Nasirayesha_sisp@gmail.comNowadays, aerial vehicles (drones) are becoming more popular. Over the past few years, Unmanned Aerial Vehicles (UAVs) have been used in various remote sensing applications. Every aerial vehicle is now either partially or completely automated. The tiniest type of aerial vehicle is the UAV. The widespread use of aerial drones requires numerous safe landing site detection techniques. The paper aims to review literature on techniques for automatic safe landing of aerial drone vehicles by detecting suitable landing sites, considering factors such as ground surfaces and using image processing methods. A drone must determine whether the landing zones are safe for automatic landing. Onboard visual sensors provide potential information on outdoor and indoor ground surfaces through signals or images. The optimal landing locations are then determined from the input data using various image processing and safe landing area detection (SLAD) methods. UAVs are acquisition systems that are quick, efficient, and adaptable. We discuss existing safe landing detection approaches and their achievements. Furthermore, we focus on possible areas for improvement, strength, and future approaches for safe landing site detection. The research addresses the increasing need for safe landing site detection techniques in the widespread use of aerial drones, allowing for automated and secure landing operations.2023-06-28T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTCS/article/view/1473A Study Towards Exploring Access Control Mechanisms and its Limitations in Cloud Computing2023-07-11T06:30:16+05:00Baby Marinamarina@sbbusba.edu.pkIrfana Memonifanahameed@quest.edu.pkFizza Abbas Alvifizza_alvi@quest.edu.pkMairaj Nabimairaj3738@gmail.comAdnan Manzor RajperAdnan7888@gmail.comUbaidullah Rajputubaidullah@quest.edu.pkCloud computing technologies are growing fast day by day. Cloud technologies are attracting enterprises to themselves by providing great and enhanced services. There is no doubt that cloud technologies reduced the burden of the digital world by giving manageable computing services, huge room for unlimited data storage, on-demand software services, great platforms, and access control management systems. To use cloud-based manageable services users and organizations must have access to the cloud. Before using any access control mechanism, the organizations should know about the limitations of the access control mechanism. At present, many access control mechanisms are available in cloud computing. In this paper, our main goal is to identify the access control mechanisms in cloud computing and their limitations in cloud computing.2023-06-05T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTCS/article/view/1443A Blockchain-Enabled Machine Learning Mask Detection method for Prevention of Pandemic Diseases2023-07-11T06:30:16+05:00Anwar Ali Sathioanwar.sathio@bbsul.edu.pkShafiq Ahmed Awanshafiq.awan@bbsul.edu.pkAli Orangzeb Panhwarorangzeb.panhwar@szabist.edu.pkAli Muhammad AamirAli.Aamir@bbsul.edu.pkAriz Muhammad Brohiariz.brohi@bbsul.edu.pkAsadullah Burdiariz.brohi@bbsul.edu.pk<p>During the COVID-19 pandemic, finding effective methods to prevent the spread of infectious diseases has become critical. One important measure for reducing the transmission of airborne viruses is wearing face masks but enforcing mask-wearing regulations can be difficult in many settings. Real-time and accurate monitoring of mask usage is needed to address this challenge. To do so, we propose a method for mask detection using a convolutional neural network (CNN) and blockchain technology. Our system involves training a CNN model on a dataset of images of people with and without masks and then deploying it on IoT-enabled devices for real-time monitoring. The use of blockchain technology ensures the security and privacy of the data and enables the efficient sharing of resources among network participants. Our proposed system achieved 99% accuracy through CNN training and was transformed into a blockchain-enabled network mechanism with QR validation of every node for authentication. This approach has the potential to be an effective tool for promoting compliance with mask-wearing regulations and reducing the risk of infection. We present a framework for implementing this technique and discuss its potential benefits and challenges</p>2023-05-21T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTCS/article/view/1436Enhancing Card Swipe Machines using Mathematical Model with JFLAP Formal Methods and Automation: A Mathematical Model with JFLAP2023-07-11T06:30:16+05:00Farrukh Arslanmubashirali@lgu.edu.pkSana Hameedmubashirali@lgu.edu.pkNaveed Imranmubashirali@lgu.edu.pkZaid Bin Faheemmubashirali@lgu.edu.pkMubashir Alimubashirali@lgu.edu.pkAutomation is a novel approach that can enhance production capacity, work quality, and working environment, while minimizing labor disputes by automating all handling parameters. Formal methods are scientific techniques used to design complex mathematical systems. They involve specifying requirements and verifying software systems. The card swipe machine is a widely used point-ofsale terminal in supermarkets, medical centers, and shopping malls. Customers can easily make payments through these machines, which also provide detailed receipts of all transactions, including reversed transactions. This resolves cash management issues, improves customer service, and supports marketing. While multiple conventional machines are available in the market, they lack visual representations, making it difficult to understand their working mechanism without graphical representations. Deterministic finite automata (DFA) is a mathematical model that has limited states and moves from one state to another based on input and transition functions. This study proposes the use of the JFLAP software to create a mathematical model of card swipe machine transactions. The proposed model allows for viewing each processing step in a card swipe machine, offering a new approach to understanding their working mechanism.2023-03-31T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTCS/article/view/1415Identifying Cancer Patients at risk for Heart Failure using deep learning models2023-07-11T06:30:16+05:00Muhammad Anismalikanees48@gmail.comAdnan Majeedmalikanees48@gmail.comMudassir Khalilmalikanees48@gmail.comNaeem Aslammalikanees48@gmail.comThe cardiotoxicity that may occur as a side effect of cancer treatments has emerged as a significant problem. Cancer patient’s quality of life may be improved if those at risk of cardiotoxicity are identified early and given prophylactic treatments before receiving cardio toxic drugs. The advancement of deep learning will help to support medical practitioners in their ability to make accurate. This study will focus on predicting the enhancement of heart failure in cancer patients. The purpose of this research is to determine whether historical data from electronic health records can accurately predict the occurrence of heart failure in cancer patients. We investigated deep learning algorithms by applying them to 300 cancer patient’s dataset drawn from the Seer database. We determined that there were a total of 300 eligible cases and matched them with controls according to gender age and the primary cancer type etc. Results from the tests suggest that techniques<strong> </strong>based on deep learning may effectively capture clinical characteristics linked with heart failure in cancer patients.2023-03-18T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTCS/article/view/1413Evaluation of Deep Learning Approaches for Sentiment Analysis2023-07-11T06:30:16+05:00Sheikh Muhammad Saqibsaqibsheikh4@gu.edu.pkTariq Naeemsaqibsheikh4@gu.edu.pkShakeel Ahmadsaqibsheikh4@gu.edu.pkAlmuhannad Sulaiman Alorfisaqibsheikh4@gu.edu.pk<p>Due to the increasing popularity of posting evaluations, sentiment analysis has grown to be a crucial area of study. Machine learning techniques that are supervised, unsupervised, and semi-supervised have worked very hard to harvest this data. The complicated and technological area of feature engineering falls within machine learning. Using deep learning, this tedious process may be completed automatically. Numerous studies have been conducted on deep learning models like LSTM (Long Short-Term Memory), CNN (Convolutional Neural Network), RNN (Recurrent Neural Network), and GRU (Gated Recurrent Unit). Each model has employed a certain type of data, such as CNN for pictures and LSTM for language translation, etc. To discover the optimal deep learning methodology for the given data, authors here proposed many deep learning methodologies for text data on sentiment analysis. A publicly available dataset including both positive and negative reviews on LSTM, CNN, RNN, and GRU was used in the experiments, and the findings showed that CNN had the highest accuracy compared to the other models. Based on the experimental results of CNN, it was found that prediction from the proposed work exhibited a significant improvement over existing work.</p>2023-03-17T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTCS/article/view/1407Statistical Methods in Computer Science: A Comparative Review of Inductive and Deductive Approaches2023-07-11T06:30:16+05:00Sidra Niazsidraniaz@sbbwu.edu.pkDr. Fouzia jabeensidraniaz@sbbwu.edu.pkDr.Tabinda Salamsidraniaz@sbbwu.edu.pkDr. Shah Nazirshahnazir@uoswabi.edu.pkCombination issues lie at the core of computer science and modern discrete mathematics. Artificial intelligence lays the foundation for induction and deduction techniques. Induction in computer science involves establishing statements based on specific to general observations, while deduction operates in the opposite direction. In this paper, we analyze induction and deduction using three criteria: the difference in space and time complexity, inconsistencies within induction and deduction, and their application areas within the computer science domain. Induction enhances the power of observation and analysis, whereas deduction plays a crucial role in the logical realm of computer science. Deduction is primarily employed for quantitative analysis, including statistical analysis.2023-05-30T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTCS/article/view/1396DeepImmuno-PSSM: Identification of Immunoglobulin based on Deep learning and PSSM-Profiles2023-07-11T06:30:16+05:00Ali Ghulamgarahu@sau.edu.pkZar Nawab Khan Swatizarnawab@kiu.edu.pkFarman Alifarman335@yahoo.comSaima Tuniosaima.tunio@gmail.comNida Jabeenjabeennda@yahoo.comNatasha Iqbaliqbalnatasha51@gmail.com<p>Immunoglobulin has a close connection to a number of disorders and is important in both biological and medicinal contexts. Therefore, it is crucial for illness research to employ efficient techniques to increase the categorization accuracy of immunoglobulins. Computational models have been used in a small number of research to address this important issue, but the accuracy of the predictions is not good enough. As a result, we use a cutting-edge deep learning technique with convolutional neural networks to enhance the performance results. In this study, the immunoglobulin features were extracted using the dipeptide acid composition (DPC) with the position-specific scoring matrix (DPC-PSSM) and position-specific scoring matrix-transition probability composition (PSSM-TPC) methods. we apply extracted features information from the DPC-PSSM profiles and PSSM-TPC profile by using a 1D-convolutional neural network (CNN) over an input shape. The outcomes demonstrated that the DeepImmuno-PSSM method based on sequential minimal optimization was able to properly predict DPC-PSSM accuracy score 93.44% obtained and of the immunoglobulins using the greatest feature subcategory produced by the PSSM-TPC feature mining approach accuracy score 89.92% obtained. Our findings indicate that we are able to provide a useful model for enhancing immunoglobulin proteins' capacity for prediction. Additionally, it implies that employing sequence data in deep learning and PSSM-based features may open up new path for biochemical modelling.</p>2023-03-17T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTCS/article/view/1385A Survey on Blockchain-based Intrusion Detection Systems for IoT2023-07-11T06:30:16+05:00Jawad Hassanjawadhassan521@gmail.comMuhammad Kamran Abidjawadhassan521@gmail.comMughees ahmadgarahu@sau.edu.pkAli Ghulamgarahu@sau.edu.pkMuhammad Salman Fakhargarahu@sau.edu.pkMuhammad Asifgarahu@sau.edu.pk<p>The Internet of Things (IoT) is a contemporary concept that unifies the Internet and physical objects across various domains, such as home automation, manufacturing, healthcare, and environmental monitoring. This integration enables users to leverage Internet-connected devices in their daily routines. Despite its numerous advantages, IoT also presents several security challenges. As the popularity of IoT continues to grow, ensuring the security of IoT networks has become a critical concern. While encryption and authentication can enhance the security of IoT networks, protecting IoT devices against cyber-attacks remains a complex task. A successful cyber-attack on an IoT system may not only result in information loss but also potentially cripple the entire system. Intrusion detection systems (IDS) are instrumental in identifying malicious activities that could compromise or disrupt network performance. Consequently, there is a pressing need for effective IDS solutions to safeguard IoT systems. Blockchain, an emerging technology, bolsters security systems to counter modern threats. In this paper, we provide an extensive review of state-of-the-art blockchain-based intrusion detection systems for IoT applications. Additionally, we present recent advancements in addressing security concerns in a tabular format. Lastly, we identify open challenges and current limitations that warrant further exploration.</p>2023-05-02T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTCS/article/view/1384Detection of Crackle and Wheeze in Lung Sound using Machine Learning Technique for Clinical Decision Support System2023-07-11T06:30:16+05:00Syed Waqad Aliswaqad@ssuet.edu.pkMuhammad Asifabc@gmail.comMunaf Rashidbnu@gmail.comSania Tanvirabc@gmail.comSarmad Shamswty@gmail.comSidra Abidsdf@gmail.comThis study aims to develop a computer-based clinical decision support system that will help clinicians and healthcare personnel to make an early and correct decision to prevent the patient from nontransmissible respiratory diseases. The main contribution of this study is to analyze, investigate, and extraction of the useful feature of pathological respiration and Classification of Crackle and Wheeze from recorded lungs sound by using machine learning techniques. In the particular spectrogram, Time-frequency and Mel-Frequency cepstral coefficient (MFCC)technique is applied for feature analysis and data conversion into a format that can be useful for feature extraction and training models. PCA dimensional reduction technique is used to reduce the dimensionality of the extracted feature. In order to apply various machine learning techniques a widely used dataset freely available dataset ICBHI-2017 is used. The respiratory lungs sound is comprised of 126 patients with 920 Chest sound annotations that include adventitious sounds such as “Crackle” and “Wheeze”. Machine learning algorithms such as MusicANN, VGGish, and OpenL3 were applied for testing the better accuracy of the classification model. The accuracy of the utilized classifier with the extracted feature set is determined as 72%, 81%, and 69% respectively.2023-03-18T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTCS/article/view/1379Comparative Analysis of Privacy Preserving Location Based Services Mechanisms2023-07-11T06:30:16+05:00Muzamil Hussainfizza_alvi@quest.edu.pkFizza Abbas Alvifizza_alvi@quest.edu.pkUbaidullah Rajputfizza_alvi@quest.edu.pkRecent trends in computing have enabled the provision of location-based services, offering practicality and convenience to users. Moreover, this has also given rise to new challenges and vulnerabilities that can potentially compromise user privacy. As these services are predominantly used on handheld devices, the risk of security breaches is higher. This research collates existing studies that have conducted quantitative and qualitative comparisons and analyses on how to address related challenges, with a particular focus on protecting user privacy in location-based services.2023-05-08T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTCS/article/view/1373Hate Speech Detection Model on Web 3.0 Based Platform using Blockchain and NLP2023-03-13T18:34:54+05:00Muhammad Shahraiz Durranishoaib.farooq@umt.edu.pkUsman Alis2021114004@umt.edu.pkAbstract With the increased usage of social media applications like Facebook, Twitter, or Instagram, hate speech is also rising. Hate speech can be defined as ill<br />talk toward any race, caste, religion, or ethnicity. Now with the new development of web 3.0, which is decentralized, it is challenging to control elements like hate speech because there is no central body that can control it. This research paper presents a novel approach for detecting hate speech on web 3.0-based platforms using blockchain technology and natural language processing (NLP) techniques. The proposed model utilizes blockchain to ensure the immutability and transparency of the data, while NLP algorithms are used to analyze and classify the text. The experimental results show that the proposed model achieves high accuracy in detecting hate speech, and the use of blockchain technology enhances the trustworthiness and security of the system. The proposed system can effectively<br />detect and mitigate hate speech on web 3.0-based platforms and may serve as a valuable tool for promoting online safety and inclusivity.2022-06-30T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTCS/article/view/1364A Review of Cellphone Healthcare Applications: Content Privacy and Safety Issues, Challenges and Recommendations2023-07-11T06:30:16+05:00Hudabia MurtazaS2022288008@umt.edu.pkMuhammad Zubair KhanS2022288008@umt.edu.pkMansoor Ahmad RasheedS2022288008@umt.edu.pkShahzaib IkramS2022288008@umt.edu.pkMannan Ahmad RasheedS2022288008@umt.edu.pkMehnaz RasheedS2022288008@umt.edu.pk<p class="Abstract">Nowadays, cellphone healthcare applications are receiving a considerable amount of attentiveness from both researchers and developers. Advances in communication technologies have aided the evolution in the usage of cellphones and digital devices and present challenges in terms of the accuracy and reliability of cellphone healthcare applications. Nevertheless, these applications may compromise crucial threats related to the seclusion and safety of users’ health content. Awareness of these challenges can help cellphone and cellphone application producers to manufacture efficient tools to allow patients and users to access the services of these technologies very effectively. The main objective of this research paper is to recognize the potential limitations and strengths regarding content seclusion and safety for the development and widespread utilization of effective cellphone healthcare applications. We have employed a literature survey and a relative comparison of the top ten top-rated cellphone healthcare applications to recognize security threats and characteristics that can support developers in building healthcare applications with necessary seclusion and safety standards and allow the users to select the appropriate application for their personal use.</p>2023-03-17T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTCS/article/view/1363The Significance of IoT: A Healthcare Systems Perspective2023-02-24T18:03:02+05:00Mansoor Ahmad RasheedS2022288008@umt.edu.pkHudabia MurtazaS2022288008@umt.edu.pkHamza Shahab AwanS2022288008@umt.edu.pkShahzaib IkramS2022288008@umt.edu.pkMannan Ahmad RasheedS2022288008@umt.edu.pkMehnaz RasheedS2022288008@umt.edu.pk<div><table width="680" cellspacing="0" cellpadding="0"><tbody><tr><td align="left" valign="top" height="282"><div><p><em>In the current era of modern technologies, the health of the patient demands real time monitoring system. This dynamic system can be developed by using efficient sensors, network and internet cloud either wire or wireless. For example, for heart patient blood pressure and pulse must be measure constantly, in case if the patient is in moving and changing his position. For this purpose, an efficient system is required. In future there will be many other problems such as viruses attach detection, dingy fever detection, and sugar problems. For all these problems there will be multiple parameters of patient must me monitor and control. In this paper a method will be device to monitor all these parameters in real time. Moreover, we are concentrating on using mobile agents to provide patient assistance and healthcare services in order to help with the diagnosis of patient’s illnesses Furthermore, platform-agnostic solutions for healthcare data collection and dissemination over NoSQL are being studied. The Apache Jena Fuseki NoSQL database with the JAVA Example Application Framework -JADE client platform was used in testing environment. The consequences show that No Structure Query Language version beats the rel-database implementation. </em></p></div></td></tr></tbody></table></div>2022-12-31T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTCS/article/view/1355Formal Specification and Verification of Distributed Denial of Service (DDoS)2023-02-24T18:03:02+05:00Sara Hafeezsarahafeez48@gmail.comMuhammad Atifmuhammad.atif@cs.uol.edu.pkMudasser Naseermudasser.naseer@cs.uol.edu.pkDDoS (Distributed Denial of Service) attack is the main cause for interrupting the requests of users. DDoS uses more than one IP addresses. It makes botnets (machines that are affected with malware), through which interruption of a service begins and the requests are either denied or delayed to the legitimate users. A protocol is introduced in [DDoS Attack Detection Method Based on Network Abnormal Behavior in big data environment, CoRR, vol. abs/1903.11844, 2019] for the detection of DDoS in which a threshold is defined for detection of illegitimate users. We exhibited simulating of the protocol using a model checker UPPAAL and formally verified the functional requirements of the protocol to determine the system’s accuracy.2022-12-31T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTCS/article/view/1351AOPs-XGBoost: Machine learning Model for the prediction of Antioxidant Proteins properties of peptides2023-10-16T23:02:00+05:00Sikander Rahusikander@stu.xidian.edu.cnAli Ghulamsikander@stu.xidian.edu.cnZar Nawab Khan Swatisikander@stu.xidian.edu.cnJawad Usman Arshedsikander@stu.xidian.edu.cnMuhammad Shahid Maliksikander@stu.xidian.edu.cnNauman khansikander@stu.xidian.edu.cn<p>Abstract Antioxidant proteins are essential for protecting cells from free radicals. The accurate identification of antioxidant proteins via biological tests is difficult because of the high time and financial investment required. The potential of peptides produced from natural proteins is demonstrated by the fact that they are generally regarded as secure and may have additional advantageous bioactivities. Antioxidative peptides are typically discovered by analyzing numerous peptides created when a variety of proteases hydrolysis proteins. The eXtreme Gradient Boosting (XGBoost) technique was used to create a novel model for the current study, which was then compared to the most popular machine learning models. We suggested a machine-learning model that we named AOPs-XGBoost, built on sequence features and Extreme Gradient Boosting (XGBoost). We used 10-fold cross-validation testing was performed on a testing dataset using the propose. AOPs-XGBoost classifier, and the results showed a sensitivity of 67.56%, specificity of 93.87%, average accuracy of 80.72%, mean cross-validation (MCC) of 66.29%), and area under the receiver operating characteristic curve (AUC) of 88.01%. The outcomes demonstrated that the XGBoost model outperformed the other models with accuracy of 80.72% and area under the receiver operating characteristic curve of 88.01% which were better than the other models. Experimental results demonstrate that AOPs-XGBoost is a useful classifier that advances the study of antioxidant proteins.</p>2022-12-31T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTCS/article/view/1347XGboost-Ampy: Identification of AMPylation Protein Function Prediction Using Machine Learning2023-02-24T18:03:02+05:00Zar Nawab Khan Swatizarnawb@kiu.edu.pkAli Ghulamgarahu@sau.edu.pkMuhammad Sohailzarnawb@kiu.edu.pkJawad Usman Arshedzarnawb@kiu.edu.pkRahu Sikanderzarnawb@kiu.edu.pkMuhammad Shahid Malikzarnawb@kiu.edu.pkNauman khanzarnawb@kiu.edu.pk<p>A developing post-translational modification known as AMPylation involves the formation of a phosphodiester bond on the hydroxyl group of threonine, serine, or tyrosine. Adenosine monophosphate is covalently attached to the side chain of an amino acid in a peptide during this process, which is catalyzed by AMPylation. We used AMPylation peptide sequence data from bacteria, eukaryotes, and archaea to train the models. Then, we compared the results of several feature extraction methods and their combinations in addition to classification algorithms to obtain more accurate prediction models. To prevent additional loss of sequence information, the PseAAC feature is employed to construct a fixed-size descriptor value in vector space. The basic feature set is received from 2nd features extraction method. All of this was accomplished by deriving the protein characteristics from the evolutionary data and sequence of the BLOUSM62 amino acid residue. The eXtreme Gradient Boosting (XGBoost) technique was used to create a novel model for the current study, which was then compared to the most popular machine learning models. In this research, we proposed framework for AMPylation identification that makes use of the XGBoost algorithm (AMPylation) and sequence-derived functions. XGBoost -Ampy has an accuracy of 86.7%, a sensitivity of 76.1%, a specificity of 97.5%, and a Matthews’s correlation coefficient (MCC) of 0.753 for predicting AMylation sites. XGBoost -Amp, the first machine learning model developed, has shown promise and may be able to help with this problem.</p>2022-12-31T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTCS/article/view/1342Questgator: A Platform for Content Aggregation and Text Classification2023-02-24T18:03:02+05:00Abdul Latif Shaikh18cs21@quest.edu.pkFizza Abbas Alvifizza_alvi@quest.edu.pkBabar AliBabarburiro@gmail.comUbaidullah Rajputubaidullah@quest.edu.pkHadi Bux18cs03@quest.edu.pkThe Web has witnessed a surge in content over recent years. Content is revolutionizing the way people conduct business, communicate, and make informed decisions. However, the vast amount of data used for communication today is often<br />unstructured and challenging to comprehend. Content aggregators provide a solution to this problem by collecting data from various sources and organizing it into a structured format in one place. This research proposed the content aggregator "Questgator" that extracts content for example news, scholarships, jobs, books, video content, and research papers. In this paper Naive Bayes theorem is used for text classification. Moreover, paper also provides comparison with other platforms to show the efficiency of proposed content aggregator.2022-12-31T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTCS/article/view/1329Identification of an Optimized Google PageSpeed Audit-Rule-Sequence to Optimize Page Speed2023-07-11T06:30:16+05:00Abdul Ghaffarabdul.ghafar@umt.edu.pkFazeel Abidfazeel.abid@umt.edu.pkMohsin Ashrafmohsin636@yahoo.comAbdul Jamilabdul.jamil@ucp.edu.pkAli Abbasali.abbas@ucp.edu.pkFarah Rauf Malikfarahrauff878@gmail.comWorld Wide Web is a collection of online resources and websites including e-commerce, social sites, educational content, etc. To find relevant online resources, people search these by using search engines by providing their desired keywords. After filtering those keywords, search engine list the most relevant websites which are more optimized and efficient in terms of loading speed. Search engine optimization is a set of techniques used to make a website optimized and relevant to those keywords, and set the rank of a website. An online resource or website will be on the top of the search result set if it has a higher rank in search engines. Page speed is one of the most important on-page search engine optimization techniques that is used to make web site efficient in load time, so the user will get the content of the websites in a minimum time. Google has set page speed as the main factor in a higher ranking in search engines. Getting higher page speed is not an easy task, as several performance matrices must be optimized to get efficient loading time. There are many audit rules which are irrelevant or have less impact on the performance score. So selection of audit rules to be optimized is one of the main decisions before starting page speed optimization work. It will waste of time to investigate audit rules for their impact on performance scores. In this paper, we have analyzed all of the audit rules and identified the most important and relevant audit rules in optimizing page speed. A tool is used to generate the best sequence of relevant audit rules based on weighted performance benefit scores in the execution of each audit rule. The same audit rule sequence is applied on five different websites and is found more than 80% improvement in performance scores by applying the first three audit rules only and above 90% performance score obtained by using the first five to seven audit rules in our proposed audit rules sequence.2023-04-02T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTCS/article/view/1311Business Growth Prediction Using Social Media Data Analytics2023-02-24T18:03:02+05:00Hadi Bux18cs03@quest.edu.pkBabar Alibabarburiro@gmail.comFizza Abbas Alvifizza_alvi@quest.edu.pkIrfana Memonirfanahameed@quest.edu.pkMuhammad Awais Rajputawaisrajput@quest.edu.pkMarketing has become an important aspect of the growth of any business. Without good strategies for sharing content across social media platforms, no business can flourish and will lose its customers. Many social media platforms provide various analytics tools for free. These tools provide analytics of content engagement. Many proprietary tools provide such features with enhanced capabilities. These tools require shared content of users for analysis. These tools do not exactly state the content being shared. Businesses need marketing teams for creating attractive content. However, a lot of money is needed for hiring skilled personnel. This research proposed an efficient platform that provides analysis of content shared by successful businesses on social media platforms. Firstly, it’s free and public shared data, no surveys to be done because the analysis is done on businesses who are experts in marketing, and secondly, there is no headache for searching trends because the analysis is done on real-time data.2022-12-31T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTCS/article/view/1305Research in Collaborative Tagging Applications: Choosing the Right Dataset2023-07-11T06:30:16+05:00Dr. Fouzia Jabeenfouzia.jabeen@sbbwu.edu.pkShah Khusrokhusro@uop.edu.pkNasreen Anjumnanjum@glos.ac.ukCollaborative tagging is an interesting approach that provides the flexibility to add description(s) to a resource according to the user’s own perception about that resource. These applications are the hottest in the areas of Social Bookmarking, Media Content Sharing and E-Commerce. Being favorite among users, these applications accumulate users’ interactions in the form of embedded datasets very quickly. These datasets are very important for further improving these applications and subsequently facilitating the user in better performing his/her activities. We feel there is a need to study these datasets to help researchers test their proposed algorithms on the right dataset and make valuable assessment and informed decisions. In this paper, we have identified measures for evaluating collaborative tagging applications’ datasets suitability for research experiments. The appropriateness of the identified measures is tested through experiments. Based on the results, recommendations are made on the suitability of the available datasets and how future dataset should look like. Researchers working not only in tagging but also in other disciplines can utilize these datasets to test their proposed algorithms without developing their own. This article provides measures which we dig out by reviewing existing available datasets. These measures are significant in selection of suitable and appropriate dataset(s), as selection of inappropriate dataset leads to errors in the results researchers are expecting. This work will prove extremely relevant and beneficial to all researchers who wish to use datasets of collaborative tagging applications for their research experiments.2023-03-05T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTCS/article/view/1278Performance Prediction for Undergraduate Degree Programs Using Machine Learning Techniques - A Preliminary Review2023-02-24T18:03:02+05:00Waqar Un Nisawaqarmudasser@gmail.comMudasser Naseermudasser.naseer@cs.uol.edu.pkMuhammad Atifmuhammad.atif@cs.uol.edu.pkSalwa Muhammad Akhtarsalwa.akhtar@umt.edu.pkMehr Un Nisamehrunisa@gmail.comAcademic Performance prediction for undergraduate students is considered as one of the hot research areas since last couple of decades. An accurate and timely prediction of the student’s performance can directly influence the three participants; learner, instructor and the institution. This study presents a brief, preliminary review to explore existing literature from 2010 to 2022 in the context of performance prediction for Undergraduate Degree Programs (UDP). This review is organized according to Online and Traditional Education Systems (TES), and granularity level of performance output i.e., Degree program (Final CGPA), Next-semester, and the Course level grades. Aggregate analysis of the extracted data reveals that course level prediction is highly worked area deploying classification and regression techniques using data from academic domain. Existing empirical studies are mostly evaluated using accuracy, precision, recall and F1-measure and are validated with 10-fold cross validation. Contribution of this study is the novel categorical distribution of studies with respect to education system and granularity levels. Another important finding was the Success ratio of different Machine learning (ML) techniques used for these prediction studies. It is concluded that further research is required for TES to discover interdependent group of courses and Course Clusters for a certain degree program and then to develop prediction models for those course clusters.2022-12-31T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTCS/article/view/1273Formal Verification of Twin Clutch Gear Control2023-03-12T02:43:54+05:00Muhammad Zamanzamansharif90@gmail.comMuhammad Atifmuhammad.atif@cs.uol.edu.pkMudassar Naseermudassar.naseer@cs.uol.edu.pk<p>Twin clutch model enables the power-shifts as conventional planetary automatic transmission and eradicates the disadvantages of single clutch transmission. The automatic control of the dual clutches is a synchronization problem. Particularly, to control the clutching component that engages torque when running in one direction of revolution and disengages when running in the other direction, which exchange the torque smoothly during torque phase of the gear-shifts on planetary-type automatic transmissions, seemed for quite a while hard to compensate through clutch control. Another problem is to skip gears during multiple gearshifts. However, the twin clutch gear control described in ["M Goetz, M C Levesley and D A Crolla. Dynamics and control of gearshifts on twin clutch transmissions, Proceedings of the Institution of Mechanical Engineers, Journal of Automobile Engineering 2005"], a significant improvement in twin clutch gear control system is discussed. We formally specify the algorithm for the twin clutch gear control system and verify it using the model-checking. Formal methods have a high potential to measure correctness of communicating protocols. We use UPPAAL for formal specification and verification. Our results show that the twin clutch gear control model partially fulfills its functional requirements</p>2022-12-30T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTCS/article/view/1271Pneumonia Classification from Chest X-ray Images Using Pre-Trained Network Architectures2023-03-12T02:44:45+05:00Aqsa Shahzadaqsashahzad888@gmail.comMuhammad Asad Arshedmuhammadasadarshed@gmail.comFarrukh Liaquatfarrukh.liaquat@umt.edu.pkMuhammad Tanveermuhammad_tanveer@umt.edu.pkMahmood Hussainmahmood.hussain@umt.edu.pkRabbia Alamdarrabbia.alamdar0@gmail.com<span>Pneumonia is a serious disease caused by a lung infection that affects young and old people and approximately cause of 4 million deaths each year. Patients that are facing disorders such as weak immune systems, asthma, and babies all are at risk specifically if pneumonia is not detected at an early stage. An early diagnosis of pneumonia is required to plan a potential treatment strategy to control and treat the condition. The objective of this study is to analyze chest radiograph images to identify lung abnormalities using pretrained architecture. After extracting features from the images using convolutional neural network models that have been pre-trained on a large dataset called ImageNet, they are typically passed through a classifier for further processing and diagnosis. Pre-trained networks variants including VGG16, VGG19, DenseNet121, ResNet50, and InceptionV3 architecture were utilized in this study & results show that VGG-16 architecture performance is effective with a test accuracy of 90% and validation accuracy of 93.98% than other pretrained architectures.</span>2022-12-30T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTCS/article/view/1268Application of Blockchain Technology in Energy Sector for Sustainable Future2023-03-12T02:43:11+05:00Lubna Farhilfashi@ssuet.edu.pkUmme Lailamishaaahmed242@gmail.comAfshaar Ahmedafshaarahmed123@gmail.comMishaal Ahmedmishaaahmed242@gmail.comManzar Ahmedmanzara@ssuet.edu.pkFahad Ahmad Siddiquifahmeds@ssuet.edu.pkIn old energy control system, there was no freedom for users to sale or purchase energy with their own choice and rate because system was centralized and also there were many issues such as electricity theft cases and losses and burden of these losses directly inculdded in public bills. Now after the introduction of blockchain these issues has been resolved such as the blockchain technology give freedom to user to sale or purchase energy according to the own rate with secure transaction system. The conventional energy system with centralizedcontrol technique fails to resolve many issues such as freedom to user’s to sale or purchase energy in network in secure way and combination of blockchain and Microgrid has all feature to resolve all present isssues. In this paper, the blockchain technology features and application of blockchain with clean energy system will be investigate to provide cheap electricity to users by using Microgrid because Blockchain provide complete solutions for energy distribution and trading. In addition, somemajor present issues will be focus such as low efficiency, losses and ant algorithm model to distribute the energy in the network efficiently.2022-12-26T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTCS/article/view/1259Pathway-disease Association Prediction Based on Graph Regularized Logistic Matrix Factorization (PDA-GRLMF)2023-03-13T18:34:54+05:00Ali Ghulamgarahu@sau.edu.pkComplex alterations to the cellular machinery occur as a result of diseases. There are distinctive patterns associated with a disease in the gene expression profile of the affected cells. As a result, these profiles can be used to extract additional biological information about an illness, which helps us better identify and evaluate disease risks. Human pathway-disease interaction research is a recurrent area of interest for the biomedical community. Finding the processes or connections between diseases and pathways can be aided by this association. This paper provides an overview of human pathway and human disease, with the accuracy of disease identification has been less than satisfactory. In predicting disease-pathway interactions, this study suggests a computer model. In this research study we proposed the Graph Regularized Logistic Matrix<br />Factorization (GRLMF) method for pathway-disease association prediction. A cutting-edge computational model called the PDA-GRLMF disease-pathway association<br />model can predict probable pathway-disease associations. The model can also assist pathologists in comprehending the relationships between diseasepathway linkages, therapies, and outcomes. In order to increase the association<br />between disease variation and new molecular correlations between genetic mutations, we carried out a pathway-based investigation. On the basis of shared gene interactions among pathways-disease, we created a biological network, and then we used network analysis to try and understand how a disease constructed the pathway-pathway network and then disease-disease network. To merge the gathered biological data, which was based on the pair similarity of sequence expression weights, we employed the heterogeneous network of pathway-disease relationships. The ROC (AUC) score achieved for the best prediction results was 0.8018%, and the precision-recall curve had two classes. These findings suggest that our strategy outperforms previously suggested methods in terms of scientific performance. By contrasting them with established connections and conducting a literature search, we projected relationships between pathogen, DD, and disease-pathway.2022-06-30T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTCS/article/view/1258Identifying disease genes based on machine learning approaches for classification2023-03-13T18:34:54+05:00Rahu Sikandersikander@stu.xidian.edu.cnAli Ghulamgarahu@sau.edu.pkMujeeb -ur- Rehmangarahu@sau.edu.pk<p>In recent years, researchers have become increasingly interested in disease-gene association prediction. In the postgenomic era, this is one of the toughest jobs around. It is also challenging to determine biological research since complex disorders sometimes have very varied genotypes. Machine learning methods are used widely in the identification of crawl marks, but their images depend heavily on their quantity and quality. In crawling studies, we find that the recognition of genes reconciling diseases can be improved by an machines classifier qualified in practical gene seamlessness from gene ontology (GO). In order to predict the genes of the disease, we’ve developed a supervised machine learning system. In the proposed pipeline, the use of autism spectrum disorder (ASD) is assessed. Similarity tests from various semantics have been used to quantitatively measure similarity in gene function. In this paper we suggest various techniques for classifying data from one-hot encoding method. This experiment is complicated by the fact that the into training and test sets. This is generally called an algorithm evaluation divided-train-test split method. ASD is a disease associated with high health care costs and early intervention will significantly minimize these costs. ASD is a neurodevelopment disorder. Unfortunately, wait times are lengthy for an ASD diagnosis and treatments are not cheap. The economic effects of autism and an increase in ASD cases worldwide show an urgent need to establish methods of screening that are quickly enforced and efficient. A timely and affordable ASD screening is therefore imminent to help health practitioners and to let individuals know whether they will be formally diagnosed clinically. Classifiers qualified and validated for ASD and non-ASD genes work better than ASD classifiers previously reported. For instance, in order to predict new ASD genes, the complementary forest classification (CF) classification reached AUC 0.80 above the reported classification (0.73). Continuing, 73 novel ASD candidate bases can be predicted by the classifier function. Such genes enrich the central ASD syndrome, such as autism and compulsion.</p>2022-06-30T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTCS/article/view/1257AI and Machine Learning-based practices in various domains: A Survey2023-03-13T18:34:54+05:00Ali Ghulamgarahu@sau.edu.pkRahu Sikandergarahu@sau.edu.pkFarman Aligarahu@sau.edu.pk<p>In several projects in computational biology (CB), bioinformatics, health informatics(HI), precision medicine(PM) and precision agriculture(PA) machine learning(ML) has become a primary resource. In this paper we studied the use of machine learning in the development of computational methods for top five research aeras. The last few years have seen an increased interest in Artificial Intelligence (AI), comprehensive ML and DL techniques for computational method development. Over the years, an enormous amount of research has been biomedical scientists still don’t have more knowledge to handle a biomedical projects efficiently and may, therefore, adopt wrong methods, which can lead to frequent errors or inflated tests. Healthcare has become a fruitful ground for artificial intelligence (AI) and machine learning due to the increase in the volume, diversity, and complexity of data (ML). Healthcare providers and life sciences businesses already use a variety of AI technologies. The review summarizes a traditional machine learning cycle, several machine learning algorithms, various techniques to data analysis, and effective use in five research areas. In this comprehensive review analysis, we proposed 10 ten rapid and accurate practices to use ML techniques in health informatics, bioinformatics, computational and systems biology, precision medicine and precision agriculture, avoid some common mistakes that we have observed several hundred times in several computational method works.</p>2022-06-30T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTCS/article/view/1256Design and Analysis of an Anthropomorphic Finger with Three Points Pneumatic Actuation2023-02-24T18:03:02+05:00Imran Ali Bhandimranalibhand127@gmail.comSaifullah Samosaifullah.samo@faculty.muet.edu.pkNoor Fatima Memonnoormemon457@gmail.comSaifullah Memonmemonsaifullah@gmail.comRaheel Ahmed Nizamaniraheel.nizamani@faculty.muet.edu.pkMuhammad Ali Soomroali.soomro@admin.muet.edu.pk<em>The human being’s hand is a set of fingers and can achieve any shape to hold or grip or grasp the object of different shapes. In the industrial sectors, various robot manipulators with different types of end-effectors (robot grippers) are used to perform tasks like gripping the object, picking & dropping the object, holding the tool, etc. The different types of end-effectors are required for grasping according to the geometry of the object. In this paper, an anthropomorphic finger is designed to mimic the human being’s finger to achieve any shape as the human’s finger and this finger can be a part of the robotic hand easily. This single type of robotic hand can perform all tasks for grasping any geometry of the object. The proposed finger consists of three pin joints with three pneumatic muscles, which help to achieve the desired shape with maximum holding/grasping power. The CAD model is developed to visualize and analyze finger motion. The comparison of the proposed finger and a real human finger is presented for validation of results. The results show that the proposed system can mimic the human finger and shape modulation.</em>2022-12-24T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTCS/article/view/1177K-Nearest Neighbor Classifier for Classifying user Reviews on Social Media Networks2023-03-13T18:34:54+05:00Fahad Alotaibinashwan.alromema@gmail.comNashwan Ahmed Alromemanashwan.alromema@gmail.com<p class="Default"><em>Gigantic content generated on social media networking sites have made the online users enabled to communicate their opinions and sentiments about products and other entities like political events etc. Opinion mining applications aim to provide facilities to user and companies for know about products in which they are interested. In this work, opinion mining system for comparative reviews is developed using supervised machine learning approach. For this purpose, K-nearest neighbor classifier is trained on a publicly available dataset. Effectiveness of the system is validated by comparing its performance with other classifiers.</em></p>2022-06-30T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTCS/article/view/1004Analyzing updates in Amino Acid Composition and Translation Algorithm towards Predicting Membrane Proteins using Machine Learning Approaches2022-03-28T16:38:12+05:00Abdulsalam Mohammed Alfarsisnoke.7rb@gmail.comAbdulrahman Mohammed Alghanmisnoke.7rb@gmail.com<div><table width="685" cellspacing="0" cellpadding="0"><tbody><tr><td align="left" valign="top" height="225"><div><p><em>Membrane proteins are of different types that take on different functions. Classification of protein sequences in a data set is very important for understanding cell functions, disease prevention, and drug discovery. Initially, traditional methods were used for transmembrane protein classification. However, due to advanced technology and new research, it increases the transmembrane protein datasets by thousands which are almost impossible to obtain accurate results based on traditional methods. Computational methods are very useful for membrane protein classification. Several methods such as Pseudo Amino Acid Composition (PseAAC) can extract many silent features of a protein sequence. In this work, we intended to modify an existing algorithm of amino acid composition and translation to extract membrane protein features with better accuracy. To validate our algorithm, we will use the Support Vector Machine SVM and KNN.</em></p></div></td></tr></tbody></table></div>2022-03-28T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTCS/article/view/1001Specification of Operating Rules for Water Reservoir to Manage Flood Using Z-Notation2022-03-28T16:38:12+05:00Hasrat Alamhasrat.cs@gmail.com<div><table width="687" cellspacing="0" cellpadding="0"><tbody><tr><td align="left" valign="top" height="263"><div><p><em>Flood is natural event; it brings a lot of destruction. Due to flood not only loss of human life and misery of millions of people occur, but tremendous damages occur in public and private property. It cannot be stopped, but can be managed to save the lives and property of the people. To manage a flood, there are two solutions, physical and logical. In physical solutions, different physical constructions are made to manage flood like levee, channel improvement, flood ways, and widening of barrages, but these control works have many deficiencies. In logical solutions, models and techniques are developed to manage the flood, however, these systems also have some deficiencies. To overcome the deficiencies in the existing models, we focus on to develop a flood management model consisting of an off-river reservoir and diverted canals having regulators. Reservoirs are most effective water storage that smooth down extreme inflow. The optimal operations of reservoirs determine the release and accumulation of water over time. For effective operative decision, operating rules will be defined in Z-Specification. For these operating rules, we will develop an algorithm, will verify the rules in Z-Notation and will implement them in the Java programming language. </em></p></div></td></tr></tbody></table></div>2021-12-05T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTCS/article/view/1000Discrimination of SARS-COV2 virus protein strain of three major affected countries: USA, China, and Germany2022-03-28T16:38:12+05:00Khalid Allehaibikallehaibi@kau.edu.sa<div><table width="685" cellspacing="0" cellpadding="0"><tbody><tr><td align="left" valign="top" height="267"><div><p><em>In this paper, we discuss the discrimination of SARS-COV2 viruses associated with three major affected countries the USA, China, and Germany. The discrimination can reveal the mutation as the result of viral transmission and its spread due to mutation associated with its protein structure which makes small changes in the Spike protein. To investigate the mutation in SARS-COV2, we downloaded the protein strains associated with the USA, China, and Germany from the UniProtKB by advance search through SARS-COV2, country name, and protein name: Accessory protein 7b, 6, ORF3a, 10, 8 protein, Envelope small membrane protein, Nucleoprotein, Membrane protein, Spike glycoprotein, 3C-like proteinase, and 2'-O-methyltransferase. After retrieving the protein sequences, we transform the biological form of sequences to their equivalent numerical form by using statistical moments. Further classification algorithms like Random Forest, SVM are used for their training and classification. Finally, performance evaluation is carried out using K-fold cross-validation, independent testing, self-consistency, and jackknife testing. The result received through all testing is more than 97%, which shows the visible discrimination among the protein strains of mentioned countries, which shows the strong mutation in SARS-Cov2 </em><em>sequences. </em><em></em></p></div></td></tr></tbody></table></div>2021-12-02T00:00:00+05:00Copyright (c)