https://vfast.org/journals/index.php/VTSE/issue/feedVFAST Transactions on Software Engineering2024-02-29T11:42:58+05:00Dr. Farooq Ahmadvtse1@vfast-iccass.comOpen Journal Systems<p>The <em><strong>VFAST Transactions on Software Engineering</strong></em> is a peer-reviewed scientific journal published by the VFAST-Research Platform. It was established in 2013 and covers the areas of software engineering and its applications. The aim of this journal is to provide an international platform for engineers and academicians all over the world to promote, share, and discuss various new issues and development in the field of software engineering and its application in Machine learning, Bioinformatics, Image processing, Robotics, Artificial Intelligence, and data science.</p> <p>The Journal has started 4 issues per year from 2021 (January-March, April-June, July-September, and October-December)</p> <p>Editor-in-Chief: Prof. Hejiao Huang, Department of Computer Science and Technology, Harbin Institute of Technology Shenzhen Graduate School, China</p> <p>Dr. Farooq Ahmad, Associate Professor, COMSATS Lahore, Pakistan</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/VTSE/user/register"><button class="pkpButton"> REGISTER</button></a> <a href="https://vfast.org/journals/index.php/VTSE/about/submissions"><button class="pkpButton"> SUBMISSION</button></a> <a href="https://vfast.org/files/VTSE.zip"><button class="pkpButton"> LATEX TEMPLATE</button></a> <a href="https://vfast.org/journals/index.php/VTSE/about/editorialTeam"><button class="pkpButton">EDITORIAL TEAM</button></a></p> <p> </p> <p><strong>The Journal is indexed by:</strong></p> <ol start="1"> <li><a href="https://hjrs.hec.gov.pk/index.php?r=site%2Fresult&id=912639#journal_result">HEC-Y Category </a></li> <li><a href="file:///D:/VFAST/Journal%20Requirements/Peer%20Review%20Process.docx">Google Scholar</a></li> <li><a href="http://www.repindex.com/">Repindex</a></li> <li><a href="https://www.worldcat.org/title/vfast-transactions-on-software-engineering/oclc/985064061&referer=brief_results">Worldcat</a></li> <li><a href="http://emis.mi.sanu.ac.rs/ZMATH/zmath/en/journals/search/">ZMATH</a></li> <li><a href="https://www.researchgate.net/journal/2309-3978_VFAST_Transactions_on_Software_Engineering">Research Gate</a></li> <li><a href="https://journals.indexcopernicus.com/search/details?id=35208">Index Copernicus</a></li> <li><a href="http://www.journaltocs.ac.uk/index.php?action=browse&subAction=subjects&publisherID=8&journalID=28942&pageb=3&userQueryID=&sort=&local_page=&sorType=&sorCol=5">Journal Tocs</a></li> <li><a href="https://catalogue-bibliotheque.sciencespo.fr/discovery/fulldisplay?docid=alma991006818403205808&context=L&vid=33USPC_SPO:SPO&lang=fr&search_scope=MyInst_and_CI&adaptor=Local%20Search%20Engine&tab=Everything&query=any,contains,VFAST">Sciences Po</a></li> <li><a href="https://publons.com/journal/349456/vfast-transactions-on-software-engineering/">Publons</a></li> <li><a href="https://portal.issn.org/api/search?search%5b%5d=MUST=default=VFAST&search_id=5981797%23">ISSN + ROAD</a></li> <li><a href="http://ulrichsweb.serialssolutions.com/login">Ulrich’s Periodicals Directory/ProQuest</a></li> <li><a href="http://sfx.princeton.edu:9003/sfx_pul/az?param_letter_group_save=&param_chinese_checkbox_type_save=Pinyin&param_current_view_save=table&param_langcode_save=en&param_pattern_save=VAWKUM+Transaction+on+Computer+Sciences&param_services2filter_save=getFullTxt&param_jumpToPage_save=&param_chinese_checkbox_save=0&param_starts_with_browse_save=0&param_sid_save=b2d32284a5f202b8c792b440b6535c2f&param_type_save=textSearch&param_lang_save=eng&param_textSearchType_save=startsWith&param_perform_save=searchTitle&param_letter_group_script_save=&param_type_value=textSearch&param_jumpToPage_value=&param_pattern_value=vfast&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 Library</a></li> <li><a href="https://quest.library.illinois.edu/OAIRegistry/Home/Details/7417">University of Illinois Library</a></li> <li><a href="http://mperio.ru/resursy-otkrytogo-dostupa/v/">World of Periodicals</a></li> <li><a href="https://ouci.dntb.gov.ua/en/?backlinks_to=10.1109%2Ftc.2011.245&exclude=2456-3307&journal=VFAST+Transactions+on+Software+Engineering">Ouci Dntb</a></li> </ol>https://vfast.org/journals/index.php/VTSE/article/view/1740FlightForecast: A Comparative Analysis of Stack LSTM and Vanilla LSTM Models for Flight Prediction2024-02-29T11:42:58+05:00Rohail Qamarrohailqamar@cloud.neduet.edu.pkRaheela Asifrahmed@cloud.neduet.edu.pkLaviza Falak Nazlavizaniazi2001@gmail.comAdeel Mannanadeel.mannan@hamdard.edu.pkAfzal Hussainafzal.hussain@hamdard.edu.pk<p>The Coronavirus was first reported in China in the city of Wuhan in December 2019, after a couple of months, it was widespread around the world. The whole world was in a state of lockdown. This hazardous disease affects the normal daily life of every individual and the tourism industry, especially the airline business was at a greater loss. Considering the airline business, this study contains data on commercial flights from 2019 to 2020. The conducted research analyzed the rise and fall of different flights in the lockdown period. The research is based on the variants of Long Short-Term Memory (LSTM) such as standard Recurrent Neural Network (RNN) and stack LSTM. The comparative research shows that the prediction of the stack LSTM model is better than the standard RNN keeping view of taking a considerable amount of time to train.</p>2024-03-08T00:00:00+05:00Copyright (c) 2024 VFAST Transactions on Software Engineeringhttps://vfast.org/journals/index.php/VTSE/article/view/1700The Impact of Data Mining on Digital Libraries – A bibliometric Study2023-12-26T11:54:51+05:00Sana Alamsana.alam@iobm.edu.pkShehnila Zardarishehnilaz@neduet.edu.pkUmm-e-Laila mehdiulaila2002@gmail.comMohammad AbbasDr.abbas@iobm.edu.pkNool Ul Hudanoor.huda@iobm.edu.pkMuhammad Asghar Khanmuhammad.asghar@iobm.edu.pk<p><strong>Purpose</strong>: The study provides a comprehensive bibliometric assessment of Data Mining in Digital/ Virtual Libraries to depict the importance of Data Mining technology with respect to Digital/ Virtual Libraries. <strong>Methodology: </strong>Our research work includes 215 studies from the past 23 years that are analyzed on the basis of carefully articulated 10 research questions. The tools used for performing analysis regarding visualization aspects include VoSViewer and Bibliometrix (R studio). <strong>Findings: </strong>The evaluation shows that the year 2017 has the highest number of publications. Our work also represents that the use of Data Mining in Digital/ Virtual Libraries has influenced multiple domains, however, it is frequently used in Computer Science. An assessment of the top 20 countries suggests that USA and China are the major contributors in terms of published articles for a time period of 23 years. In the study, we use VoSViewer for co-word analysis to represent the relatedness of documents based on keywords. Our study further explores the research themes and topic dendrogram with respect to Data Mining in Digital/ Virtual Libraries by using Bibliometrix (R studio). Our research findings also show that although most research work is published in the English language yet there are few major studies in other languages also. <strong>Originality: </strong>The research provides insight into the above-mentioned aspects of bibliometrics, enabling researchers and scholars to make better decisions regarding their research</p>2023-12-31T00:00:00+05:00Copyright (c) 2024 VFAST Transactions on Software Engineeringhttps://vfast.org/journals/index.php/VTSE/article/view/1698A Study of Brain Tumor detection using MRI images2024-02-21T02:15:12+05:00Asadullah Keharasad.kehar@salu.edu.pkMashooq Ali Maharmashooq.mahar@salu.edu.pkShahid Hussain Danwershahid.danwer@salu.edu.pkSidra Parveensidsoomro7@gmail.comMariya Bhuttomariyabhutto07@gmail.comZoya Qutriozoya.nazqutrio123@gmail.com<p>This study investigates the advantages of an algorithm for detecting brain tumors using magnetic resonance imaging. The thematic analysis demonstrates how the algorithm can be understood and changed through narrative descriptions. The findings highlight areas for improvement, which aids in the direction of future research. Based on unexpected results, the algorithm was improved over time. Even though the study had some restrictions and limitations, this makes the algorithm a versatile tool for detecting brain tumors. This study is an important step toward better understanding algorithmic applications and demonstrates the significance of qualitative insights in shaping the future of brain tumor detection methods.</p>2024-02-19T00:00:00+05:00Copyright (c) 2024 VFAST Transactions on Software Engineeringhttps://vfast.org/journals/index.php/VTSE/article/view/1684Enhancing Breast Cancer Detection through Thermal Imaging and Customized 2D CNN Classifiers2024-01-10T19:38:16+05:00Saif ur Rehman Khansaifurrehman.khan@csu.edu.cnAsif Razaasifraza.raza14@gmail.comMuhammad Tanveer MeeranTanveer_miran@yahoo.comUmair Bilhajumair.bilhaj@gmail.com<p>Breast cancer is one of the most prevalent and life-threatening forms of cancer due to its aggressive nature and high mortality rates. Early detection significantly improves a patient's chances of survival. Currently, mammography is the preferred diagnostic method, but it has drawbacks such as radiation exposure and high costs. In response to these challenges, thermography has become a less invasive and cost-effective alternative, gaining popularity. We aim to develop a cutting-edge model for breast cancer detection based on thermal imaging. The initial phase involves creating a customized machine-learning (ML) model built on convolutional neural networks (CNN). Subsequently, this model undergoes training using a diverse dataset of thermal images depicting breast abnormalities, enabling it to identify breast cancer effectively. This innovative approach promises to revolutionize breast cancer diagnosis and offers a safer and more accessible alternative to traditional methods. In our recent study, we leveraged thermal image processing techniques to forecast breast cancer precisely based on its external manifestations, particularly in cases where multiple factors are interconnected. This research employed various image classification methods to categorize breast cancer effectively. Our comprehensive approach encompassed segmentation, texture-based feature extraction from thermal images, and subsequent image classification, leading to the successful detection of malignant images. Our study harnessed the power of machine learning to create a tailored classifier, merging key components from GoogleNet, including the utilization of 2D CNNs and activation functions, with the ResNet architecture. This hybrid approach incorporated batch normalization layers following each convolutional layer and employed max-pooling to enhance classification accuracy. Next, we used a sample dataset of carefully selected images from DMR-IR to train our proposed model. The outcomes of this training demonstrated significant improvement over existing methods, with our suggested 2D CNN classifiers achieving an impressive classification rate of 95%, surpassing both the SVM and current CNN models, which achieved rates of 91% and 71%, respectively.</p>2023-12-31T00:00:00+05:00Copyright (c) 2024 VFAST Transactions on Software Engineeringhttps://vfast.org/journals/index.php/VTSE/article/view/1681An Investigation of the Implementation Status of Team Communication in the Pakistani Software Industry2023-12-05T22:30:41+05:00Syed Umar ShahEngsyedumarshah@gmail.comMuhammad Sohail Khanmsohail@gmail.com<p>This study explores the current state of team communication implementation in the Pakistani software industry. By examining communication strategies such as direction, frequency, content, and modality, the research aims to comprehensively analyze the existing dynamics among team members and their leaders. Data were collected via separate questionnaires administered to team members and managers in various software firms, resulting in 100 responses. The findings indicate a positive trajectory in the implementation of team communication, emphasizing the crucial role of strategic approaches in fostering effective communication practices. While acknowledging limitations, including sample size and the study’s cross-sectional nature, the research suggests potential avenues for future exploration, including longitudinal studies and assessing the impact of team communication on project success. Overall, this investigation contributes valuable insights into the current landscape of team communication within the Pakistani software industry.</p>2023-12-31T00:00:00+05:00Copyright (c) 2024 VFAST Transactions on Software Engineeringhttps://vfast.org/journals/index.php/VTSE/article/view/1680Hire IT Application Transforming Labor Hiring with Innovative Technologies2024-01-10T19:38:27+05:00Muhammad Saadmsaad@ssuet.edu.pkFatima Waseemfwsatti@ssuet.edu.pkSarfaraz Nathasasattar@ssuet.edu.pkBilal Ahmedbilalahmed@ssuet.edu.pkAbdul Raufabdulrauf@ssuet.edu.pkBaasirbaasir@ssuet.edu.pk<p>In recent years, the gig economy has grown rapidly, with an increasing number of workers finding employment through online platforms such as labor hiring apps. These apps connect employers with a large pool of workers for short-term or temporary jobs, and have become a popular way for businesses to fill job openings quickly and easily. However, there are also concerns about the impact of labor hiring apps on employment and wages. This paper conducts a literature review of existing studies on labor hiring apps and the gig economy, surveys and interviews with employers and workers who have used these apps, and an analysis of app data to understand the usage pattern and user behavior. This article also explores the evolution and impact of labor hiring apps on the contemporary job market. Labor hiring apps have emerged as a disruptive force, revolutionizing the way businesses find, connect with, and employ labor. This study investigates the key features, advantages, challenges, and future prospects of labor hiring apps, shedding light on their implications for both employers and workers. Through a comprehensive analysis of existing literature, case studies, and expert opinions, this article aims to provide a holistic understanding of the dynamics surrounding labor hiring apps.</p>2023-12-31T00:00:00+05:00Copyright (c) 2024 VFAST Transactions on Software Engineeringhttps://vfast.org/journals/index.php/VTSE/article/view/1667Optimizing the Efficiency of Web Mining through Comparative Web Ranking Algorithms2023-11-23T01:00:35+05:00Nida Khalilnkhalil@ssuet.edu.pkSaniah Rehansrehan@ssuet.edu.pkAbeer Javed Syedajsyed@ssuet.edu.pkKhalid Mahboobkmahboob@ssuet.edu.pkFayyaz Alifayyaz.ali@ssuet.edu.pkFatima waseemfwsatti@ssuet.edu.pk<p>Millions of web pages carrying massive amounts of data make up the World Wide Web. Real-time data has been generated on a wide scale on the websites. However, not every piece of data is relevant to the user. While scouring the web for information, a user may come upon a web page that contains irrelevant or incomplete information. As a response, search engines can alleviate this issue by displaying the most relevant pages. Two web page ranking algorithms are proposed in this study along with the Dijkstra algorithm; the PageRank algorithm and the Weighted PageRank algorithm. The algorithms are used to evaluate a web page's importance or relevancy within a network, such as the Internet. PageRank evaluates a page's value based on the quantity and quality of links leading to it. It is commonly utilized by nearly all search engines around the world to rank web pages in order of relevance. This algorithm is used by Google, the most widespread Internet search engine. In the process of Web mining, page rank is quite weighty. The most important component of marketing is online use mining, which investigates how people browse and operate a business on a company's website. The study presents two proposed models that try to optimize web links and improve search engine results relevancy for users.</p>2023-12-31T00:00:00+05:00Copyright (c) 2024 VFAST Transactions on Software Engineeringhttps://vfast.org/journals/index.php/VTSE/article/view/1657Enhanced Diabetic Prediction Using Fuzzy C-Means Preprocessing and Random Forest Ensemble Learning2024-01-10T19:42:36+05:00Priha Bhattifa23phcs0001@maju.edu.pkKhalid MahboobkMahboob@ssuet.edu.pkSyed Saad Naeemsyedsaadnaeem@gmail.comIqra Heer Bhattiiqra.heer@zu.edu.pkNoorulain Kamrannoorulain.kamran@duhs.edu.pk<p>Diabetes claims the lives of thousands each year, and many individuals remain oblivious to their condition until it reaches a critical stage. This study presents a data mining-based approach aimed at enhancing the early detection and prediction of diabetes, utilizing data from the Pima Indian Diabetes dataset. Despite the adaptability of fuzzy C-Means for various data types, the ultimate outcome of the clustering process hinges on the initial placement of cluster centers. Additionally, precision in data clustering is crucial; it can furnish either extensive, well-grouped data for the random forest or limited data, constraining its efficacy. Our principal objective was to enhance the accuracy of fuzzy C-means clustering and the random forest. To boost the model's performance, we incorporated PCA, fuzzy c-means, and the Random Forest approach. Various algorithmic combinations were employed, and the results unequivocally demonstrate that our model surpasses the original outcomes of the Pima Indian Diabetes Dataset in terms of accuracy. The diabetic prediction model achieved a remarkable accuracy of 97.40\% through the utilization of PCA, logistic regression, and K-Means. However, when employing PCA in conjunction with fuzzy C-means and random forests, an even higher accuracy of 98.96\% was attained. Empirical evidence confirms that the implementation of PCA significantly enhanced the accuracy of both the fuzzy C-means clustering approach and the random forest classifier, deviating from previous findings. To improve the model's performance, we used PCA, fuzzy c-means, and the Random Forest approach. Different algorithm combinations were used, and the results clearly show that our model outperforms the original Pima Indian Diabetes Dataset outcomes in terms of accuracy. The diabetic prediction model was improved to 97.40% accuracy using PCA, logistic regression, and K -Means. Using PCA with fuzzy C-means and random forests, however, we achieved an accuracy of 98.96%. Based on empirical evidence, it has been demonstrated that the implementation of PCA improved the accuracy of the fuzzy C-means clustering approach and the random forest classifier. These findings differ from previous findings.</p>2023-12-02T00:00:00+05:00Copyright (c) 2023 VFAST Transactions on Software Engineeringhttps://vfast.org/journals/index.php/VTSE/article/view/1656Securing Electronic Health Records using Blockchain2024-01-10T19:38:39+05:00dureshawar Aghaengr.dureshawaragha@gmail.com<p><strong>This research explores the application of blockchain technology in securing Electronic Health Records (EHRs) while integrating IoT sensors for real-time patient monitoring. The primary goal is to address critical healthcare industry challenges, including security, privacy, data integrity, and accessibility. Our system focuses on enhancing EHR security and reliability through blockchain's decentralized and tamper-resistant features. Additionally, IoT sensors provide real-time monitoring of vital signs, enabling prompt interventions. This study not only delves into technical aspects but also considers practical implementation in healthcare, contributing to improved data security and patient care.</strong></p>2023-12-12T00:00:00+05:00Copyright (c) 2023 VFAST Transactions on Software Engineeringhttps://vfast.org/journals/index.php/VTSE/article/view/1647An Efficient Deep Learning Approach for Prediction of Student Performance Using Neural Network2024-01-10T19:38:51+05:00Namraizanamraizaaslam842@gmail.comKamran Abidkamranabidhiraj@gmail.comNaeem AslamNaeemaslam@nfciet.edu.pkMuhammad FuzailM.fuzail@nfciet.edu.pkMuhammad Sajid Maqboolsajidmaqbool7638@gmail.comKainat Sajidkainat.ispm1@gmail.com<table width="688"> <tbody> <tr> <td> <p>In recent years, schools have shown interest in utilizing data mining to improve the quality of education. To enhance academic performance, accurately predicting how students will perform in their classes is crucial, which is essential for their progress in further education. Some students encounter challenges upon entering higher education, and predicting their performance early on is vital to keeping them on the right track. Our research aims to assess student performance using various classification strategies to identify the most accurate one. We utilize a Kaggle dataset for this study. Initially, we clean up the dataset by removing duplicate records and filling in any missing information. Subsequently, we apply six different classifiers, including Neural Networks and methods such as Random Forest and Support Vector Machine, utilizing the Weka tool. Additionally, we employ Principal Component Analysis (PCA) to extract optimized features that enhance model accuracy. We evaluate all models on Training and Testing splits, as well as the 10-K Fold options provided by the Weka tool. Finally, we calculate Training Accuracy, Testing Accuracy, Precision, Recall, and F1-Score for each model and compare their results. Notably, Neural Networks and Random Forest demonstrate superior results compared to other models.</p> </td> </tr> </tbody> </table> <p> </p>2023-12-12T00:00:00+05:00Copyright (c) 2023 VFAST Transactions on Software Engineeringhttps://vfast.org/journals/index.php/VTSE/article/view/1642A Privacy-Preserving Based Technique for Customer Churn Prediction in Telecom Industry2023-10-24T12:10:21+05:00Gul Zaman Khanengrgulzamankhan@gmail.comIkram UlhaqIkramulhaq2062000@gmail.comIhsan AdilIhsanadil0448@gmail.comSajad Ulhaqsajadulhaq26@gmail.comInam UllahInamullahbcs@gmail.com<p><strong>In recent years, customer churn has been one of the most prominent topics, especially in the telecom industry. The telecommunications industry is producing massive amounts of data every minute. Thus, the telecom industry is seeking more ways to analyze and predict their potential and churn customers. According to telecom analysis, acquiring a new customer is costlier than keeping a current one. To lessen customer churn, it is very compulsory for industries to detect an increase in customer churn factors. The number of service suppliers is increasing daily, especially in the telecom industry. Phishing attacks and fraud are crucial points in customer churn. The aim of this study is to predict customer churn with profitable churn models for retention campaigns to satisfy the business requirement of profit maximization. The proposed research used the BAT-ANN classification model with the BigML dataset to predict customer churn in the telecom industry. The proposed model achieved 89.2% testing accuracy.</strong></p>2023-09-30T00:00:00+05:00Copyright (c) 2023 VFAST Transactions on Software Engineeringhttps://vfast.org/journals/index.php/VTSE/article/view/1641An Ensemble Modeling Approach to Enhance Grade Prediction in Academic Engineering Programming Courses2024-01-10T19:33:39+05:00Khalid Mahboobkmahboob@ssuet.edu.pkSarfaraz Abdul Sattar Nathasasattar@ssuet.edu.pkSyed Saood Ziaszia@ssuet.edu.pkPriha Bhattipbhatti@ssuet.edu.pkAbeer Javed Syedajsyed@ssuet.edu.pkSamra Mehmoodsamra.mehmood@datasoft.com.pk<table width="688"> <tbody> <tr> <td> <p><em>Predicting the future academic grades of students can play a pivotal role in enhancing their performance in specific courses, consequently yielding a positive impact on their prospective academic, professional, and personal achievements, as well as on society at large. The field of programming is rapidly gaining prominence as an essential profession spanning multiple domains, marked by abundant opportunities and financial rewards. To cater to the diverse interests of students, the recommended curriculum structure for engineering programs in computing adeptly combines theoretical knowledge with practical programming skills. This approach ensures that students acquire a comprehensive understanding of programming courses, allowing them to choose the path that aligns best with their envisioned careers as programmers This research endeavors to introduce ensemble prediction techniques aimed at identifying students who exhibit the potential for advancement, or conversely, those who may not excel in four university-level programming courses. The outcomes of this study are presented alongside valuable performance assessment metrics for five ensemble methodologies, namely AdaBoost, Bagging, Random Forest, Stacking, and Voting. This evaluation employs a 10-fold cross-validation methodology and incorporates the Principal Component Analysis (PCA) for feature ranking. The results unequivocally demonstrate that both the Stacking and Random Forest ensemble approaches have attained the highest level of accuracy when applied to two distinct datasets.</em></p> </td> </tr> </tbody> </table> <p> </p>2023-11-13T00:00:00+05:00Copyright (c) 2023 VFAST Transactions on Software Engineeringhttps://vfast.org/journals/index.php/VTSE/article/view/1633Clusters of Success: Unpacking Academic Trends with K-Means Clustering in Education2024-01-10T19:42:40+05:00Dua Aghaduaagha2@gmail.comAreej Fatemah Meghjiareej.fatemah@faculty.muet.edu.pkSania Bhattisania.bhatti@faculty.muet.edu.pk<p>Integrating Educational Data Mining (EDM) into the sector of education has heralded a new era, profoundly impacting learning outcomes by analyzing student performance and preventing academic disengagement. Using the K-Means clustering approach, this study carefully examines the academic accomplishments of students at Mehran University of Engineering and Technology and offers a sophisticated view of student performance patterns through the rigorous analysis of their learning data. A dataset comprising of the academic data of three student batches of the Department of Software Engineering was broken down into the subject categories of Computer Core, General, and Mathematics. The approach of clustering was then applied to find distinct performance patterns across the three subject categories. The findings of the research reveal that students have the highest performance in the computer core category, followed by mathematics, while the weakest overall performance across all three batches was exhibited in the general subject category. The study highlights the disparities in academic performance across distinct clusters and adds to our understanding of academic success while also illuminating the complex interactions between student characteristics and educational outcomes, providing useful information for educators and policymakers.</p>2023-11-14T00:00:00+05:00Copyright (c) 2023 VFAST Transactions on Software Engineeringhttps://vfast.org/journals/index.php/VTSE/article/view/1626Comparative Analysis of Feature Extraction Methods for Cotton Leaf Diseases Detection2024-01-10T19:44:28+05:00Shahzad Mehmoodengr.shahzad.mehmood@gmail.comFarida Memonfarida.memon@faculty.muet.edu.pkArbab Nighatarbab.nighat@faculty.muet.edu.pkFayaz Ahmed Memonfarida.memon@faculty.muet.edu.pkErum Sabaerumsaba@sau.edu.pk<p>Cotton leaf diseases must be accurately detected and classified to reduce plant diseases and output losses. Feature extraction strategies for automated cotton leaf disease diagnosis are compared in this study. The research uses HOG, SIFT, SURF, GLCM, and Gabor wavelets filter feature extractor to extract features. We gathered and preprocessed 2400 cotton leaf images of healthy and diseases, Angular Leaf Spot, Bacterial Blight, Cotton curl leaf disease (CLCuD), as well as Alternaria Disease. K-means clustering separates leaf areas and improves feature extraction in image segmentation. Discriminative features are extracted using the mentioned methods, and Support Vector Machine (SVM) classifier is employed for disease identification. The comparative analysis based on Accuracy, Precision, and Sensitivity reveals the Gabor Wavelet Filter Feature Extractor as the top performer, achieving 92% accuracy on the test dataset containing bacterial blight, curl virus, alternaria, and healthy leaves. While HOG, SIFT, SURF, and GLCM methods also perform well, they are outperformed by the Gabor Wavelet method. This study shows Gabor wavelet-based features can accurately identify and classify cotton leaf illnesses, helping farmers fight plant diseases. The results underscore the need of choosing proper feature extraction methods for autonomous plant disease diagnostic systems.</p>2023-09-30T00:00:00+05:00Copyright (c) 2023 VFAST Transactions on Software Engineeringhttps://vfast.org/journals/index.php/VTSE/article/view/1615Author Profiling from Short Romanized Urdu Messages: A Preliminary Investigation using Transfer Learning Models2023-10-09T21:25:47+05:00Abid Aliabidalicu@gmail.comMuhammad Sohail Khansohail.khan@uetmardan.edu.pkMuhammad Amin Khanmuhammadaminkhan180@gmail.com<table width="688"> <tbody> <tr> <td> <p><em>Author profiling, a crucial task in natural language processing, involves identifying various attributes of an author, such as gender and age, from text. This study examines how transfer learning models in the context of author profiling from Roman Urdu text. We conduct experiments employing prominent models such as ELECTRA , BERT, RoBERTa, XLNet, Distil Bert, Distil RoBERTa,. Our analysis reveals superior performance in gender prediction using BERT, attaining an accuracy of 0.74698, precision of 0.7505, recall of 0.7462, and F1 score of 0.7456. On the other hand, RoBERTa demonstrates remarkable proficiency in age prediction with an accuracy of 0.8221, precision of 0.8215, recall of 0.8221, and F1 score of 0.8215. These findings showcase the effectiveness of transfer learning models in author profiling tasks offer insightful analysis for further research and applications in this domain.</em></p> </td> </tr> </tbody> </table> <p> </p>2023-09-30T00:00:00+05:00Copyright (c) 2023 VFAST Transactions on Software Engineeringhttps://vfast.org/journals/index.php/VTSE/article/view/1610User-Centric Advertisement using Software Sensors Technique2024-01-10T19:42:33+05:00Abdul Rehman Balocharehman.baloch@usindh.edu.pkKamran Taj Pathankamran.taj@usindh.edu.pkProf. Dr. Azhar Ali Shahazhar.shah@usindh.edu.pk<p>Contextual advertising is one of the most critical components in the economic system of internet due to increase internet publisher’s income highly dependent on the user-centric advertisement that is displayed on the sites according to the user context during interaction with the multiple sites. Previous contextual advertisement research work generally emphasises on investigating either to the keyword they type, content of the sites or uses any other application from the network hence, this finding has identified work when being extended through the user’s context. In this work we have looked at users’ profile information and user preferences to reach the users according to their context. These smart devices are ready with all capabilities to give useful contexts including information about physical environment, social connection, user internal and external context. These logical contexts beyond just content of the web pages, search keywords, and profile information are well used and organized for user-centric advertising. Here we are also arguing the appearances of the logical contexts which are available on the user browser, profile and visibly define the challenges of results from these logical contexts to improve the advertisement. We present a user-centric advertisement architecture and model that collects to integrate the users’ profile context and activity context to select, generate and to present advertisement with context. Finally, we discuss to implement the aspects of design and one specific application and outline our plans for future.</p>2023-12-04T00:00:00+05:00Copyright (c) 2023 VFAST Transactions on Software Engineeringhttps://vfast.org/journals/index.php/VTSE/article/view/1604Enhancing Energy Efficiency and Coverage in HetNets through Antenna Optimization2023-09-20T10:19:43+05:00safia Dahriengrsafia@quest.edu.pkMuhammad Mujtaba Shaikhmujtabashaikh@quest.edu.pkFozia Panhwerfoziapanhwer@gmail.comFatima Qureshiqureshi080@gmail.comIqrar ali PaliIqaralipali@quest.edu.pkMuhammad Afzalm.a.soomro3@gmail.comThe advent of 5G technology has opened up new opportunities across various fields, including healthcare. In the context of wireless communication, the deployment of a two-tier heterogeneous network (HetNet) plays a crucial role in ensuring robust connections among devices, users, and healthcare infrastructure. This study focuses on optimizing coverage and energy efficiency (EE) in HetNets, tailored for specific application domains. We begin by examining how antenna height impacts coverage within macro and pico cells. Precise antenna placement is critical, as it significantly alters coverage patterns, particularly in healthcare settings, which can range from large hospital complexes to remote telemedicine locations. Additionally, we investigate the strategic adjustment of antenna gain in macro and pico cells, showing how this optimization enhances coverage and minimizes interference. Achieving this balance is essential for the reliable transmission of data. Our research also considers the interplay of antenna height, EE, and the maximum number of users ($N_{max}$). Surprisingly, we find that $N_{max}$ has a limited impact on coverage and EE compared to antenna configuration. This emphasizes the crucial role of antenna design and placement in crafting efficient wireless networks.Our study provides insights into improving coverage and EE in HetNets, with implications for various applications. It underscores the importance of strategic antenna optimization in shaping efficient and resilient communication systems. Furthermore, we explore the impact of $\beta$ on EE and leverage idle mode capabilities for further EE enhancements.2023-09-30T00:00:00+05:00Copyright (c) 2023 VFAST Transactions on Software Engineeringhttps://vfast.org/journals/index.php/VTSE/article/view/1598An ensembling approach to predict hepatitis in patients with liver disease using machine learning2024-01-10T19:43:54+05:00Muhammad Arifengrmuhammadarif786@gmail.comMohsin Abbasabbasmohsin202@gmail.comMuhammad Ahmed Shehzadahmad.shehzad@bzu.edu.pkZakia Batoolzakiabatool.uaf@gmail.comMahwish Rabiaabbasmohsin202@gmail.comAbdul Majid Soomroamaramajid@gmail.com<p>With a 3.5% mortality rate, liver disease is one of the worst diseases in existence. Pakistan is targeting this major health issue from several perspectives, to improve prevention, diagnosis, and treatment due to having the highest incidence of liver disorders in the world. For liver problem disease, also known as HEP C, Pakistan is now the second most prevalent country in the world. This is due to the rapid progression of HEP C, which can only be stopped by early diagnosis. If not, it progresses to the last stage of HEP C cirrhosis, which has no other treatment options besides liver transplantation. One and only machine learning algorithms like logistic regression, random forest, KNN, K-Means, and XGBoost can be used to predict liver illness utilizing modern methods like artificial intelligence. Data is gathered from Kaggle and subjected to several machine learning algorithms after pre-processing in order to quickly diagnose liver disease. Additionally, to improve accuracy, all of these algorithms are ensemble, and accuracy is 78.96%, along with precision, recall, and F1 score. In this work, liver disease is predicted early on using pre-processing, feature extraction, and classification techniques. Recall, precision, and f1score metrics are used to compare the accuracy of the six algorithms, and these algorithms are then combined to provide the most accurate diagnosis of liver disease.</p>2023-10-02T00:00:00+05:00Copyright (c) 2023 VFAST Transactions on Software Engineeringhttps://vfast.org/journals/index.php/VTSE/article/view/1590Advanced Vehicle Safety: A Prototype Circuit for Accident Prevention and Emergency Response2023-09-20T10:15:04+05:00Urooj Oaduroojgianchand@gmail.comMuhammad Mujtaba Shaikhmujtabashaikh@quest.edu.pkSafia Amir Dahriengrsafia@quest.edu.pkMariam Fatimaf.18tc07@quest.edu.pkFozia Panhwerfoziapanhwer@gmail.comSarfaraz Ahmadsarfarazahmed@quest.edu.pk<div>In contemporary society, the pursuit of robust accident prevention, detection, and reporting systems is paramount, particularly within the context of vehicular safety. This study introduces a meticulously designed prototype circuit, adaptable for deployment across diverse vehicle types. This intelligent circuitry endeavors to mitigate accidents and safeguard human lives by employing a multifaceted approach.</div><div>The system's primary functions encompass the verification of seat belt usage and the assessment of alcohol consumption by the driver. Additionally, it incorporates a vibration sensor to detect accidents promptly. Complementing these features, the integration of GPS and GSM modules facilitates the rapid notification of emergency services, ensuring prompt assistance in the event of an accident.</div><div>The core of this system is an Arduino microcontroller, orchestrating the interconnected components to process data and trigger actions based on predefined conditions. The circuit's performance has been rigorously tested, initially through simulation in Proteus software, and subsequently via real-world hardware implementation. Comparative analysis of software and hardware results lends insights into the system's functionality and reliability.</div><div>The overarching objective of this study is to curtail accidents arising from intoxicated driving, unforeseen driver fatigue, and road obstructions. In instances of accidents, the electronic apparatus employed has the capacity to dispatch spontaneous and precise distress signals to law enforcement and medical personnel, thereby expediting casualty recovery and potentially saving lives. This research advances the fusion of technology and safety measures to augment road safety comprehensively.</div><div class="ui-layout-center ui-layout-pane ui-layout-pane-center ui-layout-pane-hover ui-layout-pane-center-hover ui-layout-pane-open-hover ui-layout-pane-center-open-hover" style="box-sizing: border-box; color: #5d6879; font-family: Lato, sans-serif; font-size: 16px; position: absolute; margin: 0px; inset: 0px 7px 0px 331px; height: 454px; width: 708px; z-index: 0; visibility: visible;"><div class="full-size ng-scope" style="box-sizing: border-box; inset: 0px; position: absolute;"><div class="pdf full-size" style="box-sizing: border-box; background-color: #e4e8ee; inset: 0px; position: absolute;"><div class="pdf-viewer" style="box-sizing: border-box; inset: 32px 0px 0px; position: absolute;"><div class="pdfjs-viewer pdfjs-viewer-outer" style="box-sizing: border-box; background-color: transparent; inset: 0px; overflow: hidden; position: absolute; outline: none;"><div class="pdfjs-viewer-inner" style="box-sizing: border-box; -webkit-font-smoothing: initial; height: 422px; overflow-y: scroll; position: absolute; width: 708px;"><div class="pdfViewer" style="box-sizing: border-box; padding-bottom: var(--pdfViewer-padding-bottom); min-height: 100%;"><div class="page" style="box-sizing: content-box; background-clip: content-box; background-color: #ffffff; border: none; direction: ltr; height: 842px; margin: 10px auto; overflow: visible; position: relative; width: 651px; box-shadow: #bbbbbb 0px 0px 8px;" data-page-number="10" data-loaded="true" data-listening-for-double-click="true"><div class="textLayer" style="box-sizing: border-box; text-size-adjust: none; inset: 0px; line-height: 1; opacity: 0.2; overflow: hidden; position: absolute; text-align: initial; width: 651px; height: 842px;"><span style="box-sizing: border-box; color: transparent; cursor: text; position: absolute; transform-origin: 0px 0px; white-space: pre; left: 80.4262px; top: 107.462px; font-size: 10.5975px; font-family: sans-serif; transform: scaleX(1.02819);" dir="ltr">[6] Upadhyay, V., Gupta, S., Chaturvedi, S. and Singh, D. [2020], ‘Integrated accident prevention detection</span><br style="box-sizing: border-box; color: transparent; cursor: text; position: absolute; transform-origin: 0px 0px; white-space: pre;" /><span style="box-sizing: border-box; color: transparent; cursor: text; position: absolute; transform-origin: 0px 0px; white-space: pre; left: 98.7605px; top: 122.722px; font-size: 10.5975px; font-family: sans-serif; transform: scaleX(1.02592);" dir="ltr">and response system (iapdrs)’,</span><span style="box-sizing: border-box; color: transparent; cursor: text; position: absolute; transform-origin: 0px 0px; white-space: pre; left: 249.802px; top: 122.722px; font-size: 10.5975px; font-family: sans-serif; transform: scaleX(0.999429);" dir="ltr">International journal of engineering and advanced technology</span><span style="box-sizing: border-box; color: transparent; cursor: text; position: absolute; transform-origin: 0px 0px; white-space: pre; left: 538.802px; top: 122.722px; font-size: 10.5975px; font-family: sans-serif;" dir="ltr">9</span><span style="box-sizing: border-box; color: transparent; cursor: text; position: absolute; transform-origin: 0px 0px; white-space: pre; left: 544.851px; top: 122.722px; font-size: 10.5975px; font-family: sans-serif; transform: scaleX(0.971578);" dir="ltr">(3), 2086–</span><br style="box-sizing: border-box; color: transparent; cursor: text; position: absolute; transform-origin: 0px 0px; white-space: pre;" /><span style="box-sizing: border-box; color: transparent; cursor: text; position: absolute; transform-origin: 0px 0px; white-space: pre; left: 98.7605px; top: 137.983px; font-size: 10.5975px; font-family: sans-serif; transform: scaleX(1.02104);" dir="ltr">2089.</span><br style="box-sizing: border-box; color: transparent; cursor: text; position: absolute; transform-origin: 0px 0px; white-space: pre;" /><span style="box-sizing: border-box; color: transparent; cursor: text; position: absolute; transform-origin: 0px 0px; white-space: pre; left: 80.4262px; top: 161.721px; font-size: 10.5975px; font-family: sans-serif; transform: scaleX(1.0602);" dir="ltr">[7] Vitkar, S. P., Banare, A. and Nadar, J. [2022], ‘Conceptual framework for accident detection and pre-</span><br style="box-sizing: border-box; color: transparent; cursor: text; position: absolute; transform-origin: 0px 0px; white-space: pre;" /><span style="box-sizing: border-box; color: transparent; cursor: text; position: absolute; transform-origin: 0px 0px; white-space: pre; left: 98.4957px; top: 176.981px; font-size: 10.5975px; font-family: sans-serif; transform: scaleX(1.05173);" dir="ltr">vention’,</span><span style="box-sizing: border-box; color: transparent; cursor: text; position: absolute; transform-origin: 0px 0px; white-space: pre; left: 142.733px; top: 176.981px; font-size: 10.5975px; font-family: sans-serif; transform: scaleX(0.974303);" dir="ltr">Journal of Pharmaceutical Negative Results</span><span style="box-sizing: border-box; color: transparent; cursor: text; position: absolute; transform-origin: 0px 0px; white-space: pre; left: 345.638px; top: 176.981px; font-size: 10.5975px; font-family: sans-serif; transform: scaleX(1.02101);" dir="ltr">pp. 7449–7455.</span><br style="box-sizing: border-box; color: transparent; cursor: text; position: absolute; transform-origin: 0px 0px; white-space: pre;" /><span style="box-sizing: border-box; color: transparent; cursor: text; position: absolute; transform-origin: 0px 0px; white-space: pre; left: 80.4262px; top: 200.719px; font-size: 10.5975px; font-family: sans-serif; transform: scaleX(1.00165);" dir="ltr">[8] Wu, C., Zhang, P., Zhang, Z., Zheng, W., Xu, B., Wang, W., Yu, Z., Dai, X., Zhang, B. and Zang, K. [2023],</span><br style="box-sizing: border-box; color: transparent; cursor: text; position: absolute; transform-origin: 0px 0px; white-space: pre;" /><span style="box-sizing: border-box; color: transparent; cursor: text; position: absolute; transform-origin: 0px 0px; white-space: pre; left: 98.2202px; top: 215.98px; font-size: 10.5975px; font-family: sans-serif; transform: scaleX(1.10221);" dir="ltr">‘Slip partitioning and crustal deformation patterns in the tianshan orogenic belt derived from gps</span><br style="box-sizing: border-box; color: transparent; cursor: text; position: absolute; transform-origin: 0px 0px; white-space: pre;" /><span style="box-sizing: border-box; color: transparent; cursor: text; position: absolute; transform-origin: 0px 0px; white-space: pre; left: 98.7605px; top: 231.241px; font-size: 10.5975px; font-family: sans-serif; transform: scaleX(1.06334);" dir="ltr">measurements and their tectonic implications’,</span><span style="box-sizing: border-box; color: transparent; cursor: text; position: absolute; transform-origin: 0px 0px; white-space: pre; left: 332.466px; top: 231.241px; font-size: 10.5975px; font-family: sans-serif; transform: scaleX(0.927503);" dir="ltr">Earth-Science Reviews</span><span style="box-sizing: border-box; color: transparent; cursor: text; position: absolute; transform-origin: 0px 0px; white-space: pre; left: 436.755px; top: 231.241px; font-size: 10.5975px; font-family: sans-serif; transform: scaleX(1.02383);" dir="ltr">p. 104362.</span><br style="box-sizing: border-box; color: transparent; cursor: text; position: absolute; transform-origin: 0px 0px; white-space: pre;" /><span style="box-sizing: border-box; color: transparent; cursor: text; position: absolute; transform-origin: 0px 0px; white-space: pre; left: 80.4262px; top: 254.979px; font-size: 10.5975px; font-family: sans-serif; transform: scaleX(1.04775);" dir="ltr">[9] Xu, X., Hu, X., Zhao, Y., Lü, X. and Aapaoja, A. [2023], ‘Urban short-term traffic speed prediction with</span><br style="box-sizing: border-box; color: transparent; cursor: text; position: absolute; transform-origin: 0px 0px; white-space: pre;" /><span style="box-sizing: border-box; color: transparent; cursor: text; position: absolute; transform-origin: 0px 0px; white-space: pre; left: 98.7605px; top: 270.239px; font-size: 10.5975px; font-family: sans-serif; transform: scaleX(1.06446);" dir="ltr">complicated information fusion on accidents’,</span><span style="box-sizing: border-box; color: transparent; cursor: text; position: absolute; transform-origin: 0px 0px; white-space: pre; left: 325.835px; top: 270.239px; font-size: 10.5975px; font-family: sans-serif; transform: scaleX(0.972793);" dir="ltr">Expert Systems with Applications</span><span style="box-sizing: border-box; color: transparent; cursor: text; position: absolute; transform-origin: 0px 0px; white-space: pre; left: 480.319px; top: 270.239px; font-size: 10.5975px; font-family: sans-serif; transform: scaleX(1.04017);" dir="ltr">p. 119887.</span><div> </div><div class="endOfContent" style="box-sizing: border-box; inset: 842px 0px 0px; cursor: default; position: absolute; user-select: none; z-index: -1;"> </div></div></div></div></div><div class="pdfjs-controls" style="box-sizing: border-box; display: inline-block; left: 0px; padding: 12.5px; position: absolute; top: 0px; z-index: 10;"> </div></div></div></div></div></div>2023-10-02T00:00:00+05:00Copyright (c) 2023 VFAST Transactions on Software Engineeringhttps://vfast.org/journals/index.php/VTSE/article/view/1580Blockchain Technology Performance of Asymmetric Algorithms: An Empirical Study2023-09-16T17:14:17+05:00Mujeeb-ur-Rehman Jamalimujeebjamali@usindh.edu.pkDr. Najma Nawaz Channanajma.channa@usindh.edu.pkAadil Jamaliaadil.jamali@usindh.edu.pkAsad Ali Jamaliasadjamali15@gmail.comMazher Alimazhara94@yahoo.comAbdul Khalique Balochak.balouch94@gmail.com<p>Blockchain technology is a transparent, and unchangeable distributed ledger. It has the potential to transform the way to interact with the digital world by allowing to construct a decentralized database that is tamper-proof. Concerns regarding the security of confidential and sensitive data being outsourced are rising. It is possible that service providers may be dishonest since unscrupulous administrators have access to, may alter, and can misuse private and sensitive data. Security precautions are necessary because sensitive data stored on public clouds has to be safeguarded. There is no mechanism to detect data changes, as data are stored in plaintext. Therefore, maintaining privacy and secrecy is impossible. It is important that data must always be kept secure, even after it has been kept on the server. Data stored on the server must be safeguarded against outsider access and, if the insider cannot be trusted, must also be safeguarded against hostile insiders. Asymmetric algorithms are employed to safeguard data during transmission. Asymmetric cryptography is required in modern security systems, and several algorithms have been devised to provide safe and effective encryption and decryption. Asymmetric algorithms are empirically compared in this study. We evaluated each algorithm's performance by taking into account criteria such as key size, memory utilization, and execution time. Our results show that while all algorithms provide safe encryption and decryption, there are significant performance disparities between them. It is determined, in particular, that ECC required the least amount of memory and had the shortest key size. The findings show that ECC's prime and binary fields created pairs of keys faster and with more security than other asymmetric algorithms with smaller bit sizes. On small, medium, and big datasets, ECC had the fastest execution time for plaintext encryption operations. These findings have important implications for the selection and deployment of asymmetric algorithms in various security systems.</p>2023-09-30T00:00:00+05:00Copyright (c) 2023 VFAST Transactions on Software Engineeringhttps://vfast.org/journals/index.php/VTSE/article/view/1577Design and Implementation of Brain-Based Home Automation System2023-09-16T17:12:11+05:00Mujahid Mujahid Rafiqrafiqmujahid55@gmail.comSerosh Karim Noonseroshkarim@nfciet.edu.pkAbdul Mannanmannan@nfciet.edu.pkTehreem Awantehreemawan@nfciet.edu.pkNoshaba Nisarnoshabanisar874@gmail.com<div><table width="688" cellspacing="0" cellpadding="0"><tbody><tr><td align="left" valign="top" height="236"><div><p><em>This paper supports the utilization of EEG signals to control a smart home automation system. The study involves calculating the human brain's attention level using EEG data and subsequently employing this information to operate various devices based on the attention value obtained. The process commences with multichannel EEG recordings, which are then processed using MATLAB software. The first channel (FP1) is isolated from the multichannel EEG data, and subsequent steps involve noise and artifact removal through a bandpass filter ranging from 0.3 to 100 Hz. The Alpha and Beta sub-bands of the EEG data are computed, and the Power Spectral Density is derived from the Alpha and Beta waves. By analyzing the intensities of the Alpha and Beta PSD signals, the subject's attention level is computed and categorized. This attention level indicator is then used to control the operation of smart home electrical devices. The study demonstrates the viability and effectiveness of the proposed EEG-based system for controlling domestic appliances, confirming its successful functionality.</em></p></div></td></tr></tbody></table></div>2023-09-30T00:00:00+05:00Copyright (c) 2023 VFAST Transactions on Software Engineeringhttps://vfast.org/journals/index.php/VTSE/article/view/1575Mobility and Health Monitoring in People with Different Abilities: A Prototype Enhancing Independence: Innovating an IoT-Integrated Wheelchair for2023-08-26T06:18:03+05:00Zuhra Banofahad.shamim@lumhs.edu.pkFarwa Qureshifahad.shamim@lumhs.edu.pkMoomal Ansarfahad.shamim@lumhs.edu.pkNimra Imdadfahad.shamim@lumhs.edu.pkSarmad Shamsfahad.shamim@lumhs.edu.pkFahad Shamimfahad.shami@lumhs.edu.pk<div><table width="684" cellspacing="0" cellpadding="0"><tbody><tr><td align="left" valign="top" height="323"><div><p><em>Wheelchair is an essential tool for people with disabilities, enabling them to move around independently and participate fully in society. They come in different types, such as manual wheelchairs, power wheelchairs, sports wheelchairs, and pediatric wheelchairs among others. Certain types of disabilities such as Monoplegia, Hemiplegia, Paraplegia, and Quadriplegia pose difficulties in using conventional power wheelchairs. To overcome these hurdles and provide ease to differently-abled individuals, an Advance Monitoring and Assistive Wheelchair (AMAW) is proposed in this work. The Prototype includes a voice-controlled system for controlling the movement of a wheelchair, an IoT-based real-time health monitoring system to monitor the vitals of the patient remotely, a fall detection system for detecting falls, a tracking system for position and location, and an alarm system to alert caretaker in case of a fall. The real-time embedded monitoring system allows the monitoring of the user’s vital signs like temperature, pulse rate and oxygen saturation and the assistive part allows the wheelchair to move around electronically either through voice or through mobile application. With the assistance of various sensors, the data can easily be monitored remotely by the caretaker at regular intervals of the time. The data display on the LCD fitted onto the wheelchair and in the designed mobile application. Furthermore, the whereabouts of the user are sent via the alert system that notifies the caretaker through GSM in case of changes in parameters and if the user has lost the balance. The vitals through the sensors on the prototype has undergone testing on number of individuals with precise outcomes. In comparison to typical joystick-controlled wheelchairs, this project excels in several aspects, such as its ability to stop or turn using voice commands and avoid collisions with people, furniture, fixed objects, and walls. The user friendly AMAW prototype with real-time monitoring, assistance and alert system may serve as a cost-effective solution in maintaining and providing an independent quality life to differently-abled individuals.</em></p></div></td></tr></tbody></table></div>2023-06-30T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTSE/article/view/1574Identification and Classification of Extremist by Topic Modeling Sentiment Analysis2023-08-26T06:18:03+05:00Hafsa Bano2k19mscs112@nfciet.edu.pkWasif AkbarWasif.akbar@nfciet.edu.pkNaeem Aslamnaeemaslam@nfciet.edu.pkMuhammad Bilal2k19mscs118@nfciet.edu.pk<div><table width="687" cellspacing="0" cellpadding="0"><tbody><tr><td align="left" valign="top" height="311"><div><p>Social Media forums were formerly seen as the promised land for amusement, education, and boosting purposes that energize the evolution of text analysis to acknowledge the complications of real world. A seedbed for toxic conduct, fanatical content, and political propaganda, they have now become a sump. YouTube is one of the finest platforms where millions of comments thrown per day which consists of valuable and misleading information. Comments may contain slang, foreign and misspelled words that’s very laborious to perform natural language processing (NLP) with those informal languages. Most preceding research diffused the analysis of gigantic unstructured data that comes in different formats and not simply classify in current databases. This study aims to analyze dynamic textual data from randomly selected channels on YouTube. For this ambition YouTube information API v3 was used to scrape a variety of data from YouTube videos. We investigated a few hot topics that are having mordant remarks about racism, LGBTQ, sub teen life aspect, and women and girls are just some of the areas where bullying is ordinary. In this study we summarize a custom dataset of 50 video’s comments related to rap songs and other social events to perform topic modelling sentiment analysis that dwindle the cost of data labeling and annotating. The main objective of our research is to identify and classify each word with their probability from the dataset by applying model hyper parameters alpha, beta, gamma and examine the topic coherence score to measure the semantic similarity of words from extracted topics. This study’s experimental results reveal that the analysis was able to achieve significant sentiment analysis efficiency at both the document and word levels.</p></div></td></tr></tbody></table></div>2023-06-30T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTSE/article/view/1571Predicting the Karachi Stock Price index with an Enhanced multi-layered Sequential Stacked Long-Short-Term Memory Model2023-08-26T06:18:03+05:00Khalid Mahboobkmahboob@ssuet.edu.pkMuhammad Huzaifa Shahbazmhuzaifadev@gmail.comFayyaz Ali1fayyaz.ali@gmail.comRohail Qamarmuhammadrohailqamar@gmail.com<div><table width="683" cellspacing="0" cellpadding="0"><tbody><tr><td align="left" valign="top" height="267"><div><p><em>The study proposes the use of a stacked Long-Short-Term Memory (LSTM) model to predict the KSE-100 stock exchange trend and provides a comprehensive review of the literature on deep learning models and time series forecasting in the stock market. The study's findings suggest that the stacked LSTM model outperforms other models in terms of prediction accuracy. The study's contribution lies in its approach to improving the accuracy of stock price prediction using deep learning models. The stacked LSTM model architecture is a novel approach that provides better results than other traditional time series forecasting models. Furthermore, the study's use of hyper-parameter optimization techniques demonstrates the importance of model tuning for improving performance intended for accurate time series forecasting in the financial market. The study's results have practical implications for investors, who can use the stacked LSTM model to make informed decisions about buying or selling stocks in the KSE-100. The model's ability to predict stock prices accurately can help investors maximize their profits and minimize their losses. Hence, the proposed stacked LSTM model can effectively predict stock prices in the KSE-100 and can assist investors in making informed decisions in the stock market. </em></p></div></td></tr></tbody></table></div>2023-06-30T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTSE/article/view/1568Evaluating Accuracy of Pathogenicity Prediction Methods for Single Nucleotide Polymorphisms2024-01-14T01:56:36+05:00Hira Manzoorhiramanzoor850@gmail.comNaeem Aslamnaeemaslam@nfciet.edu.pkMuhammad Tariq Pervezm.tariq@vu.edu.pkSyed Shah Muhammadsyed@vu.edu.pkAyesha Mubashraayeshamubshra64@gmail.com<div><table width="685" cellspacing="0" cellpadding="0"><tbody><tr><td align="left" valign="top" height="237"><div><p><em>Pathogenicity of single nucleotide polymorphism is the potential ability to produce disease. </em><em>Testing each of the SNPs separately can lead to an erroneous measurement of the effect of the SNPs on the disease risk. In this research analysis of seven most popular tools for predicting the deleteriousness of single nucleotide polymorphisms namely SIFT, SNPs&GO, I Mutant, MUPro, Fathmn, PANTHER, and PhD-SNP was conducted. The ClinVar database was used to retrieve the pathogenic and benign SNPs, and the UniProt database to get protein sequences respectively. The SIFT, PhD-SNP, and SNP&Go outperformed all of the other prediction algorithms based on accucy and Matthews Correlation Coefficient with scores of (0.68,0.38), (0.66, 0.33) and (0.64, 0.29) respectively with highlighting error rates and recommended to avoid the use of MuPro for predicting the pathogenic variants. To improve the performance and accuracy of pathogenicity predictors the tools must be considered to upgrade.</em></p></div></td></tr></tbody></table></div>2023-06-30T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTSE/article/view/1566Detecting Monkeypox in humans using deep learning2024-01-14T01:56:47+05:00Muhammad Arslan Ijaz2k20mscs209@nfciet.edu.pkMuhammad Kamran Abid2k20mscs209@nfciet.edu.pkNaeem Aslam2k20mscs209@nfciet.edu.pkAbdul Qadeer Mudaseer2k20mscs209@nfciet.edu.pk<div><table width="683" cellspacing="0" cellpadding="0"><tbody><tr><td align="left" valign="top" height="208"><div><p><em>The monkeypox virus is an orthopox virus that causes a contagious illness of the same name. The most visible symptom, along with fever, headache, and muscular pains, is a broad rash that develops into fluid-filled blisters. In the event of a monkeypox outbreak, swift response and efficient public health management depend on an early and accurate diagnosis. In this study, the feasibility of using deep keep learning techniques to diagnose monkeypox in humans is investigated. Long short-term memory (LSTM) networks are used to analyse time-series recordings of symptoms or patient data, whereas convolutional neural networks (CNNs) are used to process medical images of skin lesions. These models need to be trained on a large and reliable data set so that they can identify patterns and attributes that are specific to monkeypox.</em></p></div></td></tr></tbody></table></div>2023-06-30T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTSE/article/view/1559A Novel Method for Ranking a Website Rating via Search Engine Optimization2024-01-14T01:56:58+05:00Muhammad Ahsan Razaahsan.raza@ue.edu.pkBinish Razaengr.binishraza@gmail.comMahmood Ashrafmahmoodkhn24@gmail.comSehrish Razasehrish.6025@wum.edu.pk<div><table width="688" cellspacing="0" cellpadding="0"><tbody><tr><td align="left" valign="top" height="236"><div><p><em>Everyone uses the internet and a search engine (SE) to find what they need, making SE indispensable. Search engines are used to find any sort of information, which is why most companies want to rank well in SE result pages in order to reach their ideal clients. Without a website, companies nowadays have little chance of competing in the industry. As a consequence, the companies have prioritized and funded efforts to improve their website SE rankings. There are a plethora of methods that may be used to optimize a website for search engines. These methods come under a heading, namely, search engine optimization (SEO) by webmasters. In this research, we propose a methodology that combines on-page and off-page SEO strategies to improve user search and website ranking over SE. The proposed method outperforms in terms of website ranking, whereby a website ranking is improved from fifth to second position on Google SE. This significant shift illustrates that on and off page SEO can work together to boost a website visibility over SE result page.</em></p></div></td></tr></tbody></table></div>2023-06-30T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTSE/article/view/1547The Design and Evaluation of Novel Ananimated CAPTCHA Schemes Based on Humans’ Natural Vision Capabilities2024-01-14T01:57:09+05:00Rafaqat Hussain Arainrafaqat.arain@salu.edu.pkRiaz Ahmed Shaikhrafaqat.arain@salu.edu.pkSafdar Ali Shahrafaqat.arain@salu.edu.pkSajjad Ali Shahrafaqat.arain@salu.edu.pkSaima Rafiquerafaqat.arain@salu.edu.pk<div><table width="685" cellspacing="0" cellpadding="0"><tbody><tr><td align="left" valign="top" height="256"><div><p><em>CAPTCHAs are ubiquitously found on the web these days. It is most commonly used security mechanism against bots. Numerous design variants of static text-based CAPTCHAs were proposed and implemented on the internet over the years. However due to advancements in machine learning and image processing techniques they were proved vulnerable against automated attacks. In this research a new and robust animated CAPTCHA scheme is presented which is based on human’s natural vision capabilities. The newly designed CAPTCHAs are user friendly for humans but extremely hard for bots. The security and usability is kept in mind while designing these CAPTCHAs. Various types of characters, patterns and filters are used to protect them against automated attacks. Overall, 20 types of animated CAPTCHAs are designed in this work. Further in this research, a group of participants have evaluated the usability of newly designed CAPTCHAs and solved with an average success rate of 76.85%. The analysis has proved that the proposed scheme is very much usable for humans and extremely difficult for bots.</em><em></em></p></div></td></tr></tbody></table></div>2023-06-30T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTSE/article/view/1538Azure-Based Multi-Sensor IoT Network for Smart Rice-Nursery Field2024-01-14T01:57:20+05:00Muhammad Juman Jhatialjuman@quest.edu.pkDr. Riaz Ahmed Shaikhriaz.shaikh@salu.edu.pkDr Rafaqat Hussain Arainrafaqat.arain@salu.edu.pkKhalid Hussain Bhuttofor4khalid@gmail.comSawan Ali Talpursavisanvi.ss@gmail.com<div><table width="685" cellspacing="0" cellpadding="0"><tbody><tr><td align="left" valign="top" height="239"><div><p>Rice farmers rely on nurseries for various reasons, as they play a pivotal role in cultivating high-quality rice crops. These nurseries provide essential seedlings for subsequent transplantation to the paddy fields. The success of rice cultivation hinges on maintaining a robust and thriving nursery, resulting in improved yields and superior grain quality. To enhance nursery management, a novel method proposes real-time monitoring of environmental conditions. A trial study evaluated the system's performance, demonstrating a significant increase in precision and efficiency, leading to higher crop yields and reduced production costs. This innovative approach has the potential to revolutionize rice nursery practices, promoting sustainability and effectiveness. The study introduces an Internet of Things (IoT)-based real-time monitoring system implemented in a rural area of Sindh, Pakistan. Utilizing a network of sensors, the system gathers vital environmental data that impacts rice nursery growth. The recorded information is then analyzed on the Azure cloud platform, and data visualization is achieved through Power BI. Additionally, an email notification component alerts farmers and agricultural experts based on the sensor data, facilitating timely actions and informed decision-making.</p></div></td></tr></tbody></table></div>2023-06-30T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTSE/article/view/1533Brain Tumor Segmentation using Deep Learning2024-01-14T01:57:32+05:00Muhammad Sajidauksajid@gmail.comWajeeha Yaseenwajeehayaseen88@gmail.comAman Ullah Khanaukua2@gmail.com<div><table width="684" cellspacing="0" cellpadding="0"><tbody><tr><td align="left" valign="top" height="256"><div><p><em>In addition to helping doctors discover and measure tumors, it also helps them develop better recovery and treatment plans. Recent MRI brain tumor segmentation algorithms have focused on U-Net design to combine high-level and low-level features for improved accuracy. Fully convolutional networks, which are also used for this purpose, are unable to successfully reconstruct the image through the decoder path because of the insufficient and low-level information from the encoder path. More effort needs to be done to optimise the low-level information flow from the encoder path to the decoder path in order to improve image reconstruction. In this study, we suggested a transfer learning residual U-Net model that combines the U-Net and VGG-16 architectures. To improve </em><em>image</em><em> reconstruction, VGG-16 is combined with the encoder. Additionally, a residual path in skipping connection is included to highlight key feature details while muting noisy and unnecessary feature replies. It is trained using The Cancer Imaging Achieve (TCIA) and Brats 2018 datasets, and It makes it easier to segment small brain tumors. When compared to previous brain tumor segmentation techniques, the suggested model performs competitively.</em></p></div></td></tr></tbody></table></div>2023-06-30T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTSE/article/view/1527Optimized Classification of Cardiovascular Disease Using Machine Learning Paradigms2023-08-26T06:18:02+05:00Fouzia KanwalFouziaKanwal@gmail.comMr. Kamran Abidkamran.abid@nfciet.edu.pkMuhammad Sajid Maqboolsajidmaqbool7638@gmail.comDr Naeem Aslamnaeemaslam@nfciet.edu.pkMuhammad Fuzailfuzail@nfciet.edu.pk<div><table width="688" cellspacing="0" cellpadding="0"><tbody><tr><td align="left" valign="top" height="255"><div><p><em>Nearly 19 million people die each year from cardiovascular and chronic respiratory diseases, which are a global threat. It is necessary to address the causes of these diseases because of the high death rate. The investigation uncovered a number of causes, but the inability to forecast these diseases symptoms is by far the most significant. In this work, we developed a method for anticipating these diseases crucial symptoms, which will aid in early disease diagnosis and allow patients to begin treatment. This research will introduce a new computational medicine research using machine learning (ML) paradigms to forecast cardiovascular disease (CVD). Data were processed by methods in sequence with various parameters. different models created that predicts CVD risk based on individual age, gender, ethnicity, body mass etc., and lifestyle factors. The research will also focus on performing complete comparison of ML models. We will apply Five ML based algorithems such as Decision Tree (DT), K-Nearest Neighbors (KNN), Naïve Bayes (NB), XGBOOST and Random Forest and evaluate these models on the basis of Training and Testing and also calculated the Presicion Recall and F1-Score for each model. Naïve Bayes and XGBOOST Classifier perform better with accuracy of 92.31 and 92.34 percent as compared to other models.</em></p></div></td></tr></tbody></table></div>2023-07-10T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTSE/article/view/1514LeafNet: Using Convolutional Neural Network for Plant Leaf Detection2024-01-14T01:59:24+05:00Saba Saeedsabasaeed410@gmail.comSana Faizsanafaiiiz1122@gmail.comAreej Fatemah Meghjiareej.fatemah@faculty.muet.edu.pk<div><table width="683" cellspacing="0" cellpadding="0"><tbody><tr><td align="left" valign="top" height="245"><div><p><em>Pakistan is home to thousands of plant species. As a result of pollution, natural disasters, and climate change, many of these species are at risk of extinction. Plant categorization and detection systems are designed to assist non-experts in automatically identifying plants based on their leaves to ensure their safety. The current study proposes a plant leaf detection system utilizing a Convolutional Neural Network architecture. Making use of the PlantVillage dataset, the proposed system can identify seven species of plants namely apple, cherry, tomato, potato, soybean, strawberry, and corn. Data augmentation strategies have been used to provide more training examples to get around the problem of bias and imbalanced data. The accuracy achieved on the training set was 98.87% which improved to 99.5% when using data augmentation. Apart from the monitoring of endangered species, the adoption of the proposed model can also aid the evaluation of weed management efforts and analysis of species distribution under climate change.</em></p></div></td></tr></tbody></table></div>2023-06-17T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTSE/article/view/1502An empirical study of performance of block cipher algorithms in cloud computing environment2024-01-14T01:57:43+05:00Mujeeb-ur-Rehman Jamalimujeebjamali@usindh.edu.pkGhulam Nabirajperghulamnabi@gmail.comAbdul Khalique Balochak.balouch94@gail.comAbdul Rehman Balocharehman.usindh@usindh.edu.pkAadil Jamaliaadil.jamali@usindh.edu.pkRiaz Ahmed Shaikhriaz.shaikh@salu.edu.pk<div><table width="683" cellspacing="0" cellpadding="0"><tbody><tr><td align="left" valign="top" height="250"><div><p><em>The security of private and sensitive data stored in the public domain is a major problem. It is critical for the user that data be safe both in transit and even after it has been stored on the server. The data owner must be guaranteed that the data held on the service provider site is safeguarded against data theft from outsiders, and the data must be protected even from the service providers. The secret key generation is one of the most important factors for the security of any cryptographic system because the length of the key directly affects the performance and prevents various cryptographic attacks such as brute force attacks. At the application level, our developed system efficiently secures sensitive, private, and personally identifiable information by ensuring privacy and confidentiality of data at rest in the public domain. This study also compares the performance of block cipher algorithms DES, 3DES, Blowfish, and AES. It was deduced from the result that AES consumes less time when compared to other symmetric algorithms with small consistent behavior for various cryptographic operations with small, medium and big datasets..</em></p></div></td></tr></tbody></table></div>2023-06-30T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTSE/article/view/1501Deep Emotions Recognition from Facial Expressions using Deep Learning2024-01-14T01:59:12+05:00Iram Shahzadishahzadiiram402@gmail.comMr. Muhammad Fuzailshahzadiiram402@gmail.comDr. Naeem Aslamshahzadiiram402@gmail.com<div><table width="688" cellspacing="0" cellpadding="0"><tbody><tr><td align="left" valign="top" height="295"><div><p class="DefaultParagraphFont1"><em>Deep emotion recognition has a wide range of applications, including human-robot communication, business, movies, services hotels, and even politics. Despite the use of various supervised and unsupervised methods in many different fields, there is still a lack of accurate analysis. Therefore, we have taken on this challenge as our research problem. We have proposed a mechanism for efficient and fine-grained classification of human deep emotions that can be applied to many other problems in daily life. This study aims to explore the best-suited algorithm along with optimal parameters to provide a solution for an efficient emotion detection machine learning system. In this study, we aimed to recognize emotions from facial expressions using deep learning techniques and the JAFFE dataset. The performance of three different models, a CNN (Convolutional Neural Network), an ANN (Artificial Neural Network), and an SVM (Support Vector Machine) were evaluated using precision, recall, F1-score, and accuracy as the evaluation metrics. The results of the experiments show that all three models performed well in recognizing emotions from facial expressions. The CNN model achieved a precision of 0.653, recall of 0.561, F1-score of 0.567, and accuracy of 0.62. The ANN model achieved a precision of 0.623, recall of 0.542, F1-score of 0.542, and accuracy of 0.59. The SVM model achieved a precision of 0.643, recall of 0.559, F1-score of 0.545, and accuracy of 0.6. Overall, the results of the study indicate that deep learning techniques can be effectively used for recognizing emotions from facial expressions using the JAFFE dataset.</em></p></div></td></tr></tbody></table></div>2023-06-19T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTSE/article/view/1500Identification of Lungs Cancer by using Watershed Machine Learning Algorithm2024-01-14T01:59:01+05:00Razia Parveenraziarafiq34@gmail.comUjala Saleemraziarafiq34@gmail.comKamran Abidraziarafiq34@gmail.comNaeem Aslamraziarafiq34@gmail.com<div><table width="684" cellspacing="0" cellpadding="0"><tbody><tr><td align="left" valign="top" height="265"><div><p><em>The most dangerous and </em><em>quickly spreading form </em><em>of cancer in the world is lung </em><em>cancer.</em><em> </em><em>In </em><em>terms </em><em>of </em><em>fatalities </em><em>among cancer diseases, it </em><em>comes </em><em>in first </em><em>place, </em><em>and </em><em>therapy </em><em>is </em><em>made </em><em>more </em><em>challenging by </em><em>late-stage </em><em>diagnosis</em><em>.</em><em> Early identification and detection are crucial for treating this lethal condition, though. Benign and malignant tumors are the two forms that manifest in the early stages of this illness. These are visible with a computed tomography (CT) scan. Thanks to machine learning, these pictures can be used to determine the stages of cancer. In this study, a machine learning framework is presented using the proposed convolutional neural network techniques in order to develop a reliable and precise classification model for the diagnosis of lung cancer and to address the problem of class imbalance datasets, a general problem in medical data that results in difficulties and mistakes in prediction. The data source for the investigation was the IQ-OTHNCCD dataset. Scale Invariant Feature Transform (SIFT) and Watershed were the best feature extraction methods employed in this work, which was provided as a segmentation method. A dataset imbalance is later resolved by data augmentation, and CNN is used to achieve classification. In the malignant lung image, we finally identify the nodule. An accuracy rate of 0.97% is achieved with the</em><em> </em><em>proposed CNN-based classification of CT scan pictures</em><em>.</em></p></div></td></tr></tbody></table></div>2023-06-23T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTSE/article/view/1497LCCNet: A Deep Learning Based Method for the Identification of Lungs Cancer using CT Scans2024-01-14T01:58:39+05:00Kiran Khaliq2k20mscs219@nfciet.edu.pkAhmed Naeemahmad.naeem@nfciet.edu.pkNaeem Aslamnaeemaslam@nfciet.edu.pkAbdul Malikabdul.ravian@gmail.comKamran Abidkamran.abid@nfciet.edu.pk<div><table width="688" cellspacing="0" cellpadding="0"><tbody><tr><td align="left" valign="top" height="305"><div><p><em>Lung cancer is a highly lethal disease affecting both males and females nowadays. It is essential to identify cancer accurately at the initial stage of lung cancer. However, accurately diagnosing cancer remains a challenging task for pathologists. Among the various techniques available, CT Scan plays a crucial role in the early identification and treatment of lung cancer. For the classification of lung cancer, lots of developing techniques are used in the medical research field. Unfortunately, these techniques achieve less classification accuracy due to poor learning rate, class imbalance, data overfitting, and vanishing gradient. It is essential to develop an accurate, faster, and well-organized system for the classification of lung cancer. To address these issues, an efficient framework called LCCNet is presented, which is transfer learning applied to the pre-trained Densely Connected Convolutional Networks (DenseNet-121) CNN model. LCCNet is used to accurately classify lung cancer. The most common transfer learning and data augmentation approaches are used to deal with a large dataset. LCCNet utilized CT Scans for the accurate classification of lung cancer. To assess the performance, the model utilizes various evaluation metrics such as accuracy, F1-score, precision, and recall along with a confusion matrix to validate the efficiency of the model for lung cancer classification. Furthermore, this study also compares several current studies with the proposed LCCNet model in terms of accuracy measures, showing that the proposed LCCNet model attained the greatest accuracy of 99% when compared to the various existing research fields of study. To the best of our knowledge, the proposed methodology performs efficiently.</em></p></div></td></tr></tbody></table></div>2023-06-27T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTSE/article/view/1487Using Machine Learning Models for The Prediction of Coronary Arteries Disease2024-01-14T01:57:54+05:00Muhammad Bilal2k19mscs118@nfciet.edu.pkNaeem Aslamnaeemaslam@nfc.iet.pkAhmad Naeemahmad.naeem@nfciet.edu.pkMuhammad Kamran Abidkamran.abid@nfciet.edu.pk<div><table width="687" cellspacing="0" cellpadding="0"><tbody><tr><td align="left" valign="top" height="263"><div><p>Globally, the leading cause of mortality among both men and women is coronary heart disease. This disease is widely recognized as the primary killer worldwide, and its early detection poses a significant challenge. Given the current state of affairs, it is crucial to promptly identify heart disease in its initial stages to ensure successful patient treatment. Despite numerous attempts by various researchers to develop hybrid and ensemble models for early detection, the desired outcomes have not been achieved. Consequently, the machine learning and algorithmic research community has directed its focus towards improving these methodologies. In this particular study, six supervised machine learning classifiers, namely Random_Forest, extreme gradient boost, Logistic of Regression, Decision_Tree, KNN, and N-Bayes, were employed. The UCI repository dataset was utilized as the sample data, comprising attributes and corresponding values. Data preprocessing techniques were employed to eliminate any missing values. An ensemble model incorporating three algorithms, namely DT (decision-tree), RF (random-forest), and XGB, was constructed. Remarkably, the ensemble model achieved an impressive accuracy rate of 95.33% for predicting coronary heart disease.</p></div></td></tr></tbody></table></div>2023-06-30T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTSE/article/view/1486Sentiment Analysis on Disputed Territory Discrepancies Using Machine Learning-based Text Mining Approach2024-01-14T02:00:09+05:00Mustajeeb ur Rehmanmustajeeb.rehman@nfciet.edu.pkMaria Bashirmaria.bashir@nmbu.no<em>Conducting a comparative study of real-time sentiment analysis poses a significant challenge due to the continuous variation in individuals' accents and the difficulty in quantifying them. In computer science, specifically supervised machine learning classifiers, researchers face the obstacle of lacking direct observation. This study explores the performance of well-known supervised machine learning classifiers such as SVM, K-SVM, and Multinomial Naïve Bayes. We utilize a comprehensive corpus of real-time Twitter tweets and news blogs related to disputed territories. These classifiers are trained on the Kaggle dataset for real-time sentiment analysis to achieve the highest accuracy and subsequently tested on real-time data. Notably, the kernel support vector machine performs better in real-time data, as evidenced by the substantial proportion of positive sentiments detected. Furthermore, our study offers a pathway for young scholars to assess the real-time sentiment correlation between corresponding countries, enabling predictions of potential conflicts that may lead to significant casualties</em>2023-05-30T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTSE/article/view/1485A Novel Face Spoofing Detection Using hand crafted MobileNet2024-01-14T01:59:46+05:00Sayyam Zahrasayyamzahra123@gmail.comMohibullah Khanmohibullahkhan@nfciet.edu.pkKamran Abidkamran.abid@nfciet.edu.pkNaeem Aslamnaeemaslam@nfciet.edu.pkEjaz Ahmad Kheraejaz.khera@iub.edu.pk<div><table width="688" cellspacing="0" cellpadding="0"><tbody><tr><td align="left" valign="top" height="235"><div><p><em>There are several uses for face spoofing detection, including human-robot communication, business, film, hotel services, and even politics. Despite the adoption of numerous supervised and unsupervised techniques in a wide range of domains, proper analysis is still lacking. As a result, we chose this difficulty as our study problem. We have put out a method for the effective and precise classification of face spoofing that may be used for a variety of everyday issues. This work attempts to investigate the ideal method and parameters to offer a solution for a powerful deep learning spoofing detection system. In this study, we used the LCC FASD dataset and deep learning algorithms to recognize faces from photos. Precision and accuracy are used as the evaluation measures to assess the performance of the CNN (Convolutional Neural Network) model. The results of the studies demonstrate that the model was effective at spoofing face picture detection. The accuracy of the CNN model was 0.98. Overall, the study's findings show that spoofing detection from photos using the LCC FASD dataset can be successfully performed utilizing deep learning algorithms. Yet, the findings of this study offer a strong framework for further investigation in this area.</em></p></div></td></tr></tbody></table></div>2023-06-02T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTSE/article/view/1477Smart Agricultural Genetic Divergence Pattern Estimation of Morphological Traits in Cotton2024-01-14T01:58:06+05:00Muhammad Arslan Rajputazeemayaz@sbbusba.edu.pkFatima Javeria Javeriafatimajaved524@gmail.comDua Noorfaisalbaloch553@gmail.comAmeer Hussain Changarslan2k14@gmail.comZulqarnain ChannaArslan2k14@gmail.comFaisal Nabi Mazarifaisalbaloch553@gmail.com<div><table width="683" cellspacing="0" cellpadding="0"><tbody><tr><td align="left" valign="top" height="316"><div><p><em>Cotton (Gossypium hirsutum L.), an important agricultural fiber crop belonging to the Malvaceae family, exhibits wide genetic diversity that requires thorough investigation for the development of climate-smart cotton. This study aimed to assess the genetic variation of cotton varieties in relation to yield-related characteristics. A total of fifty genotypes were sown at the Cotton Research Institute (CRI) in Multan using a randomized complete block design (RCBD) with two replications. The row-to-row and plant-to-plant distances were maintained at 75 cm and 23 cm, respectively. Data were collected for various morphological traits, including plant height (PH), monopodial branches per plant (MO), sympodial branches per plant (SY), number of nodes (NO), boll length (BL), boll width (W), boll weight (BW), total boll weight per plant (TB), and seed cotton yield (SCY). Maximum values were recorded for PH (109.40 cm), MO (8.0500 branches/plant), SY (25.100 branches/plant), NO (41.550 nodes), BL (41.750 mm), W (41.300 mm), BW (3.9500 mg), TB (33.750 g), and SCY (95.400 g). ANOVA results indicated significant differences among all the genotypes. Positive and significant correlations were observed between PH, SCY, and BL, demonstrating the successful utilization of selection criteria based on these traits to improve cotton yields. Cladogenesis studies revealed that class I, II, and III were represented by FH-183, VH-281, and AGC-2, respectively, exhibiting superior genetic potential in terms of morphological traits. Principal component analysis (PCA) demonstrated that 81.88% of the total variance was primarily attributed to traits such as SY, TB, PH, SCY, and BW, with the first five components having eigenvalues greater than 1. These findings provide breeders with valuable insights into selecting desirable characteristics for cotton varieties. </em></p></div></td></tr></tbody></table></div>2023-06-30T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTSE/article/view/1475Using Educational Data Mining to Predict Student Academic Performance2024-01-14T01:59:35+05:00Areej Fatemah Meghjiareej.fatemah@faculty.muet.edu.pkFarhan Bashir Shaikhfarhan.shaikh@usindh.edu.pkShuaib Ahmed Wadhoshoaib.qau09@gmail.comSania Bhattisania.bhatti@faculty.muet.edu.pkRamesh Kumar Ayyasamyrameshkumar@utar.edu.my<div><table width="684" cellspacing="0" cellpadding="0"><tbody><tr><td align="left" valign="top" height="253"><div><p><em>An educational institution's primary objective is to create a learning environment that enhances student academic success by mitigating academic failure and promoting higher performance. In order to accomplish this, the institute needs an effective mechanism for quickly identifying students’ performance, in particular students at the risk of falling behind or failing a course. Using the classification approach of educational data mining, this study utilizes student descriptive, behavioral, and attitudinal data to predict academic performance at an early stage during a semester. Specifically, this study makes use of ruled-based, decision tree, function-based, lazy, multilayer perceptron, and probabilistic classification techniques for early student performance prediction. The models generated by several classifiers exhibited good performance with the model generated by the Random Forest classifier exhibiting an accuracy of 93.40% and a Kappa score of 0.9160. The experimental results of the study indicate the effectiveness of using a set of descriptive, behavioral, and attitudinal attributes to predict student performance at an earlier stage during the conduct of a semester.</em></p></div></td></tr></tbody></table></div>2023-06-07T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTSE/article/view/1472RLTD: A Reliable, Link Quality, Temperature and Delay Aware Routing Protocol for Wireless Body Sensor Networks2024-01-14T01:59:58+05:00Shahid Iqbalshahid.iqbal@bzu.edu.pkAli Raza Bhangwararbaloch@quest.edu.pkAdnan AhmedAdnan.ahmed03@quest.edu.pkFayaz AhmedEngr_fayaz@quest.edu.pkMuhammad Awaisawaisrajput@quest.edu.pkAbrar Hussainabrar.tunio@yahoo.com<div><table width="685" cellspacing="0" cellpadding="0"><tbody><tr><td align="left" valign="top" height="276"><div><p><em>The miniaturization of biomedical sensor nodes has paved the way for remote patient monitoring using wearable wireless sensor nodes. The network of such invasive and non-invasive sensor nodes is most commonly known as Wireless Body Sensor Network (WBSN). The healthcare applications of WBSN are delay sensitive and of critical nature, therefore, it require reliable and timely dissemination of patients’ critical data to the remote location to ensure Quality of Service (QoS).</em><em> </em><em>However, poor link quality (LQ) may affect QoS and result in higher transmission delay, loss of critical data packets data corruption, packet retransmissions, thereby, degrading network performance and compromising the patient’s privacy and confidentiality. Furthermore, the in-vivo wireless sensor node produces </em><em>electromagnetic radiations which are absorbed by the human body thereby, causing temperature rise around the implanted sensor node. The prolonged communication of such in-vivo nodes creates a hotspot node that results in sensitive tissue damage. Therefore, ensuring hotspot-free communication is a necessity in WBSN. Considering such issues, we propose a Reliable, Link Quality and Temperature aware routing protocol (RLTD) for delay-sensitive application of WBSNs that route data through reliable nodes and good quality links to the destination node. The efficacy of the proposed (RLTD) routing protocol is confirmed by comparing results with the well-known thermal-aware protocols for WBSN.</em></p><p> <em></em></p></div></td></tr></tbody></table></div>2023-06-02T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTSE/article/view/1471Humanoid Robots: Cybersecurity Concerns And Firewall Implementation2024-01-14T02:00:43+05:00Safa Munir2k20mscs105@nfciet.edu.pkKashaf Khan2k20mscs105@nfciet.edu.pkDr Naeem Aslam2k20mscs105@nfciet.edu.pkKamran Abid2k20mscs105@nfciet.edu.pkMustajib-ur- Rehman2k20mscs105@nfciet.edu.pk<div><table width="686" cellspacing="0" cellpadding="0"><tbody><tr><td align="left" valign="top" height="289"><div><p><em>Technology has grown more important in our lives, and scientists are developing new products to make people’s life easier and more pleasant. One of these innovations is the humanoid robot. The use of humanoid robots in our daily lives is expanding at an unprecedented rate as robots are being used in different aspects of life. The market is becoming more automated and optimized, Robotics serves as one of the primary instruments used for these reasons. Yet, security continues to pose a concern for robotics. As humanoid robots begin to function "in the open," we must assess the threats they will confront. Through the literature review, researchers found that security assessments were not performed on the robots which cause the robots to be weak against cybersecurity attacks. In this research, we perform different security assessments to identify the vulnerabilities in humanoid robots. Furthermore, different metrics were used to check and perform security assessments on the robot as well as the results of security assessments has been shown. It was shown that humanoid robots are vulnerable as anyone will be able to hack the login credentials of robot’s website as well as there are some open ports in the robot’s network which can be used by the hackers to exploit robot’s working. Based on the results of assessment methods and our findings, we gave the firewall framework which will be helpful to protect the humanoid robot against those security vulnerabilities and attacks.This firewall framework will be able to protect the humanoid robots in aspects of both network and website/webpage exploitation.</em></p></div></td></tr></tbody></table></div>2023-03-31T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTSE/article/view/1470Decision Support System for early Diagnosis of Heart Diseases2023-08-26T06:18:02+05:00Rubaisha Waqar Ahmedrubaisha22@gmail.com<div><table width="683" cellspacing="0" cellpadding="0"><tbody><tr><td align="left" valign="top" height="268"><div><p>Heart disease remains a leading cause of death worldwide, emphasizing the critical need for early diagnosis to enable effective treatment and management. Decision support systems (DSS) have the potential to significantly enhance the accuracy and efficiency of heart disease diagnosis. An advanced DSS designed for early diagnosis can provide healthcare professionals with essential information, expert advice, and treatment recommendations based on comprehensive patient data. By gathering information from various sources including medical history, risk factors, and test results, the DSS analyzes and processes the data using established diagnostic criteria and the latest medical research. The DSS then generates a diagnosis or a list of possible diagnoses, along with appropriate treatment recommendations, empowering healthcare professionals to make well-informed decisions and deliver more effective patient care. Incorporating machine learning algorithms into the DSS can further enhance its accuracy and efficiency. By training the DSS on extensive patient datasets, it can identify patterns and make predictions based on new patient data, ultimately leading to improved decision-making and better patient outcomes. In conclusion, the utilization of a DSS for heart disease diagnosis holds the potential to revolutionize the field by providing healthcare professionals with vital information, expert guidance, and treatment recommendations, thereby enhancing the accuracy, efficiency, and overall outcomes of heart disease diagnosis and management.</p></div></td></tr></tbody></table></div>2023-07-05T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTSE/article/view/1467An Efficient approach for Firearms Detection using Machine Learning2024-01-14T01:58:50+05:00Aamna Rahoofizza_alvi@quest.edu.pkFizza Abbas Alvifizza_alvi@quest.edu.pkUbaidullah Rajputubaidullah@quest.edu.pkImtiaz Ali Halepotohalepoto@quest.edu.pk<div><table width="685" cellspacing="0" cellpadding="0"><tbody><tr><td align="left" valign="top" height="225"><div><p><em>Each year, there is a significant number of people impacted by gun-related violence globally. To address this issue, we have created a computer-based system that can automatically identify firearms, specifically pistol. Recent advancements in machine learning has shown success in the fields of recognition and object detection. Our system utilizes the You Only Look Once (YOLO V3) object detection model, which was trained on a personalized dataset. Our training results indicate that YOLO V3 outperforms both traditional convolutional neural network (CNN) models and YOLO V2. Notably, our approach did not require high computation resources or intensive GPUs to train our model. By incorporating this YOLO V3 model into our security system, we hope to rescue lives and decrease the occurrence of manslaughter or mass killings. Moreover, detecting weapons or other dangerous materials and preventing harm or risk to human life could be accomplished by integrating this system into sophisticated surveillance and security robots.</em></p></div></td></tr></tbody></table></div>2023-06-27T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTSE/article/view/1462Enhancing SCTP Performance through the Selection of Appropriate Retransmission Policies2024-01-14T02:00:20+05:00Imtiaz Ali Halepotohalepoto@quest.edu.pkFouzia Halepotofouziahalepoto@gmail.comFayaz Ahmed Memonengr_fayaz@quest.edu.pkAli Raza Bhangwararbaloch@quest.edu.pkBaqir Ali Zardaribazardari34@quest.edu.pkShahid Iqbalshahid.iqbal@bzu.edu.pk<div><table width="688" cellspacing="0" cellpadding="0"><tbody><tr><td align="left" valign="top" height="285"><div><p><em>The Stream Control Transmission Protocol (SCTP) is a reliable transport protocol that provides message oriented communication services between applications. One of the critical functions of SCTP is to ensure reliable delivery of data by detecting the lost or missing packets due to transmission errors. Once the errors are detected the SCTP uses retransmission policies for immediate retransmission of data along the same or alternate path. However, the performance of SCTP retransmission policies can significantly impact its efficiency and reliability in different network conditions. In this paper, we analyzed three retransmission policies of SCTP that are (1) CWND, (2) SSTHRESHOLD and (3) LOSSRATE, and evaluated their performance in terms of network bandwidth, propagation delay and packet loss. We conducted simulations using the NS-2 network simulator and evaluated the performance of each policy under different network conditions and in each simulation the impact on throughput is analyzed. From the simulation results, the retransmission policy that uses loss rate parameter (LOSSRATE) for the transmission of data outperforms the retransmission policy that uses parameters such as congestion window (CWND) and the slow start threshold (SSTHRESHOLD). The analysis on the obtained results provides valuable insights into the tradeoffs between different SCTP retransmission policies and can help network administrators and application developers optimize SCTP performance in different network environments</em><em>.</em></p></div></td></tr></tbody></table></div>2023-05-28T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTSE/article/view/1460Review of Artificial Intelligence-based COVID-19 Detection and A CNN-based Model to Detect Covid-19 from X-Rays and CT images2024-01-14T01:58:17+05:00Mushtaq Ahmedmalikmushee7@gmail.comGhulam Gilanieghulam.gilanie@iub.edu.pkMuhammad Ahsanahsan_aib@gmail.comHafeez Ullahhafeezullah@iub.edu.pkFaseeh Abid Sheikhfaseeh_sh@hotmail.com<div><table width="688" cellspacing="0" cellpadding="0"><tbody><tr><td align="left" valign="top" height="225"><div><p><em>Various diseases are rising in the world in different regions. Each disease is diagnosed through its signs, & symptoms, and is cured accordingly. Some persons have immunity to fight against such diseases, but most of the persons become the victim of these diseases. The epidemic in China triggered by a novel coronavirus (Covid-19) presents an unprecedented danger to general safety, worldwide. Covid-19 has a more rapid transmission rate. A speedy symptomatic standard check to identify the infectious disease is required to prevent its spread. In an existing situation, testing kits of Covid-19 are available in less quantity and they require significant time to produce outcomes. The purpose of this research is to explore recently reported techniques for automated identification of Covid-19 from medical images and to report an efficient method for the detection of Covid-19 from digital X-Ray and computed tomography images. The proposed model can assist in the identification of Covid-19 at its initial level in lesser time. Publically available and locally developed datasets have been used for research and experiments. The highest classification accuracy achieved through the reported model is 99.40%.</em><em></em></p></div></td></tr></tbody></table></div>2023-06-30T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTSE/article/view/1450Sentiment Analysis of Omicron Tweets by using Machine Learning Models2024-01-14T02:00:55+05:00Unaiza Fazalunaizasumra@gmail.comMuhibullah Khanmuhibullah@nfciet.edu.pkMuhammad Sajid Maqboolsajidmaqbool7638@gmail.comHadia Bibisyedahadiakhalil@gmail.comRubaina Nazeernrubaina@gmail.com<div><table width="687" cellspacing="0" cellpadding="0"><tbody><tr><td align="left" valign="top" height="286"><div><p><em>The COVID-19 epidemic has been affecting a lot of individuals worldwide since 2019. It is emerging as an infectious disease that set off a disaster with far-reaching effects on things like education, economics, and health. During the coronavirus outbreak, new COVID-19 mutations such the Beta, Delta, and Omicron variants emerged, terrifying and alarmed the population. Around 6 million people reportedly died as a result of COVID-19 variations, according to World Meter. The SARS-CoV-2 omicron strain was initially identified in South Africa on November 24, 2021, and it has since spread to more than 57 nations. In this essay, we examine how people feel and act toward the omicron variation. On Omicron, we proposed an approach for determining sentiment analysis for tweets from Twitter. The analysis of Twitter data's sentiment has a lot of potential. In the intended methodology, we extract the best characteristics from the Omicron tweets using NLP techniques in Python, resulting in a dataset that can be used to</em><em> </em><em>train the Models. The produced dataset was employed by four ML Classifiers, including “Naive Bayes (NB), Random Forest (RF), Decision Tree (DT), and Support Vector Machine (SVM)”, to accurately categorise users' emotional behavior into three categories: neutral, negative, and positive. The Class Neutral receives the best score and the Class Negative receives the lowest score based on the</em><em> </em><em>accuracy of the forecast level.</em></p></div></td></tr></tbody></table></div>2023-03-31T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTSE/article/view/1444Agent-based Modeling of COVID-19: A case study of Hyderabad city2024-01-14T02:01:07+05:00Iqbal Khatoon Mangrioiqbalkhatoonm@gmail.comAmirita Dewaniamirita@faculty.muet.edu.pkAreej Fatemah Meghjiareej.fatemah@faculty.muet.edu.pkSania Bhattisania.bhatti@faculty.muet.edu.pkThis research aims to design and develop an agent-based model (ABM) that can simulate the COVID-19 outbreak, presenting the interaction dynamics and impact of various control strategies imposed in the city of Hyderabad, Pakistan. The observations include how ABM controls the disease outbreak depending on different scenarios. The individuals are visually represented in the form of agents that can interact with each other and can make decisions depending on the situation. The observations are made by studying the dynamics of the behavior of individual agents, and their movements from one compartment to the other. The ABM model is developed in NetLogo and simulates various hypothetical scenarios that reflect the real behavior of the virus’s interaction with humans and their environment while adjusting medical, social, and demographic parameters. The study results provide details on how restricting the social interactions between individuals and their movement decreases the rate of the spread of the virus.2023-03-31T00:00:00+05:00Copyright (c) https://vfast.org/journals/index.php/VTSE/article/view/1439Financial Prices Prediction of Stock Market using Supervised Machine Learning Models2024-01-14T02:00:31+05:00Muhammad Rehman2k19mscs111@nfciet.edu.pkMuhammad Fuzailfuzail@nfciet.edu.pkMuhammad Kamran Abidkamranabid@nfciet.edu.pkNaeem Aslamnaeemislam@nfciet.edu.pk<em>The process of predicting stock market movements may initially appear to be non-statistical due to the multitude of factors involved. However, machine learning techniques can be utilized to establish connections between past and present data, enabling the training of machines to make accurate assumptions based on the information. By effectively linking historical data to current data using machine learning, it becomes possible to make precise predictions regarding stock performance. These predictions can lead to substantial profits for individuals and their brokers. Traditionally, stock market predictions have exhibited chaotic patterns rather than randomness, which is why a thorough analysis of a market's historical data allows for predictions to be made. Machine learning offers an efficient means of modeling such processes. By closely aligning market predictions with actual values, the analysis's accuracy can be raised greatly. The field of stock prediction has seen a growing interest in machine learning among researchers due to its effectiveness and precision. Regression-based models are commonly employed when the objective is to forecast continuous values based on independent variables.</em> <em>To predict stock market closing prices for the upcoming ten to fifteen days, we used SVR, RF, KNN, LSTM, GRU, and LSTM with GRU in our study. In regression modeling, the R-squared (R2) value represents the percentage of difference explained by the independent variable(s). A higher (R2) value near to 1 indicates better performance. Our experiments yielded R2 values of 0.832, 0.832, 0.574, 0.838, 0.825, and 0.815 for SVR, RF, KNN, LSTM, GRU, and LSTM with GRU, respectively. Consequently, the most effective model for correctly predicting stock market closing prices is the LSTM learning model, which had the greatest R2 value of 0.838.</em>2023-05-25T00:00:00+05:00Copyright (c)