Journal of Software Engineering http://sjhse.smiu.edu.pk/sjhse/index.php/SJHSE en-US sjhse@smiu.edu.pk (Editor-in-Chief) ameen.chhajro@smiu.edu.pk (Muhammad Ameen Chhajro) Sat, 07 Oct 2023 00:00:00 Pakistan Daylight Time OJS 3.1.1.4 http://blogs.law.harvard.edu/tech/rss 60 Performance Analysis of Classification Algorithms for Software Defects Prediction by Mathematical Modelling & Simulations http://sjhse.smiu.edu.pk/sjhse/index.php/SJHSE/article/view/54 <p>This study explores machine learning (ML) techniques for Software defects prediction (SDP) by using<br>Mathematical Modelling &amp; Simulation. The SDP is also used in the critical systems of aviation, healthcare, manufacturing,<br>and robotics. Many organizations face difficulty in forecasting the accurate defect before software deployment which is<br>actually very crucial for estimating delivery time, maintenance efforts, and ensuring quality expectations. SDP enhances<br>software quality by spotting potential defects in the upkeep phase. The current models of SDP rely on static program metrics<br>for machine learning classifiers, but manual feature engineering may miss vital information impacting defect prediction<br>accuracy. This study initially explores the past SDP results then aims to develop methods by adapting to future anomaly<br>detection techniques. The study explores the various approaches of SDP which include K-Means methodology, Support<br>Vector Machines (SVM) linear, Random Forest (RF) &amp; Multi-layer Perceptron (MLP) algorithms and discussed the current<br>models of SDP. The proposed SDP models are rigorously evaluated by using metrics like false alarm rate, precision, and<br>detection rate. The results show high accuracy for K-Means and MLP (99.67%), K-Means and SVML (99.19%), and KMeans and RF (97.76%) for defect prediction.</p> Shadab Yameen Shaikh, Naseem Afzal Qureshi, Muhammad Zohaib Khan, Muhammad Ali Khan, Aisha Imroz, Muhammad Ahmed Kalwar ##submission.copyrightStatement## http://sjhse.smiu.edu.pk/sjhse/index.php/SJHSE/article/view/54 Wed, 22 Nov 2023 04:57:29 Pakistan Standard Time Cyber SecurityApproaches and Trends in Internet of Things: Systematic Literature Review and Unwrapped Issues http://sjhse.smiu.edu.pk/sjhse/index.php/SJHSE/article/view/55 <p>Currently, the revolution in Internet of Things (IoT) has immensely been witnessed since the last decade. Internet of<br>things is based on diverse devices that consist on sensors, actuators, devices, and other technologies. The goal is to use the<br>internet to connect and share data with other devices and systems. Internet of Things and Cyber Security are the fastest growing<br>buzzwords that have a deeprelation to each other. The revolution in IoT enhances cybercrimes which maliciously affect critical<br>and confidential information.Therefore, there is a dire need for essential cybersecurity approaches and algorithms to secure the<br>exchange of data between IoT devices over the internet. In this paper, we have conducted a systematic literature review of<br>current trends and approaches that are essential for securing IoT. Furthermore, we have founded widely popular cybercrimes<br>that distort the performance of IoT such as; Denial of service attacks, routing attacks, viruses, malicious open-source software,<br>external interruption, malicious code injection, and email fraud. In addition to this, we have presented existing effective<br>solutions and recommendations for effective Cybersecurity in IoT including; Ghost European framework, Block chain<br>technology, layers-based security, societal model, secure authentication, and various machine learning algorithms. Finally, we<br>have also addressed some unwrapped issues for future scholars and this SLR will play an essential role for the researchers who<br>engage in the research of IoT and Cybersecurity</p> Ali Aizaz, Aurangzaib Ali ##submission.copyrightStatement## http://sjhse.smiu.edu.pk/sjhse/index.php/SJHSE/article/view/55 Wed, 22 Nov 2023 05:02:43 Pakistan Standard Time Challenges and Proposed Solution Towards the Legacy Customer Relationship Management System (CRM) In Pakistan Bank http://sjhse.smiu.edu.pk/sjhse/index.php/SJHSE/article/view/56 <p>Customer relationship management (CRM) is a widely adopted concept in various organizations to acquire,<br>retain and retain customers. In the banking sector, CRM plays an important role as it serves as the foundation of banking<br>operations. However, in today's dynamic environment, CRM has evolved beyond sales and marketing, covering a wide<br>range of activities aimed at providing exceptional customer focus and value. This research focuses bank`s legacy of CRM<br>system to integrate it with other banking systems that helps to improve day-to-day operational activities, complying with<br>new policies set by the regulatory authority can be ensured and meet the growing business needs. Which includes<br>Estimated Cost Breakdown, Project Delivered Form, Project Assumption, Project Key Stakeholders Matrix, Project<br>Planning, System (WBS) Work Breakdown Structure, Project Configuration Activities and Project Resources.</p> Haresh Kumar, Fahad Ali Abbasi, Ravi Shankar, Gulfam Ahmed ##submission.copyrightStatement## http://sjhse.smiu.edu.pk/sjhse/index.php/SJHSE/article/view/56 Wed, 22 Nov 2023 05:09:52 Pakistan Standard Time BUSINESS PROCESSING REENGINEERING METHODOLOGY FOR OPEN-SOURCE ERP USED IN PAKISTAN GOVERNMENT ORGANIZATION http://sjhse.smiu.edu.pk/sjhse/index.php/SJHSE/article/view/57 <p>Enterprise Resources Planning (ERP) frameworks have been executed all over the planet in numerous<br>administration associations. Be that as it may, business process re- engineering in an administration climate in Pakistan<br>is itself a mind-boggling task. A few contextual investigations have detailed the achievement and disappointment factors,<br>the right Execution techniques as well as examples gained from business process re-designing in ERP execution. In this<br>paper, we feature the variables that aided in executing the ERP in an OK way and point out the elements that should be<br>kept away from and give BPR technique to carry out ERP in government association. Executing the ERP in government<br>associations has its own flavor. This paper will depict the difficulties, preparing snags and result of cycle reengineering<br>in Government associations. We give BPR procedure in ERP execution so the manual course of government establishment<br>are change into less paper climate with better effect on their capabilities. We would urge any execution to deal with the<br>significant examples gained from this examination. ERP execution in Government Associations can be considered as an<br>Government Resources Planning (GRP) as they observe the guideline government strategies and methods where they<br>need to stay with those cycles regardless of whether they are not exceptionally effective. This report features the positive<br>elements expected in carrying out the ERP in an adequate way and furthermore portrays the entanglements that should be<br>stayed away from. This paper depicts different difficulties and impediments experienced during execution process and<br>our endeavors to beat them by changing administration strategy in like manner for better cycle reengineering.</p> Fahad Ali Abbasi, Haresh Kumar, Ravi Shankar, Gulfam Ahmed ##submission.copyrightStatement## http://sjhse.smiu.edu.pk/sjhse/index.php/SJHSE/article/view/57 Wed, 22 Nov 2023 06:49:01 Pakistan Standard Time Predicting Heart Disease Using Supervised Machine Learning Techniques: A Comparative Analysis http://sjhse.smiu.edu.pk/sjhse/index.php/SJHSE/article/view/58 <p>Early diagnosis of diseases can improve patient outcomes and increase the chances of successful treatment. <br>One of the biggest causes of death worldwide is cardiovascular disease. Deep learning models have recently been <br>shown to be quite accurate at doing this task, and machine learning techniques are increasingly being used to predict <br>cardiac illness. The supervised learning algorithms KNN, Random Forest, Logistic Regression, SVM, and deep <br>learning model artificial neural networks are all compared in this research, for the prediction of heart disease. We used <br>a publicly available dataset of Cleveland Heart Disease Dataset on heart disease to train and test the models as well as <br>compare their performance in terms of various accuracy metrics. Random Forest got highest accuracy with 92.17% <br>and Logistic Regression with 88.4%, KNN with 90.0% and SVM with 90.08%, while deep learning model <br>outperformed with 98.92% accuracy. Our results show that across all models, Random Forest has the highest accuracy, <br>while deep learning models beat other supervised learning techniques in terms of overall accuracy. Additionally, we<br>developed a web based model and integrated the model with web based for further analysis and research purposes. We <br>learn that the best model to use relies on the specifics of the task and the available data and that mixing different <br>models might lead to even better performance gains. Our study clarifies the advantages and disadvantages of different <br>machine learning methods for predicting heart disease, and it may aid in the development of more accurate and reliable <br>prediction systems for use in clinical settings.</p> Madan Lal, Ali Akbar ##submission.copyrightStatement## http://sjhse.smiu.edu.pk/sjhse/index.php/SJHSE/article/view/58 Wed, 22 Nov 2023 06:54:56 Pakistan Standard Time