Journal of Software Engineering

Performance Analysis of Classification Algorithms for Software Defects Prediction by Mathematical Modelling & Simulations

Shadab Yameen Shaikh — 2023-11-22

This study explores machine learning (ML) techniques for Software defects prediction (SDP) by using
Mathematical Modelling & Simulation. The SDP is also used in the critical systems of aviation, healthcare, manufacturing,
and robotics. Many organizations face difficulty in forecasting the accurate defect before software deployment which is
actually very crucial for estimating delivery time, maintenance efforts, and ensuring quality expectations. SDP enhances
software quality by spotting potential defects in the upkeep phase. The current models of SDP rely on static program metrics
for machine learning classifiers, but manual feature engineering may miss vital information impacting defect prediction
accuracy. This study initially explores the past SDP results then aims to develop methods by adapting to future anomaly
detection techniques. The study explores the various approaches of SDP which include K-Means methodology, Support
Vector Machines (SVM) linear, Random Forest (RF) & Multi-layer Perceptron (MLP) algorithms and discussed the current
models of SDP. The proposed SDP models are rigorously evaluated by using metrics like false alarm rate, precision, and
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.

Cyber SecurityApproaches and Trends in Internet of Things: Systematic Literature Review and Unwrapped Issues

Ali Aizaz — 2023-11-22

Currently, the revolution in Internet of Things (IoT) has immensely been witnessed since the last decade. Internet of
things is based on diverse devices that consist on sensors, actuators, devices, and other technologies. The goal is to use the
internet to connect and share data with other devices and systems. Internet of Things and Cyber Security are the fastest growing
buzzwords that have a deeprelation to each other. The revolution in IoT enhances cybercrimes which maliciously affect critical
and confidential information.Therefore, there is a dire need for essential cybersecurity approaches and algorithms to secure the
exchange of data between IoT devices over the internet. In this paper, we have conducted a systematic literature review of
current trends and approaches that are essential for securing IoT. Furthermore, we have founded widely popular cybercrimes
that distort the performance of IoT such as; Denial of service attacks, routing attacks, viruses, malicious open-source software,
external interruption, malicious code injection, and email fraud. In addition to this, we have presented existing effective
solutions and recommendations for effective Cybersecurity in IoT including; Ghost European framework, Block chain
technology, layers-based security, societal model, secure authentication, and various machine learning algorithms. Finally, we
have also addressed some unwrapped issues for future scholars and this SLR will play an essential role for the researchers who
engage in the research of IoT and Cybersecurity

Challenges and Proposed Solution Towards the Legacy Customer Relationship Management System (CRM) In Pakistan Bank

Haresh Kumar — 2023-11-22

Customer relationship management (CRM) is a widely adopted concept in various organizations to acquire,
retain and retain customers. In the banking sector, CRM plays an important role as it serves as the foundation of banking
operations. However, in today's dynamic environment, CRM has evolved beyond sales and marketing, covering a wide
range of activities aimed at providing exceptional customer focus and value. This research focuses bank`s legacy of CRM
system to integrate it with other banking systems that helps to improve day-to-day operational activities, complying with
new policies set by the regulatory authority can be ensured and meet the growing business needs. Which includes
Estimated Cost Breakdown, Project Delivered Form, Project Assumption, Project Key Stakeholders Matrix, Project
Planning, System (WBS) Work Breakdown Structure, Project Configuration Activities and Project Resources.

BUSINESS PROCESSING REENGINEERING METHODOLOGY FOR OPEN-SOURCE ERP USED IN PAKISTAN GOVERNMENT ORGANIZATION

Fahad Ali Abbasi — 2023-11-22

Enterprise Resources Planning (ERP) frameworks have been executed all over the planet in numerous
administration associations. Be that as it may, business process re- engineering in an administration climate in Pakistan
is itself a mind-boggling task. A few contextual investigations have detailed the achievement and disappointment factors,
the right Execution techniques as well as examples gained from business process re-designing in ERP execution. In this
paper, we feature the variables that aided in executing the ERP in an OK way and point out the elements that should be
kept away from and give BPR technique to carry out ERP in government association. Executing the ERP in government
associations has its own flavor. This paper will depict the difficulties, preparing snags and result of cycle reengineering
in Government associations. We give BPR procedure in ERP execution so the manual course of government establishment
are change into less paper climate with better effect on their capabilities. We would urge any execution to deal with the
significant examples gained from this examination. ERP execution in Government Associations can be considered as an
Government Resources Planning (GRP) as they observe the guideline government strategies and methods where they
need to stay with those cycles regardless of whether they are not exceptionally effective. This report features the positive
elements expected in carrying out the ERP in an adequate way and furthermore portrays the entanglements that should be
stayed away from. This paper depicts different difficulties and impediments experienced during execution process and
our endeavors to beat them by changing administration strategy in like manner for better cycle reengineering.

Predicting Heart Disease Using Supervised Machine Learning Techniques: A Comparative Analysis

Madan Lal — 2023-11-22

Early diagnosis of diseases can improve patient outcomes and increase the chances of successful treatment.
One of the biggest causes of death worldwide is cardiovascular disease. Deep learning models have recently been
shown to be quite accurate at doing this task, and machine learning techniques are increasingly being used to predict
cardiac illness. The supervised learning algorithms KNN, Random Forest, Logistic Regression, SVM, and deep
learning model artificial neural networks are all compared in this research, for the prediction of heart disease. We used
a publicly available dataset of Cleveland Heart Disease Dataset on heart disease to train and test the models as well as
compare their performance in terms of various accuracy metrics. Random Forest got highest accuracy with 92.17%
and Logistic Regression with 88.4%, KNN with 90.0% and SVM with 90.08%, while deep learning model
outperformed with 98.92% accuracy. Our results show that across all models, Random Forest has the highest accuracy,
while deep learning models beat other supervised learning techniques in terms of overall accuracy. Additionally, we
developed a web based model and integrated the model with web based for further analysis and research purposes. We
learn that the best model to use relies on the specifics of the task and the available data and that mixing different
models might lead to even better performance gains. Our study clarifies the advantages and disadvantages of different
machine learning methods for predicting heart disease, and it may aid in the development of more accurate and reliable
prediction systems for use in clinical settings.