A5038692993- Software Reliability and Analysis Research
- Software Engineering Research
- Software System Performance and Reliability
- Imbalanced Data Classification Techniques
- Customer churn and segmentation
- Software Engineering Techniques and Practices
- Spam and Phishing Detection
- ECG Monitoring and Analysis
- Sentiment Analysis and Opinion Mining
- Network Security and Intrusion Detection
- Customer Service Quality and Loyalty
- Software Testing and Debugging Techniques
- EEG and Brain-Computer Interfaces
- Advanced Text Analysis Techniques
- Data Mining Algorithms and Applications
- Consumer Retail Behavior Studies
- Non-Invasive Vital Sign Monitoring
- Advanced Malware Detection Techniques
- Topic Modeling
- Artificial Intelligence in Healthcare
- Flexible and Reconfigurable Manufacturing Systems
- Digital Media Forensic Detection
- Biometric Identification and Security
- Robotics and Automated Systems
- Additive Manufacturing and 3D Printing Technologies
University of Ilorin
2019-2025
Gdańsk University of Technology
2022-2025
University Ucinf
2020
Feature selection (FS) is a feasible solution for mitigating high dimensionality problem, and many FS methods have been proposed in the context of software defect prediction (SDP). Moreover, empirical studies on impact effectiveness SDP models often lead to contradictory experimental results inconsistent findings. These contradictions can be attributed relative study limitations such as small datasets, limited search methods, unsuitable respective scope studies. It hence critical conduct an...
Customer churn is a critical issue impacting enterprises and organizations, particularly in the emerging highly competitive telecommunications industry. It important to researchers industry analysts interested projecting customer behavior separate from non-churn consumers. The fundamental incentive firm’s intent desire keep current consumers, along with exorbitant expense of gaining new ones. Many solutions have been developed address prediction (CCP), such as rule-based machine learning...
The strategic significance of software testing in ensuring the success development projects is paramount. Comprehensive testing, conducted early and consistently across lifecycle, vital for mitigating defects, especially given constraints on time, budget, other resources often faced by teams. Software defect prediction (SDP) serves as a proactive approach to identifying components that are most likely be defective. By predicting these high-risk modules, teams can prioritize thorough...
Software Defect Prediction (SDP) provides insights that can help software teams to allocate their limited resources in developing systems. It predicts likely defective modules and helps avoid pitfalls are associated with such modules. However, these may be inaccurate unreliable if parameters of SDP models not taken into consideration. In this study, the effect parameter tuning on k nearest neighbor (k-NN) was investigated. More specifically, impact varying selecting optimal value, influence...
Customer churn is a vital and reoccurring problem facing most business industries, particularly the telecommunications industry. Considering fierce competition among firms high expenses of attracting gaining new subscribers, keeping existing loyal subscribers becomes crucial. Early prediction disgruntled can assist in identifying reasons for deploying applicable innovative policies to boost productivity, maintain market competitiveness, reduce monetary damages. Controlling customer through...
As a result of the rapid advancement mobile and internet technology, plethora new security risks has recently emerged. Many techniques have been developed to address associated with Android malware. The most extensively used method for identifying malware is signature-based detection. drawback this method, however, that it unable detect unknown consequence problem, machine learning (ML) methods detecting classifying applications were developed. goal conventional ML approaches improve...
Failure of software systems as a result testing is very much rampant modern are large and complex. Software which an integral part the development life cycle (SDLC), consumes both human capital resources. As such, defect prediction (SDP) mechanisms deployed to strengthen phase in SDLC by predicting prone modules or components systems. Machine learning models used for developing SDP with great successes achieved. Moreover, some studies have highlighted that combination machine form ensemble...
In recent times, customer churn has become one of the most significant issues in business-oriented sectors with telecommunication being no exception. Maintaining current customers is particularly valuable due to high degree rivalry among companies and costs acquiring new ones. The early prediction churned may help identify causes design industrial tactics address or mitigate problem. Controlling by developing efficient reliable (CCP) solutions essential achieving this objective. Findings...
Electrocardiography (ECG) is one of the most widely used recordings in clinical medicine. ECG deals with recording electrical activity that generated by heart through surface body. The measured using electrodes are attached to body surface. use diagnosis and management cardiovascular disease (CVD) has been existence for over a decade, research this domain recently attracted large attention. Along line, an expert system (ES) decision support (DSS) have developed interpretation diagnosis....
Software testing using software defect prediction aims to detect as many defects possible in before the release. This plays an important role ensuring quality and reliability. can be modeled a classification problem that classifies modules into two classes: defective non-defective; algorithms are used for this process. study investigated impact of feature selection methods on via clustering techniques prediction. Three were selected; Farthest First Clusterer, K-Means Make-Density three...
Due to the exponential rise of mobile technology, a slew new security concerns has surfaced recently. To address hazards connected with malware, many approaches have been developed. Signature-based detection is most widely used approach for detecting Android malware. This disadvantage being unable identify unknown As result this issue, machine learning (ML) identifying and categorising malware apps was created. Conventional ML methods are concerned increasing classification accuracy....
This study presents a novel framework based on heterogeneous ensemble method and hybrid dimensionality reduction technique for spam detection in micro-blogging social networks. A of Information Gain (IG) Principal Component Analysis (PCA) (dimensionality reduction) was implemented the selection important features consisting Naïve Bayes (NB), K Nearest Neighbor (KNN), Logistic Regression (LR) Repeated Incremental Pruning to Produce Error Reduction (RIPPER) classifiers Average Probabilities...
In the past few years, there has been an explosion in amount of text data from a variety sources. This volume is valuable source information and knowledge which needs to be effectively summarized useful. this paper, automatic summarization with K-means clustering techniques presented by employing two different distance measurement methods (Euclidean Manhattan). The dataset extracted African prose was preprocessed using stopwords removal tokenization. document converted into vector...
The process of software defect prediction (SDP) involves predicting which system modules or components pose the highest risk being defective. projections and discernments derived from SDP can then assist development team in effectively allocating its finite resources toward potentially susceptible defective modules. Because this, models need to be improved refined continuously. Hence, this research proposes deployment a cascade generalization (CG) function enhance predictive performances...