Browsing by Author "Akintola, Abimbola G."
Now showing 1 - 3 of 3
Results Per Page
Sort Options
Item Comparative Analysis of Selected Heterogeneous Classifiers for Software Defects Prediction Using Filter-Based Feature Selection Methods(Faculty of Engineering, Federal University Oye-Ekiti, Ekiti State, Nigeria., 2018-03) Akintola, Abimbola G.; Balogun, Abdullateef O.; Lafenwa-Balogun, Fatimah; Mojeed, Hameed A.Classification techniques is a popular approach to predict software defects and it involves categorizing modules, which is represented by a set of metrics or code attributes into fault prone (FP) and non-fault prone (NFP) by means of a classification model. Nevertheless, there is existence of low quality, unreliable, redundant and noisy data which negatively affect the process of observing knowledge and useful pattern. Therefore, researchers need to retrieve relevant data from huge records using feature selection methods. Feature selection is the process of identifying the most relevant attributes and removing the redundant and irrelevant attributes. In this study, the researchers investigated the effect of filter feature selection on classification techniques in software defects prediction. Ten publicly available datasets of NASA and Metric Data Program software repository were used. The topmost discriminatory attributes of the dataset were evaluated using Principal Component Analysis (PCA), CFS and FilterSubsetEval. The datasets were classified by the selected classifiers which were carefully selected based on heterogeneity. Naïve Bayes was selected from Bayes category Classifier, KNN was selected from Instance Based Learner category, J48 Decision Tree from Trees Function classifier and Multilayer perceptron was selected from the neural network classifiers. The experimental results revealed that the application of feature selection to datasets before classification in software defects prediction is better and should be encouraged and Multilayer perceptron with FilterSubsetEval had the best accuracy. It can be concluded that feature selection methods are capable of improving the performance of learning algorithms in software defects prediction.Item Student Web Self-Service Portal for a Tertiary Institution(Covenant University, 2016-12) Akintola, Abimbola G.; Adewole, Kayode S.; Mabayoje, Modinat A.; Oke, John oThe optimum condition for students to study is in an environment where they can access virtually all they need to know about courses, lecturers, locate places (for fresh and prospective students), validate staff identity, access past examination questions easily, identify vacant student hostels within and outside the school premises. Some of the reasons for students’ failure can be attributed to finding accommodation within or outside the school premises. Also, fresh students find it difficult to locate specific places in the university environment and some students find it very difficult to interact with staff. This paper presents a student self-service portal to address some of these challenges. Unified Modeling Language (UML) was used to model the system. The model was implemented using Microsoft C#, Microsoft ASP.net, Microsoft SQL Server, and Google Map. The proposed system was tested and the result obtained during the execution shows that the system is capable of addressing some of the challenges confronted by students.Item A Survey of Empirical Studies on Performance Enhancement Features for IR-Based Bug Localization Process(Afr. J. Comp. & ICT, 2018) Salihu, Shakirat A.; Abikiye, Oluwakemi C.; Bajeh, Amos O; Akintola, Abimbola G.Software is inevitable to have bugs. Localization of bugs has attracted many researchers due to its importance in software maintenance. Automation of Bug localization using Information Retrieval (IR) -Based approach has been proposed to attract more researchers due to its relatively low computational cost. Despite this automation, localization of bugs still takes the developers many hours or days to locate bugs. This paper tends to do a survey of some features that can be added to IR-Based bug localization process to enhance its performance and give a better result in terms of accuracy. The result from the six tools considered for this survey shows that there is an improvement in those with enhancement features compare with the baseline that has no enhancement features. The top N, MAP and MRR values of these tools outperform the technique without any enhancement.