Papers by AHMED OLODUOWO AMEEN
Ilorin Journal of Computer Science and Information Technology, Jun 30, 2020
Software Defect Prediction (SDP) is a significant and emerging concept in the field of software d... more Software Defect Prediction (SDP) is a significant and emerging concept in the field of software development processes. Without an accurate model for predicting flaws in software, a product may be released in an unsatisfactory condition which might lead to expensive post-developmental activities. Therefore, the prediction of defects at the early stage of the software development process has become an issue of concern in the domain of software engineering. Several feature selection (FS) methods on defect prediction models have been proposed, some of which rely on the behavioural analysis of the software metrics. Support Vector Machine (SVM), Naïve Bayes (NB), Bagging, Neural network (NN), and Decision Tree (DT) classifiers are known to perform well in predicting defects in software systems. This study deployed metaheuristics-based Correlation Feature Selection (CFS) methods with classification algorithms. The proposed FS methods used Firefly Algorithm (FA) and Wolf Search Algorithm (WSA) as metaheuristic search methods for evaluation and selection of relevant features. The proposed FS methods with SVM and Random Forest (RF) classifiers were used on selected software defect datasets from NASA repository. Based on the experimental results, this study discovered that metaheuristic-based FS methods have positive effects on the prediction performances of SVM and RF. Besides, SVM with WSA-based CFS method had the best prediction performance amongst the evaluated methods. Thus, it can be concluded that using metaheuristic methods for optimization of FS methods can produce better results in the prediction of software defects.
Advances on Smart and Soft Computing, 2021
Computational Science and Its Applications – ICCSA 2021, 2021
Annals of African Medicine, 2010
Background: The computer and information technology (IT) revolution have transformed modern healt... more Background: The computer and information technology (IT) revolution have transformed modern health care systems in the areas of communication, storage, retrieval of medical information and teaching, but little is known about IT skill and use in most developing nations. Objectives: The aim of this study has been to evaluate the reported preparedness and disposition by medical students in a Nigerian university toward the use of IT for medical education. Methods: A self-administered structured questionnaire containing 24 items was used to obtain information from medical students in the University of Ilorin, Nigeria on their level of computer usage, knowledge of computer software and hardware, availability and access to computer, possession of personal computer and e-mail address, preferred method of medical education and the use of computer as a supplement to medical education. Results: Out of 479 medical students, 179 (37.4%) had basic computer skills, 209 (43.6%) had intermediate skills and 58(12.1%) had advanced computer skills. Three hundred and thirty (68.9%) have access to computer and 451(94.2%) have e-mail addresses. For medical teaching, majority (83.09%), preferred live lecture, 56.78% lecture videos, 35.1% lecture handout on web site and 410 (85.6%) wants computer as a supplement to live lectures. Less than half (39.5%) wants laptop acquisition to be mandatory. Students with advanced computer skills were well prepared and disposed to IT than those with basic computer skill. Conclusion: The findings revealed that the medical students with advanced computer skills were well prepared and disposed to IT based medical education. Therefore, high level of computer skill is required for them to be prepared and favorably disposed to IT based medical education.
The absence of adequate automated teller machines (ATMs) and banks in and around some university ... more The absence of adequate automated teller machines (ATMs) and banks in and around some university campuses has left students high and dry on many occasions. After banking hours, in a situation where ATMs are unable to dispense cash, students are left unable to purchase products they need at that time. The research methodology develops a new prototype for a practical e-wallet whose goal is to allow the instant money transfers between two users. Although the e-Wallet concept has many implementations, we improve the present level of knowledge by joining the online technology and the classic concepts about money restricted to the university students portal/server due to lack of bank network most times on campus. As opposed to the storing of various plastic card details on the mobile device, a single virtual card is suggested. Monetary value can be transferred to the virtual card. The proposed e-wallet system is very essential as it ensure access to funds kept in the virtual account at al...
2014 IEEE International Symposium on Software Reliability Engineering Workshops, 2014
Data Integration is classified as an Open and Lingering (OL) problem which must be sufficiently a... more Data Integration is classified as an Open and Lingering (OL) problem which must be sufficiently addressed due to its myriad benefits and significances, especially in the health sector where collaborative medicine is vital. Data integration problem evolved from the disparity in semantics and syntactic representations of medical data. It is a challenge, which must be solved to realize effective collaboration in the health sector and paramount for efficient health care service provisioning. In recent times, different approaches and software artifacts such as services, components and tools have been proposed for resolving data integration problem. However, existing approaches are faced with data inaccuracy, data unreliability, increased query response time, network bottleneck and poor system performance. The focus of this paper is to present our technique and the CAMDIT toolkit which efficiently achieves data integration, data accuracy, reliability and reduced query-response time and impacts of network bottleneck on systems performances.
Nigerian Journal of Technological Development, 2017
Data and information in storage, in transit or during processing are found in various computers a... more Data and information in storage, in transit or during processing are found in various computers and computing devices with wide range of hardware specifications. Cryptography is the knowledge of using codes to encrypt and decrypt data. It enables one to store sensitive information or transmit it across computer in a more secured ways so that it cannot be read by anyone except the intended receiver. Cryptography also allows secure storage of sensitive data on any computer. Cryptography as an approach to computer security comes at a cost in terms of resource utilization such as time, memory and CPU usability time which in some cases may not be in abundance to achieve the set out objective of protecting data. This work looked into the memory construction rate, different key size, CPU utilization time period and encryption speed of the four algorithms to determine the amount of computer resource that is expended and how long it takes each algorithm to complete its task. Results shows that key length of the cryptographic algorithm is proportional to the resource utilization in most cases as found out in the key length of Blowfish, AES, 3DES and DES algorithms respectively. Further research can be carried out in order to determine the power utilization of each of these algorithms.
Journal of the Nigerian Association of Mathematical Physics, 2009
Fuzzy logic methods give effective system appraisal solution to some classification problems as a... more Fuzzy logic methods give effective system appraisal solution to some classification problems as against some techniques on probability prediction of solution. This paper used fuzzy logic approach as a comparative method to visual encoding technique. Journal of the Nigerian Association of Mathematical Physics , Volume 15 (November, 2009), pp 355 - 362
While certain computationally expensive novel methods can construct predictive models with high a... more While certain computationally expensive novel methods can construct predictive models with high accuracy from highdimensional data, it is still of interest in many applications to reduce the dimension of the original data prior to any modeling of the data. Hence, this research presents a précis of ensemble methods (Stacking, Voting and Multischeme) and Multilayer perceptron, K Nearest Neighbour and NBTree with a framework on the performance measurement of base classifiers and ensemble methods with and without feature selection techniques (Principal Component Analysis, Information Gain Attribute Selection and Gain Ratio Attribute Selection). The enhancement is based on performing feature selection on dataset prior to classification. The notion of this study is to evaluate the performances of the ensemble methods on original and reduced datasets. A 10-fold cross validation technique is used for the performance evaluation of the ensemble methods and base classifiers (Root to Local) R2L...
Compulsory SIM registration in Nigeria started in 2008 in response to several mobile crimes being... more Compulsory SIM registration in Nigeria started in 2008 in response to several mobile crimes being perpetrated by fraudsters and also to improve service delivery. The decentralized systems currently in use in the country lack flexibility to register heterogeneous SIM cards and encourage multiple registrations. This work, the “design and development of a centralized, unified subscribers‟ SIM registration platform” therefore seeks to address these loopholes. The work employs top-down design approach using HTML, PHP, JAVASCRIPT, CSS, and MySQL as development tools. The new system surpasses the existing one as it is able to register all SIM cards of the four (4) major telecommunication operators in Nigeria and verify if a SIM had already been registered thus bringing stability, flexibility, and single platform for all. It is recommended that SIM card availability/sales on the road side should be stopped or such SIM cards be denied access to network until they are properly registered. Key...
Buying and selling has gone beyond what is carried out only in a physical environment, as the ava... more Buying and selling has gone beyond what is carried out only in a physical environment, as the availability of internet has made market and marketing a thing done online. Most online marketplaces (Websites) are individually managed in a way that it monopolises and restricts users to only products and services placed on them, thereby making users to think that only goods placed on such media are those available in the market. The paper proposed, designed and developed a web-based marketplace system using UML (Unified Model Language) and PHP as the Front-end (Programming Language) and MYSQL as the back-end (Database) running under WAMP (Window, Apache, PHP and MYSQL) Platform. The study used Case diagram and Class diagram, offered by UML for designing the system. The system provides a secured marketplace for products and services with the resources available online which is secure and provide customers marketplace with unlimited and unrestricted search. With the adoption of limited sea...
Advances in Science, Technology & Innovation
Advances in Science, Technology & Innovation
MALAYSIAN JOURNAL OF COMPUTING
Students’ Academic Performance (SAP) is an important metric in determining the status of students... more Students’ Academic Performance (SAP) is an important metric in determining the status of students in any academic institution. It allows the instructors and other education managers to get an accurate evaluation of the students in different courses in a particular semester and also serve as an indicator to the students to review their strategies for better performance in the subsequent semesters. Predicting SAP is therefore important to help learners in obtaining the best from their studies. A number of researches in Educational Psychology (EP), Learning Analytics (LA) and Educational Data Mining (EDM) has been carried out to study and predict SAP, most especially in determining failures or dropouts with the goal of preventing the occurrence of the negative final outcome. This paper presents a comprehensive review of related studies that deal with SAP and dropout predictions. To group the studies, this review proposes taxonomy of the methods and features used in the literature for S...
Data mining is used to discover knowledge from information system. Clustering is one of the techn... more Data mining is used to discover knowledge from information system. Clustering is one of the techniques used for data mining. It can be defined as a technique of grouping un-labelled data objects such that objects belonging to one cluster are not similar to the objects belonging to another cluster. Data mining tools refer to the software that are used for the process of efficiently analysing, summarizing and extracting useful information from different perspectives of data. This paper presents a comparative analysis of four open-source data mining software tools (WEKA, KNIME, Tanagra and Orange) in the context of data clustering, specifically K-Means and Hierarchical clustering methods. The results of the performance analysis based on the execution time and quality of clusters showed that WEKA tool outperforms the other tools with the lowest SSE of 199.7308 with an average execution time of 1.535 seconds. Knime has SSE of 222.217 but with an average execution time of 7.13 seconds, an...
Data and information in storage, in transit or during processing are found in various computers a... more Data and information in storage, in transit or during processing are found in various computers and computing devices with wide range of hardware specifications. Cryptography is the knowledge of using codes to encrypt and decrypt data. It enables one to store sensitive information or transmit it across computer in a more secured ways so that it cannot be read by anyone except the intended receiver. Cryptography also allows secure storage of sensitive data on any computer. Cryptography as an approach to computer security comes at a cost in terms of resource utilization such as time, memory and CPU usability time which in some cases may not be in abundance to achieve the set out objective of protecting data. This work looked into the memory construction rate, different key size, CPU utilization time period and encryption speed of the four algorithms to determine the amount of computer resource that is expended and how long it takes each algorithm to complete its task. Results shows th...
Data Integration is classified as an Open and Lingering (OL) problem which must be sufficiently a... more Data Integration is classified as an Open and Lingering (OL) problem which must be sufficiently addressed due to its myriad benefits and significances, especially in the health sector where collaborative medicine is vital. Data integration problem evolved from the disparity in semantics and syntactic representations of medical data. It is a challenge, which must be solved to realize effective collaboration in the health sector and paramount for efficient health care service provisioning. In recent times, different approaches and software artifacts such as services, components and tools have been proposed for resolving data integration problem. However, existing approaches are faced with data inaccuracy, data unreliability, increased query response time, network bottleneck and poor system performance. The focus of this paper is to present our technique and the CAMDIT toolkit which efficiently achieves data integration, data accuracy, reliability and reduced query-response time and impacts of network bottleneck on systems performances.
Uploads
Papers by AHMED OLODUOWO AMEEN