Department of Computer Sciences

Permanent URI for this collection

https://repository.run.edu.ng/handle/123456789/72

Browse

Now showing 1 - 19 of 19

Analysis of Employees' Engagement and Retention of Selected Banking Industry in Lagos State, Nigeria.
(Uniosun Journal of Employment Relations and Management., 2019-01) Olaniyan, Oluwabunmi Omobolanle
Retention of employees had become a major issue confronting the Nigerian banking industry; due to this course effective employee engagement was discovered to aid the retention of their valued employees. The banking sector in Nigeria faced the problems of wrong employee engagement and posed employee retention challenges. This paper examined the analysis of employees' engagement and retention of selected banking industry in Lagos State, Nigeria. The descriptive survey research design was adopted and the target population comprised 4,084 staff of the head offices of the selected banks in Lagos State. Sample size of 678 was used. A structured questionnaire was adapted, validated and used to collect data for the study. Simple random sampling technique was used to select the sample size and the response rate was 92.5%. Data were analyzed using descriptive and inferential statistical technique. Findings revealed that Employee engagement had positive and significant effect on employee retention of selected banks in Lagos State (â = 2 0.287; F = 109.815; R = 0.134; p<0.05). It was concluded that Employee (1,712) engagement had positive and significant effect on employee retention in selected deposit money banks in Lagos State, Nigeria. Therefore, it was recommended that there should be proper employee engagement in an organization.
Analytic Hierarchy Process Model for Evaluation of Mobile Health Applications
(2019-07) Olaniyan, Oluwabunmi Omobolanle
Assessing the usability of mHealth apps is still a herculean task among software usability researchers/engineers as evaluating the usability attributes of these apps require substantial efforts from a wide range of knowledge domains and prospective users. Most usability models possess numerous attributes that can be adequately used to assess these apps but current usability techniques cannot effectively rank numerous qualitative and quantitative usability attributes simultaneously. Hence, the main objective of this work is to rank and prioritize the usability attributes embedded in a model for mobile app evaluation purposes. The model was designed hierarchically based on People at the Center of Mobile Application Development (PACMAD) MODEL and the Integrated Measurement Model (IMM). Attributes considered include efficiency, effectiveness, satisfaction, learnability, operability, user interface aesthetics and universality. They were ranked using their respective priority weights based on the Analytic Hierarchy Process (AHP). Pairwise comparison matrix was formulated based on decision makers’ judgements that were aggregated and normalized. Consistency of decision makers’ judgements was obtained using Saaty’s Eigen value and Eigen vector approach as a result of their simplicity and accuracy. Results of evaluation showed that efficiency and effectiveness had the highest priorities with 30% and 27% while satisfaction and user interface aesthetics had the lowest ranks with 6% and 5% respectively. Overall AHP group consensus results was 68%. In conclusion, it was established that the mathematical technique used is a powerful yet simple tool that has the ability to evaluate both the quantitative and qualitative usability attributes simultaneously. The work presented the assessment of a unified framework that combined the judgements from multiple levels of mHealth apps usability evaluation process. It is recommended that further studies extend the usability model used by increasing the number of usability attributes and for the evaluation to be done using other Multi-criteria Decision Making (MCDM) approaches and for the results obtained to be compared so as to be able to determine the differences or relationships between other MCDM techniques on usability models.
Comparative Study and Detection of COVID-19 and Related Viral Pneumonia using a Fine-tuned Deep Transfer Learning
(2021) Olaniyan, Oluwabunmi Omobolanle
The Design of a Hybrid Model-Based Journal Recommendation System
(Advances in Science, Technology and Engineering Systems Journal, 2020-12) Olaniyan, Oluwabunmi Omobolanle
Development of a Clinical Predictive Model for Stratification of Cancerous Diseases: A Case Study of Chronic Myeloid Leukemia
(International Journal of Advanced Science and Technology, 2020) Olaniyan, Oluwabunmi Omobolanle
E-payment Challenges: The Genesis and Remedies to the Problem
(Journal of Scientific Research & Reports, 2022-05-16) Olaniyan, Oluwabunmi Omobolanle
Switching between internet solutions in an organization can be challenging, mainly if it affects the core operations and running of the organizations, such as e-payment. It becomes problematic when the role of e-government is not properly considered in an organization. In this study, the school fees e-payment project of a Nigerian University and the losses incurred due to the lack of incorporation of ICT- government into the e-payment process was evaluated. This study recommends good outsourcing, corporate and ICT governance practices such as the incorporation of frameworks like the Control Objectives for Information and Related Technology (COBIT) and IT Infrastructure Library (ITIL), can be integrated to minimize such problems. This would help any University to avert likely losses.
Economic Impact of Software Product Line Engineering Method - A Survey
(Journal of Advanced Research in Computer Science, 2020) Olaniyan, Oluwabunmi Omobolanle
Economic Responsibilities and Firm Reputation as Indicators of Corporate Social Responsibilities and Organizational Performance: A Study of Nigerian Breweries Plc.
(UNIOSUN Journal of Employment Relations and Management, 2019) Olaniyan, Oluwabunmi Omobolanle
Effect of Strategic Entrepreneurial Orientation on Sales Growth of SMEs in Lagos State.
(2018) Olaniyan, Oluwabunmi Omobolanle
The global competition faced by SMEs has brought about a growing pressure from their customers. Economic development and growth all over the world rest upon SME contribution especially in developing economy as Nigeria where this sector is seen as the ‘engine for economic development. The achievement of economic development is made possible and successful if entrepreneurial orientation is incorporated by SMEs in Nigeria where competition is high. Small businesses are more exposed to the threat compared to large businesses, due to their incapability to expand, insufficient capital to compete with the decline or loss of market revenues, and higher operational costs per unit of revenue. But they can profit from the advantages of being small businesses, as they are more flexible and they easily regulate to the quality of changes due to their simple structure, owner dominance decision making and informal planning and controlling activities. The main objective of the paper is to examine the effect of strategic entrepreneurial orientation on sales growth of SMEs in Lagos State, Nigeria. This study adopted the descriptive survey research design. The effect of strategic entrepreneurial orientation and sales growth shows a positive and significant relationship with p < 0.05, R = 0.492, R2 = 0.242, B = 0.395and F = 130.155. A positive and significant effect was established between entrepreneurial orientation and sales growth with R= 0.744, R2 = 0.553, p < 0.05, B = 0.717 and F value = 504.339. The paper concluded that strategic entrepreneurial orientation has a statistically significant effect on Sales growth of SMEs development in Lagos State.
An Enhanced Usability Model for Mobile Health Application
(International Journal of Computer Science and Information Security, 2019) Olaniyan, Oluwabunmi Omobolanle
Evaluation of A Cross Platform Persuasive M-Health App for Body Fitness Using Analytic Hierarchy Process
(2019-07) Olaniyan, Oluwabunmi Omobolanle
Persuasive mobile health apps are types of information systems that are aimed at motivating or encouraging people towards a pragmatic approach at an improved quality of life. The app store market is gradually becoming saturated with numerous types of mobile apps and designing apps to be persuasive in nature is a novel way of attracting and encouraging more users to access and use such apps. Hence the main aim of this work is to design a cross platform persuasive mobile health application called StayFit. The app was designed from the extended Persuasive System Design (PSD) model and evaluated using the same model qualitatively. The app was also developed using Cordova platform, Windows Operating System, Android studio, MySQL database, Apache Server, Node.js, PHP, Bootstrap, Phonegap, Apache ANT and jQuery. The work provides an approach for developing cross-platform applications in order to target a wider range of platforms and the mHealth persuasive app developed is able to assist users maintain a healthier lifestyle. The usability of the developed app was compared with existing apps using the Analytic Hierarchy Process (AHP) model. Comparison was done using a group of 5 users with a usability model and evaluated with the AHP-OS. Results of analysis showed that StayFit ranked the highest with 48.4%, MyFitnesPal with 28.7% and Lose It with 23.0% while consolidated group Consistency Ratio was 4.9%. It is recommended for further studies that the app be compared with more apps in its category and evaluated using other Multi Criteria Decision Making (MCDM) techniques. The usability of the app can also be determined using appropriate usability models and techniques.
A Framework for big Data Analytics in Value Creation
(2018) Olaniyan, Oluwabunmi Omobolanle
A Logical Approach for Empirical Risk Minimization in Machine Learning for Data Stratification
(Research Journal of Mathematics and Computer Science, 2017) Olaniyan, Oluwabunmi Omobolanle
The data-driven methods capable of understanding, mimicking and aiding the information processing tasks of Machine Learning (ML) have been applied in an increasing range over the past years in diverse areas at a very high rate, and had achieved great success in predicting and stratifying given data instances of a problem domain. There has been generalization on the performance of the classifier to be the optimal based on the existing performance benchmarks such as accuracy, speed, time to learn, number of features, comprehensibility, robustness, scalability and interpretability. However, these benchmarks alone do not guarantee the successful adoption of an algorithm for prediction and stratification since there may be an incurring risk in its adoption. Therefore, this paper aims at developing a logical approach for using Empirical Risk Minimization (ERM) technique to determine the machine learning classifier with the minimum risk function for data stratification. The generalization on the performance of optimal algorithm was tested on BayesNet, Multilayered perceptron, Projective Adaptive Resonance Theory (PART) and Logistic Model Trees algorithms based on existing performance benchmarks such as correctly classified instances, time to build, kappa statistics, sensitivity and specificity to determine the algorithms with great performances. The study showed that PART and Logistic Model Trees algorithms perform well than others. Hence, a logical approach to apply Empirical Risk Minimization technique on PART and Logistic Model Trees algorithms is shown to give a detailed procedure of determining their empirical risk function to aid the decision of choosing an algorithm to be the best fit classifier for data stratification. This therefore serves as a benchmark for selecting an optimal algorithm for stratification and prediction alongside other benchmarks.
Minimal Loss Function Determination on Four Machine Learning Algorithms using Chronic Myeloid Leukemia Cancer Dataset.
(2019-07) Olaniyan, Oluwabunmi Omobolanle
In Artificial intelligence researches, machine learning (ML) algorithms are used to extract meaningful information from the datasets to aid prediction and in some cases diagnosis. The determination of loss function on the chosen machine learning algorithm(s) is discovered to be deficient in grouping or stratification of datasets. This paper used dataset of 1640 Chronic Myeloid Leukemia patients from Obafemi Awolowo University Teaching Hospitals Complex, IleIfe, Osun Sate, Nigeria. An experimental analysis was performed in Waikato Environment for Knowledge Analysis 3.8.0 using basophil count and spleen size values on four ML algorithms (BayesNet, Multilayered perceptron, Projective Adaptive Resonance Theory (PART) and Logistic Regression) to determine low and high risk patients. Two validation techniques (Holdout and 10-fold cross-validation) were used to evaluate the performance of the algorithms on correctly classified instances, time to learn, kappa statistics, sensitivity and specificity. Two algorithms (Logistic regression and PART) showed leading performances in stratifying the dataset; the loss function was minimized by finding the difference between the true output 𝓇 and the predicted output 𝓇̂. The results of the loss function of Logistic regression algorithm for low and high risk in holdout and 10-fold cross-validation showed 0.22%, 1.40% and -0.22%, -0.02% respectively. Similarly, PART algorithm yielded -1.58%, 1.40% and -0.22%, -0.26%. From the findings, Logistic regression algorithm had the loss function with minimum value in holdout technique. Therefore, the determination of minimal loss function is of high importance as it would enhance the choice of the algorithm to be used in grouping of dataset.
Modeling a Deep Transfer Learning Framework for the Classification of COVID-19 Radiology Dataset
(PeerJ Computer Science, 2021-08) Olaniyan, Oluwabunmi Omobolanle
An Overview of Artificial Life
(INTERNATIONAL JOURNAL OF ADVANCED STUDIES IN COMPUTER SCIENCE AND ENGINEERING, 2015-01-31) Olaniyan, Oluwabunmi Omobolanle
For some time now, people have speculated on what makes the living different from the non-living; and what the possibility of creating synthetic system from natural system is. From the mid-1980s, artificial life (ALife) has studied living systems using a synthetic approach. This approach builds life in order to understand it better in any of the three branches of ALife i.e. software, hardware, or wetware. Being an area that is related with other disciplines, ALife seems to be losing its boundaries and merging with other fields. This paper gives an overview of the historical background of ALife, its application areas, the common properties, and the classification of research in ALife
Security and Ethical Issues to Cloud Database
(Journal of Computer Science and its Applications, 2017-12) Olaniyan, Oluwabunmi Omobolanle
Privacy and Security of data in cloud database is a vital issue as it enables the storage, management and sharing of complex data in a secure platform. Cloud database, a technology that clings onto Cloud Computing paradigm, has privacy and security challenges such as lack of awareness and hegemony of place of data stored, transaction log of data, malicious act, amongst others. Also, ethical issue in the cloud surrounds trust issues from tenants, as the tenants find it difficult outsourcing critical information to a cloud service provider without the interference of a third party. This and many more issues were considered in this paper. This paper, therefore, discussed security, privacy and ethical concerns associated with cloud database by reviewing variety of literatures that discussed about these issues. Furthermore, the paper proposed a conceptual framework for mitigating the security and privacy issues inherent in the cloud database as a way of improving the services of the cloud service providers when deployed.
Stratification of Chronic Myeloid Leukemia Cancer Dataset into Risk Groups using Four Machine Learning Algorithms with Minimal Loss Function
(African Journal of Management Information System, 2019) Olaniyan, Oluwabunmi Omobolanle
A Usability Framework for Electronic Health Records in Nigerian Healthcare Sector.
(International Journal of Computer Science Engineering (IJCSE), 2016) Olaniyan, Oluwabunmi Omobolanle
The usability of Electronic Health Record systems, while recognized as critical for successful adoption and meaningful use, has not historically received the same level of attention as other software features, functions, and technical requirements. In the Nigerian healthcare sector, it was observed that only few had adopted the use of electronic health record. The traditional method of keeping patient records which involves the use of paper and files is the system that is practiced till date. This paper-based system had been useful but no longer adequate as a result of some likely errors that occur like illegible handwriting of medical practitioners, improper care of patients’ record, poor accessibility rate to patient’s files, high cost of registration and payment for treatments; as well as wrong diagnosis due to inaccurate diagnostic decisions made. Although there are numerous EHR in market and due to the importance of this software, it is necessary to determine the usability of the software. Hence, this paper proposed a framework that enhances the usability of Electronic Health Record systems in Nigeria healthcare sectors.

Browse

Browsing Department of Computer Sciences by Author "Olaniyan, Oluwabunmi Omobolanle"

Results Per Page

Sort Options