Bukohwo Michael Esiefarienrhe

Prof. Bukohwo Michael Esiefarienrhe

North West University, Mahikeng, North West, South Africa
orcid

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 June 2022 in Telecom
Verified
Journal Article
Open access
PDF file
BEBukohwo Michael Esiefarienrhe
Bukohwo Michael Esiefarienrhe
TPThulani Lindelwa Phakathi
Thulani Lindelwa Phakathi
FLFrancis Lugayizi
Francis Lugayizi
Most networks strive to provide good security and an acceptable level of performance. Quality of service (QoS) plays an important role in the performance of a network. Mobile ad hoc networks (MANETs) are a decentralized and self-configuring type of wireless network. MANETs are generally challenging and the provision of security and QoS becomes a huge challenge. Many researchers in literature have proposed parallel mechanisms that investigate either security or QoS. This paper presents a security framework that is QoS-aware in MANETs using a network protocol called optimized link state routing protocol (OLSR). Security and QoS targets may not necessarily be similar but this framework seeks to bridge the gap for the provision of an optimal functioning MANET. The framework is evaluated for throughput, jitter, and delay against a sinkhole attack presented in the network. The contributions of this paper are (a) implementation of a sinkhole attack using OLSR, (b) the design and implementation of a lightweight-intrusion detection system using OLSR, and (c) a framework that removes fake routes and bandwidth optimization. The simulation results revealed that the QoS-aware framework increased the performance of the network by more than 70% efficiency in terms of network throughput. Delay and jitter levels were reduced by close to 85% as compared to when the network was under attack.

4 November 2024 in Applied Sciences
Verified
Journal Article
Open access
PDF file
JOJulius Olaniyan
Julius Olaniyan
DODeborah Olaniyan
Deborah Olaniyan
IOIbidun Christiana Obagbuwa
Ibidun Christiana Obagbuwa
BEBukohwo Michael Esiefarienrhe
Bukohwo Michael Esiefarienrhe
MOMatthew Odighi
Matthew Odighi
This paper presents a transformative explainable convolutional neural network (CNN) framework for cataract detection, utilizing a hybrid deep learning model combining Siamese networks with VGG16. By leveraging a learning rate scheduler and Grad-CAM (Gradient-weighted Class Activation Mapping) for explainability, the proposed model not only achieves high accuracy in identifying cataract-infected images but also provides interpretable visual explanations of its predictions. Performance evaluation metrics such as accuracy, precision, recall, and F1 score demonstrate the model’s robustness, with a perfect accuracy of 100%. Grad-CAM visualizations highlight the key image regions—primarily around the iris and pupil—that contribute most to the model’s decision-making, making the system more transparent for clinical use. Additionally, novel statistical analysis methods, including saliency map evaluation metrics like AUC (Area Under the Curve) and the Pointing Game, were employed to quantify the quality of the model’s explanations. These metrics enhance the interpretability of the model and support its practical applicability in medical image analysis. This approach advances the integration of deep learning with explainable AI, offering a robust, accurate, and interpretable solution for cataract detection with the potential for broader adoption in ocular disease diagnosis and medical decision support systems.

23 December 2022 in The African Journal of Information and Communication (AJIC)
Verified
Journal Article
Open access
PDF file
EEEbiemi Allen Ekubo
Ebiemi Allen Ekubo
BEBukohwo Michael Esiefarienrhe
Bukohwo Michael Esiefarienrhe
This study evaluates the ability of various machine-learning techniques to predict low academic performance among Nigerian tertiary students. Using data collected from undergraduate student records at Niger Delta University in Bayelsa State, the research applies the cross-industry standard process for data mining (CRISP-DM) research methodology for data mining and the Waikato Environment for Knowledge Analysis (WEKA) tool for modelling. Five machine-learning classifier algorithms are tested—J48 decision tree, logistic regression (LR), multilayer perceptron (MLP), naïve Bayes (NB), and sequential minimal optimisation (SMO)—and it is found that MLP is the best classifier for the dataset. The study then develops a predictive software application, using PHP and Python, for implementation of the MLP model, and the software achieves 98% accuracy.

24 December 2024 in E-Journal of Humanities, Arts and Social Sciences
Verified
Journal Article
Open access
IMItumeleng Michael Maine
Itumeleng Michael Maine
BEBukohwo Michael Esiefarienrhe
Bukohwo Michael Esiefarienrhe
The benefits in the use of Artificial Intelligence (AI) in the electoral process are enormous only when AI is used ethically and all stakeholders particularly those vested with the responsibility to conduct elections are ethically upright in their use of AI. The problem this paper seeks to address is how AI can be ethically used to aid the smooth conduct of elections and how can the benefits of AI be harnessed in the electioneering process. The methodology used in both data collection and analysis was expert judgement and systematic review. This paper analysed the various AI tools and techniques that are used to assist in the conduct of credible elections. Also discussed are the various ways that AI can be used negatively to influence voters namely deepfakes, automated bots, data privacy breaches, microtargeting, psychological profiles of voters, voting pattern prediction, and cyberattacks of electronic devices with the intention to rig elections. It is recommended that the ethical use of AI in elections should be advocated, and training of the citizens on the role of AI before, during and after elections and how to handle AI-related threats should be conducted well ahead of elections. Keywords: AI in Elections, Voting and AI, Ethical AI in elections, the impact of AI in electoral process, deepfakes and elections.

8 February 2022 in Telecom
Verified
Journal Article
Open access
PDF file
MMMalebogo Mokeresete
Malebogo Mokeresete
BEBukohwo Michael Esiefarienrhe
Bukohwo Michael Esiefarienrhe
Some of the advantages of using Worldwide Interoperability Microwave Access (WiMAX) technology at the last-mile level as an access technology include an extensive range of 50 km Line of Sight (LOS), 5 to 15 km Non-Line of Sight, and fewer infrastructure installations compared to other wireless broadband access technologies. Despite positive investments in ICT fiber infrastructure by developing countries, including Botswana, servicing end-users is subjected to high prices and service disparities. The alternative, the Wi-Fi hotspot initiative by the Botswana government, falls short as a solution for last-mile connectivity and access. This study used OPNET simulation Modeler 14.5 to investigate whether Botswana’s national broadband project could adopt WiMAX IEEE 802.16e as an access technology. Therefore, using the experimental method, the simulation evaluated the WiMAX IEEE 802.16e/m over three subscriber locations in Botswana. The results obtained indicate that the deployment of the WiMAX IEEE 802.16e standard can solve most of the deployment issues and access at the last-mile level. Although the findings suggest that WiMAX IEEE 802.16e is more suitable for high-density areas, it could also solve rural areas’ infrastructure development challenges and provide the required high-speed connectivity access. However, unlike the Wi-Fi initiative, which requires more infrastructure deployment and relies less on institutional and regulatory frameworks, the deployment of WiMAX IEEE 802.16e necessitates institutional and regulatory standards.

9 December 2021
Verified
Conference Paper
Closed access
BEBukohwo Michael Esiefarienrhe
Bukohwo Michael Esiefarienrhe
IOIsaac Damilare Omolewa
Isaac Damilare Omolewa
Medical billing is a long chain of processes that cut across different sectors and institutions, evolving into a multimillion-dollar industry. Despite the emergence of institutional involvement in the practice, the parties involved face many challenges that hinder the successful management of the diverse process. Process mining uses computer-based tools and techniques to analyze business processes and ensure best practices for improving business operations as it has a track record of success in improving business processes and procedures. As research on process driving problem solving continues to grow, there is a need to start applying the tools and techniques to specific domain areas and bridge the gap between research, development and application. We demonstrated how process mining techniques can be applied to medical billing using the L * life cycle model from a structured perspective. We developed a handmade comprehensive medical billing process flow using domain knowledge reference and established some time perspective Key Performance Indicators (KPIs) of the billing process. We then explored the hospital billing event log generated from an enterprise resource planning (ERP) system to see how the “as-is” from the event log deviate from the generally known knowledge-based (handmade) model. Taking each trace of the event log as patient visit, we discover that about 63 % of all the visit were billed and also about 3 % billed got regretted. The event log used in this research does not capture the complete activity flow for a real-world medical billing system. Hence, we were not able to directly compare the process map with the model and give precise operational support