Obinna Okoyeigbo

Mr. Obinna Okoyeigbo

orcid

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
31 October 2024 in Mathematics
Verified
Journal Article
Open access
PDF file
AAAbisola Akinjole
Abisola Akinjole
Olamilekan ShobayoOlamilekan Shobayo
Olamilekan Shobayo
JPJumoke Popoola
Jumoke Popoola
Obinna OkoyeigboObinna Okoyeigbo
Obinna Okoyeigbo
Bayode OgunleyeBayode Ogunleye
Bayode Ogunleye
Predicting credit default risk is important to financial institutions, as accurately predicting the likelihood of a borrower defaulting on their loans will help to reduce financial losses, thereby maintaining profitability and stability. Although machine learning models have been used in assessing large applications with complex attributes for these predictions, there is still a need to identify the most effective techniques for the model development process, including the technique to address the issue of data imbalance. In this research, we conducted a comparative analysis of random forest, decision tree, SVMs (Support Vector Machines), XGBoost (Extreme Gradient Boosting), ADABoost (Adaptive Boosting) and the multi-layered perceptron, to predict credit defaults using loan data from LendingClub. Additionally, XGBoost was used as a framework for testing and evaluating various techniques. Moreover, we applied this XGBoost framework to handle the issue of class imbalance observed, by testing various resampling methods such as Random Over-Sampling (ROS), the Synthetic Minority Over-Sampling Technique (SMOTE), Adaptive Synthetic Sampling (ADASYN), Random Under-Sampling (RUS), and hybrid approaches like the SMOTE with Tomek Links and the SMOTE with Edited Nearest Neighbours (SMOTE + ENNs). The results showed that balanced datasets significantly outperformed the imbalanced dataset, with the SMOTE + ENNs delivering the best overall performance, achieving an accuracy of 90.49%, a precision of 94.61% and a recall of 92.02%. Furthermore, ensemble methods such as voting and stacking were employed to enhance performance further. Our proposed model achieved an accuracy of 93.7%, a precision of 95.6% and a recall of 95.5%, which shows the potential of ensemble methods in improving credit default predictions and can provide lending platforms with the tool to reduce default rates and financial losses. In conclusion, the findings from this study have broader implications for financial institutions, offering a robust approach to risk assessment beyond the LendingClub dataset.

11 November 2024 in Analytics
Verified
Journal Article
Open access
PDF file
OTOluwatosin Tanimola
Oluwatosin Tanimola
Olamilekan ShobayoOlamilekan Shobayo
Olamilekan Shobayo
OPOlusogo Joshua Popoola
Olusogo Joshua Popoola
Obinna OkoyeigboObinna Okoyeigbo
Obinna Okoyeigbo
Breast cancer is the most prevalent type of disease among women. It has become one of the foremost causes of death among women globally. Early detection plays a significant role in administering personalized treatment and improving patient outcomes. Mammography procedures are often used to detect early-stage cancer cells. This traditional method of mammography while valuable has limitations in its potential for false positives and negatives, patient discomfort, and radiation exposure. Therefore, there is a probe for more accurate techniques required in detecting breast cancer, leading to exploring the potential of machine learning in the classification of diagnostic images due to its efficiency and accuracy. This study conducted a comparative analysis of pre-trained CNNs (ResNet50 and VGG16) and vision transformers (ViT-base and SWIN transformer) with the inclusion of ViT-base trained from scratch model architectures to effectively classify mammographic breast cancer images into benign and malignant cases. The SWIN transformer exhibits superior performance with 99.9% accuracy and a precision of 99.8%. These findings demonstrate the efficiency of deep learning to accurately classify mammographic breast cancer images for the diagnosis of breast cancer, leading to improvements in patient outcomes.

7 February 2020 in Applied Computational Intelligence and Soft Computing
Verified
Journal Article
Open access
PDF file
Olamilekan ShobayoOlamilekan Shobayo
Olamilekan Shobayo
AOAYOBAMI OLAJUBE
AYOBAMI OLAJUBE
NONathan Ohere
Nathan Ohere
MOModupe Odusami
Modupe Odusami
Obinna OkoyeigboObinna Okoyeigbo
Obinna Okoyeigbo
Traffic law violation has been recognized as a major cause for road accidents in most parts of the world with majority occurring in developing countries. Even with the presence of rules and regulations stipulated against this, violators are still on the increase. This is due to the fact that the rules are not properly enforced by appropriate authorities in those parts of the world. Therefore, a system needs to be designed to assist law enforcement agencies to impose these rules to improve road safety and reduce road accidents. This work uses a Vehicle Plate Number Recognition (VNPR) system which is a real-time embedded system to automatically recognize license plate numbers. It provides an alternative means to VPNR using an open-source library known as openCV. The main aim of the system is to use image processing to identify vehicles violating traffic by their plate numbers. It consists of an IR sensor for detecting the vehicle. During testing, a minimum time was set for the sensor to detect the object which was recorded by the microprocessor. Once it was less than the set time, the camera was triggered to capture the plate number and store the image on the Raspberry Pi. The image captured is processed by the Raspberry Pi to extract the numbers on the image. The numbers on the capture imaged were viewed on a web page via an IP address. The system if implemented can be used to improve road safety and control traffic of emerging smart cities. It will also be used to apply appropriate sanctions for traffic law violators.

11 February 2025 in Analytics
Verified
Journal Article
Open access
PDF file
Olamilekan ShobayoOlamilekan Shobayo
Olamilekan Shobayo
SASidikat Adeyemi-Longe
Sidikat Adeyemi-Longe
OPOlusogo Joshua Popoola
Olusogo Joshua Popoola
Obinna OkoyeigboObinna Okoyeigbo
Obinna Okoyeigbo
This study compares three machine learning and deep learning models—Support Vector Regression (SVR), Recurrent Neural Networks (RNN), and Long Short-Term Memory (LSTM)—for predicting market prices using the NGX All-Share Index dataset. The models were evaluated using multiple error metrics, including Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Square Error (RMSE), Mean Percentage Error (MPE), and R-squared. RNN and LSTM were tested with both 30 and 60-day windows, with performance compared to SVR. LSTM delivered better R-squared values, with a 60-day LSTM achieving the best accuracy (R-squared = 0.993) when using a combination of endogenous market data and technical indicators. SVR showed reliable results in certain scenarios but struggled in fold 2 with a sudden spike that shows a high probability of not capturing the entire underlying NGX pattern in the dataset correctly, as witnessed by the high validation loss during the period. Additionally, RNN faced the vanishing gradient problem that limits its long-term performance. Despite challenges, LSTM’s ability to handle temporal dependencies, especially with the inclusion of On-Balance Volume, led to significant improvements in prediction accuracy. The use of the Optuna optimisation framework further enhanced model training and hyperparameter tuning, contributing to the performance of the LSTM model.

18 June 2024 in Analytics
Verified
Journal Article
Open access
PDF file
Olamilekan ShobayoOlamilekan Shobayo
Olamilekan Shobayo
SSSwethika Sasikumar
Swethika Sasikumar
SMSandhya Makkar
Sandhya Makkar
Obinna OkoyeigboObinna Okoyeigbo
Obinna Okoyeigbo
In this work, we evaluated the efficacy of Google’s Pathways Language Model (GooglePaLM) in analyzing sentiments expressed in product reviews. Although conventional Natural Language Processing (NLP) techniques such as the rule-based Valence Aware Dictionary for Sentiment Reasoning (VADER) and the long sequence Bidirectional Encoder Representations from Transformers (BERT) model are effective, they frequently encounter difficulties when dealing with intricate linguistic features like sarcasm and contextual nuances commonly found in customer feedback. We performed a sentiment analysis on Amazon’s fashion review datasets using the VADER, BERT, and GooglePaLM models, respectively, and compared the results based on evaluation metrics such as precision, recall, accuracy correct positive prediction, and correct negative prediction. We used the default values of the VADER and BERT models and slightly finetuned GooglePaLM with a Temperature of 0.0 and an N-value of 1. We observed that GooglePaLM performed better with correct positive and negative prediction values of 0.91 and 0.93, respectively, followed by BERT and VADER. We concluded that large language models surpass traditional rule-based systems for natural language processing tasks.

28 April 2022 in Telecom
Verified
Journal Article
Open access
PDF file
Augustus Ehiremen IbhazeAugustus Ehiremen Ibhaze
Augustus Ehiremen Ibhaze
Agbotiname Lucky ImoizeAgbotiname Lucky Imoize
Agbotiname Lucky Imoize
Obinna OkoyeigboObinna Okoyeigbo
Obinna Okoyeigbo
It is crucial to design new communication technologies to surmount the setbacks in RF communication systems. A suitable energy-efficiency scheme helps evade needless energy consumption in wireless communication. Appropriate choice of the most suitable energy-efficiency scheme aids in selecting the most energy-efficient equipment to minimize the expense of energy towards decreasing individual network element energy consumption without affecting their unique features. This review presents the energy efficiency challenges in wireless communication by employing different technologies. The emergence of visible light communication (VLC) provides an energy-efficient wireless communication system despite the various challenges inherent in its adoption that limit its physical realization. This work seeks to harness the potential of the transmission capabilities of VLC while providing an insight into novel practical implementation techniques. The work also addresses the energy consumption problem of low-active components and idle period of active components of base stations by using sleep modes for their systematic turning off and on. The high cost of power supply and the environmental emission of gases from base stations are also addressed by integrating a renewable energy resource into the conventional standalone diesel generators. Overall, the work provides an overview of information necessary for foundational research in energy-efficient resources applied to emerging wireless communication systems.