Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Matthias Omotayo Oladele has a total of 34 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A Review of Machine Learning Approaches to Eye Disease Detection: Current Trends, Challenges and Future Directions

    by Matthias Omotayo Oladele, Oyeniyi Akeem Alimi, Oludayo O. Olugbara

    Background/Objectives: Vision impairment and blindness remain a major global health challenge, with glaucoma, diabetic retinopathy, age-related macular degeneration, cataract, corneal disease, and retinopathy of prematurity representing important causes of preventable or treatable vision loss when detected early. This clinical need has accelerated research on machine learning approaches for automatic detection of eye diseases, grading, and segmentation. However, existing reviews often focus on a single disease or method. They also give limited attention to their suitability and applicability for reliable clinical deployments. This review synthesizes traditional machine learning, deep learning, vision transformers, ensemble and hybrid models, segmentation methods, and explainable AI approaches for eye disease detection. It further examines task formulation, dataset characteristics, evaluation practices, and deployment constraints, with emphasis on clinical readiness rather than benchmark performance alone. Methods: A structured narrative review was conducted using recently published articles from reputable databases and repositories, including IEEE Xplore, PubMed/MEDLINE, ScienceDirect, Scopus and arXiv. The review critically analyzes the progression from traditional machine learning to advanced models, including deep learning, vision transformers, ensemble models and explainable artificial intelligence. Studies were critically analyzed according to task formulations, dataset characteristics, segmentation approaches, evaluation metrics, explainability, and deployment constraints. Results: The synthesis shows that class imbalance, limited demographic and geographic diversity in available datasets, weak external validation, and scarce prospective evidence continue to separate benchmark performance from clinical readiness. Explainability is also often evaluated through visual plausibility rather than validated faithfulness. Currently, data-driven diabetic retinopathy screening is closest to clinical readiness, particularly for distinguishing referable from non-referable cases, whereas multi-label detection, rare disease detection, and cross-device deployment remain at the research stage. Conclusions: Progress towards clinical adoption requires stronger alignment between experimental evaluation and real-world deployment. This includes external validation and the development of equitable, interpretable, and resource-aware systems.

  • Open Access

    AI-Based Travel Recommendation Systems: Personalizing Tourist Experiences through Preference Modeling and Real-Time Behavioral Analytics in Nigeria

    by Osinubi O.B, Adigun O.I, Matthias O.O

    The rapid digitalization of tourism has increased the demand for intelligent recommendation systems capable of delivering personalized travel experiences that adapt to users' evolving preferences and contextual circumstances. Conventional tourism recommendation platforms predominantly rely on static filtering mechanisms and explicit user ratings, often producing generic recommendations that fail to reflect dynamic travel behaviors and real-time contextual information. This study presents the des...

  • Open Access

    Domain-Adaptive Retinal Vessel Segmentation for Unannotated Fundus Images

    by Matthias Omotayo Oladele, Oyeniyi Akeem Alimi, Oludayo O. Olugbara

    Accurate retinal vessel segmentation supports quantitative vascular analysis in assessing ocular and systemic diseases. Yet, its clinical scalability is constrained by limited pixel-level annotations and domain shift across heterogeneous fundus datasets. Thus, this study proposes a domain-adaptive retinal vessel segmentation model (DA-VesselNet), a weakly supervised approach that transfers vessel-segmentation knowledge from annotated source datasets to the unannotated Retinal Fundus Multi-Disease Image Dataset (RFMiD). The model was trained on DRIVE, CHASE_DB1, and FIVES, and adapted to RFMiD. The ResNet50 encoder with an attention-gated U-Net decoder, confidence-aware pseudo-label supervision, and perturbation consistency regularisation were used for the training process. Results on the held-out CHASE_DB1 indicated that DA-VesselNet achieved a Dice score of 0.5778, an Intersection over Union (IoU) of 0.4082, and an Area Under the Curve (AUC) of 0.9518. On 200 held-out FIVES test images with different pathological features, it achieved a Dice score of 0.7447 and an AUC of 0.9733, outperforming the source-only baseline model. To assess adaptation independently of source-adjacent data, the model was further tested on STARE and HRF, two domains excluded entirely from source training. Adaptation improved Dice by 0.0469 on STARE and 0.0056 on HRF with AUC gains of 0.0140 and 0.0121, respectively. Ablation analysis identified source-anchored supervision as the dominant contributor to performance. The adapted model was subsequently applied to generate vessel pseudo-labels for the RFMiD target domain, providing a structural resource for future vessel-informed analysis. These findings demonstrate that DA-VesselNet offers a scalable solution for creating clinically relevant pseudo-labelled vessels in fundus imaging with limited annotations.


  • A Hybrid Differential Evolution and Reinforcement Learning Approach for Optimizing Convolutional Neural Networks in Facial Age Group Classification

    by Matthias Omotayo Oladele, Temitope Adeyemo, Temilola Morufat Adepoju, Oluwafemi Olayanju Awodoye, Abisola Olayiwola, Dare Olayiwola, Elijah Olusayo Omidiora, Alice Oluwafunke Oke, Olaide Abiodun Olatoke

  • Open Access

    Effect of Fine-tuning Transfer Learning Layers: A Case Study of Breast Cancer Classification

    by Temilola M. Adepoju, Matthias O. Oladele, Mutairu O. Akintunde, Afolake M. Ogunleye

    Breast cancer is one of the leading causes of cancer-related mortality, specifically among women worldwide, necessitating the development of practical diagnostic tools. Much research has explored breast cancer classification using transfer learning approaches. However, despite notable success, a need remains to understand how fine-tuning different layers affects model performance, especially in tasks requiring high precision, such as breast cancer classification. This research investigates the optimization of fine-tuning strategies for transfer learning techniques, specifically the InceptionV3 and Xception architecture, to observe the effect of fine-tuning transfer learning layers in classifying breast cancer from mammographic images. The study used the CBIS-DDSM dataset and a comprehensive preprocessing pipeline that included image normalization, resizing, and data augmentation to prepare the dataset for model training. A systematic layer unfreezing strategy was implemented, allowing varying degrees of fine-tuning, from no fine-tuning to full fine-tuning of the model. The results reveal that InceptionV3 outperforms Xception, achieving a 0.65 accuracy without fine-tuning, compared to 0.64 for Xception. Performance improves with fine-tuning with the maximum value of 0.66 when fine-tuning the last two blocks of InceptionV3 and the last three blocks of Xception. However, full fine-tuning results in significant performance degradation, with InceptionV3 achieving a value of 0.61 and Xception 0.51 for accuracy. These findings emphasize the importance of selecting the right fine-tuning strategy to avoid overfitting and ensure the robustness of models for medical applications. Additional metrics, including precision, recall, and F1-score, also reflect similar trends, underscoring the critical role of fine-tuning in tailoring pre-trained models to specific tasks in medical imaging. This research contributes valuable insights into optimizing transfer learning approaches in breast cancer diagnosis, highlighting the potential for improved clinical decision-making through advanced machine-learning techniques.


  • Open Access

    Development of a Mobile-Based Convolution Neural Network Framework for Rapid Malaria Detection from Blood Smears

    by Matthias O. Oladele, Temilola M. Adepoju, Abdulahi A. Badrudeen

    Malaria, a vector-borne parasitic disease caused by Plasmodium parasites, continues to pose a substantial threat to global public health. Despite considerable progress in its control and treatment, malaria remains a significant cause of morbidity and mortality, particularly in resource-limited regions. The ability to diagnose malaria infections accurately and swiftly is paramount for effective disease management. Traditional methods of malaria diagnosis, relying on microscopic examination of blood smears, have proven to be accurate but are often hindered by limitations in infrastructure and expertise, particularly in remote and underserved areas. This research focuses on the development of a mobile-based Convolution Neural Network (CNN) framework for rapid malaria parasite detection from blood smear images using Android mobile phones. Blood smear images provide a reasonable and clinically relevant representation of malaria disease which makes it a preferred choice for malaria detection from mobile phones. By leveraging smartphone technology and state-of-the-art deep learning algorithms, this pioneering endeavour aims to normalize malaria diagnostics, providing healthcare workers with a powerful tool for early detection and treatment, irrespective of their location or access to advanced laboratory facilities. The dataset for infected and non-infected parasites was acquired online from Kaggle. The dataset was preprocessed and partitioned into training, testing, and validation sets. The developed model was converted to tflite and was used for the mobile application. A validation accuracy of 94.88% was obtained from the validation set while an accuracy of 95.81% was obtained from the testing set.


  • A Two-Stage Model for Breast Cancer Detection and Classification from Mammograms

    by Adebanjo Adekiigbe, Temilola Morufat Adepoju, Matthias Omotayo Oladele

    Breast cancer is a type of disease which is common to women. It is an abnormal behaviour which hinders the functionality of the normal breast cells which leads to forming a tumor in the form of lump. Early detection of breast cancers tends to reduce death risk and provides a chance of a suitable and better treatment. A two-stage classification model was proposed to detect and classify breast cancer using two publicly available datasets namely MIAS and the DDSM dataset. The first classification stage uses Convolution Neural Network (CNN) to classify the mammogram image as either normal or abnormal while K-Nearest Neighbour (KNN) was used for the second classification stage to classify the abnormal image into benign or malignant. The features used for the second stage classification were extracted using Gray Level Co-occurrence Matrix (GLCM), which was later used for classification. The performance was evaluated based on accuracy, sensitivity, specificity, precision, False Positive Rate (FPR), F1 score and Matthews Correlation Coefficient (MCC). The results show that CNN obtained the highest accuracy, sensitivity, specificity, precision, FPR, F1 score and MCC of 99.03%, 0.9831, 1.0000, 1.0000, 0.0000, 0.9915 and 0.9804 respectively, while KNN has an accuracy, sensitivity, specificity, precision, FPR, F1 score and MCC of 76.27%, 0.7667, 0.7586, 0.7667, 0.2414, 0.7667 and 0.5253 respectively.


  • Open Access

    Development of a Low-Cost Arduino-Based Weather Station

    by Temilola M Adepoju, Matthias O Oladele, Abdulwakil A Kasali, Gbenga J Fabiyi

    A weather station is a facility located either on land or sea consisting of instruments and equipment which can be used to measure atmospheric conditions so as to provide weather forecasts information and to study the weather. The existing instruments used for measuring the weather elements are expensive which led to the development of a low-cost Arduino-based weather station. The developed low-cost weather station consists of three separate modules which are data collection, data storage, and data communication. These modules communicate serially with each other and are controlled by three separate microcontrollers (Arduino Uno). The data collection module is interfaced with a set of sensors that collects temperature and humidity. The weather data were viewed in real-time through a graphical user interface (GUI) located at the central station. The developed weather station was able to measure the temperature and humidity of a controlled environment, giving the reading at interval of five minutes. It was observed that the average temperature from results obtained (27.360C) with the developed low-cost Arduino based weather station falls within the range of the Accuweather readings (24.00-28.000C). Also, the average humidity of the developed low-cost Arduino based weather station (80.41%) falls within the range of the Weatherspark humidity (78-82%) on 20th August 2019. Therefore, this system can be adopted as a weather station facility. The design can be extended to be web-based in the future to make it available worldwide.Keywords— Arduino Uno, Humidity, RF Transceiver, Temperature, Weather Station


  • Open Access

    OFFLINE YORÙBÁ HANDWRITTEN WORD RECOGNITION USING GEOMETRIC FEATURE EXTRACTION AND SUPPORT VECTOR MACHINE CLASSIFIER

    by Matthias Omotayo Oladele, Temilola Morufat Adepoju, Olaide ` Abiodun Olatoke, Oluwaseun Adewale Ojo

    Yorùbá language is one of the three main languages that is been spoken in Nigeria. It is a tonal language that carries an accent on the vowel alphabets. There are twenty-five (25) alphabets in Yorùbá language with one of the alphabets a digraph (GB). Due to the difficulty in typing handwritten Yorùbá documents, there is a need to develop a handwritten recognition system that can convert the handwritten texts to digital format. This study discusses the offline Yorùbá handwritten word recognition system (OYHWR) that recognizes Yorùbá uppercase alphabets. Handwritten characters and words were obtained from different writers using the paint application and M708 graphics tablets. The characters were used for training and the words were used for testing. Pre-processing was done on the images and the geometric features of the images were extracted using zoning and gradient-based feature extraction. Geometric features are the different line types that form a particular character such as the vertical, horizontal, and diagonal lines. The geometric features used are the number of horizontal lines, number of vertical lines, number of right diagonal lines, number of left diagonal lines, total length of all horizontal lines, total length of all vertical lines, total length of all right slanting lines, total length of all left-slanting lines and the area of the skeleton. The characters are divided into 9 zones and gradient feature extraction was used to extract the horizontal and vertical components and geometric features in each zone. The words were fed into the support vector machine classifier and the performance was evaluated based on recognition accuracy. Support vector machine is a two-class classifier, hence a multiclass SVM classifier least square support vector machine (LSSVM) was used for word recognition. The one vs one strategy and RBF kernel were used and the recognition accuracy obtained from the tested words ranges between 66.7%, 83.3%, 85.7%, 87.5%, and 100%. The low recognition rate for some of the words could be as a result of the similarity in the extracted features.


  • Open Access

    Curvelet Transform-Local Binary Pattern Feature Extraction Technique for Mass Detection and Classification in Digital Mammogram

    by Adeyemo Temitope Tosin, Adepoju Temilola Morufat, Oladele Matthias Omotayo, Wahab Wajeed Bolanle, Omidiora Elijah Olusayo, Olabiyisi Stephen Olatunde

    Aim: To develop a Curvelet Transform (CT)-Local Binary Pattern (LBP) feature extraction technique for mass detection and classification in digital mammograms. Study Design: A feature extraction technique. Place and Duration of Study: Sample: Department of Computer Science and Engineering LAUTECH, Ogbomoso, Nigeria 2016. Methodology: Three hundred (300) mammograms were acquired from the public available Mammographic Image Analysis Society (MIAS). One hundred and eighty images were used for training while the remaining 120 images out were used for testing purposes. The images were used pre-processed and segmented into Region of Interests (ROIs) using Histogram Normalization and Active Contour algorithms, respectively. CT algorithm was used to extract shape features from the ROIs while texture features were extracted using the LBP algorithm. K-Nearest Neighbor (KNN) algorithm was employed to classify the extracted features into normal and abnormal mammograms. The abnormal mammograms were further classified into benign (non-cancerous) and Malignant (cancerous) masses using KNN algorithm as well. The technique was implemented using Matrix Laboratory 8.2.0 (R2013b). The performance of the developed technique in classifying mammograms into normal/abnormal was investigated by comparing it with the existing CT-based and LBP-based techniques using sensitivity, specificity, and accuracy. Results: The results of the evaluation showed that the sensitivity, specificity and overall performance for CT-based and LBP-based technique techniques are 72.0, 73.7 and 75.83%; 84.0%, 83.2% and 80.83% while sensitivity, specificity and overall performance of the developed CT-LBP technique are 96.0%, 93.7 and 94.17% respectively. The developed system improved detection of abnormality and the classification rate of mammogram in term of sensitivity, specificity and overall performance, which could be adopted in clinical practices for better detection and classification of breast cancer.