Browsing by Author "Shakirat Ronke Yusuff"

Now showing 1 - 4 of 4
  • No Thumbnail Available
    Item
    An Explainable ResNet-101 Framework for Hand Fracture Classification in X-ray
    (Co hosted by Baze University Big Data Analytics and Innovation Research Group, American University Yola, and Sule Lamido University, 2026-04-23) Ayodeji Jubril Alabi; Shakirat Ronke Yusuff; Sulaiman Olaniyi Abdulsalam; Ismail Idowu Akuji; Oyindamola Eniola Ajiboye
    : Fracture detection in radiographic images continues to be a difficult task due to subtle bone disruptions and variations in anatomical structures, especially within the hand region. This study proposes an explainable deep learning framework for automated hand fracture detection using a ResNet-101 architecture. The model was trained and evaluated on the hand subset of the publicly available MURA dataset, with preprocessing methods and data balancing strategies applied to mitigate class imbalance and enhance model generalization. Bayesian hyperparameter optimization was utilized to determine the most suitable training parameters, including learning rate, dropout rate, and network capacity, thereby improving model stability and overall performance. The optimized model achieved an accuracy of 79.7% with an area under the curve (AUC) of 0.75, indicating dependable classification performance. To enhance interpretability, Grad-CAM++ was incorporated to visualize the regions of interest that influence the model’s predictions, allowing verification of clinically meaningful focus areas. The results demonstrate that the model effectively detects fracture regions while maintaining stable performance across diverse radiographic samples. In addition, the system produces automated PDF-based clinical reports that combine predictions with corresponding heatmaps, thereby improving its practical relevance in clinical environments. Overall, the proposed approach offers a robust, interpretable, and clinically valuable solution for hand fracture detection, with strong potential for integration into computer-aided diagnosis systems. Future work will focus on extending the model to multi-centre datasets and incorporating additional clinical features to further enhance generalization and diagnostic reliability
  • No Thumbnail Available
    Item
    Enhanced Interpretable Deep Learning Framework for Dengue Fever Prediction: A Rule Extraction Approach
    (co-hosted by Baze University Big Data Analytics and Innovation Research Group, American University Yola, and Sule Lamido University, 2026-04-23) Kolawole Muhammed Abdulsalam; Hamidat Ayodeji Arikewuyo; Ismail Idowu Akuji; Abdulmumeen Sekinat Shaban; Islamiyat Oluwakemi Giwa; Muhammad Sharafadeen Jimoh; Taofik Abiodun Ahmed; Shakirat Ronke Yusuff; Ronke Seyi Babatunde
    Dengue fever poses a critical public health challenge worldwide, particularly in developing countries with laboratory-constrained healthcare systems. Existing methods show promise but are prone to overfitting, which can be mitigated by LSTM-based deep learning models. However, LSTM inherently lack interpretability, a major barrier to clinical adoption in disease prediction. This study bridges robustness and clinical interpretability by integrating rule extraction with LSTM for dengue fever prediction, using a Mendeley dengue fever dataset comprising 1,003 instances and 9 features, preprocessed with label encoding, simple imputation, and synthetic minority oversampling (SMOTE).The LSTM algorithm is optimized using GridSearchCV and RandomizedSearchCV and combined with G-REX for transparent generation, evaluated using accuracy, precision, recall, F1 score, and ROC AUC. All three LSTM variants, including Baseline, GridSearchCV, and RSCV (20 iterations), achieve 100% across Accuracy, Precision, Recall, F1-Score, and ROC-AUC. However, G-REX rules deliver exceptional practical performance: 98.99% Accuracy, 98.53% Precision, 100% Recall, 99.26% F1-Score, and 99.09% ROC-AUC, while maintaining 93.3% fidelity to LSTM predictions, affirming medical validity. These findings position LSTM models as a strong reference standard for dengue classification, enabling resource-limited clinics to achieve high-quality diagnostics through transparent, rulebased support systems. This study can be strengthened in future by exploring other rule-extraction techniques and incorporating diverse, time-series datasets to enhance reliability, interpretability, and generalizability across varied clinical settings.
  • No Thumbnail Available
    Item
    Implementation of Yorùbá Unicode generation for an indigenous keyboard
    (Kwara State University, 2020) Jumoke Falilat Ajao; Ronke Seyi Babatunde; Shakirat Ronke Yusuff; Suliyat Oyindamola Asapetu
    Characters are generally represented on standard keyboards by the use of coding schemes such as ASCII and Unicode but some characters of the Yorùbá language were not captured because of the accent and diacritic signs inherent in Yorùbá language. Coding representation for Yorùbá characters has become a key problem in circuit implementations of keyboards for typing Yorùbá documents correctly. The standard keyboard layouts do not have a simple key combination for all the characters. To represent Yorùbá characters in human-computer interaction, this paper proposes the use of Unicode for the deployment of Yorùbá keyboard for effective and efficient typing of documents in Yorùbá language. The approach used for the development of the Yorùbá keyboard uses both binary and hexadecimal representation of the coding standards to codify Yorùbá characters with their diacritic signs and the under dot. This dimension introduces the complex Yorùbá character coding representations using a single code point standard. The generated Unicode point was transformed into HTML entities. The HTML entities generated were converted to its character equivalent for the Yorùbá keyboard. The new Unicode was compared with the results of the two encoding standard scheme using the bit relationships of upper and lower case characters to ascertain conformity of the new Unicode with the standard encoding scheme. This provided some insights about the efficient representation of Yorùbá character scheme. The representation is expected to quickly identify solutions to the design of Yorùbá keyboards and signage.
  • No Thumbnail Available
    Item
    The critical role of hyperparameter tuning in machine learning: Implications for reproducibility and model comparison
    (Kwara State University, 2025-12-31) Rafiu Mope Isiaka; Shakirat Ronke Yusuff; Akinbowale Nathaniel Babatunde; Shuaib Babatunde Mohammed
    Despite being a fundamental aspect of machine learning model development, hyperparameter tuning remains underreported in the literature. This article highlights the importance of hyperparameter optimisation, outlines common hyperparameters across various algorithms, and discusses the consequences of inadequate hyperparameter documentation. We argue that the lack of transparency in hyperparameter settings impedes reproducibility, hinders fair model comparisons, and contributes to the hyperparameter deception. The importance of hyperparameter tuning in machine learning was demonstrated by comparing the performance of the decision tree, support vector machine and random forest models on Iris, Digits and Breast Cancer datasets using default and tuned hyperparameters. This further justifies the need to document and report the process and values of the hyperparameter settings used in the models. To facilitate this, an architecture that encourages the documentation of the hyperparameters has been proposed. By emphasising the need for comprehensive reporting, this study aims to raise awareness and encourage best practices in machine learning research