Muhammad Aliyu Sulaiman
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Muhammad Aliyu Sulaiman has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Hauwa Ibrahim Aminu
Department of Software Engineering, Nile University of Nigeria, Abuja, NIGERIA
1 shared publication - Hayatullahi Bolaji Adeyemo
School of Computer Science, University of Birmingham
1 shared publication - Jamal Alhiyafi
Department of Computer Science, Kettering University, Flint, MI 48504, USA
1 shared publication Jane Labadin
University Malaysia Sarawak,Faculty of Computer Science and Information Technology,Kota Samarahan,Malaysia
1 shared publication- Kabiru Oluwaseun Akande
King Fahd University of Petroleum and Minerals
1 shared publication - Moussa Mahamat Boukar
Department of Computer Science, Prime University, Abuja, NIGERIA
1 shared publication
Latest Publications
- Open Access
- 12 August 2026
- Published by University of Nigeria in Nigerian Journal of Technology
- Vol. 45 (3)
INTERPRETABLE ENSEMBLE FRAMEWORK FOR PCOS RISK PREDICTION WITH SHAP AND LIME-BASED EXPLAINABILITY
Polycystic Ovary Syndrome (PCOS) affects an estimated one in ten women of reproductive age and presents with a heterogeneous range of metabolic, endocrine, and reproductive symptoms, complicating consistent clinical diagnosis. Methodology: Two related PCOS datasets (2,000 and 541 samples) were cleaned and combined for model training and external validation. Recursive Feature Elimination with Cross-Validation was used for feature selection, and class imbalance was addressed using the Synthetic Minority Over-sampling Technique (SMOTE), applied within each cross-validation fold to avoid data leakage. Random Forest (RF), Support Vector Machine (SVM), Logistic Regression (LR), and a soft-voting ensemble of the three were trained and evaluated using accuracy, sensitivity, specificity, precision, F1-score, and ROC-AUC, with statistical significance assessed via McNemar's test. Results: On the external test set, SVM, RF, and the ensemble achieved comparable accuracy (96.7-97.2%), all significantly outperforming LR (90.5%; p < 0.0001), with no significant difference among the three (p > 0.05). SHAP and LIME were applied for global and local interpretability, identifying follicle count, weight gain, skin darkening, and hormonal markers (AMH, cycle regularity) as leading predictors, though follicle count's dominance also raises a diagnostic-circularity concern given its role as a clinical diagnostic criterion. Conclusion: This framework demonstrates that ensemble and tree-based models substantially outperform linear baselines for PCOS risk prediction, with the ensemble offering comparable predictive performance alongside interpretable, dual-level explanations. These findings contribute toward more transparent and clinically trustworthy machine learning tools for PCOS diagnosis support.
- 12 August 2026
- Published by University of Nigeria in Nigerian Journal of Technology
- Vol. 45 (3)
Open AccessINTERPRETABLE ENSEMBLE FRAMEWORK FOR PCOS RISK PREDICTION WITH SHAP AND LIME-BASED EXPLAINABILITY
Polycystic Ovary Syndrome (PCOS) affects an estimated one in ten women of reproductive age and presents with a heterogeneous range of metabolic, endocrine, and reproductive symptoms, complicating consistent clinical diagnosis. Methodology: Two related PCOS datasets (2,000 and 541 samples) were cleaned and combined for model training and external validation. Recursive Feature Elimination with Cross-Validation was used for feature selection, and class imbalance was addressed using the Synthetic Minority Over-sampling Technique (SMOTE), applied within each cross-validation fold to avoid data leakage. Random Forest (RF), Support Vector Machine (SVM), Logistic Regression (LR), and a soft-voting ensemble of the three were trained and evaluated using accuracy, sensitivity, specificity, precision, F1-score, and ROC-AUC, with statistical significance assessed via McNemar's test. Results: On the external test set, SVM, RF, and the ensemble achieved comparable accuracy (96.7-97.2%), all significantly outperforming LR (90.5%; p < 0.0001), with no significant difference among the three (p > 0.05). SHAP and LIME were applied for global and local interpretability, identifying follicle count, weight gain, skin darkening, and hormonal markers (AMH, cycle regularity) as leading predictors, though follicle count's dominance also raises a diagnostic-circularity concern given its role as a clinical diagnostic criterion. Conclusion: This framework demonstrates that ensemble and tree-based models substantially outperform linear baselines for PCOS risk prediction, with the ensemble offering comparable predictive performance alongside interpretable, dual-level explanations. These findings contribute toward more transparent and clinically trustworthy machine learning tools for PCOS diagnosis support.
- 16 April 2026
- Published by Taylor & Francis
- p. 374-391
Digital Linguistic Sovereignty: The Exclusion of African Languages in Natural Language Processing
- 16 April 2026
- Published by Taylor & Francis
- p. 374-391
Digital Linguistic Sovereignty: The Exclusion of African Languages in Natural Language Processing
- 15 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-2
Information Theoretic-based Feature Selection (IFS) for Machine Learning
Mutual Information (MI) has been a popular choice for the selection criterion function of the feature selection techniques. However, only a handful of methods of formulating MI estimator for regression tasks exist, despite the existence of numerous methods of MI estimation for classification tasks in the literature. This work proposed a feature selection method based on mutual information for both classification and regression tasks. Unlike the existing MI estimator for regression tasks which are widely non-parametric, the proposed method provides a suitable way to estimate MI based on conventional kernel density estimation numerically. Two different experiments were conducted to evaluate the proposed IFS method. The first test is designed to assess the correctness of the formulated MI estimator by comparing it with various existing benchmarks. The second experiment evaluates the proposed method using natural domain data. Overall results obtained from these experiments show that the proposed method was successfully able to select relevant features.
- 15 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-2
Information Theoretic-based Feature Selection (IFS) for Machine Learning
Mutual Information (MI) has been a popular choice for the selection criterion function of the feature selection techniques. However, only a handful of methods of formulating MI estimator for regression tasks exist, despite the existence of numerous methods of MI estimation for classification tasks in the literature. This work proposed a feature selection method based on mutual information for both classification and regression tasks. Unlike the existing MI estimator for regression tasks which are widely non-parametric, the proposed method provides a suitable way to estimate MI based on conventional kernel density estimation numerically. Two different experiments were conducted to evaluate the proposed IFS method. The first test is designed to assess the correctness of the formulated MI estimator by comparing it with various existing benchmarks. The second experiment evaluates the proposed method using natural domain data. Overall results obtained from these experiments show that the proposed method was successfully able to select relevant features.
- 1 January 2019
- Published by Elsevier in Journal of Loss Prevention in the Process Industries
- Vol. 57, 156-163
Estimation of minimum ignition energy of explosive chemicals using gravitational search algorithm based support vector regression
- 1 January 2019
- Published by Elsevier in Journal of Loss Prevention in the Process Industries
- Vol. 57, 156-163
Estimation of minimum ignition energy of explosive chemicals using gravitational search algorithm based support vector regression