OOOlakekan Akinbosoye Okewale

Olakekan Akinbosoye Okewale

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Olakekan Akinbosoye Okewale has a total of 22 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Machine Learning for Pre-Test Malaria Diagnosis from Symptoms, Clinical Text and Speech: A PRISMA Systematic Review

    by Olalekan Akinbosoye Okewale, Olufemi S. Ojo, F. W. Ipeayeda, Segun Kazeem Fatoki, Mayowa Oyedepo Oyediran

    In the absence of microscopy and rapid tests, malaria diagnosis is presumptive in many clinics in Africa, leading to overuse of drugs and masking other causes of fever. It has been proposed, based on pre-test data (e.g., symptoms, clinical notes, patient voice), to use standard ML models as triage tools. We searched PubMed and Scopus for studies from 2010 to 2026 that trained and evaluated standard ML models on pre-test clinical data to paint a high RQ1 for malaria diagnosis or on voice or clini...

  • Open Access

    BLOCKCHAIN-BASED FRAMEWORK FOR MITIGATING QR CODE PHISHING ATTACKS IN FINANCIAL SYSTEMS

    by Olakekan Akinbosoye Okewale, Temitope Dickson Olajide, Hamid Kanyiti Salifu, Shakirat Oguntunde, Sholanke Oluwafunmbi Benedict, Segun Kazeem Fatoki, Shosanya Sideeqoh Oluwaseun, Monday Dickson Osadolor

    QR codes have become one of the most commonly used technologies during the COVID-19 pandemic in government, business, and various organizations, with significant usage in financial systems for payments, authentication, and access to digital services. QR codes are primarily used as digital links to web applications or for contactless interactions. Due to the advancing nature of technology, QR technology has developed along with various risks, one innovative instance of this risk being QR code phishing. QR code phishing attacks lead to significant and harmful consequences, including monetary loss and data breaches, affecting both individuals and organizations, particularly in banking, mobile payment systems, and online financial services. QR codes can be compromised and directed to harmful websites, causing unsuspecting individuals to end up on deceptive financial platforms. Recently studied countermeasures reveal significant shortcomings, such as dependence on trusted third parties for verification, excessive time complexity, and the failure to guarantee confidentiality, integrity, authentication, and availability concurrently within one system. Therefore, a stronger countermeasure is necessary for effectively reducing QR code phishing attacks, especially in financial environments where security and trust in transactions are vital. Thus, this research focused on creating a blockchain-based framework designed to reduce QR phishing attacks. The application developed includes a QR code generator along with a blockchain creation feature. The application safely saves created QR codes in Base64 format, along with related attributes like URLs, owner details, comments, and hash values by employing a proof-of-work system. Additional research is necessary regarding the preservation of the established blockchain within a distributed network, as this would improve real-time verification systems that can reduce QR code phishing threats in financial frameworks.


  • Open Access

    Comparative Evaluation of Multilayer Perceptron, Random Forest, and Support Vector Machine for Sepsis Classification Using Longitudinal Structured Clinical Data

    by Olalekan Okewale, Esther Oduntan, Chibuzo Benjamin Onuike, Olufemi S. Ojo, Sholanke Oluwafunmbi Benedict

    Sepsis classification from routinely collected clinical data is challenging because positive labels are uncommon, repeated observations from the same patient are correlated, and leakage-prone preprocessing can produce misleadingly high performance. This study re-evaluated multilayer perceptron (MLP), random forest (RF), and support vector machine (SVM) models using a leakage-controlled patient-level design. The source file contained 1,552,210 hourly observations from 40,336 patients; 2,932 patients (7.27%) were ever sepsis-positive. A reproducible stratified sample of 10,000 patients (382,387 hourly observations) was selected, preserving patient-level prevalence, and divided into 8,000 development and 2,000 independent hold-out patients with no patient overlap. Nine routinely available predictors were retained after a development-only missingness audit: heart rate, oxygen saturation, temperature, systolic blood pressure, mean arterial pressure, diastolic blood pressure, respiratory rate, age, and gender. Median imputation, missingness indicators, scaling, imbalance handling, hyperparameter tuning, and threshold selection were confined to development data and patient-grouped cross-validation. On the untouched hold-out cohort, RF achieved the highest ROC-AUC (0.671; 95% CI 0.635–0.706) and PR-AUC (0.041), with sensitivity 0.538 and specificity 0.716. RF significantly exceeded MLP in ROC-AUC (difference 0.0317, p=0.012), whereas RF and SVM did not differ significantly (p=0.054). Calibrated Brier scores were similar (0.0175–0.0176). Permutation importance and SHAP identified heart rate, respiratory rate, temperature, and blood-pressure measures as influential RF predictors. The models show moderate discrimination but low positive predictive value under severe class imbalance; therefore, they should be regarded as feasibility-level decision-support models requiring external, prospective, temporal, and fairness validation before clinical use.

  • Open Access

    THE CONVERGENCE OF MACHINE LEARNING AND DECENTRALIZED APPLICATIONS: A PARADIGM SHIFT IN CYBERSECURITY PROTOCOL

    by Temitope Dickson Olajide, Olakekan Akinbosoye Okewale, Tony Okori Anthony, Ginika Patricia Oguchi, Michael Oluwaseyi Aderibigbe, Chibuzo Benjamin Onuike, Collins Obiorai Ibezim, Segun Kazeem Fatoki

    The combination of machine learning (ML) with decentralized applications (dApps) signifies a major shift in the cybersecurity landscape, introducing both enhanced defensive capabilities and new categories of vulnerabilities. This paper presents an in-depth examination of this convergence, analyzing how ML techniques—including anomaly detection, behavioral analysis, and adaptive response models—can significantly strengthen the security posture of dApps. Using a systematic literature review and a design science research approach, the study demonstrates that ML enables a proactive and intelligent security framework for decentralized systems, achieving an estimated 20–35% improvement in threat detection accuracy as reported across reviewed implementations. The analysis also identifies a widened attack surface, particularly concerning data poisoning risks in federated learning, adversarial examples targeting on-chain inference models, and oracle manipulation vulnerabilities. In response, the paper proposes a multi-tiered security model incorporating privacy-preserving mechanisms, blockchain-based governance structures, and adversarial-resilient ML pipelines. While the abstract is concise and effectively captures the manuscript’s essence, it is strengthened by integrating specific evaluative insights that highlight the measurable benefits and risks of ML-enabled decentralized intelligence. The study underscores the need for security-centric design principles and offers actionable insights for developers, security professionals, and policymakers working to advance cybersecurity in intelligent, autonomous decentralized systems.

  • An ensemble statistical evaluation of medical image embedding with SqueezeNet neural network

    by Solanke Ilesanmi, Agbaegbu JonhBosco, Wilson C. Ahiara, Janet Akiode, Uchenna H. Udeani, Taiwo Olaleye, Olalekan A. Okewale

    The trio of data, technology, and man constitutes a formidable tripartite synergy towards enhancing health informatics through data science. This avails state-of-the-arts which employ tools like the interquartile range, probability density function, predictive analytics etc. the opportunity of medical data evaluation for pathology and medical diagnosis purposes. However, such evaluations are seldom carried out on medical image embedding acquired through transfer learning. This study therefore employs the SqueezeNet deep embedder on computerized tomography scan signals for feature extraction of pneumonia attributes. An ensemble statistical tool is used for the evaluation after the feature selection of significant attributes by analysis of variance. To answer research question that seeks to discover most significant data feature, experimental result returns an external data attribute as one with the most discriminative information for pneumonia detection. An interquartile range of 40000 to 240000 with a dispersed probability density function in the second quartile also indicates a positive case of pneumonia medical condition