Recent research:
Across multiple publications, the researcher advances AI and data-driven methods to tackle real-world problems in healthcare, education, transportation, cybersecurity, and social governance. The work frequently combines robust data preparation with advanced machine learning and ensemble/probabilistic modeling to improve predictive accuracy, interpretability, and decision support. Notable threads include fraud detection in medical claims with scalable hybrid ensembles; multi-label chest X-ray classification using pretrained CNNs; diabetes risk modeling with gradient boosting, random forests, and extensive algorithm benchmarking; EEG/EOG-based fatigue detection with explainable AI to identify physiological fatigue markers; clustering and recommender system enhancements via Bayesian NMF and dimensionality reduction; education analytics addressing employability, student success, stressors, and data-driven faculty/organizational insights; OSINT privacy and data protection considerations; and data analytics strategy for business decision-making with emphasis on data quality and organizational readiness. Collectively, these studies demonstrate a methodological emphasis on preprocessing, model selection, explainability (SHAP/LIME), and evaluation on real datasets, with impact spanning improved diagnostic support, safer roadways, informed policy, and evidence-based educational practices.

Key Topics:

• Artificial Intelligence, Machine Learning & Data Science
• Education, Pedagogy, Teacher Training & Inclusion
• Healthcare, Clinical Epidemiology & Public Health
• Optimization, Operations Research & Decision Support
• Cybersecurity, Privacy, Trust & Blockchain
• Educational Technology, Gamification, XR & Learning Analytics
• Research Methods, Measurement, Bibliometrics & Academic Practice
• Sensor, Instrumentation & Measurement Systems
• Transportation, Mobility, Vehicles & Emissions
• Governance, Law, Policy, Ethics & Regulation