Advanced persistent threats, zero-day exploits, encrypted command-and-control traffic, and botnet campaigns continue to reduce the reliability of conventional intrusion detection systems because static detectors provide limited transparency and weak adaptation under traffic drift. This paper presents an explainable and adaptive machine learning framework that integrates a LightGBM threat detector, SHAP-based decision explanations, density-aware concept drift detection, active incremental updating, and a contextual bandit defense policy. LightGBM is adopted because its leaf-wise gradient boosting structure provides high discrimination for heterogeneous flow features while maintaining low inference latency and native feature-importance support. The framework is evaluated on CIC-IDS2017, UNSW-NB15, and ToN_IoT using stratified train-validation-test splits, leakage prevention, five-run validation, and a 48-hour Kafka-based streaming simulation. The proposed model achieved 99.1% accuracy, 98.7% F1-score, 98.4% recall, and a 0.007 false alarm rate. During streaming evaluation, 14 adaptive model updates reduced mean detection latency from 27.4 s to 11.2 s, while SHAP explanations based on DNS entropy, JA3 rarity, packet interval, and flow-duration evidence reduced analyst triage time by 23%. Comparative results show that the proposed explainable adaptive pipeline improves detection reliability, reduces false alarms, and supports auditable mitigation decisions better than static and black-box IDS baselines.
P. A. Prakash, Salath Joseph A, A. M et al.· 2026 7th International Confe...· 0 citations
Chronic diseases remain a major cause of mortality and long-term disability, and proactive identification of high-risk individuals is difficult because early clinical changes are often subtle, incomplete, and distributed across heterogeneous hospital records. This study proposes a machine-learning-based predictive analytics framework for early detection of chronic disease risk using electronic health records, laboratory profiles, demographic factors, medication history, and derived clinical indicators. The study used 48,320 adult patient records collected from four tertiary hospitals between 2014 and 2023, with leakage-controlled preprocessing, multistage missing-data handling, correlation and SHAP-assisted feature selection, and stratified model development. Logistic Regression, Random Forest, XGBoost, Multilayer Perceptron, and TabNet were evaluated against clinical risk-score baselines using AUROC, PR-AUC, F1-score, recall, calibration, Brier score, and stability under missingness and imbalance. XGBoost achieved the strongest internal performance with AUROC of 0.942, PR-AUC of 0.901, F1-score of 0.901, and Brier score of 0.108. External validation on 12,950 patients from an unseen hospital produced AUROC of 0.931, confirming limited performance degradation and improved generalizability. SHAP analysis identified creatinine, HbA1c, age, systolic blood pressure, and triglycerides as dominant contributors, supporting clinically interpretable early-risk alerts for preventive care.
P. A. Prakash, Mamtha C, Manishathri R et al.· 2026 7th International Confe...· 0 citations