Scopus Index Publications

Permanent URI for this communityhttps://rda.sliit.lk/handle/123456789/2162

This collection consists of all Scopus-indexed publications produced by SLIIT researchers. Scopus is recognized worldwide as a leading and reputable academic indexing database.

Browse

Filters

2025 - 20262

Advanced Search

Filter by

Settings

Has files: YesSubject: search.filters.subject.reinforcement learning

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    ItemEmbargo
    A Reinforcement Learning Approach with Human in the Loop to Explainable Insurance Risk Scoring and Intelligent Policy Portfolio Optimization
    (Institute of Electrical and Electronics Engineers, 2026-05-29) Gamage, C; Kasthuriarachchi, T; Denuwan, C; Mallawaarachchi, P; Abeywardhana, L; Nawarathne, M
    Assessing individual risk accurately and optimizing insurance portfolios in real time remain major challenges due to static actuarial tables, opaque models, and fragmented analytical pipelines. This paper proposes a two-part Explainable AI (XAI) framework addressing both issues. The first component, Artificial Intelligence-driven risk scoring with human-in-the-loop (HIL) weight adjustment, uses a Proximal Policy Optimization (PPO) agent to suggest feature-based changes to an insurer's risk-equation weights. Shapley Additive Explanations(SHAP) attributions and Generative AI reasoning make these changes interpretable, allowing human reviewers to approve modifications that are immediately applied to future customers, creating a self-improving loop. The second component, AI-driven policy optimization, leverages a PPO supported by an XGBoost expense regressor, SHAP/LIME explainability, PPO agent and a Retrieval-Augmented Generation (RAG) layer for rider assignment. Both components share a data backbone of 100,000 anonymized insurance records stored in MongoDB, enabling incremental updates without reprocessing. Experiments show the XGBoost regressor achieves Root Mean Square Error (RMSE) 0.4406 and Mean Absolute Error (MAE) 0.3600, the HIL guided agent increases average episodic reward by 10.3%, and the RAG layer reaches 91.7% rider-assignment accuracy. The framework significantly enhances predictive accuracy, interpretability, regulatory traceability, and portfolio adaptability compared to traditional actuarial and black-box approaches.
  • Thumbnail Image
    ItemEmbargo
    Intelligent Adaptive Lighting Control: Reinforcement Learning-Based Optimization for Smart Home Energy Efficiency
    (Institute of Electrical and Electronics Engineers Inc., 2025) Hewakapuge M.M; Gamage W.G.T; Surendra D.M.B.G.D; Thejan K.G.T; Rajapaksha, S; Rajendran, K
    This study introduces a novel research paper outlining a behavioral-based adaptive lighting system that aims to revolutionise smart home lighting by integrating user behavior tracking to enhance energy efficiency and user comfort. Unlike traditional motion-sensor-based lighting, the novelty of this approach is the ability to adapt dynamically to evolving user behaviors through reinforcement learning. The system utilises Wi-Fi-based positioning, GPS and accelerometer data to monitor user movements and classify different areas of the house. Users initially calibrate the home layout through a mobile application, marking room locations and lighting configurations. The system then collects movement data over time to predict optimal lighting schedules based on user routines and refines the predictions and updates lighting adjustments accordingly, minimising energy wastage while maximising user convenience. A serverless backend architecture ensures scalability, cost-effectiveness, and seamless data processing. The adaptive framework continuously refines lighting automation, responding to evolving behavioral patterns.