Research Publications
Permanent URI for this communityhttps://rda.sliit.lk/handle/123456789/4194
This main community comprises five sub-communities, each representing the academic contribution made by SLIIT-affiliated personnel.
Browse
13 results
Filters
Advanced Search
Filter by
Settings
Search Results
Publication Open Access Solar Hotspot Detection Using VHDL-Simulated Fixed-Point SVM: A Methodology Toward FPGA Realization(Faculty of Engineering, 2026-03) Fernando, N; Seneviratne, L; Weerasinghe, N; Rathnayake, N; Hoshino, YEarly detection of thermal hotspots in photovoltaic modules is critical to ensuring their efficiency, safety, and longevity. This study presents a complete end-to-end methodology for implementing a fixedpoint Medium Gaussian Support Vector Machine classifier using VHDL for a Field Programmable Logic Array. The approach begins with feature extraction from thermal images of healthy and defective solar panels, which focuses on MPEG-7 descriptors. The study shows that high impact for hotspot detection comes from blue chrominance contrast. A medium Gaussian SVM model is trained in MATLAB and converted to a fixed-point Q1.15 format for hardware compatibility. Key parameters, including support vectors, Lagrange multipliers, bias, and kernel scale, are extracted and verified in a custom Python environment to ensure numerical alignment with MATLAB results. The validated model is then implemented in synthesizable VHDL. It is verified using GHDL and the GNU Tool Kit waveform viewer, confirming bit-accurate hardware behaviour. Results show classification accuracy exceeding 99.3% with negligible performance loss due to quantization. The design achieves deterministic latency through an FSM-based structure and parallel feature processing for a 300-support vector and 222-feature system. This method enables low-power, real-time inference on a UAV-based edge platform, primarily focusing on drones.Item Embargo Predictive Models for Urban Air Quality Management Using AI(Institute of Electrical and Electronics Engineers Inc., 2026-03-19) Liyanage, D; Vithanage, N; Wijewardane, I; Fernando, N; Wijendra, D; Dassanayake, TAir pollution threatens public health in datascarce urban areas like Sri Lanka, where sparse monitoring hinders proactive management. We propose an integrated AI framework: hybrid SARIMAX-Temporal Fusion Transformer for multi-pollutant forecasting, ensemble spatial estimation for gap-filling, CEEMDAN-Seq2Seq for 24-hour AQI risk alerting, GRU for anomaly detection, and XAI for transparency. Validated on Central Environmental Authority data (20192024), the model achieves an 81.6% decrease in the value of the RMSE metric for ozone forecasting, as well as an R2 value of 0.9077 for high-risk AQI prediction, outperforming the baseline methods by 15-81%. The framework is modular in nature, thereby providing policymakers with the ability to use real-time dashboards, thus making Sri Lanka move from reactive to proactive management.Publication Open Access Solar Hotspot Detection Using VHDL-Simulated Fixed-Point SVM: A Methodology Toward FPGA Realization Solar Hotspot Detection via FPGASVM(Faculty of Engineering, 2025-09-09) Fernando, N; Seneviratne, L; Weerasinghe, N; Rathnayake, N; Hoshino, YThe early and accurate detection of thermal hotspots in photovoltaic modules is critical to ensure the efficiency, safety, and longevity of solar power systems. This study presents a complete end-to-end methodology for implementing a fixed-point Medium Gaussian Support Vector Machine classifier using Very High-Speed Integrated Circuit - Hardware Description Language, optimized for Field Programmable Logic Array. The approach begins with feature extraction from thermal images, focusing on MPEG-7 descriptors and blue chrominance. The SVM model is trained in MATLAB and converted into a fixed-point Q1.15 format for hardware compatibility. Key parameters, including support vectors, Lagrange multipliers, bias, and kernel scale, are extracted and verified in a custom Python environment to ensure numerical alignment with MATLAB results. The validated model is then implemented in synthesizable VHDL and verified using GHDL and GNU Tool Kit waveform viewer, confirming bit-accurate hardware behavior. Results show classification accuracy exceeding 99.3% with negligible performance loss due to quantization. The design achieves deterministic latency based on FSM structure and parallel feature processing, completing classification within 2702 clock cycles for a 300-support-vector, 222-feature system. Unlike floating-point models, this approach enables low-power, real-time inference on edge platforms such as drones.Publication Open Access Development Of An Ai-Based Model With Low Computational Complexity For Accurate Solar Energy Forecasting(Faculty of Engineering, 2025-09-09) Chandrasinghe, S; Fernando, NThis paper introduces a short-term solar energy forecasting model that is designed with a focus on low computational complexity and addresses the challenges posed by fluctuations in solar energy generation, which are significantly influenced by environmental factors. These fluctuations can lead to instability when solar power generation systems are integrated into national energy grids, creating difficulties in maintaining a balanced supply and demand. If solar energy generation can be accurately forecasted before fluctuations occur, potential issues can be identified in advance, allowing for better management of the energy system, including optimizing storage facilities when energy generation is high. Current solar energy forecasting systems face significant challenges due to their high computational complexity, which results in increased power consumption and lower accuracy. To address these issues, this study focuses on the development of an artificial intelligence (AI)-based forecasting model using an Artificial Neural Network (ANN). The goal is to reduce the computational complexity of the model while maintaining high accuracy. To achieve this, various data analysis and complexity reduction techniques, such as variable reduction, pruning, and quantization, were applied. The performance of the optimized AI model was evaluated by comparing the forecasted values to actual solar energy generation data. The results demonstrate that the proposed model successfully reduces computational complexity while maintaining a satisfactory level of accuracy. This optimization makes the model more suitable for real-time forecasting, particularly in resource-constrained environments, and provides a more efficient approach to solar energy management. The findings of this study suggest that AI-based forecasting models can play a critical role in enhancing the integration of solar energy into national grids, ensuring a more reliable and sustainable energy supply. Further research could explore additional optimization techniques and the introduction of generalization techniques to improve transferability of the model and applicability across diverse geographical regions. Additionally, focus on utilizing AI techniques that minimize computational complexity without compromising the accuracy of the model, aiming to maintain high forecasting precision while optimizing the efficiency of the system.Publication Open Access Development of an AI-Based Model with Low Computational Complexity for Accurate Wind Energy Forecasting(Faculty of Engineering, 2025-09-09) Dilshan, S; Fernando, NMost countries primarily relay on fossil fuel for electricity generation, leading to fossil fuel depletion and environmental pollution. The countries are developed technologies for renewable energy generation. The wind energy being promoted as a superior renewable energy. However, wind energy has its challengers, particularly uncertainty that can affect overall system stability. The accurate short-term forecasting of wind energy was crucial for ensuring grid stability. Both physical and AI-based models can effectively be utilized for wind energy prediction. AI-based methodologies have shown superior effectiveness, efficiency, and accuracy when compared to traditional physical models. The lightweight AI-based forecasting model was particularly significant for processing devices, enabling faster computations and substantially more cost-effective forecasting. The research utilized simulation software to develop an Artificial Neural Network (ANN) model, initially incorporating eight meteorological parameters. Four of these parameters showed weak correlations and were subsequently removed from the model. Further optimization was achieved through pruning and quantization techniques, significantly reducing computational complexity. The optimized model demonstrates a notable reduction in both training time by 92.69% and inference time by 63.83%, while maintaining accuracy with only a marginal decrease of 3.99% compared to the initial model. These improvements were achieved with minimal loss in predictive accuracy, significantly reducing computational complexity. The study concludes that the optimized ANN model is wellsuited for real-time wind power forecasting, offering a balance between accuracy and computational efficiency. This approach not only facilitates better grid management but also extends the applicability of AI-based forecasting to devices with limited processing capabilities. Future work could explore additional complexity reduction techniques and broader deployment scenarios.Publication Open Access Efficient Hotspot Detection in Solar Panels via Computer Vision and Machine Learning(Multidisciplinary Digital Publishing Institute (MDPI), 2025-07-15) Fernando, N; Seneviratne, L; Weerasinghe, N; Rathnayake, N; Hoshino, YSolar power generation is rapidly emerging within renewable energy due to its cost-effectiveness and ease of deployment. However, improper inspection and maintenance lead to significant damage from unnoticed solar hotspots. Even with inspections, factors like shadows, dust, and shading cause localized heat, mimicking hotspot behavior. This study emphasizes interpretability and efficiency, identifying key predictive features through feature-level and What-if Analysis. It evaluates model training and inference times to assess effectiveness in resource-limited environments, aiming to balance accuracy, generalization, and efficiency. Using Unmanned Aerial Vehicle (UAV)-acquired thermal images from five datasets, the study compares five Machine Learning (ML) models and five Deep Learning (DL) models. Explainable AI (XAI) techniques guide the analysis, with a particular focus on MPEG (Moving Picture Experts Group)-7 features for hotspot discrimination, supported by statistical validation. Medium Gaussian SVM achieved the best trade-off, with 99.3% accuracy and 18 s inference time. Feature analysis revealed blue chrominance as a strong early indicator of hotspot detection. Statistical validation across datasets confirmed the discriminative strength of MPEG-7 features. This study revisits the assumption that DL models are inherently superior, presenting an interpretable alternative for hotspot detection; highlighting the potential impact of domain mismatch. Model-level insight shows that both absolute and relative temperature variations are important in solar panel inspections. The relative decrease in “blueness” provides a crucial early indication of faults, especially in low-contrast thermal images where distinguishing normal warm areas from actual hotspot is difficult. Feature-level insight highlights how subtle changes in color composition, particularly reductions in blue components, serve as early indicators of developing anomalies.Publication Open Access Exploring the Determinants of Medical Insurance Expenses: A Quantile Regression Approach(Department of Mathematics and Statistics, Faculty of Humanities and Sciences, SLIIT, 2025-10-10) Rathnayake, K; Somasiri, D; Abeygunawardana, T; Nugegoda, K; Fernando, N; Guruge, M. L.; Peiris, T. S. G.Healthcare insurance costs are influenced by a combination of biological and socioeconomic factors. This study investigates how age, body mass index (BMI), gender, and discount eligibility affect medical insurance expenses in the United States, using data from 1,338 individuals. Due to the right-skewed distribution of expenses, quantile regression was applied at the 25th, 50th, and 75th percentiles, providing insights across low-, medium-, and high-cost groups. Results show that age and BMI consistently increase insurance expenses, with stronger effects among high-cost patients. Genderdifferences also emerged, with females incurring higher costs than males at certain expenditure levels. Discount eligibility significantly reduced expenses across all quantiles. In contrast, the number of children was not a significant predictor and was excluded from the final model. Compared to ordinary least squares regression, quantile regression provided a more accurate assessment of cost determinants in skewed data. These findings highlight the importance of adopting advanced modeling approachesin insurance pricing and suggest that targeted policies addressing individuals having high BMI and equitable discount programs could improve healthcare affordability and risk management.Publication Open Access The Professional Life of Counsellors During the Economic Crisis of Sri Lanka(School of Psychology. Faculty of Humanities and Sciences, SLIIT, 2025-10-10) Ekanayake, T; Fernando, NEconomic recession periods can significantly heighten risks to the population's mental health and wellbeing while posing additional challenges to health systems. Despite being central to mental health care delivery, the experiences of professionals working through such crises remain underexplored. This qualitative study seeks to illuminate those experiences by addressing two core research questions: (1) What challenges have mental health counsellors in Sri Lanka faced during the economic crisis, and (2) What motivational factors have sustained their commitment under such adverse conditions? Semistructured interviews were conducted with six counsellors from Colombo, who participated voluntarily. Using Interpretative Phenomenological Analysis (IPA), the study uncovered four superordinate themes: ‘economic adversity and emotional dynamics’, ‘coping resources and protective factors’, ‘sense of fulfilment and personal growth’, and ‘professional support and availability of services’. The findings reveal that counsellors were deeply committed to providing psychological care despite economic uncertainty, social stigma, and limitations in service infrastructure. Participants emphasized the importance of both internal and external coping mechanisms, including personal resilience, peer support, and ongoing motivation rooted in a strong sense of purpose. Notably, many counsellors reflected on their growth and sense of fulfilment derived from working with vulnerable populations, highlighting the transformative nature of their roles during crises. While the study is limited by a small sample and the interpretative nature of qualitative research, it offers valuable insights for stakeholders in the mental health sector. Recommendations include strengthening practitioner support systems, enhancing professional infrastructure, and ensuring counsellors’ voices guide future policy and planning.Publication Open Access Optimum Synchronization of Grid-connected Renewable Energy Source(Sri Lanka Institute of Information Technology, 2023-03-25) Fernando, N; Ganepola, D; Hettiwatte, SIn the last decades, wind power production has become one of the major concerns to investigate in enhancing the utilization of renewable energy resources in microgrids. Wind power can regulate environmental-friendly power generation which helps to satisfy the power demand in the grid whenever it is essential. This research has been carried out for analyzing behavior of Wind Energy Conversion System (WECS) and appropriate technique for grid synchronization in optimum way. Therefore, this includes the analysis of synchronization procedures and design an optimization technique for synchronization of WECS which is connected to the grid via an inverter. Also, it comprises existing renewable energy systems and applications on synchronization techniques. Mainly, this paper proposes an optimal synchronizing control scheme which verifies deterministic and reliable reconnection to the grid. The control scheme was designed using MATLAB Simulink software and the results were interpreted that the concept is efficient and reliable to optimize the microgrid operations.Publication Embargo Automated vehicle insurance claims processing using computer vision, natural language processing(IEEE, 2022-11-30) Fernando, N; Kumarage, A; Thiyaganathan, V; Hillary, R; Abeywardhana, LTraditional insurance claims processing systems are no match for the modern world due to the increasing population of vehicles and the resulting number of accidents. In this paper, the authors present a novel idea to automate the tedious processes in the insurance industry. The presented system consists of three main components namely, re-identify the make and model of the vehicle, identify the damaged automobile component, type, and severity, and compute an accurate repair estimate using damage component identification. Also, automate the documentation process by identifying the relevant fields in the voice input provided by the user. This ensures both the parties involved in this process will be benefited from the proposed system. Presented solutions Were designed using the aid of Artificial Intelligence techniques, mainly CNN models and Natural language processing techniques.