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
2 results
Search Results
Publication Open Access Event Detection and Classification for Long Range Sensing of Elephants Using Seismic Signals(Institute of Electrical and Electronics Engineers Inc., 2025-09-08) Wijayaraja, J.L; Wijekoon, J.L; Wijesundara, MDetecting elephants through seismic signals is an emerging research topic aimed at developing solutions for Human-Elephant Conflict (HEC). Despite the promising results, such solutions heavily rely on manual classification of elephant footfalls, which limits their applicability for real-time classification in natural settings. To address this limitation and build on our previous work, this study introduces a classification framework targeting resource-constrained implementations, prioritizing both accuracy and computational efficiency. As part of this framework, a novel event detection technique named Contextually Customized Windowing (CCW), tailored specifically for detecting elephant footfalls, was introduced, and evaluations were conducted by comparing it with the Short-Term Average/Long-Term Average (STA/LTA) method. The yielded results show that the maximum validated detection range was 155.6 m in controlled conditions and 140 m in natural environments. Elephant footfall classification using Support Vector Machine (SVM) with a Radial Basis Function (RBF) kernel demonstrated superior performance across multiple settings, achieving an accuracy of 99% in controlled environments, 73% in natural elephant habitats, and 70% in HEC-prone human habitats, the most challenging scenario. Furthermore, feature impact analysis using explainable AI identified the number of Zero Crossings and Dynamic Time Warping (DTW) Alignment Cost as the most influential factors in all experiments, while Predominant Frequency exhibited significant influence in controlled settings.Publication Open Access Neural Network based automated hot water mixture(SLIIT, Faculty of Engineering, 2023-03-02) Firsan, F.N.M; Herath, G.M; Thilakanayake, T.DIn the present day and age, most residential spaces comprise a shower system and generally a conventional system of hot water showers. Throughout history, showering has developed as an essential need in a person’s life. Nevertheless, a typical hot water shower system comprises delays in hot water mixing and usually requires an average of 2 to 4 minutes to mix the cold and hot water to deliver the appropriate shower temperature. The delay in mixing provides less comfort and poor satisfaction affecting people’s lifestyles. Due to these disadvantages, a system incorporating artificial Intelligence can be utilized to enhance the performance of mixing which can offer an automated hot water mixture system with improved efficiency and effectiveness. Recently, significant research has been focused on utilizing deep learning technology due to its multiple breakthroughs in fabricating a broad range of automated novel applications since Neural Networks comprise the capacity to learn from data to offer efficient and accurate systems. In this research project, the hot water mixture is employed by an Artificial Neural Network model integrated with the combination of an embedded system of the proposed system of hot water mixture. Furthermore, the proposed system comprises temperature and flow sensors along with controllable flow valves. The tested system indicated acceptable accuracy between the actual and desired output flow rate and temperature.