Browsing by Author "Subasinghe, S"

Now showing 1 - 3 of 3

Embargo
Geo-graphical Distribution and Morphological Characterization of Terminalia catappa L. (Tropical Almond) in the Galle District, Sri Lanka
(Faculty of Humanities and Sciences,SLIIT, 2021-09-25) Ketipearachchi, K.G; Subasinghe, S; Vidanapathirana, N.P; Silva, T. D
Morphological variations occur in phenotype-based on environmental conditions. This research aimed to study the variations in morphological characters of Terminalia catappa L. plants found in different geographical locations in Galle District. The data was collected from 70 individual plants and sampling sites were identified through the snowball sampling technique based on referrals named by the primary contacts. The study found that the T. catappa plants varied in height from 8.0 - 40.0 m with irregular or spreading canopy. Bark colour had four colours and the diameter at breast height varied from 10 - 57 cm. The immature leaves were light green in colour and covered with brown hairs. The leaves were obovate with mucronate or obtuse tips and auriculate or subcordate at the base. The inflorescence length varied from 6.0- 30.0 cm and flowers were white, greenish white or cream in colour and 0.5- 1.1 cm in length and 0.2- 0.6 cm in width. The fruit varied in length and in width. Fruits were ovoid to ovate in shape and rarely rounded, green when immature and yellow or bright red when ripe. The ripe fruit weight varied from 8-35.5 g. The seed weight varied from 0.4-1.5 g.
Embargo
Optimizing LLMs for Context-Sensitive Text Summarization: Insights from PLOS and SciSummNet
(Institute of Electrical and Electronics Engineers Inc., 2025-12-09) Nawarathne U.M.M.P.K; Subasinghe, S; Rathnayake, T; Sumathipala, P
Text summarization is an important task in natural language processing (NLP), as it allows vital information to be extracted from large amounts of textual input. This work investigates the efficacy of fine tuning large language models (LLMs) for summarization tasks by comparing their performance to that of untuned alternatives. Using the PLOS dataset consisted of biomedical papers and SciSummNet dataset consisted of computing linguistics related scientific papers, LLM models such as Falconsai-T5 text summarization, T5-small, Bart and Bart-large-CNN were tested using ROUGE, BLEU, and METEOR metrics to measure their summarization abilities. The results show that fine-tuning improves model performance significantly across the evaluation metrics. Fine tuned models performed well on the SciSummNet dataset, with Bart-tuned model getting the highest scores across multiple measures, demonstrating the efficacy of targeted adaptation where the obtained results for ROUGE-1-0.6808, ROUGE-2 0.6487, BLEU - 0.4163, and METEOR - 0.5083. The analysis underscores the importance of aligning model architectures and datasets to achieve optimal results. The structured biomedical content of the PLOS dataset highlighted the vital necessity of semantic preservation, as evidenced by specially the higher METEOR scores achieved by fine tuned models. The SciSummNet dataset, which focuses on computing and linguistic publications, demonstrated the ability of the models to navigate abstract concepts and complex technical vocabulary. This study demonstrates the transformative power of fine-tuning in customizing LLMs resulting in significant increases in summarization accuracy.
Embargo
Unveiling EEG Emotional Patterns during Interactive Engagement Activities: A Performance Comparison of Machine Learning Models
(Institute of Electrical and Electronics Engineers Inc., 2025-12-09) Rathnayake, T; Subasinghe, S; Nawarathne, M; Sumathipala, P
This paper presents a comparative evaluation of machine learning and deep learning models for emotion recognition from electroencephalography (EEG) signals recorded during interactive engagement activities. EEG data were collected using a Muse headband as participants performed engagement activities designed to elicit five emotions: Afraid, Happy, Calm, Neutral, and Sensitive. After preprocessing and feature extraction, eight machine learning and deep learning models were trained. Based on the experiment, Random Forest emerged as the best-performing classifier, achieving ~95.6% accuracy with balanced precision-recall, while gradient boosting and SVM also shown comparative results. The models demonstrated potential for real-time streaming despite slightly lower accuracy, highlighting scalability with larger datasets. These findings demonstrate the feasibility of consumer-grade EEG devices, enhanced with multimodal features, for robust emotion recognition in realistic engagement activities. The results underscore the effectiveness of multimodal fusion and engagement-based design, confirming that lightweight EEG systems can support practical, real-time affective computing applications in education, adaptive interfaces, and mental well-being monitoring.