https://dl.ucsc.cmb.ac.lk/jspui/handle/123456789/4876 2026-07-18T15:17:58Z https://dl.ucsc.cmb.ac.lk/jspui/handle/123456789/4994 Title: Identification Of Felder-Silverman Based Learning Style Through Data Driven Approach In The Context Of Game Based Learning Authors: Dharmasena, P H R Abstract: ABSTRACT In the era of intelligent educational technologies, personalized learning has become a central challenge in computer science and educational data mining. This thesis presents a machine learning-driven framework for real-time identification of individual learning styles, grounded in the Felder-Silverman Learning Style Model (FSLSM). Traditional self-assessment tools, such as the Index of Learning Styles (ILS), are limited in scalability, objectivity, and adaptability to dynamic digital environments. To address these limitations, this research proposes a data-driven alternative using behavioural interaction data collected through a custom-built, web-based educational crossword puzzle game. The system architecture integrates modular front-end interfaces, backend services, and a MongoDB data store to capture gameplay data such as clue-solving order, response latency, modality preference, and hint usage. These interactions are transformed into engineered features aligned with FSLSM dimensions and processed using domain-specific Multinomial Naïve Bayes classifiers. Classifier training is conducted with stratified 2-fold cross-validation, ensuring robustness and generalization. Experimental evaluation with a diverse participant cohort demonstrates particularly high predictive performance in the Active/Reflective domain, with F1 and precision scores exceeding 90%. Classifiers for the Sensing/Intuitive, Sequential/Global, and Visual/Verbal dimensions also performed strongly, achieving average F1-scores above 85%. Model predictions showed high agreement with ILS ground truth, validated through accuracy, Cohen’s Kappa, and AUC metrics. A real-time predictive web application was developed to demonstrate practical integration of behavioural analytics into adaptive learning platforms. In addition to technical validation, a structured user study revealed that a majority of participants found the game-based system more engaging, interactive, and preferable to traditional questionnaires. Feedback highlighted ease of use, improved motivation, and usability suggestions—underscoring the importance of user-centred design. These findings affirm the system’s potential not only as a robust learning style classifier but also as a learner-friendly interface. This research contributes to computer science by unifying supervised machine learning, behavioural feature engineering, and web-based system deployment into a scalable framework for adaptive learning. It also integrates HCI principles to bridge technical design with real-world usability, offering a holistic solution for intelligent learner modelling. 2025-10-21T00:00:00Z https://dl.ucsc.cmb.ac.lk/jspui/handle/123456789/4993 Title: STUDY THE EFFECTS OF OLFACTORY STIMULATIONS IN-RELATED TO CYBERSICKNESS IN VIRTUAL REALITY Authors: Kumara, B G S Abstract: ABSTRACT Cybersickness is common in Virtual Reality Environment (VRE), and it reduces the experience of presence. The symptoms of the Cybersickness include vomiting, eye strain, headache, sweating, nausea, vertigo, disorientation, dryness of mouth, fullness of stomach, ataxia, pallor. The manipulation of more senses improves the sense of presence and olfactory is a major concern. Olfactory can be categorized into several groups and the study of effects on those olfactory categories towards the reduction of Cybersickness benefit the users of VR system to experience the improved sense of presence. This study aims to identify the factors of multiple scents and their effects towards Cybersickness. This study is focused to analyze the effects of multiple scent in related to the Cybersickness and find the limitations in use of olfactory in the VR and impact of multiple olfactory scents when they used individual and combinational. Three categories: pleasant, unpleasant and neutral are used in this study and the neutral as the baseline. Neutral scent as the baseline the study shows that the VR application introduces noticeable cybersickness from very low SSQ from 3 to significantly to about 16. Qualitative analysis demonstrates the presence enhanced under the pleasant scent while the unpleasant scent results discomfort. Moderate sickness had resulted after exposing user to VR for 5 mins without scent, which is taken as the baseline in this study 2025-11-13T00:00:00Z https://dl.ucsc.cmb.ac.lk/jspui/handle/123456789/4992 Title: Optimizing Molecular Communication Protocols through Simulated Emission and Detection Authors: Thulasigaran, S Abstract: Abstract Molecular communication offers a promising alternative to traditional electromagnetic systems, particularly in biological and constrained environments where conventional signals fail. This research presents the design, simulation, and evaluation of a molecular communication protocol using an open source simulator tailored for reaction diffusion systems. The study aimed to optimize modulation, encoding, and error-handling strategies to ensure reliable data transmission over various distances and time scales. The simulation environment was first validated against real-world experimental results, confirming that molecule arrival trends in simulation closely reflected physical diffusion behavior. Three modulation schemes direct bit mapping on-off keying, manchester encoded on-off keying, and molecule shift keying were evaluated across different set of communication ranges. Molecule shift keying consistently demonstrated the lowest bit error rates due to its use of distinct molecule types, while Manchester encoding improved bit detection in moderately noisy settings at the cost of reduced data rate.A global fixed-threshold decoding mechanism was implemented to detect bit sequences from molecule count data. For error correction, Hamming and Reed-Solomon codes were integrated and tested. Hamming performed well for single-bit errors under low noise, while Reed-Solomon codes showed potential for more complex scenarios, although it required longer bit sequences for optimal performance. The study also demonstrated the feasibility of multi-receiver communication, where distinct bit streams were decoded using molecule type differentiation. Overall, the findings contribute a practical framework for developing adaptable and optimized molecular communication systems, with clear directions for future advancement. Its novelty lies in showing how simulation driven techniques can effectively model real world behavior for optimizing molecular communication protocols under varying conditions. 2025-06-01T00:00:00Z