http://dlib.iit.ac.lk/xmlui/handle/123456789/2358 2026-04-21T07:20:24Z http://dlib.iit.ac.lk/xmlui/handle/123456789/2623 AllyArc: An Integrated Approach to Special Education using Large Language Models and Human-Centric Reinforcement Learning Fahim, Zainab "This research study aims to investigate and identify effective strategies and tools for tracking and documenting the progress of autistic students in traditional inclusive classroom settings. The primary objective of the study is to address the challenges faced by educators in terms of enhancing the social, creative, and communication skills of autistic students. A mixed-methods approach was employed, including literature review, case studies, interviews, and surveys, to gather comprehensive data on the most pressing challenges faced by educators in teaching autistic students. This approach enabled the research team to gain a deeper understanding of the situation and identify the key areas of concern. Subsequently, a variety of research, design, development, and evaluation methodologies were implemented to filter the most efficient solutions. These solutions were developed and implemented with the goal of supporting educators in their efforts to enhance the social, creative, and communication skills of autistic students. Furthermore, the study explores the potential of assistive technologies, such as conversational AI, AI art generators, NLP techniques, and transformer-based language models, to support the language and communication development of 7-12-year-old autistic children. These solutions are developed to improve the classroom experience for the students and teachers alike. The findings of this study furnish insights on ways to systematically monitor and document the progress of autistic students and bolster their language and communication skills through assistive technologies in traditional classroom settings, thus bridging the gap in current research in this area. Keywords: Autism, Inclusive Education, Teaching, Assistive Technology, Social, Creative, Communication Skills, Language and Communication development, conversational AI, AI art generator, NLP, Transformer-based Language model" 2024-01-01T00:00:00Z http://dlib.iit.ac.lk/xmlui/handle/123456789/2622 Skin Pimple Detection and Classification using Machine Learning Wickramasinghe, Yuwani The prevalence of skin diseases globally necessitates advancements in diagnostic methodologies. This project introduces a Skin Disease Detection and Classification System employing machine learning to enhance accuracy and efficiency in identifying various skin conditions. Utilizing a robust dataset of dermatological images labelled by medical professionals, we've trained a convolutional neural network (CNN) to discern patterns and markers indicative of specific diseases. The system offers a user-friendly interface for image uploads, processes the data using the trained model, and provides immediate classification results. By bridging cutting-edge technology with clinical expertise, this system stands to significantly aid early detection, potentially improving treatment outcomes and patient care in dermatology. 2024-01-01T00:00:00Z http://dlib.iit.ac.lk/xmlui/handle/123456789/2621 Classified hate speech detection in Sinhala tweets Baddegama Geeganage, Youjith Deelake "This research explores the use of Natural Language Processing (NLP) and deep learning techniques for hate speech detection in Sinhala tweets with a specific classification. With the increasing prevalence of digital platforms offer potential individuals/groups to use hate speech in them and spread toxicity. This novel approach tries to counter that with the use of 7 Long Short-Term Memory networks. Due to the scarcity of proper datasets the author created data sets manually in order to train all the LSTM models. Each model used a binary classification to identify the specific form of hate speech. An accuracy and F1 score of 90% was achieved by one model which was the highest rated one. This study computed a solution to find classified hate speech in Sinhala text." 2024-01-01T00:00:00Z http://dlib.iit.ac.lk/xmlui/handle/123456789/2620 HealthSmart: Calorie Deficit Prediction and Meal Recommendation Rangodage, Yatheesha "One of the biggest challenges in the field of personalized health management is extracting biometric data from face images. In order to solve this issue, a comprehensive system that analyzes facial features and extracts pertinent biometric data using computer vision and machine learning techniques is being developed. With the help of facial image analysis, the system seeks to precisely predict variables like height, weight, age, and gender, enabling customized health interventions and meal planning techniques. Biometric data extraction from face images is one of the major problems in the field of personalized health management. A comprehensive system that uses computer vision and machine learning techniques to analyze facial features and extract relevant biometric data is being developed as a solution to this problem. The technology uses facial image analysis to accurately predict variables such as height, weight, age, and gender, allowing for personalized health interventions and meal planning strategies. Using facial images as a rich source of biometric data, this project offers a novel approach to personalized health management through the integration of computer vision, machine learning, and data science methodologies. The created system has the potential to enable people to make knowledgeable decisions about their diet and overall health, leading to increased longevity and well-being." 2024-01-01T00:00:00Z