https://dl.ucsc.cmb.ac.lk/jspui/handle/123456789/4722 2026-03-29T23:36:25Z 2026-03-29T23:36:25Z Veivesh, K. https://dl.ucsc.cmb.ac.lk/jspui/handle/123456789/4839 2025-07-04T09:15:45Z 2024-09-27T00:00:00Z

Title: STIMULATING THE GROWTH OF A CALADIUM PLANT FOR A WEB-BASED METAVERSE ENVIRONMENT Authors: Veivesh, K. Abstract: ABSTRACT Studies on object realism in virtual environments are abundant, but tree growth stimulation in VR spaces like the Metaverse remains largely unexplored. This technology has the potential to significantly enhance the user's sense of realism within an immersive VR experience. Applications range from creating aesthetically pleasing virtual spaces to developing VR environments for scientific studies, designing realistic game scenes, and even constructing immersive virtual environments for disaster control and simulation training. This thesis presents a feasibility study on incorporating tree growth stimulation modeling into a web-based virtual environment to improve object realism. The approach focuses on a specific plant, Caladium Bicolor, and aims to model its growth stimulation using WebGL for a web-based VR environment. The evaluation involves three parts: a qualitative user test comparing the created model against an actual Caladium plant growth stimulation, a statistical analysis of data collected from the Caladium growth model, and a performance evaluation of the WebGL implementation. The results suggest that the proposed web-based approach to the metaverse that uses less computational resources, has significant potential as a foundation for a proper growth stimulation model. This thesis presents the proposed proof of concept and the evaluation results as its key contributions obtained from a simulated environment. Additionally, the thesis discusses the limitations of the created model and provides insights into aspects that require further focus when extending and implementing the approach for a real use case in an immersive virtual reality environment. Keywords: Computer Graphical Simulation, Realistic Growth Stimulation, Modeling and Simulation, Virtual Reality

2024-09-27T00:00:00Z Nirmala, M. S. https://dl.ucsc.cmb.ac.lk/jspui/handle/123456789/4838 2025-07-04T09:13:35Z 2024-10-26T00:00:00Z

Title: INTEGRATING IOT AND MACHINE LEARNING FOR EFFICIENT PEST MANAGEMENT IN GREENHOUSES Authors: Nirmala, M. S. Abstract: ABSTRACT This thesis proposes a novel design for a pest management system that increases agricultural productivity by integrating Internet of Things (IoT) technologies and Machine Learning (ML) methodologies. It describes the development of an innovative system to improve productivity in greenhouses through the use of IoT and ML. The system uses an economical and userfriendly mobile application for capturing plant images with a smartphone. These images are then processed with pre-trained TensorFlow Lite models to accurately classify pest infestations. A custom-designed tripod, equipped with Arduino, Bluetooth module, servo motor, environmental sensors, and cameras, is used to capture images and data on humidity and temperature, enabling automated and comprehensive scanning of the plantation. The data, which include pest identifications with more than 90% confidence, are synced in real time with a Firebase Realtime Database. Farmers can use the mobile application to select crops that require monitoring, enabling targeted pest management. A web application performs deep analytics, presenting insights through various charts on pest metrics, detection timelines, and the correlation of pest detections with environmental conditions and their impact on different crops. The system also provides custom pest control recommendations and real-time alerts, powered by Firebase Cloud Functions. The developed system represents a significant advancement in precision agriculture, offering a scalable and efficient solution for pest management in greenhouses or home gardens, utilizing cutting-edge IoT and ML technologies

2024-10-26T00:00:00Z Karunanayake, K. A. V. K. https://dl.ucsc.cmb.ac.lk/jspui/handle/123456789/4837 2025-07-04T07:42:12Z 2024-09-11T00:00:00Z

Title: Aspect-based Sentiment Analysis of IMDb Movie Reviews Using Machine Learning Techniques Authors: Karunanayake, K. A. V. K. Abstract: ABSTRACT Among the ever-growing field of Internet movie reviews, one cannot stress the significance of Internet movie reviews. As digital channels grow, reviews have become an increasingly potent insight into the opinions of viewers, cultivating the narrative surrounding films and impacting the choices made by consumers, studios, and directors alike. The objective of this study is to analyze and assess the sentiments connected to particular aspects or features of movies by using an Aspect-Based Sentiment Analysis (ABSA) technique using IMDb movie reviews. Using machine learning techniques, the trained model classifies movie aspects such as kid-friendliness, character development, directing, acting, story, and music, then categorizes the sentiment connected to each movie aspect. This research executes aspect-based sentiment analysis using sophisticated machine learning models such as Multinomial Naïve Bayes (MNB), Logistic Regression (LR), Support Vector Machines (SVM), KNNeighbors (KNN), Random Forest (RF), Gradient Boosting Machines (GBM) and Multilayer Perceptron (MLP) on a dataset that includes a wide range of user evaluations. The outcomes of this study offer insightful information about the advantages and disadvantages of films from the viewpoint of the audience, which helps filmmakers improve their work and empowers audiences to make wise choices. Additionally, the study looks into how different movie aspects could affect overall user fulfilment, providing insight into those aspects that have a significant impact on the opinions of the audience. This study contributes to the field of sentiment analysis while also offering filmmakers and movie enthusiasts a valuable tool to help them better comprehend the complex dynamics found in IMDb movie reviews and develop a greater appreciation for the richness of cinematic experiences.

2024-09-11T00:00:00Z Indika, P. G. N. S https://dl.ucsc.cmb.ac.lk/jspui/handle/123456789/4836 2025-07-04T07:39:03Z 2024-10-26T00:00:00Z

Title: Cardiovascular Diseases Risk In People with Mental Illnesses Authors: Indika, P. G. N. S Abstract: ABSTRACT Cardiovascular diseases (CVD) pose a significant global health burden, with various types such as coronary heart disease, stroke, peripheral arterial disease, and aortic disease contributing to mortality and morbidity worldwide. Evidence suggested a strong association between mental health disorders and CVD, wherein conditions like mood disorders, anxiety, PTSD, and chronic stress contributed to increased risk and poorer outcomes. Conversely, CVD events could also precipitate mental health disorders, creating a complex interplay between the two domains. This study aimed to explore this relationship, identify common risk factors, and develop a predictive system for assessing CVD risk among individuals with mental illnesses. Through a review of relevant literature, the study examined prevalence rates, shared risk factors, and the impact of mental health disorders on CVD management and prognosis. Utilizing machine learning techniques, a decision support web-based system was constructed to predict CVD risk factors based on patients' mental health histories. While the scope included data collection and algorithm development, the system did not offer medical consultancy services. By illuminating the nexus between mental health and CVD, this research sought to enhance risk assessment and inform preventive interventions for vulnerable populations. This study aimed to explore this relationship, identify common risk factors, and develop a predictive system for assessing CVD risk among individuals with mental illnesses. Through a review of relevant literature, the study examined prevalence rates, shared risk factors, and the impact of mental health disorders on CVD management and prognosis. Utilizing machine learning techniques, a decision support web-based system was constructed to predict CVD risk factors based on patients' mental health histories. Machine learning algorithms analyzed comprehensive datasets to identify patterns and correlations between mental health conditions and CVD risk factors. These models were trained to recognize how specific mental health disorders and their severities influence the likelihood of developing CVD.

2024-10-26T00:00:00Z