http://drr.vau.ac.lk/handle/123456789/636 Sun, 05 Apr 2026 20:10:20 GMT 2026-04-05T20:10:20Z http://drr.vau.ac.lk/handle/123456789/677 Underwater Rover using IoT to Track Objects and Organisms under the Water Thivaharan, S.; Suparoopan, S.; Gopy Prasath, S.; Sanoj, S.; Dinojen, T.; Amrithaa, P.; Lojenaa, N.; Kartheeswaran, T. Since the underwater world is so complicated, monitoring the underwater has always been challenging. A successful underwater robotic technology could aid the discovery of many hidden insights. This may also facilitate the convenient unmanned observation of underwater obstacles, facilities like the underside of bridge pillars, and other installations like monitoring devices and marine cables. An underwater rover is constructed with motors and actuators and aimed to be outfitted with a camera to capture real-time images in a predefined interval, which are then transmitted to the base station for further processing. The base station will be furnished with sophisticated software that can identify unexpected alterations in relayed images. The planned rover has been tested for 3 hours at a speed of 0.3ms1 and up to 6 feet under the water using a Radio Frequency (RF) remote control. The rover may be upgraded with cutting-edge parts in the future to explore deeper underwater and run for longer periods. Tue, 04 Oct 2022 00:00:00 GMT http://drr.vau.ac.lk/handle/123456789/677 2022-10-04T00:00:00Z http://drr.vau.ac.lk/handle/123456789/676 THE EFFECT OF FEATURE SELECTION TECHNIQUES ON THE ACCURACY OF HEART DISEASE PREDICTION USING MACHINE LEARNING Lojana, J. Artificial intelligence has recently had a significant impact, particularly on the healthcare sector. The use of machine learning has made it possible to predict a number of serious diseases that are now difficult to identify in the medical industry. In this study, the Heart Attack Analysis Prediction Dataset was considered for testing. This dataset was obtained from the Kaggle. The dataset contains 14 features and 303 patient records. To find the best classification algorithm with the highest accuracy, seven feature selection algorithms and eight classification algorithms were used. Simple logistic and Logistic Model Tree classification algorithms were found to be the best classification algorithms for the heart attack analysis and prediction dataset with 85.1485% accuracy. The accuracy of the classification was impacted with the number of features selected. Tue, 04 Oct 2022 00:00:00 GMT http://drr.vau.ac.lk/handle/123456789/676 2022-10-04T00:00:00Z http://drr.vau.ac.lk/handle/123456789/675 SECURE LIGHTWEIGHT NFV ARCHITECTURE ANALYSIS FOR IOT EDGE COMPUTING Raveenthiran, S. The IoT is a massive trend within an industry. Its exponential expansion in cloud computing creates new problems. NFV has solutions enabling service providers to scale the networks, integrate intelligence into those networks, and figure out how to monetize all these IoT devices. New threats and concerns about security breaches in the network are multilayered and dynamic. It’s no longer about the transport layer, and it’s about delivering services to users profitably. As a result, service providers are looking at NFV to help them build services, customize them, spin them up faster, and deliver a broader array of services to users. Due to the low processing capability of IoT devices, offering a lightweight NFV architecture for Edge Cloud Computing in IoT is critical for mitigating cyber assaults in this developing cyber domain Tue, 04 Oct 2022 00:00:00 GMT http://drr.vau.ac.lk/handle/123456789/675 2022-10-04T00:00:00Z http://drr.vau.ac.lk/handle/123456789/674 QUALITY PREDICTION OF WATERMELON USING RANKING FEATURE SELECTION METHODS AND MACHINE LEARNING ALGORITHMS Pirunthavi, W.; Sharnitha, T.; Mayuran, P. This study was performed on the aim of detecting the quality of the watermelon with eight features; sound, color, root, belly button, texture, sugar rate, density, and touch which were obtained from the Kaggle website. Two ranking feature selection methods; ReliefF Ranking Filter and Information Gain Ranking Filter, and six machine learning algorithms; Decision Table (DT), J48 Tree (J48), Na¨ıve Bayes (NB), Support Vector Machine (SVM), Multi-Layer Perceptron (MLP), and Random Forest (RF) accordingly have been employed for the Feature Selection and Classification Model (FS-CM) to predict the quality of this fruit. Evaluation process has been conducted with five features which were selected under Information Gain Ranking filter. The metric Accuracy and ROC area were used for the evaluation and hence, MLP with IG was selected as the best model with the highest accuracy of 87.0813 detect the quality of the watermelon. Tue, 04 Oct 2022 00:00:00 GMT http://drr.vau.ac.lk/handle/123456789/674 2022-10-04T00:00:00Z