Research Publications

Permanent URI for this communityhttps://rda.sliit.lk/handle/123456789/4194

This main community comprises five sub-communities, each representing the academic contribution made by SLIIT-affiliated personnel.

Browse

Filters

2020 - 20257

Advanced Search

Filter by

Settings

Subject: search.filters.subject.Convolutional Neural Network

Search Results

Now showing 1 - 7 of 7
  • Thumbnail Image
    ItemEmbargo
    An Adaptive E-Learning Platform for Individuals with Down Syndrome
    (Institute of Electrical and Electronics Engineers Inc., 2025) Sandaruwan U.V.S.; Dias A.H.J.S.S; Shamindi H.M.H; Priyawansha N.G.D.; Chandrasiri L.H.S.S; Attanayaka B.
    Children with Down Syndrome (DS) encounter varying degrees of learning disabilities within the traditional education framework, requiring personalized interventions. This paper presents Blooming Minds, an adaptive, Machine Learning (ML) driven e-learning platform designed to support the development of cognitive, linguistic, and motor skills in children with DS. Built on the VARK (Visual, Auditory, Reading/Writing, Kinematic) theory, the platform provides personalized activities using real-time feedback mechanisms. The system includes nine interactive modules that cover the above VARK theory. It uses ML algorithms, including Support Vector Machine (SVM) and Random Forest (RF) for screening, Convolutional Neural Networks (CNN) for handwriting and speech analysis, Long Short-Term Memory (LSTM) for sequence prediction, and Reinforcement Learning (RL) for adaptive difficulties. Handwritten letters and voice samples from children with DS, both domestic and international, were specifically considered as inputs for this research. Progress tracking dashboards provide visual insights for educators, parents, and caregivers, improving support and adaptability. The system achieved 91.26% accuracy in letter recognition and 88% in speech classification. This e-learning platform has been recognized as an effective solution in Sri Lanka, allowing for further correlations and investigations to assess the knowledge capacity and ability to express that knowledge in children with DS
  • Thumbnail Image
    PublicationOpen Access
    FocusBoost – A Study Aid with Adaptive Learning Techniques
    (SLIIT City UNI, 2025-07-08) Prabaharan, N; Dampalessa, D.R.C.G.K.
    FocusBoost is an AI-powered adaptive learning platform designed to support children with Attention Deficit Hyperactivity Disorder (ADHD) through personalized learning experiences. By integrating video-based learning with voice input analysis, the system uses speech processing techniques to assess a child's engagement and comprehension in real-time. Based on real-time analysis, the platform dynamically adjusts content difficulty and pace to the needs of the individual learner. In practical testing, the system demonstrated high accuracy in classifying learner engagement and comprehension, with more ADHD learners reporting improved focus and content retention. Additionally, parents have noticed positive changes in their child’s study habits and attention span through its use. The site has a performance tracking accuracy page for children, which shows their level of comprehension. This research highlights the effectiveness of AI-enhanced learning for students with brain and neurological issues and its potential to improve inclusive, sustainable education practices. The system is designed with scalability in mind, allowing for multilingual support, culturally adaptive content, and future integration with medical professionals, expanding its impact across a variety of educational and therapeutic settings.
  • Thumbnail Image
    PublicationOpen Access
    Implementation of Smart Parking System Using Image Processing
    (Sri Lanka Institute of Information Technology, 2023-03-25) Amarasooriya, P.M.D.S.; Peiris, M.P.P.L.; Herath, H.M.D.S.
    In recent years, the number of vehicles in use has shown a steady increase, leading to a clear demand for larger parking areas. However, the traditional methods for detecting occupancy of slots in smart vehicle parking areas are no longer feasible due to the high cost of sensors and the need to monitor larger areas. In response to this challenge, the present study aims to propose a cost-effective, fast, and accurate solution for updating and indicating the real-time number of free parking slots in a parking area. Specifically, the proposed solution utilizes video footage from a camera as the input device and applies the YOLO v3 object detection algorithm for image processing to detect the coordinates of both parking lots and parked vehicles separately. To train and evaluate the model, we used the PKLot database as the dataset and tested the model's performance under different weather conditions. The proposed model achieved an average performance of 88.01%, with the highest performance demonstrated on sunny days and the lowest performance recorded on rainy days.
  • Thumbnail Image
    PublicationEmbargo
    Advancing Canine Health and Care: A Multifaceted Approach using Machine Learning
    (IEEE, 2023-06-26) Wimukthi, Y; Kottegoda, H; Andaraweera, D; Palihena, P; Fernando, H; Kasthurirathnae, D
    This research paper proposes a comprehensive approach to enhance the well-being of dogs through a range of innovative technologies. Firstly, we develop an automated system for dog breed and age identification using a Convolutional Neural Network (CNN) and a transfer learning model. This system aims to provide an efficient and reliable solution for dog owners and new adopters who are interested in discovering more about their canine companions. Secondly, we propose the development of a system that uses Reinforcement Learning to generate personalized meal plans based on a variety of factors such as the dog's breed, age, weight, health status, and emotional state. The system aims to provide dog owners with a reliable and effective tool for generating personalized meal plans that will enhance their pets' overall health and well-being. Thirdly, we present a dog disease recognition application that utilizes an artificial neural network (ANN) for identifying dog diseases based on their symptoms. Lastly, we introduce a real-time remote dog monitoring system using loT devices with edge computing to detect aggressive and anxious sounds. Our system provides an accurate classification of dog sounds related to aggression and anxiety, which can help dog owners detect and respond to potential issues early on. This research aims to provide dog owners and veterinarians with a range of technologies that can help them better understand and care for their furry friends.
  • Thumbnail Image
    PublicationEmbargo
    An Enhanced Virtual Fitting Room using Deep Neural Networks
    (2020 2nd International Conference on Advancements in Computing (ICAC), SLIIT, 2020-12-10) Ileperuma, I.C.S.; Gunathilake, H.M.Y.V.; Dilshan, K.P.A.P.; Nishali, S.A.D.S.; Gamage, A.I.; Priyadarshana, Y.H.P.P.
    As the customer's experience in present fit-on rooms is considered as an essential part of the textile industry, these fit-on rooms play a huge role in the textile shops. It is quite an arduous method and generates problems like long queues, having to change clothes individually, privacy problems and wasting time. The proposed convolutional neural network-based Virtual Fit-on Room helps to prevent the above mentioned problems. This product contains a TV screen, two web cameras, and a PC. It captures the customer's body by using two web cameras and displays the customer's dressed body. The combination of CNN in Deep learning and AR processes the body detection and generates the customer's dressed object. The application uses the stereo vision concept to get body measurements. The system detects customer age, gender, face type, and skin tones which are used to recommend cloth styles to customers. Another requirement of this system is customizing styles according to the customer requirements and suggests different styles of clothes. The system achieved 99% accuracy when suggesting different styles using FFNN. Customers can choose clothes for another person who does not physically appear with the customer in the textile shop. The expected output delivers the most realistic dressed object to the customer which allows the efficient customizations for the textile products according to customer requirements. This product can highly influence the textile and fashion industry. Therefore, this product is suitable to compete with other applications in the industry.
  • Thumbnail Image
    PublicationEmbargo
    Comprehensive Analysis of Convolutional Neural Network Models for Non-Instructive Load Monitoring
    (IEEE, 2020-10-20) Herath, G. M; Thilakanayake, T. D; Liyanage, M. H; Angammana, C. J
    Non-Instructive Load Monitoring (NILM) schemes have become more popular in recent years with the availability of smart meters. It provides energy use data to utilities and per-appliance energy consumption details to end users. This study carries out a comprehensive analysis of existing Convolutional Neural Network (CNN) architectures that have been used for NILM. Nevertheless, it provides an unbiased comparison of the existing architectures thereby helping to select the best performing model for NILM applications. The commonly used CNN disaggregation models were categorized into distinctive groups based on their architectures which considered structure of the Neural Network (NN) and outputs. It considers regression-based sequence to sequence and sequence to point mapping, classification-based sequence to point hard association and soft association-based mapping. The CNN models are improved and modified to bring them onto a common platform for comparison. Thereafter, a rigorous comparison was performed using indices which included accuracy, precision, F-measure and recall. The results reveal interesting relationships between architectures, appliances and measures.
  • Thumbnail Image
    PublicationEmbargo
    Vehicle Insurance Policy Document Summarizer, AI Insurance Agent and On-The-Spot Claimer
    (IEEE, 2021-04-02) Samarasinghe, H. T. D; Herath, N. A. D. M; Dabare, H. S. S; Gamaarachchi, Y. R; Pulasinghe, K; Yapa, P
    This paper proposes an automated vehicle insurance policy summarizing application. “Explain to Me” is one such software/tool which enable you to summarize the content of documents regarding vehicle insurance policies by using the NLP, machine learning and deep learning applications. The program targets mainly insurance users and suppliers of insurance services. Due to the increase of vehicle accidents, the vehicle insurance industry has gained more popularity currently. Therefore, different insurance companies have introduced a variety of insurance policies to customers. Vehicle insurance policy documents consist lot of insurance terms that should be read with more attention. As the main objective, this system filters unnecessary data in the particular document, and finalize a summary as the output. As another major component, the application “On the spot claimer” which is never before in Sri Lankan vehicle insurance industry, is another major part of this project that works as suggesting the most relevant insurance claiming that can be claimed by the user after detection of the type of damage through mobile phone camera. Another part of this research project, the function known as the Recommender, which works along with the summarization tool, is a recommendation system with a view of recommending more favorable rules for the assertion of alternatives that exist in the corresponding, equivalent documents of other companies. Finally, in order to interact with custody concerns about how to insure an automobile, CNN, which are based on the extraction of images, are used for the implementation of the ETM system in NLP.