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

2021 - 20254

Advanced Search

Filter by

Settings

Subject: search.filters.subject.Artificial Intelligence (AI)

Search Results

Now showing 1 - 4 of 4
  • Thumbnail Image
    ItemEmbargo
    A Dual-Branch CNN and Metadata Analysis Approach for Robust Image Tampering Detection
    (Institute of Electrical and Electronics Engineers Inc., 2025) Zakey, A; Bawantha, D; Shehara, D; Hasara, N; Abeywardena, K.Y; Fernando, H
    Image tampering has become a widespread issue due to the availability of advanced tools such as Photoshop, GIMP, and AI-powered technologies like Generative Adversarial Networks (GANs). These advancements have made it easier to create deceptive images, undermining their reliability and fueling misinformation. To address this growing problem, we propose a hybrid approach for image forgery detection, combining deep learning with traditional forensic techniques. Our study integrates a dual-branch Convolutional Neural Network (CNN) with handcrafted features derived from Error Level Analysis (ELA), noise residuals from the Spatial Rich Model, and metadata analysis to enhance detection capabilities. Metadata analysis plays a crucial role in identifying inconsistencies in image properties such as timestamps, geotags, and camera details, which often accompany tampered images. The CASIA dataset, a publicly available benchmark for tampered images, was used to train and evaluate the proposed model. After 30 epochs of training, the hybrid method achieved an accuracy of 95%, demonstrating its effectiveness in distinguishing between authentic and tampered images. This research highlights the advantages of combining deep learning models with traditional feature extraction methods and metadata analysis, offering a robust solution for detecting manipulated images. Our findings contribute to advancing image forensics by improving detection accuracy, even in cases involving sophisticated tampering methods driven by AI.
  • Thumbnail Image
    PublicationEmbargo
    Exploring the Usage of AI Tools in Education: Insights from Gen Z Undergraduates in Sri Lanka
    (University of Nigeria Department of Mass Communication, 2025-06-02) Nishshanka, N; Karunarathna, N; Dayapathirana, N; Karunarathna, R. V; Hewage, H. K; Anthony, P
    Background: This study investigates the patterns of use and adoption of AI tools in Sri Lanka, with a special emphasis on Generation Z undergraduates who will enter the industry next. As AI is an emerging technology, how this generation interacts with and enriches knowledge through AI tools becomes a vital area of concern. Objective: To identify key subjective factors influencing the adoption and usage of AI tools in education among Gen Z undergraduates in Sri Lanka. Methodology: This study employs qualitative research methods, specifically semi-structured interviews, to gather insights from 18 university students across various disciplines. Thematic analysis was used to identify recurring themes related to undergraduates' subjective experiences, benefits received, and attitudes, for which MAXQDA is used as the analytical software. Results: The findings demonstrate four key subjective factors that influence adoption and usage, such as academic work, awareness and adoption, challenges and risk, and helpful and supportive factors. The frequently used AI tool in Sri Lanka was noted as ChatGPT, which showed a high usage pattern in the analysis. Conclusion: Understanding the usage patterns and adoption factors helps the community use AI tools effectively, as it makes them aware of the risks and helpful factors. Also, the facilities that aid in adopting these AI tools could elevate the efficiency of their usage by making many students, future undergraduates, AI developers, and educational institutions aware of its benefits. Unique Contribution: This research provides insights for future research by helping to understand the usage of emerging AI tools among Gen Z undergraduates in a developing country like Sri Lanka. The findings can be applied to understanding different generations and emerging generations, such as Generation Alpha.
  • Thumbnail Image
    PublicationOpen Access
    Adaptive Multi-model Machine-Learning and AI Systems for Strengthening the Emotional Well-being of Children with Trisomy 21
    (SLIIT City UNI, 2025-07-08) Balasuriya, M.I.D.C.; Ellepola, N.
    This research study demonstrates a web application designed to strengthen children's cognitive skills and emotional well-being with Trisomy 21, utilizing interactive and tailored tools. Trisomy 21 is a chromosomal anomaly caused by an extra copy of the 21st chromosome, which affects a child's cognitive development. Despite the technological evolution, a significant gap persists in accessibility and multimodal approaches that meet the unique needs of children with Trisomy 21. The main objective of the research study was to develop a multi-model web-based application, “Mockley kids,” customized for children with Trisomy 21 that helps to enhance their cognitive skills and emotional wellbeing. The developed system integrated an artificial intelligence (AI) powered voice assistance to enhance communication, and learning, an emotion-based music recommender to enhance emotional well-being and provide a calm and uplifting environment, a text-based bot to enhance literacy skills and communication, and interactive games “Who am I?”, “Tic-tac-toe”, “Simon-says” to increase attention span, decision making, which are tailored to enhance their cognitive skills and emotional well-being. The development and implementation of this project follows a structured process aligned with Agile project methodology. To evaluate the “Mockley kids” system’s impact on children with Trisomy 21, 16 children who were diagnosed with Trisomy 21 engaged with the system for 20 minutes for a week, under the supervision of 8 professionals, including 3 speech therapists, 3 occupational therapists, and 2 educators. Overall results show that the children were excited to integrate with the system and enjoyed the system. Both the professionals and the parents stated that they had evident noticeable improvements in cognitive abilities, including enhanced communication, memory recall, enhanced attention span, and improvements in emotional well-being.
  • Thumbnail Image
    PublicationEmbargo
    ASD Screening for Toddlers via Physical Interpretation through Advanced AI
    (2021 3rd International Conference on Advancements in Computing (ICAC), SLIIT, 2021-12-09) Jayasekera, D.; Alwis, H.; Dissanayaka, H.; Mudalinayake, R.; Piyawardana, V.; Pulasinghe, K.
    Autism Spectrum Disorders (ASD) are generally causing challenges for significant communication, social interaction, and behavioral patterns to elderly people and children. Providing early treatments can make a huge advancement in the lives of children. Meanwhile, there is a limited number of systems to screen and identify ASD children. This research project is about developing a set of tools bonding together to one system called “AI - Bot Simon” to screen kids with ASD by filling the gap. In the system development process mainly, Audio, Facial expressions, Gestures, and the Gates of a targeted group of children are considered for screening. Since the target group is 6 months to 4 years, they are in early language development age. On the technical side of view Machine Learning (ML) and Deep Learning (DL) with Neural Networks (NN) are used for advanced screening and monitoring for automation of the process. In the last step of the development, all the outputs or information gathered from each tool or model, processed, analyzed, and provided to the users of the system by an Artificial Intelligence (AI) bot implemented with a web application and a mobile application whether children are suffering from ASD or not.