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
11 results
Filters
Advanced Search
Filter by
Settings
Search Results
Item Embargo Interactive Sign Language Learning System with Multimodal Emotion and Interaction Recognition Analysis(Institute of Electrical and Electronics Engineers Inc., 2026-05-21) Rupasinghe S.N; Lakshman P.A.D.K; Dilumina K.S.; Mahoshadhi K.M.; Siriwardana, S.E.R; Weerathunga IChild-centric intelligent applications increasingly require adaptive mechanisms to understand emotional engagement and provide inclusive learning experiences. However, existing systems often rely on single-modal emotion recognition or non-interactive learning approaches, limiting reliability and accessibility. This paper presents a twocomponent intelligent framework that addresses these challenges through a multimodal emotion and interaction analysis module that fuses facial emotion recognition and hand movement intensity, and a gamified sign language learning and progress-tracking module designed for deaf and mute children. The first component employs an EfficientNet-B0-based facial emotion recognition model trained on FER2013 and fine-tuned using CK+, achieving 96.9% validation accuracy, combined with motion-based hand interaction analysis to generate stable session-level engagement insights. The second component introduces a camera-assisted, game-based sign language learning environment with a landmark-based DNN gesture validation model achieving 97% validation accuracy, along with a parent-oriented progress dashboard. Experimental results demonstrate improved robustness in engagement detection and effective learning support through gamification. The proposed system highlights the novelty of integrating multimodal behavioral analysis with accessible, child-friendly learning mechanisms suitable for real-time environments.Publication Open Access Evaluating the Role of Gamification on AI Technology tools for addressing Post-Traumatic Stress Disorders(Faculty of Engineering, 2025-09-09) Withanage, R.PThe VERA AI platform offers an innovative, AI-driven neuro-engineering approach to delivering scalable, trauma-informed interventions for Post-Traumatic Stress Disorder (PTSD) among ex- combatants and internally displaced persons (IDPs) in post-conflict Sri Lanka. By combining CBT, DBT, mindfulness, and gamification within a secure, GDPR-compliant ecosystem, it aligns with Disarmament, Demobilisation, and Reintegration (DDR) objectives, supporting both individual recovery and community reintegration.Integrating neuro-sensing technologies such as EEG and HRV with machine-learning models enables personalised, real-time therapy, while policy applications include strengthening DDR programme evaluation and informing national mental health strategies. Ethical deployment emphasising privacy, informed consent, and cultural sensitivity remains central. VERA AI demonstrates how gamified, AI-enabled neuro-engineering can provide effective, cost- efficient, and user-centred psychosocial rehabilitation, empowering individuals in Sri Lanka and other post-conflict settings to rebuild their lives and contribute to sustainable peace.Item Embargo CodeHarbor: A Code Analysis Tool(Springer Science and Business Media Deutschland GmbH, 2026) Dewmin T.Y; Kodithuwakku Y.S.; Dayananda I.H.M.B.L; Fernando K.R.A.W; De Silva D.I; Rathnayake S.As software systems grow more complex, developers face increasing challenges in maintaining and evolving codebases, often resulting in higher costs and longer development cycles. To address these issues, this study presents CodeHarbor, an intelligent tool that integrates machine learning with code analysis to simplify complex code segments. CodeHarbor calculates complexity metrics and offers personalized, context-aware suggestions for improving code quality. By automating code reviews, detecting anomalies, and recommending optimized refactoring strategies, it enables early issue resolution and enhances maintainability. The backend leverages artificial intelligence to identify patterns, enforce coding standards, and generate actionable insights, while the intuitive frontend provides real-time feedback, visualizations, and detailed improvement summaries. CodeHarbor also highlights repetitive patterns and compliance issues, helping developers track progress and reduce manual review effort. With its seamless integration of analysis and interface, CodeHarbor streamlines development workflows and promotes sustainable, high-quality software engineering.Publication Open Access Fitness Warrior: Fitness and Nutrition Tracker with Personalized Goal Generation(SLIIT City UNI, 2025-07-08) De Mel, Y.D; Nallapperuma, P.MFitness Warrior is a comprehensive mobile fitness tracking application developed using React Native and Firebase that addresses critical limitations in existing solutions through the innovative integration of machine learning, gamification, and social features. Traditional fitness applications suffer from inaccurate step detection (with error rates exceeding 20% error rates), inefficient nutrition tracking interfaces, poor user retention (with 73% abandonment within three months), and a lack of adaptive personalization. This project uniquely implements ondevice machine learning via TensorFlow.js for privacypreserving step detection, combines TF-IDF vectorization with cosine similarity for efficient food searching, and incorporates principles of Self-Determination Theory through a cohesive social motivation framework. Development followed the Agile Scrum methodology, implementing a CNN-based model processing sensor data at 50Hz sampling rate, creating a database of 2,395 food items with optimized search algorithms, and designing gamified social features. The application achieves 95.2% real-world step counting accuracy compared to manual counting, significantly outperforming conventional threshold-based approaches (48.3% accuracy), while the calorie tracker delivers 92.7% relevant results in top-5 suggestions with 126ms search latency. Evaluation with 21 users demonstrated exceptional impact: 95.3% reported increased daily steps, 90.4% experienced greater calorie intake awareness, and 71.4% found social features strongly motivating. The application received outstanding approval with 90.5% of testers rating overall satisfaction at 8 or higher on a 10-point scale. This research successfully demonstrates how integrated, machine learning-enhanced fitness applications can meaningfully impact user health behaviours while overcoming significant limitations in existing solutions.Publication Open Access Agent-Based Gamified Learning Environments for Data Science Education(SLIIT Business School, 2023-12-14) Jayalath, N; Rajapakse, CBecause of the rapid advancement of technology and the increasing importance of the inferences that can be drawn from the big data available in organizations, modern organizations require managers and data Analysts who are capable of data-driven decision-making. But data science students need a natural environment when it comes to learning data-driven decisionmaking, especially when it comes to predictive and prescriptive analytics. Due to costs and other associated risks in a natural organisation setting, it is hard for educational institutions to teach these aspects of decision-making for data science students. Even Though gamification has been implemented in the data analysis domain in various forms, the field still requires a suitable environment to learn predictive analytics interactively for the students. Even though Researchers have identified that Gamified learning environments can improve Predictive analytics learning can be improved by 15.8%, still there is the lack of proper implementation of a suitable gamified learning environment. This research focused on identifying drawbacks of existing learning environments and whether Agent-Based Modeling can be used in modelling a suitable gamified learning environment. Therefore, an agent-based prototype model of a parameterized environment that enables data-driven decision-making in a simulated environment was modeled using Agentbased modeling, which depicts real-life donor interactions. Results suggest that fill in blanks This Agent-based model can be used as a learning environment for data analysis. Upon further modification, A game that applies this Agent-based model can be developed.Publication Embargo STEP UP: Systematically Motivating the Children with Low Psychological Maturity Level and Disabled Children using Gamification and Human Computer Interaction(IEEE, 2022-07-18) Dharmarathne, R. S. C. K; Medagedara, K. A; Madhubashinee, N. B. W. N.; Maitipe, P. T.; Sriyaratna, DChildren are the future of this world. Therefore, teaching them to have a better future is very important. Also, as the adults we have to motivate them to overcome the obstacles and challenges they face throughout their lifetime. When considering about the children, there are various types of children in our society. As examples there are children with special needs and there are children who are mentally and physically stable. Children with special needs require special attention than the other children. These kinds of children with special needs have various types of development disabilities. They are children with low psychological maturity level, autism, down syndrome, genetic disorders etc. We have proposed a system to motivate these children who are with low psychological maturity level named as ‘STEP-UP’. This system is a combination of four individual modules that have the common goal to motivate these kinds of children which were implemented using gamification, Image processing, machine learning and Human Computer Interaction. One individual module is focused on disabled children, and it will motivate those children using gamification. Another two modules are focusing on the children who are with low psychological maturity level. And that will motivate those kinds of children using gamification and HCI based technologies like Virtual Reality. The other module is a protocol to secure the data sent between the system and the database. The common goal of this overall STEP-UP system is to motivate the children with low psychological maturity level and disabled children.Publication Embargo ATHWEL: Gamification Supportive Tool for Special Educational Centers in Sri Lanka(IEEE, 2019-12-19) Kiriwaththage, P. N; Morawaka, ALearning Disability is a neurologically-based problem which involves in learning basic skills such as reading, writing and math. Intellectual Disability is characterized by below-average intelligence. Children with Intellectual Disability can do and learn new skills, but they learn them more slowly than average children of their age. Game-based learning is an effective way of getting learners actively involved in educational activities. Educating children with Intellectual Disability is a challenging process. They usually learn and progress more slowly than average children. Such children may have issues with motivation and interest in education; the use of Gamification approach becomes important as a motivational and interested affordance. A prototype desktop Gamification Supportive Tool called “ATHWELA” is proposed which operates through Assistive Technology. Assistive technology can be a device or a service that is used to increase, maintain, or improve functional capabilities of individuals with disabilities. Children with Intellectual Disability can be less interested in Mathematics, some can be not good in reading and some can be not good in writing. ATHWELA is targeting at increasing, maintaining, or improving these three points and ATHWELA can be used in special education classrooms as a tool of gratification and extrinsic motivation. Points and rewards will be presented as the motivational technique. The main objective of our research is to help children with Intellectual Disability with their primary educational skills with less effort and in an interactive way and this prototype desktop application is developed in the Sinhala language because the Sinhala is the mother-tongue of Sri Lanka. In addition, it has used Machine Learning and Image Processing techniques to improve the educational skills of children with Intellectual Disability.Publication Embargo Memory Improvement Tool for Dementia Alzheimer’s Patients(Elsevier, 2018-01-01) Weerakoon, D. S. D; Kahandawaarachchi, K. A. D. C. P; Dissanayake, J. D. S. Y; Thilakasiri, W. P. M; Shanthakumara, W. D. M. BThe Alzheimer’s disease is one of the top ten causes of death among the elderly. Studies show that there is a significant increase in deaths reported after early 1990s due to the lack of a cure in preventing the disease in modern medicine. Hence, there are numerous attempts made towards managing the progression of the disease which results in improving the wellbeing of the patient. One of the recommended methods of managing it long-term is through providing many memory related activities to the patients. With the limited amount of resources and investments, Sri Lanka is finding it difficult to manage the significant number of patients. Furthermore, not all patients get the opportunity to visit the Alzheimer’s Foundation and receive treatments. This research is a small step towards creating a computer-aided platform for Alzheimer’s patients to improve their livelihood thorough activities focusing on 4As of Alzheimer’s (long-term memory, short-term memory, language and communication skills and fine motor skills) disease under the guidance of clinical Psychiatrists (1). The application is tested with over 75 Alzheimer’s patients under the guidance of their physicians. The comprehensive record keeping for patient condition analysis, gamification-based environment for patients and assistive tool for memory management are among the benefits of this application.Publication Embargo Technology in retail marketing and the way forward with Gamification: An exploratory study(SLIIT Business School, 2019-12-10) Alles, T.; Jayasooriya, S.The retail landscape is evolving rapidly as firms embrace innovative technologies in an attempt to stay ahead of the aggressive competition prevalent within the industry. The focus of this paper deems to be to explore technologies used by retail firms in the execution of their marketing efforts as well as the drivers and challenges in adopting Gamification for such efforts. A qualitative inductive research approach was taken whereby critical analysis of literature was followed through with in-depth interviews with marketing professionals in the moderntrade retail industry. The interviewees were selected through judgmental purposive sampling technique and the thematic analysis was conducted in generating insights. Findings show that the retail firms currently employ several technologies in line with those discussed in existing literature such as loyalty card systems, digital signage, VR technologies, online Gamification amidst others in carrying out their marketing efforts. Mobile Instant Messaging & Autonomous shopping carts are to be employed in the near future while firms are receptive to experiment on Hologram technologies and In-store Gamification. Furthermore, key drivers that propel firms to implement novel technology like Gamification are; to generate customer insights, enhance customer experience and achieve marketing related KPI targets. Conversely, inadequate technology infrastructure, justifying focus on a niche crowd of tech-oriented customers and slow ROI pose as challenges in the process of Gamification adoption. The study offers theoretical contribution to the knowledge gap in this domain especially in the Sri Lankan context and while it is limited to modern-trade retailers future research can be extended to other formats of retail.Publication Embargo Amazon Biology: An Augmented Reality-Based E-Book for Biology(2020 2nd International Conference on Advancements in Computing (ICAC), SLIIT, 2020-12-10) Somakeerthi, D.C.S.; De Silva, G. W. I.U.; De Silva, L.D.T.; Chandrasiri, S.; Joseph, J.K.Biology is a conventionally struggling subject to learn from both high school and college students due to its complexity. Students are used to learning Biology from various methods such as reading textbooks, attending lectures. Biology is based on more practical and most of the schools not available proper lab facilities, anatomic structures, and resources to learn the module easily. And teachers who teach the module face a considerable number of issues when delivering the concepts. Some of them face unavailability of teaching aids, time-consuming, lack of lecture materials. Apart from that, the nature of the topic and the teaching style are the main learning problems faced by the students. Therefore, students do not learn the concepts perfectly and interest in the module has been reduced day by day. To overcome these difficulties “Amazon Biology,” mobile application has been proposed. The application consists of three major modules including image processing for the plant classification, augmented reality for human anatomy, and gamification. The proposed application has used the techniques in augmented reality and game-based learning. The developed system delivers nearly 85% level of accuracy and provides more advantages for students. They are effective and efficient learning, teaching via visual materials, and practical.