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 - 20255

Advanced Search

Filter by

Settings

Subject: search.filters.subject.AI

Search Results

Now showing 1 - 5 of 5
  • Thumbnail Image
    PublicationOpen Access
    Development of an AI-Based Model with Low Computational Complexity for Accurate Load Demand Forecasting
    (Faculty of Engineering, 2025-09-09) Hettiarachchi, D.R.A.; Fiernando, N
    This research addresses the challenge of short-term load demand forecasting in microgrids, where renewable energy unpredictability destabilizes power systems. Current forecasting models often suffer from high computational complexity, resulting in increased power consumption and reduced real-time applicability. To overcome these limitations, this study develops and optimizes an Artificial Neural Network (ANN)-based shortterm forecasting model with significantly reduced computational demands. In this study, a model was constructed utilizing historical operational data from a microgrid system. To optimize the computational efficiency of the model, various techniques were applied to reduce its complexity. The model’s performance was systematically evaluated using appropriate performance metrics. The experimental results demonstrate that the proposed approach significantly decreases the computational complexity of the final model, while preserving an acceptable level of accuracy when compared to the original, unoptimized model. The practical implications of this research include enabling real-time demand forecasting on resource-constrained microgrid controllers and edge devices, facilitating more efficient energy management in sustainable power systems. Future work will focus on enhancing the model's generalization capabilities by incorporating additional geographical and climatic factors, enabling accurate demand forecasting across diverse microgrid environments beyond the specific conditions of the initial dataset.
  • Thumbnail Image
    PublicationOpen Access
    Keynote 02: Triple Play: AI, MV, and HTC
    (Faculty of Engineering, 2025-09-09) Koucheryavy, A.
    At the beginning of the 21st century, with the convergence of communication networks, the term Triple Play, which included voice, video, and data services, became a popular term for the provision of services by next-generation networks. At that time, this approach meant the unity of the convergent network and the universality of the services provided to the user.Now, about a quarter of a century after that time, the development of communication networks is taking place in the direction of creating various kinds of universes based on artificial intelligence technologies. Even urban universes have appeared as a development of smart cities. At the same time, the design Artificial Intelligence (AI) plus Metaverse (MV) was considered quite popular for some time. At the global standardization symposium in New Delhi in October 2024 during WTSA-24, it was proposed to supplement this dual with a holographic type of communications (HTC). This was necessary because there is a fairly widespread opinion that society will become holographic by 2030. This proposal was made by the ITUT Focus Group Leader Richard Lee in 2018 at the first meeting of the focus group. Considering the great potential of holographic universes and the development of technologies in the field of providing holographic telepresence services, it seems useful to use the triune design of AI + MV + HTC at present. The report further discusses the development of artificial intelligence in the field of communication networks, the transformation of metauniverses into holographic network universes (HolNetVerse), work in the field of creating various terminals for holographic interactions and implementing telepresence services, the creation of holographic universities, the creation of holographic cities using the example of St. Petersburg, the development of a telepresence suit with parametric feedback, the capabilities of such telepresence suits together with a network universe for remote rehabilitation of patients using the example of recovery for children with upper limb injuries. All these applications show how effective the use of the new Triple Play AI + MV + HTC can be.
  • Thumbnail Image
    ItemEmbargo
    AI-Driven Vehicle Valuation and Market Trend Analysis for Sri Lanka's Automotive Sector
    (Institute of Electrical and Electronics Engineers Inc., 2025) De Silva K.P.N.T.; Shehan H.A.; Jayawardhane A.S; Premarathne A.P.S.; Krishara, J; Wijendra, D.R
    The automotive sector in Sri Lanka faces challenges in vehicle valuation accuracy and market trend analysis due to fluctuating prices, varying vehicle conditions, and environmental concerns. This paper presents an AI-driven vehicle valuation system integrating machine learning models for automated vehicle identification, damage detection, market trend analysis, and environmental sustainability assessments. Using deep learning techniques such as Convolutional Neural Networks (CNNs) and time-series models like Long Short-Term Memory (LSTM), the system delivers accurate valuation and market trend insights. Experimental results demonstrate 9 2% accuracy in damage classification and a mean absolute error (MAE) of 5.3% in repair cost estimation, supporting informed decision-making. This research bridges gaps in valuation transparency and sustainability in emerging automotive markets.
  • Thumbnail Image
    PublicationOpen Access
    An AI-Powered Web Application for Waterfall Recognition and Eco-Tourism Enhancement in Sri Lanka: Falls Explorer
    (SLIIT City UNI, 2025-07-08) Ranasinghe, S; Jayaweera, Y
    This research presents the development of Falls Explorer Sri Lanka, a mobile-responsive web application that uses artificial intelligence for automatic waterfall recognition. The core innovation lies in applying a custom-developed convolutional neural network (CNN) to classify waterfall images based on their visual features. A custom image dataset was created by collecting and organizing photos of popular waterfalls in Sri Lanka, and the model was trained using TensorFlow. The custom CNN model achieved 92% validation accuracy after 25 epochs of training, with inference times under 1 second per prediction. The system successfully classified waterfall images across 20 different waterfall classes with precision scores ranging from 88% to 95%. Users upload a photo of a waterfall through the interface, and the system returns the predicted waterfall name along with travel details from a local JSON database. In addition to the recognition feature, the platform offers comprehensive functionalities such as displaying detailed waterfall information (name, location, description), listing nearby hotels, showing current weather forecasts for safe travel planning, hosting a community forum for users to share experiences and images, providing a carbon footprint calculator to estimate travel impact, and an interactive location search map to explore specific sites manually. This solution bridges the gap between technology and ecotourism, supporting conservation-friendly tourism by enabling travellers to appreciate natural attractions without invasive markers or infrastructure.
  • Thumbnail Image
    PublicationEmbargo
    Sinhala Conversational Interface for Appointment Management and Medical Advice
    (2020 2nd International Conference on Advancements in Computing (ICAC), SLIIT, 2020-12-10) Rajapakshe, D. D. S.; Kudawithana, K. N. B.; Uswatte, U. L. N. P.; Nishshanka, N. A. B. D.; Piyawardana, A. V. S.; Pulasinghe, K. N.
    This paper proposes an intelligent conversational user interface to assist Sinhala speaking users to make appointments with doctors and to obtain medical advices. This Sinhala Conversational Interface for Appointment Management and Medical Advice (SCI-AMMA) consists of Speech Recognition unit, Query Processing unit, Dialog Management unit, Voice Synthesizer unit, and User Information Management unit to handle user requests and maintain a meaningful dialogue. The SCI-AMMA gets the users' speech utterances and recognize the language content of it for further processing. Language content is further processed using query processing unit to identify users' intent. To fulfil the users' intent, a reply is generated from Dialogue Management Unit. This reply/answer will be delivered to the user by means of a voice synthesizer. The proposed system is successfully implemented using state of the art technology stack including Flutter, Python, Protégé and Firebase. Performance of the system is demonstrated using several sample scenarios/dialogues.