Scopus Index Publications

Permanent URI for this communityhttps://rda.sliit.lk/handle/123456789/2162

This collection consists of all Scopus-indexed publications produced by SLIIT researchers. Scopus is recognized worldwide as a leading and reputable academic indexing database.

Browse

Filters

2020 - 20236

Advanced Search

Filter by

Settings

Author: search.filters.author.Kasthurirathna, D

Search Results

Now showing 1 - 6 of 6
  • Thumbnail Image
    PublicationEmbargo
    "Talking Books" : A Sinhala Abstractive Text Summarization Approach for Sinhala Textbooks
    (IEEE, 2023-05-23) Rathnayake, B.R.M.S.R.B.; Manathunga, K; Kasthurirathna, D
    The ability for books to talk would be an exciting concept, and this research discussion paves the path for an identical approach. The research objectives discussed in this paper address several burning problems, solve them and adapt them to future technological enhancements from a Sri Lankan context. Burning problems include reducing printing costs for textbooks, addressing students’ health, promoting green technology, and identifying a suitable summarising approach to the native language, Sinhala resulting in students’ learning ease. Other symptoms for the betterment indicate paths taken to reduce the weight of school bags carried by students, reduce paper usage by the government on printing textbooks, and spread technological awareness to teenagers regarding e-Learning. Textbooks issued by the government will be digitized and centralized into a single system that the government officials themselves can administer. The paper discusses limited hindsight literature and proposes 2 new algorithms for abstractive and extractive summarization for Sinhala text. The 2 algorithms are compared against one another in terms of performance, efficiency, precision and accuracy. Experts in the education domain have verified the derived summary of both algorithms. The deliverable artefacts are the mobile application, a RESTful auto-summarization plugin service, and new data sets extracted to train the GPT-3 models.
  • Thumbnail Image
    PublicationEmbargo
    TRIPORA: Intelligent Machine Learning Solution for Sri Lanka Touring Access and Updates
    (IEEE, 2022-12-09) Legrand, T.R; Bandara, K.M.R.A.I; Stefania Crishani, J.A.D; Uvindu, L.W.P; Amarasena, N; Kasthurirathna, D
    Sri Lanka is one of the top tourist destinations in the world. However, tourists face various inconveniences due to the obsolescence of facilities. There are various tools designed to solve such problems. But they are scattered in different places and users have to use different tools. The biggest issue in the tourist sector is that travelers are unable to get the most out of their tours since there may be days when a large number of people visit the same location, causing the location to become overcrowded, and preventing tourists from enjoying their visit as anticipated. There are seasons when natural disasters occur, as well as human-centered crises. Also, there are situations when travelers feel helpless because they are unable to find the best tour guide for them. We developed a cost-effective, automatic, and efficient Machine Learning-based recommendation system as a result of this research. Based on past data on tourists and data received from the SLTDA, this research can provide the best trip plan with the tour guide and provide destination news alerts on regular basis. Furthermore, in order to achieve the best accuracy through the system, unique machine learning approaches were used in this study.
  • Thumbnail Image
    PublicationEmbargo
    Deep Vision-Data Mining To Find Insights and Visualization in Code Repositories
    (Institute of Electrical and Electronics Engineers, 2022-09-16) Ariyarathne, I.G.P.S; Wimalasuriya, M.K; Abesinghe, N.D.N.S; Edirisinghe, E.A.S.H.; Kodagoda, N; Kasthurirathna, D
    Deep Vision is a code mining system for analyzing and visualizing a repository's codebase so that its users may obtain a sense of the repository's insights. This system will examine codebases and support as many languages as feasible. This system visualizes the file structure, vocabulary and length change rates, comprehensibility and defect rates, etc. It is vital to have a comprehensive grasp of the codebase to manage the program's complexity by calculating multiple factors and presenting them in a descriptive and engaging dashboard to enhance the quality of the software process and the project's controllability. Improved code visualization may help improve code understandability while lowering development costs. In addition, our visualization regions and methodologies are one-of-a-kinds. To get rapid and reliable results, we will create new machine learning models and algorithms for analysis and new categories of a code repository. Our dataset for this research will be GitHub open-source code repositories
  • Thumbnail Image
    PublicationOpen Access
    2D Pose Estimation based Child Action Recognition
    (Institute of Electrical and Electronics Engineers Inc., 2022-11) Mohottala, S; Abeygunawardana, S; Samarasinghe, P; Kasthurirathna, D; Abhayaratne, C
    We present a graph convolutional network with 2D pose estimation for the first time on child action recognition task achieving on par results with LRCN on a benchmark dataset containing unconstrained environment based videos.
  • Thumbnail Image
    PublicationOpen Access
    MNet-Sim: A Multi-layered Semantic Similarity Network to Evaluate Sentence Similarity
    (2021-11) Kasthurirathna, D; Jeyaraj, M. N
    Similarity is a comparative - subjective measure that varies with the domain within which it is considered. In several NLP applications such as document classification, pattern recognition, chatbot questionanswering, sentiment analysis, etc., identifying an accurate similarity score for sentence pairs has become a crucial area of research. In the existing models that assess similarity, the limitation of effectively computing this similarity based on contextual comparisons, the localization due to the centering theory, and the lack of non-semantic textual comparisons have proven to be drawbacks. Hence, this paper presents a multi-layered semantic similarity network model built upon multiple similarity measures that render an overall sentence similarity score based on the principles of Network Science, neighboring weighted relational edges, and a proposed extended node similarity computation formula. The proposed multi-layered network model was evaluated and tested against established state-of-the-art models and is shown to have demonstrated better performance scores in assessing sentence similarity
  • Thumbnail Image
    PublicationOpen Access
    Comparative Analysis of Deep Learning Models for Multi-Step Prediction of Financial Time Series
    (researchgate.net, 2020-10-21) Aryal, S; Nadarajah, D; Rupasinghe, P.L; Jayawardena, C; Kasthurirathna, D
    Financial time series prediction has been a key topic of interest among researchers considering the complexity of the domain and also due to its significant impact on a wide range of applications. In contrast to one-step ahead prediction, multi-step forecasting is more desirable in the industry but the task is more challenging. In recent days, advancement in deep learning has shown impressive accomplishments across various tasks including sequence learning and time series forecasting. Although most previous studies are focused on applications of deep learning models for single-step ahead prediction, multi-step financial time series forecasting has not been explored exhaustively. This paper aims at extensively evaluating the performance of various state-of-the-art deep learning models for multiple multi-steps ahead prediction horizons on real-world stock and forex markets dataset. Specifically, we focus on Long-Short Term Memory (LSTM) network and its variations, Encoder-Decoder based sequence to sequence models, Temporal Convolution Network (TCN), hybrid Exponential SmoothingRecurrent Neural Networks (ES-RNN) and Neural Basis Expansion Analysis for interpretable Time Series forecasting (N-BEATS). Experimental results show that the latest deep learning models such as NBEATS, ES-LSTM and TCN produced better results for all stock market related datasets by obtaining around 50% less Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE) scores for each prediction horizon as compared to other models. However, the conventional LSTM-based models still prove to be dominant in the forex domain by comparatively achieving around 2% less error values.