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

2016 - 201922020 - 20261

Advanced Search

Filter by

Settings

Author: search.filters.author.Gunathilake, B

Search Results

Now showing 1 - 3 of 3
  • Thumbnail Image
    ItemEmbargo
    Machine Learning-Based Early Detection Of Autism Using Multimodal Conversational Features
    (Institute of Electrical and Electronics Engineers Inc., 2026-06-26) Haturusinghe, R; Gunathilake, B; Abeysundara, S; Senadeera, S; Thelijjagoda, S; Jayalath, T
    Early and reliable screening for autism spectrum disorder (ASD) remains challenging in low-resource and high-variance conversational settings. This paper presents an end-to-end multimodal screening system that analyzes child-caregiver interaction data from audio recordings, CHAT-format transcripts, and text inputs to estimate ASD likelihood and provide clinician-facing explanations. The system integrates three feature families: pragmatic-conversational, acoustic-prosodic, and syntactic-semantic, supporting component-wise classification and late-fusion strategies with modality-aware weighting. Beyond prediction, the platform provides transcript-level behavioral annotations, global and local feature attributions, and counterfactual what-if analysis. Experiments on cross-validated ASDBank data show multimodal fusion achieving 87.2% accuracy (ROC-AUC 0.92), outperforming unimodal baselines by 2-4%.
  • Thumbnail Image
    PublicationOpen Access
    Simplifying Law Statements Using Natural Language Processing
    (SLIIT, 2016-11-16) Dharmasiri, N; Gunathilake, B; Pathirana, u; Senevirathne, S; Nugaliyadde, A; Thelijjagoda, S
    Understanding the law statements for general public is evidently complex. The research derives a computational solution on reducing the complexity of the law statements. Given a law statement, the research will use both wordnet and “LawNet” to create a simpler meaning. The research will focus on information extraction, information retrieval, question analysis and answer generation techniques to derive better meaning of law statements. The law statement will be treated as a question and the “LawNet” and wordnet will be used in as information extraction points. The law statement will be analyzed as a question; more information will be retrieved through the wordnet and “LawNet”. This process mostly acts similar to a search engine’s process. The results provide on average 80% accuracy for a 1500 dataset.
  • Thumbnail Image
    PublicationEmbargo
    Smart Mirror with Virtual Twin
    (IEEE, 2019-12-05) Abeydeera, S. S; Bandaranayake, M; Karunarathna, H. U; Pallewatta, S; Dharmasiri, P; Gunathilake, B; Saparamadu, S; Senanayake, B; Jayawardena, C
    Smart Mirror with a virtual twin who helps the user as a close companion. The virtual twin monitors the user's physical appearance and tracks the data gathered from given inputs. Since this is an intelligent virtual twin it uses machine learning techniques. It helps to improve the user's mental and physical health by detecting medical conditions and providing suitable suggestions in a more personalized way. This virtual twin not only focuses on physical or mental health conditions but also gives friendly suggestions about suitable styles which helps to improve the person's life quality.