Ms. Thilini Bakmeedeniya
Lecturer Probationary
Contact
- thilini.b@nsbm.ac.lk
- +94 11 544 5000
- Department of Computer and Data Science
- Faculty of Computing
- Google Scholar
Profile
Thilini Bakmeedenya is currently serving as a Probationary Lecturer in the Department of Computer and Data Science at the Faculty of Computing, NSBM Green University. She has served as a permanent academic staff member with over eight years of experience in reputed government universities and higher education institutions.
Thilini holds a Master of Science in Computer Science from the University of Peradeniya and a Bachelor of Science (Honours) in Computing and Information Systems from the University of Sabaragamuwa. She has also completed the Staff Development Course at the University of Kelaniya.
Her primary areas of expertise include Data Mining, Database Management Systems, Machine Learning, and Artificial Neural Networks.
Research Interests
- Physiological Signal Processing
- Machine Learning
- Deep Learning and LLM
- Explainable AI
- Software Engineering
Journal Publications
- Bakmeedeniya, AHMTC 2024, ‘Leveraging Conversational AI, Specifically ChatGPT, for Enhanced Learning Experiences: Exploring Challenges and Proposing Mitigation Strategies’, International Journal of Science and Research Technology vol.9, no.1, pp.767-772
- Bakmeedeniya, AHMTC, Wepathana, YMRD 2022, ‘Tackling the Class Imbalance Problem in Multiclass Brain Signal Classification’, Journal of Academic Sessions Advanced Technological Institute
- Bakmeedeniya, AHMTC, Wepathana, YMRD 2021, ‘Estimation of Software Development Effort Based on Decision Tree Approach’, Journal of Academic Sessions Advanced Technological Institute
- Bakmeedeniya, AHMTC 2020, ‘Random Forest Approach for Sleep Stage Classification’, International Journal of Scientific and Research Publications vol.10, no.5, pp.767-772
Conference (Full Paper) Publications
- Bakmeedeniya, AHMTC, Wijeykoon, WBMSC and Ukgoda, UWHK 2024 ‘Autoencoder Empowered EEG Data Classification: Self-Supervised Learning Approach’, in 17th International Research Conference General Sir John Kotelawala Defence University, Sri Lanka (Best Paper Presenter)
- Dhanapala, WWGDS, Bakmeedeniya, AHMTC, Amarakeethi, S and Jayaweera, P 2017, A brain signal-based credibility assessment approach, in Joint 17th World Congress of International Fuzzy Systems Association (IFSA) and 9th International Conference on Soft Computing and Intelligent Systems (SCIS), Japan
Ongoing Research
- Self-Supervised Learning for EEG Signals: Navigating Challenges and Seizing Opportunities in Brain Dynamics.
- Multimodal Physiological Signal Framework Using Interpretable Deep Learning