Dr Praboda Rajapaksha

Dr Praboda Rajapaksha

Lecturer in Health Data Science

Computer Science

Contact Details

Dr Praboda Rajapaksha is a Lecturer in Health Data Science at Aberystwyth University and a Data Scientist at Hywel Dda University Health Board (HDUHB), NHS Wales. She holds a PhD in Computer Science from Institut Polytechnique de Paris (IP Paris), ranked 43rd worldwide - QS Rankings 2027, where she continued as a postdoctoral research fellow. She also holds an M.Eng. in Computer Science from the Asian Institute of Technology, Thailand; an M.Sc. in Communication Networks and Services from IMT, France; and a B.Eng. in Computer Engineering from the University of Peradeniya, Sri Lanka.

With more than eleven years of research experience, she specialises in multimodal AI, natural language processing, generative AI, machine learning, and data science. At IP Paris, she contributed to European (ITEA, BPI, Horizon) and French national (FUI) projects, gaining extensive experience in international, multi-partner academic and industrial research.

She currently leads a UKRI EPSRC-funded project applying computer vision to the spatial mapping of chemical concentrations, and co-leads an Innovate UK-funded project on plant disease detection using AI and hyperspectral imaging. She previously co-led DeepDetect, an AI-based mobile platform for plant disease detection. Internationally, she collaborates with IP Paris on multimodal AI applications in finance, healthcare, and digital twins. She also works with Shanghai Maritime University on LLM-driven automation of maritime engineering systems, and with Chiang Mai University on the impact of PM2.5 pollution on hospital admissions and mortality.

As a data scientist at HDUHB, she is working on optimising the use of patient-reported outcomes. She is also examining how geographical assumptions in healthcare planning affect rural patient access across West and Mid Wales. In addition, she co-leads KidneyWise, which is developing a mobile application with AI chatbots to support patient well-being in cancer prehabilitation.

She was selected for the Aberystwyth University Visibility Award 2025 and the Welsh Crucible 2026, a leadership programme for future research leaders in Wales, and is a Fellow of the Higher Education Academy (FHEA). Working with PhD and MSc researchers across the UK, France, and China, she is particularly interested in applying cutting-edge, responsible AI to real-world challenges in human and plant health.

Leveraging ensemble deep models and llm for visual polysemy and word sense disambiguation. / Setitra, Insaf; Rajapaksha, Praboda; Myat, Aung Kaung et al.
In: Multimedia Tools and Applications, Vol. 84, No. 29, 102088, 30.09.2025, p. 35727-35759.

Research output: Contribution to journal › Article › peer-review

SA-CLIP: Language Guided Image Spatial and Action Feature Learning. / Li, Guanlin; Shao, Wenhao; Rajapaksha, Praboda et al.
Findings of the Association for Computational Linguistics: EMNLP 2025. ed. / Christos Christodoulopoulos; Tanmoy Chakraborty; Carolyn Rose; Violet Peng. Association for Computational Linguistics, 2025. p. 20808-20814 (EMNLP 2025 - 2025 Conference on Empirical Methods in Natural Language Processing, Findings of EMNLP 2025).

Research output: Chapter in Book/Report/Conference proceeding › Conference Proceeding (ISBN)

Securing software-defined networks: ML-based detection of ARP spoofing attacks. / Tang, Meng; Li, Zhiheng; Akpokodje, Edore et al.
Autonomous Systems for Security and Defence II. ed. / Leo Kampmeijer; Beatrice Masini; Zorana Milosevic. SPIE, 2025. 136800M (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 13680).

Research output: Chapter in Book/Report/Conference proceeding › Conference Proceeding (ISBN)

Can Hallucination Reduction in LLMs Improve Online Sexism Detection? / Ding, Leyuan; Rajapaksha, Praboda; Myat, Aung Kaung et al.
Intelligent Systems and Applications - Proceedings of the 2024 Intelligent Systems Conference IntelliSys Volume 1. ed. / Kohei Arai. Springer Nature, 2024. p. 625-638 (Lecture Notes in Networks and Systems; Vol. 1065 LNNS).

Research output: Chapter in Book/Report/Conference proceeding › Conference Proceeding (ISBN)

CCIM-SLR: Incomplete multiview co-clustering by sparse low-rank representation. / Liu, Zhenjiao; Chen, Zhikui; Lou, Kai et al.
In: Multimedia Tools and Applications, Vol. 83, No. 22, 01.07.2024, p. 61181-61211.

Research output: Contribution to journal › Article › peer-review

More publications on the Research Portal