Dulan Dias, Ph.D.

Research

Where Algorithms Meet Impact

Research isn’t just about finding answers—it’s about asking the right questions. My work bridges the gap between AI, healthcare, and enterprise innovation, pushing the limits of what’s possible. From machine learning models that optimize patient care to generative AI systems that craft music, every project is a step toward a smarter, more intuitive world. Join me on this journey of discovery, where data transforms into groundbreaking solutions.

Research Interests & Focus Areas

Artificial Intelligence & Machine Learning

Developing algorithms for predictive analytics, deep learning, and automation.

Generative AI & Natural Language Processing

Advancing AI-driven content generation, text analysis, and natural language processing.

Healthcare Data Science

Using AI to optimize healthcare workflows, patient discharge, and predictive modeling.

Digital Transformation & Enterprise AI

Applying AI to optimize business workflows and automate decision-making processes.

LegalTech & Generative AI with RAG

Applying AI & Retrieval-Augmented Generation (RAG) to automate legal research and contract analysis.

Ongoing Research & Projects

  • TextXtract – Intelligent Document Processing for Modern Business (EchonLabs)
    A cutting-edge AI-powered document processing system designed to extract, analyze, and categorize unstructured business data. TextXtract leverages natural language processing (NLP) and machine learning to automate document workflows, improving efficiency and accuracy in modern enterprises.
  • Jurisdiction-based Resource Augmented Generation (RAG) for Legal Contract Generation, Explanation, and Analysis (EchonLabs & Verdic.ai)
    An AI-driven system that enhances legal contract drafting and interpretation by incorporating jurisdiction-specific legal resources. This project explores how Retrieval-Augmented Generation (RAG) can be used to create more precise, compliant, and understandable legal contracts, ensuring clarity for legal professionals and businesses.
  • Genre Classification of Sinhala Songs Using Machine Learning Based on Audio Features (Supervising S.M.K.N.Nawamini Karunathilake – Undergraduate Research)
    A machine learning model designed to classify Sinhala songs into distinct genres based on audio characteristics such as rhythm, pitch, and timbre. This research aims to develop a robust classification system that can help in music recommendation, digital archiving, and cultural preservation of Sinhala music.

Publications

  • Dias, D.S., Marshall, A.H., & Novakovic, A. (2024). Predictive Modelling for Length of Stay with the MIMIC-III Critical Care Database. Proceedings of the 10th International Conference on Health Informatics & Medical Systems (HIMS’24), July 22-25, 2024, Las Vegas, USA.
  • Dias, D.S., Marshall, A.H., & Novakovic, A. (2024). Using Mixed Exponentials for Unsupervised Discretization. Proceedings of the Future Technologies Conference 2024 (FTC 2024), November 14-15, 2024, London, United Kingdom.
  • Dias, D.S., Welikala, M.D., & Dias, N.G.J. (2018). Identifying Racist Social Media Comments in Sinhala Language Using Text Analytics Models with Machine Learning. Proceedings of the 18th International Conference on Advances in ICT for Emerging Regions (ICTer 2018), 1-6. IEEE.
  • Dias, D.S., & Fernando, T.G.I. (2019). Komposer–Automated Musical Note Generation Based on Lyrics with Recurrent Neural Networks. Proceedings of the 1st International Conference on Artificial Intelligence and Data Sciences (AiDAS 2019), 76-82. IEEE.
  • Dias, D.S., & Dias, N.G.J. (2018). Forecasting Monthly Ad Revenue from Blogs Using Machine Learning. Proceedings of the 3rd International Conference on Advances in Computing and Technology (ICACT 2018).
  • Dias, D.S., & Perera, M.D.R. (2018). Virtual Airplay Drum Kit Based on Hand Gesture Recognition. Proceedings of the 3rd International Conference on Advances in Computing and Technology (ICACT 2018).
  • Dias, D.S., & Dias, N.G.J. (2017). A Simple Machine Learning Approach for Identifying Promotional Short Message Service (SMS) Messages. Faculty of Computing and Technology, University of Kelaniya, Sri Lanka.