Pamuditha Somarathne

PhD Candidate | Human Motion Modelling | HCI, ML, Biosignal Processing

Projects

Adaptive Communication Interfaces

Leading the development of a real-time gesture recognition system for non-verbal communication at The University of Sydney, currently in IP development.

Active | 2025

A Dual Classifier-Regressor Architecture for Heart Sound Onset/Offset Detection

This project explored robust detection of heart sound onset and offset events by combining phonocardiogram (PCG) and electrocardiogram (ECG) signals using a joint classifier-regressor architecture.

Active | 2024

Generative Motion Modelling

PhD research developing generative architectures for high-fidelity 3D human motion reconstruction and optimising latent space representations for sparse sensor data inputs.

Active | 2024

Efficient and Robust Heart Rate Estimation Approach for Noisy Wearable PPG Sensors Using Ideal Representation Learning

A cardiac sensing research project that uses ideal representation learning to estimate heart rate robustly from noisy PPG signals while remaining efficient enough for mobile deployment.

Completed | 2023

Adaptive Compressive Sensing for Differentiable Microscopy

Final-year research project on adaptive online compressive sensing algorithms for differentiable microscopy, in collaboration with researchers at Harvard University and UC Berkeley.

Completed | 2022

Green-Machine: FPGA Management System

Intel InnovateFPGA design contest entry implementing CNN-based image classification on an Intel Cyclone V SoC FPGA for autonomous mini-greenhouse management; Gold Award (Asia-Pacific) and Global Silver Award.

Completed | 2021

Smart Breadboard: Remote Electronics Laboratory

A MOSFET-matrix smart breadboard that physically reconstructs circuits drawn in a remote UI, enabling electronics lab work during the pandemic; first place (Sri Lanka) at the IEEE PES remote-lab design competition.

Completed | 2020