Biography
I obtained my PhD degree in 2023 from UNSW. My research focused on ‘Vertebral Compression Fracture Detection with a Novel 3D Localization Algorithm.’ I combined deep reinforcement learning with imitation learning to achieve this. Initially, I used a fully supervised learning approach for predicting vertebral compression fractures within localized regions. Later, I explored weakly supervised multiple instance learning. Additionally, I...view more
I obtained my PhD degree in 2023 from UNSW. My research focused on ‘Vertebral Compression Fracture Detection with a Novel 3D Localization Algorithm.’ I combined deep reinforcement learning with imitation learning to achieve this. Initially, I used a fully supervised learning approach for predicting vertebral compression fractures within localized regions. Later, I explored weakly supervised multiple instance learning. Additionally, I adapted my localization algorithm to work in a semi-supervised setting.
My Master’s degree in Computer Science, which I earned from UNSW in 1994, centered around detecting Latin characters using artificial neural networks.
With over 30 years of industry experience, I’ve contributed to complex projects related to real-time embedded systems, intelligent networks, and operation support systems. I retired voluntarily in 2016 as a senior project manager at Nokia/Alcatel Lucent.
I’ve also collaborated with the Biological Earth and Environmental Sciences (BEES) group at UNSW. Together, we developed house dust mite and pest detection systems. Additionally, I contributed to an Android-based app for wildlife species detection as part of the Bushfire Recovery program.
Currently, I work as a senior research associate in collaboration with the Black Dog Institute, focusing on people behavior analysis for suicide detection and prevention. My role involves pedestrian detection and tracking in various settings, including GAP parks, railway stations, bridges, and shopping centers."
My Qualifications
PhD: Computer Science, UNSW 2023
MCompSc: UNSW 1994
BE (Hons): Electrical and Electronics Engineering from Birla Institute of Technology and Science Pilani (India)
My Research Activities
In collaboration with the Black Dog Institute, I’m actively engaged in a critical project centered around suicide detection. Our primary focus is analyzing human behavior using anomaly detection algorithms. Here are the key aspects:
-
Anomaly Detection:
- We’re developing algorithms to identify unusual or concerning behavior patterns.
- These patterns may indicate potential suicidal tendencies.
-
Pedestrian Detection and Tracking:
- To achieve our goals, we rely on pedestrian detection and tracking.
- For pedestrian detection, we utilize YOLOv5 (You Only Look Once), a real-time object detection model.
- DeepSORT (Deep Learning-based SORT) is our chosen method for tracking pedestrians.
-
Technology Stack:
- The entire project is built using PyTorch, a versatile deep learning framework.
-
Deployment Settings:
- Our system operates in various settings, including GAP parks, railway stations, bridges, and shopping centers.
ORCID as entered in ROS
https://orcid.org/0000-0001-7580-5602