My research includes image quality assessment, computer vision, machine learning, signal processing, cybersecurity, IoT and networked systems.
Full-reference IQA, cross-content generalisation, structural complexity, perceptual similarity, restoration and enhancement.
Deep learning, classical ML, object detection, segmentation, classification, model optimisation and data-centric workflows.
Acoustic classification, feature engineering, information-theoretic representations, iris recognition and intelligent sensing.
Cybersecurity, digital forensics, IoT, networking and related computing systems.
28 October 2026 · MIT Research Seminar (27–28 October 2026)
At the Melbourne Institute of Technology Research Seminar, I presented my work on image quality assessment and perceptual image reconstruction, and discussed why visual improvement must be considered alongside information fidelity. The talk also connected these questions with current challenges in generative AI image restoration.
My current research is not limited to one application area. I continue to work on image quality assessment and computer vision, while also exploring how machine learning can support connected and resource-constrained systems. Current manuscripts under review examine digital twins with edge intelligence for connected healthcare and deep-reinforcement-learning-based resource allocation for 6G-enabled Internet of Medical Things networks. Through research supervision, I am also engaged with federated learning, privacy, explainable AI, cybersecurity and IoT. Across these areas, I am especially interested in work that connects technical development with practical use.