Thomas Napier

I am a final-year PhD Candidate and IT educator at James Cook University, working at the intersection of machine learning and ecoacoustics. My research addresses foundational challenges in terrestrial soundscape analysis, with the aim of overcoming the bottlenecks of manual annotation in large-scale biodiversity monitoring. Recently I've been working on adaptive sound event detection, clustering in the presence of polyphony, and human-in-the-loop verification to direct expert effort where it is most valuable. The broader goal of my work is to move beyond narrow, fully supervised approaches and enable generalisable AI systems that can operate effectively in messy, real-world conditions.

My work has been recognised through a range of competitive awards, grants, and international opportunities. I was selected as one of a small cohort of doctoral researchers worldwide to participate in the prestigious AAAI 2026 Doctoral Consortium, and have received multiple competitive research training grants supporting my work. I have also been awarded external and institutional recognition, including the University Medal for academic excellence and several travel awards enabling participation in leading conferences. My research has been accepted at international conference venues such as PAKDD, and several high-impact journals such as Expert Systems with Applications, Ecological Informatics, and Computers and Electronics in Agriculture.

In parallel, I have over 7 years of teaching experience across cybersecurity, programming, and database systems, with a strong focus on curriculum design and student outcomes. I have led the design and development of cybersecurity subjects from the ground up, building course structures, assessments, and practical components aligned with both academic standards and industry expectations. My teaching consistently receives strong student feedback, and I have recieved formal recognition through a Sessional Teaching Award for Outstanding Contributions to Student Learning in 2025.

Before entering academia, I spent over 3.5 years working in industry in IT support (Level 1/2), where I developed a strong foundation in systems thinking, troubleshooting, and user-focused problem solving. That experience continues to shape how I approach both research and teaching.

• Unsupervised learning and data clustering for high-dimensional ecoacoustics analysis;
• Machine learning and feature extraction from raw signal, image and video data;
• Mobile-based augmented reality for education and improving real-world workflows
• Applied artificial intelligence and machine learning algorithms
• Open source software tools to support decision making
• Data mining and knowledge discovery

Programming, Machine Learning, Data Mining, Software Development, Databases, Cloud Computing, Ecoacoustics, Remote Sensing, Signal Processing