Thomas Napier profile picture

Thomas Napier

PhD Candidate and Graduate Researcher
Discipline of Information Technology
College of Science and Engineering
James Cook University

Townsville, Queensland
Australia
CV [Updated 04/2025]
thomas.napier@jcu.edu.au
LinkedIn
ORCID
GitHub
GitLab
Google Scholar
ResearchGate
Academic Portfolio

Short Bio

I am a PhD Candidate, Sessional Lecturer and Graduate Research Worker at the Discipline of Information Technology, College of Science and Engineering, James Cook University (JCU). I graduated with a Bachelor of Information Technology with Distinction (GPA 6.78/7.00) in 2020 and with First-Class Honours (1A) in 2021, earning the University Medal under the supervision of Prof. Ickjai Lee.

Currently, I am in the final year of my PhD (completion in August 2026) at JCU, where I develop applied machine learning and signal processing frameworks for analysing large-scale natural soundscapes. I am supervised by an interdisciplinary advisor panel including Prof. Ickjai Lee, Dr. Euijoon Ahn (Information Technology) and Distinguished Prof. Lin Schwarzkopf, and Dr. Slade Allen-Ankins (Ecology and Zoology).

I have also collaborated on several multidisciplinary, industry-based projects, including designing machine learning models for marine biology with the Australian Abalone Growers Association, developing advanced tourism analytics with ResPax, and improving insurance claims processing workflows with HelloClaims. These projects involved applying deep learning, data mining, and augmented reality solutions to address real-world challenges.

Research Interests

Keywords: AR and AI in education, Bioacoustics, Data visualization, Dimensionality reduction, Domain generalisation, Ecoacoustics, Environmental informatics, Environmental monitoring, Generative AI, Human-computer interaction, Machine learning, Representation learning, Signal processing, Software development, Sound event detection, Unsupervised pattern discovery

My research focuses on creating scalable, generalisable, and data-driven approaches for ecoacoustic analysis, with the aim of overcoming the bottlenecks of manual annotation in large-scale biodiversity monitoring. I investigate unsupervised and semi-supervised methods that prioritise structure discovery before labelling, integrating human-inspired feature representations, auditory scene analysis, and ecological reasoning to produce acoustically pure and ecologically meaningful clusters of sound events. This work emphasizes 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

In parallel, I explore the use of AR and GenAI technologies in education, developing tools that improve the teaching of complex IT concepts and leveraging generative AI to support assessment and feedback. Across both domains, my goal is to design user-friendly, scalable solutions that reduce friction, enhance interpretability, and enable broader adoption—supporting biodiversity monitoring, conservation, and educational innovation.

Education

James Cook University Logo
James Cook University

Doctor of Philosophy (PhD), Information Technology

Feb 2022 - Aug 2026

Research Area: Species Classification using Machine Learning-Based Signal Processing Techniques in Natural Soundscapes

James Cook University Logo
James Cook University

Bachelor of Information Technology (Honours)

2020 - 2021

Grade: First Class (1A), 7.00 GPA, University Medal

Research Area: Using Mobile-Based Augmented Reality and Object Detection for Real-Time Abalone Growth Monitoring

View Dissertation
James Cook University Logo
James Cook University

Bachelor of Information Technology

2017 - 2020

Grade: 6.78/7.00 GPA, Graduated With Distinction

Minoring in Human-Computer Interactions and Games Design

Grants, Honours and Awards

AAAI-26 DC Travel Award – Singapore ($900) · AAAI · Nov 2025

Competitive travel grant awarded to support participation in the AAAI-26 Doctoral Consortium, covering flights and accommodation.

Sessional Teaching Award for Outstanding Contributions to Student Learning ($500) · JCU · Sept 2025 Certificate

Recognises the most outstanding sessional university teachers who demonstrate innovation, leadership, and sustained impact on student learning and the overall student experience.

HDR CSE Incentive Award ($500) · JCU · Oct 2024 Certificate

Awarded to higher degree by research candidates in the College of Science and Engineering for strong research performance, including accepted publications and external grant success that support timely completion.

CSE Competitive Research Training Grant 2023 ($2000) · JCU · Apr 2023

Highly competitive internal research training grant awarded from a pool of 70 applications, supporting HDR research activities and development.

Bev Frangos Graduate Instructor Prize ($500) · JCU · Mar 2023 Award

Prize awarded to a masters or PhD student in Electrical and Electronic Engineering, Electronic Systems and Internet of Things Engineering, or Information Technology who has made an outstanding contribution to teaching.

AJCAI 2022 DC Travel Grant – Perth, Western Australia ($900) · AJCAI · Nov 2022

Competitive travel grant supporting attendance at the AJCAI 2022 Doctoral Consortium, including flights and accommodation.

Research Training Program Scholarship · JCU · Jan 2022

Highly competitive postgraduate scholarship funded under the Australian Government Research Training Program, awarded on the basis of academic merit and research potential.

University Medal · James Cook University · Sep 2021 Award Photo Photo

Awarded for outstanding academic achievement at undergraduate level, including a GPA above 6.50, first class Honours (Level A), completion of an Honours research component, and endorsement by the College Dean as a meritorious recipient.

Letter of Commendation · James Cook University · May 2018

Recognition for achieving a GPA of 6.00 or higher across first-year Information Technology subjects.

News

  • December, 2025: I won the 1st Place Award for best presentation: "Faster, Smarter Listening: Reducing Friction in Passive Acoustic Monitoring Using the LEAVES Framework" at the Annual Engineering, IT, and Physical Sciences HDR Conference at James Cook University. Special thanks to the event organisers and my supervisors, and congratulations to all other presenters for their fascinating talks. link
  • November, 2025: I was chosen as one of 41 doctoral researchers worldwide to participate in the prestigious AAAI-26 (Top-2 AI conference) Doctoral Consortium in Singapore.
  • September, 2025: I was pleased to accept 1 of 5 Sessional Teaching Awards for Outstanding Contributions to Student Learning at the Celebrating Excellence in Learning & Teaching at JCU: Teaching Excellence Awards ceremony.
  • August, 2025: I was appointed as the lecturer for the JCU-Xi’an University of Technology international partnership program for CP1404: Python Programming and CP2404: Database Modelling.
  • May, 2025: I was appointed as the subject coordinator and lecturer for CP5804: Database Systems.
  • March, 2025: I was invited to present at the BioacousTalks series hosted by the K. Lisa Yang Center for Bioacoustics at the Cornell Lab of Ornithology. Watch it here.
  • January, 2025: I was appointed as the subject coordinator for CP2414: Network Security and CP2501: Cloud Computing.
  • January, 2025: Our paper, 'LEAVES: An open-source web-based tool for the scalable annotation and visualisation of large-scale ecoacoustic datasets using cluster analysis', was accepted by Ecological Informatics (IF=7.3)
  • December, 2024: I was contracted to lecture the JCU subjects CP1402: Internet Fundamentals and CP2414: Network Security in TR1, 2025.
  • December, 2024: The subject, CP2501/CP3511: Cloud Computing, which I lectured, recieved 84% overall satisfaction from internal JCU student feedback.
  • December, 2024: The teaching and research grant project I collaborated on, CodeCraft: Augmented Learning for IT Students ($10,000), successfully passed student testing (26 participants) and evaluation, receiving >80% excellent overall ratings in terms of usefulness.

Experience & Skills

Key Skills

Programming Languages & Frameworks
  • Proficient in: Python, JavaScript, C#, CSS3, HTML5, TensorFlow, PyTorch, Django, Flask, Unity, GitLab, LaTeX
  • Familiar with: Java, Express.js, Linux, R, Jupyter Notebook, Ubuntu, Apple ARKit, AWS, Docker
  • Currently Learning: Electron, TypeScript
Tools & Development Environments
  • GitHub, Android Studio, PyCharm, Visual Studio Code, Sublime Text, Ubuntu
  • REST APIs, Docker, PostgreSQL, librosa
Machine Learning & Data Science
  • Deep Learning: TensorFlow, PyTorch
  • Data Mining & Clustering: HDBSCAN, DBSCAN, UMAP
  • Object Detection, Augmented Reality (AR), librosa
  • Data Analysis, Visualization, Dimensionality Reduction
Professional Skills
  • Leadership & Mentorship
  • Agile Development, Scrum Methodologies
  • Interpersonal Communication, Customer Service
  • Collaborative & Creative Problem-Solving
  • Technical Support & Troubleshooting
Teaching & Academic Skills
  • University-level Teaching (IT Courses)
  • Curriculum Design (e.g., Data Mining, Cloud Computing)
  • Assessment Development & Evaluation
  • Student Mentorship & Support
Other Technical Skills
  • Mobile Application Development
  • Motion Graphics, Game Design
  • Network Security & Troubleshooting
  • Search Engine Optimization (SEO)

Publications

2025

LEAVES: An open-source web-based tool for the scalable annotation and visualisation of large-scale ecoacoustic datasets using cluster analysis
Thomas Napier, Euijoon Ahn, Slade Allen-Ankins, Lin Schwarzkopf, Ickjai Lee
Ecological Informatics (IF=7.3) | January 2025
PDF BibTeX
@article{napier2025leaves, title={LEAVES: An open-source web-based tool for the scalable annotation and visualisation of large-scale ecoacoustic datasets using cluster analysis}, author={Napier, Thomas and Ahn, Euijoon and Allen-Ankins, Slade and Schwarzkopf, Lin and Lee, Ickjai}, journal={Ecological Informatics}, volume={87}, pages={103026}, year={2025}, publisher={Elsevier} }

2024

Advancements in preprocessing, detection and classification techniques for ecoacoustic data: A comprehensive review for large-scale Passive Acoustic Monitoring
Thomas Napier, Euijoon Ahn, Slade Allen-Ankins, Lin Schwarzkopf, Ickjai Lee
Expert Systems with Applications (IF=8.5) | October 2024
PDF BibTeX
@article{NAPIER2024124220, title = {Advancements in preprocessing, detection and classification techniques for ecoacoustic data: A comprehensive review for large-scale Passive Acoustic Monitoring}, journal = {Expert Systems with Applications}, volume = {252}, pages = {124220}, year = {2024}, issn = {0957-4174}, doi = {https://doi.org/10.1016/j.eswa.2024.124220}, url = {https://www.sciencedirect.com/science/article/pii/S0957417424010868}, author = {Thomas Napier and Euijoon Ahn and Slade Allen-Ankins and Lin Schwarzkopf and Ickjai Lee}, keywords = {Ecoacoustics, Passive acoustic monitoring, Deep learning, Machine learning, Acoustic signal processing, Bioacoustics, Species identification}, abstract = {Computational ecoacoustics has seen significant growth in recent decades, facilitated by the reduced costs of digital sound recording devices and data storage. This progress has enabled the continuous monitoring of vocal fauna through Passive Acoustic Monitoring (PAM), a technique used to record and analyse environmental sounds to study animal behaviours and their habitats. While the collection of ecoacoustic data has become more accessible, the effective analysis of this information to understand animal behaviours and monitor populations remains a major challenge. This survey paper presents the state-of-the-art ecoacoustics data analysis approaches, with a focus on their applicability to large-scale PAM. We emphasise the importance of large-scale PAM, as it enables extensive geographical coverage and continuous monitoring, crucial for comprehensive biodiversity assessment and understanding ecological dynamics over wide areas and diverse habitats. This large-scale approach is particularly vital in the face of rapid environmental changes, as it provides crucial insights into the effects of these changes on a broad array of species and ecosystems. As such, we outline the most challenging large-scale ecoacoustics data analysis tasks, including pre-processing, visualisation, data labelling, detection, and classification. Each is evaluated according to its strengths, weaknesses and overall suitability to large-scale PAM, and recommendations are made for future research directions.} }

2023

An Optimised Grid Search Based Framework for Robust Large-Scale Natural Soundscape Classification
Thomas Napier, Euijoon Ahn, Slade Allen-Ankins, Ickjai Lee
36th Australasian Joint Conference on Artificial Intelligence (20% Acceptance Rate) | November, 2023
PDF BibTeX
@InProceedings{10.1007/978-981-99-8388-9_38, author="Napier, Thomas and Ahn, Euijoon and Allen-Ankins, Slade and Lee, Ickjai", editor="Liu, Tongliang and Webb, Geoff and Yue, Lin and Wang, Dadong", title="An Optimised Grid Search Based Framework for Robust Large-Scale Natural Soundscape Classification", booktitle="AI 2023: Advances in Artificial Intelligence", year="2024", publisher="Springer Nature Singapore", address="Singapore", pages="468--479", abstract="Large-scale natural soundscapes are remarkably complex and offer invaluable insights into the biodiversity and health of ecosystems. Recent advances have shown promising results in automatically classifying the sounds captured using passive acoustic monitoring. However, the accuracy performance and lack of transferability across diverse environments remains a challenge. To rectify this, we propose a robust and flexible ecoacoustics sound classification grid search-based framework using optimised machine learning algorithms for the analysis of large-scale natural soundscapes. It consists of four steps: pre-processing including the application of spectral subtraction denoising to two distinct datasets extracted from the Australian Acoustic Observatory, feature extraction using Mel Frequency Cepstral Coefficients, feature reduction, and classification using a grid search approach for hyperparameter tuning across classifiers including Support Vector Machine, k-Nearest Neighbour, and Artificial Neural Networks. With 10-fold cross validation, our experimental results revealed that the best models obtained a classification accuracy of 96{\%} and above in both datasets across the four major categories of sound (biophony, geophony, anthrophony, and silence). Furthermore, cross-dataset validation experiments using a pooled dataset highlight that our framework is rigorous and adaptable, despite the high variance in possible sounds at each site.", isbn="978-981-99-8388-9" }

Using mobile-based augmented reality and object detection for real-time Abalone growth monitoring
Thomas Napier, Ickjai Lee
Computers and Electronics in Agriculture (IF=7.7) | April, 2023
PDF BibTeX
@article{NAPIER2023107744, title = {Using mobile-based augmented reality and object detection for real-time Abalone growth monitoring}, journal = {Computers and Electronics in Agriculture}, volume = {207}, pages = {107744}, year = {2023}, issn = {0168-1699}, doi = {https://doi.org/10.1016/j.compag.2023.107744}, url = {https://www.sciencedirect.com/science/article/pii/S0168169923001321}, author = {Thomas Napier and Ickjai Lee}, keywords = {Deep learning, Greenlip Abalone, Augmented reality, Object detection, Aquaculture}, abstract = {Abalone are becoming increasingly popular for human consumption. Whilst their popularity has risen, measuring the number and size distribution of Abalone at various stages of growth in existing farms remains a significant challenge. Current Abalone stock management techniques rely on manual inspection which is time consuming, causes stress to the animal, and results in mediocre data quality. To rectify this, we propose a novel mobile-based tool which combines object detection and augmented reality for the real-time counting and measuring of Abalone, that is both network and location independent. We applied our portable handset tool to both measure and count Abalone at various growth stages, and performed extended measuring evaluation to assess the robustness of our proposed approach. Our experimental results revealed that the proposed tool greatly outperforms traditional approaches and was able to successfully count up to 15 Abalone at various life stages with above 95% accuracy, as well as significantly decrease the time taken to measure Abalone while still maintaining an accuracy within a maximum error range of 2.5% of the Abalone’s actual size.} }

2022

Species Classification Using Deep Learning Signal Processing Techniques in Large-Scale Natural Soundscapes
Thomas Napier, Lin Schwarzkopf, Ickjai Lee, Euijoon Ahn, Slade Allen-Ankins
QUT Ecoacoustics Symposium | November, 2022
Poster Program

One year of spectroscopic high-frequency measurements of atmospheric CO2, CH4, H2O and δ13C-CO2 at an Australian Savanna site
Niels C. Munksgaard, Ickjai Lee, Thomas Napier, Costijn Zwart, Lucas A. Cernusak, Michael I. Bird
Geoscience Data Journal (IF=3.3) | October, 2022
PDF BibTeX
@article{https://doi.org/10.1002/gdj3.180, author = {Munksgaard, Niels C. and Lee, Ickjai and Napier, Thomas and Zwart, Costijn and Cernusak, Lucas A. and Bird, Michael I.}, title = {One year of spectroscopic high-frequency measurements of atmospheric CO, CH, HO and δC-CO at an Australian Savanna site}, journal = {Geoscience Data Journal}, volume = {10}, number = {4}, pages = {461-470}, keywords = {atmospheric CO2, CH4, NE Australia, savanna, δ13C-CO2}, doi = {https://doi.org/10.1002/gdj3.180}, url = {https://rmets.onlinelibrary.wiley.com/doi/abs/10.1002/gdj3.180}, eprint = {https://rmets.onlinelibrary.wiley.com/doi/pdf/10.1002/gdj3.180}, abstract = {Abstract We provide a 1-year dataset of atmospheric surface CO2, CH4 and H2O concentrations and δ13C-CO2 values from an Australian savanna site. These semi-arid ecosystems act as carbon sinks in wet years but the persistence of the sink in dry years is uncertain. The dataset can be used to constrain uncertainties in modelling of greenhouse gas budgets, improve algorithms for satellite measurements and characterize the role of vegetation and soil in modulating atmospheric CO2 concentrations. We found pronounced seasonal variations in daily mean CO2 concentrations with an increase (by 5–7 ppmv) after the first rainfall of the wet season in early December with peak concentrations maintained until late January. The CO2 increase reflected the initiation of rapid microbial respiration from soil and vegetation sources upon initial wetting. As the wet season progressed, daily CO2 concentrations were variable, but generally decreased back to dry season levels as CO2 assimilation by photosynthesis increased. Mean daily concentrations of CH4 increased in the wet season by up to 0.2 ppmv relative to dry season levels as the soil profile became waterlogged after heavy rainfall events. During the dry season there was regular cycling between maximum CO2/minimum δ13C-CO2 at night and minimum CO2/maximum δ13C-CO2 during the day. In the wet season diel patterns were less regular in response to variable cloud cover and rainfall. CO2 isotope data showed that in the wet season, surface CO2 was predominantly a two-component mixture influenced by C3 plant assimilation (day) and soil/plant respiration (night), while regional background air from higher altitudes represented an additional CO2 source in the dry season. Higher wind speeds during the dry season increased vertical mixing compared to the wet season. In addition, night-time advection of high-altitude air during low temperature conditions also promoted mixing in the dry season.}, year = {2022} }

Projects

LEAVES: Large-scale Ecoacoustics Annotation and Visualization with Efficient Segmentation

LEAVES is a Python Dash-based open-source tool designed for large-scale ecoacoustics annotation and visualization.

LEAVES Screenshot 1 LEAVES Screenshot 2 LEAVES Screenshot 2
Source Code Paper Live Demo

CodeCraft: AR-based Database Normalization Tool

CodeCraft is an augmented reality educational tool combining AR and AI to teach database normalization effectively.

CodeCraft Screenshot 1 CodeCraft Screenshot 2
[Private Source Code]

Real-time Abalone Monitoring with AR

Developed a mobile tool combining AR and object detection to automate measurement and counting of Abalone in aquaculture.

Abalone Screenshot 1 Abalone Screenshot 2 Abalone Screenshot 3
Source Code Paper Thesis

Pirapelago: A Unity-based 2D Pirate-Themed Rogue-like Game

Pirapelago is a pirate-themed rogue-like bullet hell developed by a small team for a university project. Experience multiple enemy types, ship upgrades, and scaling difficulty as you fight your way across the archipelago.

Pirapelago Screenshot 1 Pirapelago Screenshot 2 Pirapelago Screenshot 3
Source Code Live Demo

TrueLogic: An interactive Mobile-Based Problem-Solving Education Game

TrueLogic is a simple timed quiz-style Android app aimed at early highschool kids to help improve thier problem-solving and lateral thinking skills. It includes accelerometer gesture control, basic social network integration with Twitter4J API and high score recordkeeping with SQLite.

TrueLogic Screenshot 1 TrueLogic Screenshot 2
Source Code

Interference: Motion Graphics TV Show Intro
Created a high-energy motion graphics intro for a hypothetical TV show, "Interference," inspired by the hacking and cyberpunk themes of Ubisoft's WatchDogs*. The intro featured glitch effects, dynamic text animations, and a neon-hued urban aesthetic. The short film simulated a world of digital intrusion, surveillance, and hacking set in a futuristic cityscape.
Interference Glitch Effect Cyberpunk Urban Aesthetic Cyberpunk Urban Aesthetic
Watch Short Film

Cool Links

Tools (AI, and others)
  • Elicit

    Elicit uses language models to extract data from and summarize research papers.

  • Obsidian

    Obsidian is the private and flexible writing app that adapts to the way you think.

  • Quillbot

    QuillBot helps to rewrite and paraphrase text using AI.

Research/Academic
Other
  • 12ft Ladder

    Remove popups, banners, ads and paywalls from any website.

  • DrawIO

    draw.io is free online diagram software for making flowcharts, process diagrams, org charts, UML, ER and network diagrams.

God (Psalm 34:4-5, 8)
  • BibleGateway

    For God so loved the world that he gave his one and only Son, that whoever believes in him shall not perish but have eternal life. For God did not send his Son into the world to condemn the world, but to save the world through him - John 3:16-17

  • BibleRef

    Online Bible commentary.