Electricity consumption forecasting for residential sector using temporal co-learning
Song H., ..., Kamoona A.M. et al. (2026). "Electricity consumption forecasting for residential sector using temporal co-learning." Applied Energy, 395, 125856.
CV
A PDF version of the CV is available here.
Research Summary
AI/ML researcher with expertise in developing novel learning architectures for intelligent sensing and decision-making systems. Research focus on deep anomaly detection, transformer-based temporal learning, Vision Language Models, and computer vision for electronic and infrastructure systems. Ten peer-reviewed publications (h-index: 11, 80% Q1), over $5.6M in competitive collaborative funding, and demonstrated ability to deploy research as production AI systems. Five years of university teaching in AI, machine learning, and electrical engineering.
Education
- PhD, Advanced Manufacturing and Mechatronics Engineering (Computer Vision and AI), RMIT University, Melbourne, 2018–2022
- Thesis: Deep Learning Methods for Visual Anomaly Detection and Defect Recognition
- Supervisors: Prof. Alireza Bab-Hadiashar, Prof. Reza Hoseinnezhad
- Master of Engineering Science, Electrical and Electronic Engineering, Swinburne University of Technology, Melbourne, 2014–2016
- Bachelor of Electrical Engineering (Power Systems), University of Kufa, Iraq, 2006–2010
Academic and Professional Appointments
- AI Scientist / Computer Vision Engineer, Powercor Australia (CitiPower & Powercor), Melbourne, 2024–Present
- Research Fellow, AI and Machine Learning, RMIT University, Melbourne, 2022–Present
- AI and Embedded Systems Engineer, Cornerstone Solutions Pty Ltd, Melbourne, 2018–2019
- Lecturer, Electrical Engineering, University of Kufa, Iraq, 2016–2018
Competitive Research Funding ($5.6M+ total)
- NexusCharge: $4M (Australian Economic Accelerator, 2024). Intelligent EV charging, commercial translation. Role: Collaborative Entrepreneur / ML Lead.
- CSIRO Next Generation AI Graduates Program: $1.4M (2023). AI for energy systems. Role: Investigator.
- ARC Linkage LP230100439: $150K (2023). AI for electrification research with AGL, AusNet, SpendWatt. Role: Investigator.
- RMIT RACE AWS Cloud Computing: $60K (2023, 2026). Two merit allocations for large-scale AI training. Role: Sole Chief Investigator.
- iMOVE CRC (2022). Connected and automated transport AI. Role: Investigator.
Publications
See the Publications page for the full list of ten peer-reviewed papers (h-index: 11, 80% Q1).
Impact of electric vehicle adoption on residential load profiles: An Australian case study
Kamoona A.M., Al Khafaf N., Ali S.M.N., Jalili M., Razzaghi R., Yu X. (2026). "Impact of electric vehicle adoption on residential load profiles: An Australian case study." Sustainable Energy, Grids and Networks, 102481.
Online electric vehicle charging detection based on a memory-augmented transformer architecture
Kamoona A.M., Lazarevic L., Al Khafaf N., Ali S.M.N., Jalili M., Razzaghi R. (2025). "Online electric vehicle charging detection based on a memory-augmented transformer architecture." Applied Energy, 377, 124549.
Anomaly detection of defect using energy of point pattern features within random finite set framework
Kamoona A.M., Bab-Hadiashar A., Hoseinnezhad R. (2024). "Anomaly detection of defect using energy of point pattern features within random finite set framework." Engineering Applications of Artificial Intelligence, 132, 107857.
Multiple instance-based video anomaly detection using deep temporal encoding-decoding
Kamoona A.M., Bab-Hadiashar A., Hoseinnezhad R. (2023). "Multiple instance-based video anomaly detection using deep temporal encoding-decoding." Expert Systems with Applications, 214, 119079.
Machine learning for energy demand prediction
Al Khafaf N., Jalili M., Kamoona A.M., Zhu J.G. (2023). "Machine learning for energy demand prediction." Energy Reports, 9.
Prediction of photovoltaic power generation
Al Khafaf N., Kamoona A.M., Zhu J.G., Ali S.M.N., Jalili M. (2023). "Prediction of photovoltaic power generation." Energy Reports, 9.
Video anomaly detection using deep temporal encoding-decoding with multi-head attention
Kamoona A.M., Bab-Hadiashar A., Hoseinnezhad R. (2022). "Video anomaly detection using deep temporal encoding-decoding with multi-head attention." Expert Systems with Applications, 205, 117699.
Particle swarm optimisation-based approach for multi-objective design
Kamoona A.M., Prayag M.B. (2019). "Particle swarm optimisation-based approach for multi-objective design." Applied Soft Computing.
An improved chaotic sequence based on neural network and its application to image encryption
Kamoona A.M., Alsaad S.N. (2018). "An improved chaotic sequence based on neural network and its application to image encryption." Journal of Kufa for Mathematics and Computer.
Paper Title Number 3
Your Name, You. (2015). "Paper Title Number 3." Journal 1. 1(3).
Paper Title Number 2
Your Name, You. (2010). "Paper Title Number 2." Journal 1. 1(2).
Paper Title Number 1
Your Name, You. (2009). "Paper Title Number 1." Journal 1. 1(1).
Teaching Experience
RMIT University (2019–2025):
- Intelligent Systems (EEET2171, 2025): Machine learning, neural networks, optimisation, Python. CES score: 3.4.
- Modelling and Simulation of Engineering Systems (2019–2021): Computational modelling, numerical methods, MATLAB/Python. 40+ students per semester.
- Digital Fundamentals (2019): Digital logic, hardware-software interfaces.
University of Kufa, Iraq (2016–2018):
- Digital Circuit Design: Full course coordinator for 60+ students. VHDL, FPGA implementation, hands-on laboratories designed from scratch.
- Engineering Electromagnetic Fields: Independent delivery, Maxwell’s equations, wave propagation, transmission lines.
HDR Supervision
- Associate Supervisor, PhD candidate (RMIT, ongoing).
- Supervised four industry-connected capstone projects in applied AI (Powercor, iMOVE, Cornerstone).
Industry Partnerships and Impact
- Powercor Australia (2024–present): Production AI systems for electrical network inspection, Vision Language Models for document understanding, MLOps infrastructure.
- SpendWatt (2022–present): Deep learning for solar panel segmentation from aerial imagery, deployed as an AWS Lambda service.
- AGL, AusNet, C4NET (2022–present): AI for electrification, EV charging detection, energy demand prediction.
- Cornerstone Solutions (2018–2019): IoT anomaly detection for construction site safety, embedded AI systems.
- NexusCharge / ABB Australia: Commercial translation of ML research into an intelligent EV charging product.
Key Research Contributions
- Novel temporal learning architectures: Memory-augmented transformer for online event detection from time-series data, advancing learning paradigms for sequential sensor data (Applied Energy, 2025).
- Deep anomaly detection: Multi-head attention temporal encoding-decoding networks for video understanding, developing new models for electronic surveillance systems (Expert Systems with Applications, 2022–2023).
- Vision Language Models: Production deployment of multimodal reasoning systems combining vision and language for automated document understanding (Powercor, 2024–present).
- Point-pattern learning: Novel Random Finite Set framework for defect detection, contributing new mathematical foundations for learning in manufacturing inspection systems (EAAI, 2024).
- Temporal co-learning: Multi-task learning framework for electricity consumption forecasting, advancing collaborative learning paradigms (Applied Energy, 2026).
Awards and Recognition
- Australian National Innovation Visa (Global Talent), recognising exceptional achievement in AI and technology.
- AWS Cloud Computing Merit Allocation, sole Chief Investigator (2023, 2026).
- IEEE Congress on Evolutionary Computation, presenter (Rio de Janeiro, 2018).
- ANZAAS Science Talk, invited speaker (2022).
- RMIT IoT Research Forum, presenter (2019).
Talks
Particle swarm optimisation for multi-objective engineering design
Conference presentation at IEEE Congress on Evolutionary Computation (CEC 2018), Rio de Janeiro, Brazil
IoT anomaly detection for construction site safety
Research forum presentation at RMIT IoT Research Forum, Melbourne, Australia
Deep learning for visual anomaly detection and defect recognition
Invited talk at ANZAAS Science Talk, Melbourne, Australia
Teaching
Professional Memberships
- Member, Institute of Electrical and Electronics Engineers (IEEE), 2018–present.
- Member, Engineers Australia, 2024–present.
Service
- Active reviewer for Expert Systems with Applications, Applied Energy, Engineering Applications of Artificial Intelligence, and other Q1 journals.