Matthew D'Souza

Dr. Matthew D'Souza is a Lecturer in the School of Electrical Engineering and Computer Science at the University of Queensland, within the Faculty of Engineering, Architecture and Information Technology. He holds a Bachelor of Engineering (Computer Systems) with First Class Honours and a PhD in Electrical Engineering from the University of Queensland, completed in 2008 with a focus on wireless communications, interactive interfaces, and embedded systems. Prior to his current role, which began around 2016, he served as a Postdoctoral Research Fellow and Visiting Research Scientist at the CSIRO Autonomous Systems Laboratory and the Australian E-Health Research Centre in Brisbane. He is a member of the Institute of Electrical and Electronics Engineers (IEEE) and contributes to the Human-Centred Computing team at UQ. D'Souza coordinates courses such as CSSE4011 and COMP3301, emphasizing practical skills in computer science and software engineering.

His research specializations encompass pervasive and ubiquitous computing, wireless communications, wireless sensor networks, embedded systems, biomedical engineering, mobile computing, and cyber-physical systems. Key publications include the journal article 'A machine learning approach for detecting fatigue during repetitive physical tasks' (2023, Personal and Ubiquitous Computing) co-authored with Guobin Liu, Chelsea Dobbins, and Ngoc Phuong; 'Indoor position tracking using received signal strength-based fingerprint context aware partitioning' (2016, IET Radar, Sonar & Navigation) with Brendan Schoots and Montserrat Ros; conference papers such as 'Automated real-time methane monitoring system to provide insights into environmental drivers of emissions from reservoirs' (2025, 20th World Lake Conference); 'Human instancing and tracking on sparse mmwave radar data' (2025, 6th Australian Microwave Symposium); 'Mostly online project-based learning during the COVID-19 pandemic' (2022, 33rd Australasian Association for Engineering Education Conference); and 'Analysis of biometric sensor data for predicting fatigue: a framework towards reducing work-related musculoskeletal disorders in aviation manufacturing workers' (2021, 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society). These works demonstrate applications in indoor localization, fatigue detection, environmental monitoring, and educational adaptations during the pandemic.Professional Email: m.dsouza@uq.edu.au