Associate Professor Mitchell Welch

Associate Professor of Computational Science , Computer Science - Precision Agriculture Research Group (PARG); School of Science and Technology

Mitchell Welch

Phone: +61 2 6773 5004

Email: mwelch8@une.edu.au

Biography

Mitchell Welch is currently working as an Associate Professor at the University of New England after completing his postgraduate research and undergraduate studies in Computer and Data science.  Previously, Mitchell worked as a software engineer, focusing on the development and customisation of cloud-hosted software, database systems and the integration platforms that connect enterprise information systems together.

Since 2014 Mitchell has worked on a range of research projects focusing on data science, machine learning and high-performance computing. His PhD project focused on the development of an Agent-Based Models for the establishment and spread of invasive insects and their situated effects on Australia’s agricultural industries. This research has included the application of parallel processing technologies (including NVidia CUDA), data compression techniques and the integration of Geographical Information systems (GIS) to produce highly detailed agent-base simulations.

Since then, Mitchell has carried out research on the application of machine learning and analytical techniques to agricultural applications. Some of these projects have included the development of approaches for livestock monitoring system using inertial sensors, the development of virtual herding/fencing technologies in sheep and the implementation of RFID tag-based tracking systems for monitoring layer hens in industrial poultry production.

More recently, Mitchell’s research has focused on the application of algorithms and approaches to the analysis collective behaviour and performance in team-based sport. He is currently working on a range of projects that aim to quantify the movement/collective behaviours of sports players within field-based sports and how this relates to the patterns of collective movement in nature. These multi-faceted projects incorporate the analysis of data from GPS-based tracking systems, the development of object tracking approaches for extracting player and animal positions from video data and the use of HPC platforms to analyse the resulting large datasets. The over-arching goal of these projects is to develop simulations that allow for the experimentation on the rules of interaction that govern the movement of teams and groups of animals.

Since 2015, Mitchell has served as the Postgraduate Coordinator for the computational science discipline. In 2016, he was responsible for the re-development of the course plans and curriculums for the Master of Computer Science, Master of Data Science, Master of Information Technology and their corresponding graduate diplomas/certificates.

Qualifications

BCompSc(Hons) UNE, PhD UNE

Teaching Areas

  • Databases
  • Introductory Information Technology
  • Computer Networks
  • Systems Analysis and Design

Research Interests

  • Agent-based Modelling in Ecology, Agriculture and Biology
  • Analysis and modelling of collective behaviour in team-based sports and livestock/animal groups.
  • Applied Machine learning (E.g. Activity classification from inertial sensors, performance and risk prediction from movement data in sports)
  • Applied computer vision-based object tracking.
  • Development of Intelligent sensing devices for integration into information systems in sports science, agriculture and ecology

Research Supervision Experience

I am on the supervision register and available as a primary supervisor for HDR students. I have successfully supervised multiple PhD, Masters and Honours students to completion.

Publications

Barwick J, Lamb DW, Dobos R, Welch M, Schneider D, Trotter M. Identifying Sheep Activity from Tri-Axial Acceleration Signals Using a Moving Window Classification Model. Remote Sensing. 2020; 12(4):646.

Sibanda TZ, Walkden-Brown S, Kolakshyapati M, et al. Flock use of the range is associated with the use of different components of a multi-tier aviary system in commercial free-range laying hens. British poultry science. 2019:1-10.

Ruhnke I, Boshoff J, Cristiani I, et al. Free-range laying hens: using technology to show the dynamics and impact of hen movement. Animal Production Science. 2019; 59(11):2046-2056.

Kolakshyapati M, Flavel R, Sibanda T, Schneider D, Welch M, Ruhnke I. Various bone parameters are positively correlated with hen body weight while range access has no beneficial effect on tibia health of free-range layers. Poultry science. 2019; 98(12):6241-6250.

Guo L, Wang W, Kwan P, et al. Advances in livestock behavior monitoring based on accelerometer motion sensor. Journal of Agricultural Science and Technology (Beijing). 2019; 21(3):94-101.

Cummins C, Welch M, Inkster B, et al. Modelling the relationships between volume, intensity and injury-risk in professional rugby league players. Journal of science and medicine in sport. 2019; 22(6):653-660.

Al Kindi KM, Kwan P, Andrew NR, Welch M. Modelling the potential effects of climate factors on Dubas bug (Ommatissus lybicus) presence/absence and its infestation rate: A case study from Oman. Pest management science. 2019; 75(11):3039-3049.

Guo L, Welch M, Dobos R, Kwan P, Wang W. Comparison of grazing behaviour of sheep on pasture with different sward surface heights using an inertial measurement unit sensor. Computers and electronics in agriculture. 2018; 150:394-401.

Barwick J, Lamb DW, Dobos R, Welch M, Trotter M. Categorising sheep activity using a tri-axial accelerometer. Computers and Electronics in Agriculture. 2018; 145:289-297.

Barwick J, Lamb D, Dobos R, Schneider D, Welch M, Trotter M. Predicting lameness in sheep activity using tri-axial acceleration signals. Animals. 2018; 8(1):12.

Al‐Kindi KM, Al‐Wahaibi AK, Kwan P, et al. Predicting the potential geographical distribution of parasitic natural enemies of the Dubas bug (Ommatissus lybicus de Bergevin) using geographic information systems. Ecology and evolution. 2018; 8(16):8297-8310.

Foley J, Kwan P, Welch M. A Web-Based Infrastructure for the Assisted Annotation of Heritage Collections. Journal on Computing and Cultural Heritage (JOCCH). 2017; 10(3):1-25.

Al-Kindi KM, Kwan P, Andrew NR, Welch M. Remote sensing and spatial statistical techniques for modelling Ommatissus lybicus (Hemiptera: Tropiduchidae) habitat and population densities. PeerJ. 2017; 5:e3752.

Al-Kindi KM, Kwan P, Andrew NR, Welch M. Impacts of human-related practices on Ommatissus lybicus infestations of date palm in Oman. PloS one. 2017; 12(2).

Al-Kindi KM, Kwan P, Andrew NR, Welch M. Modelling spatiotemporal patterns of dubas bug infestations on date palms in northern Oman: A geographical information system case study. Crop protection. 2017; 93:113-121.

Al-Kindi KM, Kwan P, Andrew N, Welch M. Impact of environmental variables on Dubas bug infestation rate: A case study from the Sultanate of Oman. PloS one. 2017; 12(5).

Welch M, Kwan P. Applying Graphics Processing Unit Technologies to Agent-Based Simulation, in Encyclopedia of Information Science and Technology, IGI Global, 2015.

Kwan PW, Welch MC, Foley JJ. A knowledge-based Decision Support System for adaptive fingerprint identification that uses relevance feedback. Knowledge-Based Systems. 2015; 73:236-253.

Welch M, Kwan P, Sajeev A. Applying GIS and high performance agent-based simulation for managing an Old World Screwworm fly invasion of Australia. Acta tropica. 2014; 138:S82-S93.

Welch M, Kwan P, Sajeev A, Garner G. Improving the efficiency of large-scale agent-based models using compression techniques, in Multidisciplinary Computational Intelligence Techniques: Applications in Business, Engineering, and Medicineed^eds, IGI Global, 2012.

Conferences

Welch MC, Cummins C, Thornton H, King D, Murphy A. Training Load Prior to Injury in Professional Rugby League Players: Analysing Injury Risk with Machine Learning. ISBS Proceedings Archive. 2018; 36(1):330.

Welch M, Kwan P, Sajeev A. A high performance, agent-based simulation of old world screwworm fly lifecycle and dispersal using a graphics processing unit (GPU) platform. MODSIM 2013: 20th International Congress on Modelling and Simulation-Adapting to change: the multiple roles of modelling: Modelling and Simulation Society of Australia and New Zealand; 2013.

Happold J, Garner G, Miron DJ, Sajeev A, Kwan PH, Welch M. Towards a national livestock disease model. Poster presented at the Foot and Mouth Disease (FMD) International Symposium and Workshop2010.

Welch M, Kwan PW, Sajeev A. On Engineering Challenges of Applying Relevance Feedback to Fingerprint Identification Systems. 2010 International Conference on Computational Intelligence and Software Engineering: IEEE; 2010:1-5.