Augmented Fitness

Computational Intelligence for Weight Lifting

A man and a women doing push-ups with hand weights

Project overview

Wearable fitness trackers, such as Fitbit, Garmin and Microsoft band are becoming increasingly popular and inexpensive coming in different shapes and sizes with different types of functionality. Though there are many fitness trackers available in the market nowadays, they are designed to support cardio-aerobic exercises with little qualitative feedback for weight training.

In this project, the research team will explore how wearable technology can support weight lifters in analyzing their performance. The major cause of injuries at the gym is incorrect technique. By offering users a way to evaluate their performance, we can not only prevent injury, but also direct users into maximizing the effectiveness of their time at the gym. This is crucial for ensuring safe and optimal outcomes. However, specifying what a correct movement looks like is challenging. To address this, the researchers aim to develop human motion models (e.g. how a weight lifting exercise should be executed in terms of the movement on the joints of the body) based on written descriptions (e.g. the exercise instructions on a weight lifting book).  The team will also develop data visualization tools for weight lifters and trainers to evaluate performances.

This project will also explore how technology can support and motivate users at the gym. Given the worldwide obesity epidemic, motivating people to exercise remains a significant challenge with the potential to substantially improve their quality of life. Through this project, we will employ insights from fields such as gamification, collaborative systems and social psychology to design systems that motivate people to work out and maintain their exercise routine.

The planned outputs of this project will include: Machine learning algorithms to segment and classify exercise data, natural language and inertial measurement unit data processing algorithms for movement model extraction, data visualisation tools for weight lifters and trainers to evaluate performances and an interactive system that combines wearable and remote sensors that analyse users’ performances and gives them feedback.

Project team

  • Eduardo Velloso, Research Fellow, Microsoft Research Centre for SocialNUI, University of Melbourne
  • Yousef Kowsar, PhD Candidate, Microsoft Research Centre for SocialNUI, University of Melbourne
  • Masud Moshtaghi, Research Fellow, Dept of Computing and Information Systems, University of Melbourne
  • Lars Kulik, Professor, Dept of Computing and Information Systems, University of Melbourne
  • Chris Leckie, Professor, Dept of Computing and Information Systems, University of Melbourne
  • Eduardo Oliveira, Research Fellow, Melbourne Centre for the Study of Higher Education, University of Melbourne
  • Justin Fong, PhD Candidate, Mechanical Engineering, University of Melbourne
  • Thuong Hoang
    Thuong Hoang, Research Fellow, Microsoft Research Centre for SocialNUI, University of Melbourne

Contact details

Publications

Kowsar, Y., Moshtaghi, M., Velloso, E., Kulik, L., & Leckie, C. (in press) Detecting Unseen Anomalies in Weight Training Exercises. In Proceedings of the Annual Meeting of the Australian Special Interest Group for Computer Human Interaction (OzCHI 2016), November 2016, Launceston, Australia. [PDF]