Contextual gait analysis using state-of-the-art technologies
Gait is a person’s manner of walking. Gait monitoring and analysis has been used to assess, plan, and treat individuals with conditions affecting their ability to walk; to identify posture-related or movement-related problems in people with injuries; and to help athletes in sports biomechanics. Gait monitoring and recognition is relatively recent research projects. Machine vision (MV) based, floor sensor (FS) based and wearable sensor (WS) based approaches have been applied in various research. However, limited work has been reported on gait monitoring and recognition in pervasive environments. The research challenges include how to assess the external and internal factors of gait changes, and how dynamic gait analysis can be used for person recognition and condition monitoring.
This project aims to address these challenges using state-of-art technologies such as mobile technology, sensor technology and games. The project will investigate the contextual impact on gait analysis and develop a contextual gait monitoring and assessment framework. Sensor data from multi devices will be integrated to improve gait assessment and recognition accuracy. Data to be used in this study are generated from pervasive healthcare and daily living environments.
It is envisaged that inter-disciplinary (clinical and telecare service) collaborations will support the development of this project.
For additional information please contact Dr. Huiru (Jane) Zheng (h.zheng@ulster.ac.uk).
1. M.J. Yang, H. R. Zheng, H. Y. Wang, S. McClean, J. Hall and N. Harris, A machine learning approach to assessing gait patterns for Complex Regional Pain Syndrome, Medical Engineering & Physics, 2011.
2. H. Chan, M. Yang, H. Zheng, H. Wang, R. Sterritt, S. McClean and R. E. Mayagoitia, Machine Learning and Statistical Approaches to Assessing Gait Patterns of Younger and Older Healthy Adults Climbing Stairs, Natural Computation (ICNC), 2011 Seventh International Conference on, vol.1, pp.588-592, 26-28 July 2011.
3. H. Chan, H. Zheng, H. Wang, R. Gawley, M. Yang and R.Sterritt, Feasibility study on iPhone Accelerometer for Gait Analysis, Pervasive Computing Technologies for Healthcare (PervasiveHealth), 2011 5th International Conference on, pp.184-187, 23-26 May 2011 .
4. M.J. Yang, H. R. Zheng, H. Y. Wang, S. McClean and N. Harris, A Combination of Feature Ranking with PCA: an Application to Gait. 2010 International Conference on Machine Learning and Cybernetics, Qindao, China, July 15-17, 2010.
Personnel Involved
First Supervisor: Zheng, H Dr
Second Supervisor: Wang, HY Dr
Third Supervisor: McClean, SI Prof
Collaboration: This project does not involve collaboration with another establishment