Conference proceeding
An asynchronous multi-view learning approach for activity recognition using wearables
2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Vol.2016-, pp.3105-3108
08/2016
Handle:
https://hdl.handle.net/2376/104228
PMID: 28268968
Abstract
In this paper, we introduce an Asynchronous Multiview Learning (AML) approach to allow accurate transfer of activity classification models across asynchronous sensor views. Our study is motivated by the highly dynamic nature of health monitoring using wearable sensors. Such dynamics include changes in sensing platform (e.g., sensor upgrade) and platform settings (e.g., sampling frequency, on-body sensor location), which result in failure of the machine learning algorithms if they remain untrained in the new setting. Our approach allows machine learning algorithms to automatically reconfigure without any need for labeled training data in the new setting. Our evaluation using real data collected with wearable motion sensors demonstrates that the average classification accuracy using our automatically labeled training data is 85.2%. This accuracy is only 3.4% to 4.5% less than the experimental upper bound, where ground truth labeled training data are used to develop a new activity recognition classifier.
Metrics
10 Record Views
Details
- Title
- An asynchronous multi-view learning approach for activity recognition using wearables
- Creators
- Yuchao Yuchao Ma - Sch. of Electr. Eng. & Comput. Sci., Washington State Univ., Pullman, WA, USAHassan Ghasemzadeh - Sch. of Electr. Eng. & Comput. Sci., Washington State Univ., Pullman, WA, USA
- Publication Details
- 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Vol.2016-, pp.3105-3108
- Academic Unit
- Electrical Engineering and Computer Science, School of
- Publisher
- IEEE
- Identifiers
- 99900547072501842
- Language
- English
- Resource Type
- Conference proceeding