Accelerometer based intelligent system for human movement recognition
- 1 June 2013
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 20-24
Abstract
This paper presents the development of a system based on computational intelligence techniques and on an accelerometer to perform, in a comfortable and non-intrusive manner, the recognition of basic movements of a person's routine. The information provided by this system can be directed to support promoting health and well-being of the individual, as well as diagnosing and remote patient monitoring. The system provides an overall success rate in recognition of movements around 93% by using support vector machines for signal classification and Fisher's discriminant ratio to select the most significant features.Keywords
This publication has 5 references indexed in Scilit:
- Activity classification using a single wrist-worn accelerometer2011
- Recognizing human activities from accelerometer and physiological sensors2008
- Detection of Daily Activities and Sports With Wearable Sensors in Controlled and Uncontrolled ConditionsIEEE Transactions on Information Technology in Biomedicine, 2008
- Living assistance systems2006
- Validation of a two-axis accelerometer for monitoring patient activity during blood pressure or ECG holter monitoringBlood Pressure Monitoring, 2003