Title: Identifying individuals from gait pattern using waist-mounted accelerometer
Authors: Yuexiang Li; Xiaobo Wang; Feng Qiao
Addresses: School of Computer and Information Technology, Shanxi University, 92 Wucheng Road, Xiaodian District, Taiyuan, Shanxi, 030006, China. ' School of Computer and Information Technology, Shanxi University, 92 Wucheng Road, Xiaodian District, Taiyuan, Shanxi, 030006, China. ' Faculty of Information and Control Engineering, Shenyang Jianzhu University, 9 Hunnan East Road, Hunnan New District, Shenyang, Liaoning, 110168, China
Abstract: A novel algorithm to identify individuals via gait pattern by waist-mounted MEMS accelerometer is presented. Vertical acceleration signal is selected and represented as a seven-feature-tuple extracted from continuous wavelet transform. A multi-criterion model is designed to match the feature sequences using dynamic time wrapping algorithm. Experiments with a dataset of 24 subjects show that the equal error rate of the proposed algorithm has achieved 5% which is superior to that of 6.4% and 6.7% in the previous work.
Keywords: individual identification; waist mounted accelerometers; gait patterns; dynamic time wrapping algorithm; multicriteria modelling; wavelet transforms; feature sequences; behavioural biometrics; gait recognition.
DOI: 10.1504/IJAMECHS.2012.045494
International Journal of Advanced Mechatronic Systems, 2012 Vol.4 No.1, pp.3 - 10
Published online: 30 Aug 2014 *
Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article