A genetic algorithm-based feature selection method for human identification based on ground reaction force

  • Authors:

  • Su Xu;Xu Zhou;Yi-ning Sun

  • Affiliations:

  • The Key lab of Biomimetic Sensing and Advanced Robot Tech, Inst. of Intel Machines, Chinese Academy of Science, Hefei, Anhui, China;The Key lab of Biomimetic Sensing and Advanced Robot Tech, Inst. of Intel Machines, Chinese Academy of Science, Hefei, Anhui, China;The Key lab of Biomimetic Sensing and Advanced Robot Tech, Inst. of Intel Machines, Chinese Academy of Science, Hefei, Anhui, China

  • Venue:
  • Proceedings of the first ACM/SIGEVO Summit on Genetic and Evolutionary Computation
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

Biometrics-based identification is a promising technology. Ground reaction force (GRF), with its characteristics of non-invasion, easily measurement and low environment-affection, shows a potential in this field. Feature selection is an important step in biometrics-based identification. In this paper, a genetic algorithm-based feature selection method was discussed. The proposed algorithm has the advantage of finding small subsets of features that perform well in identification. Two contrast experiments were conducted to show the effectiveness of the algorithm, which shows that with GA, higher identification accuracy and smaller feature size were reached