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

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

REFERENCES

• 1: Tian Jie, Yang Xing. Theories and Applications of Biometrics Identification Technologies. Beijing: publishing house of electronics industry, 2005.9: 2
• 2: Michael S. Orendurff, Greta C. Bernatz, Jason A. Schoen, Glenn K. Klute. Kinetic mechanisms to alter walking speed. Gait & Posture 27 (2008) 603--610
• 3: Kirtley C, Whittle MW, Jefferson RJ. Influence of walking speed on gait parameters. J Biomed Eng. 1985; 7: 282--288
• 4: T S Keller, A M Weisberger, J L Ray, S S Hasan, R G Shiavi,D M Spengler. Relationship between vertical ground reaction force and speed during walking, slow jogging, and running. Clinical Eiomerhanics Vol. 11. No. 5, pp. ?S3--259, 1996
• 5: White R,Agouris I.The Variability of Force Platform Data in Normal and Cerebral Palsy Gait{J}.Clinical Biomechanics,1999,14:185--192
• 6: Evie Vereecke, Kristiaan D'Août, Dirk De Clercq, Linda Van Elsacker, Peter Aerts. The Relationship between Speed, Contact Time and Peak Plantar Pressure in Terrestrial Walking of Bonobos. Clinical BiomeChanics Vol. 11. No. 5, pp. 253--259, 1996
• 7: Julie EP James OH Brian LD, Simultaneous measurement of plantar pressure and shear forces in diabetic individuals. Gait&posture 2002: 15:101--107
• 8: Metin Yavuz,, Azita Tajaddini, Georgeanne Botek, Brian L. Davis. "Temporal characteristics of plantar shear distribution: Relevance to diabetic patients," Journal of Biomechanics, vol. 41, no. 3, 2008, p 556--559
• 9: Muniz, A. M. S.; Manfio, E. F.; Andrade, M. C.; Nadal, J.; Principal Component Analysis of Vertical Ground Reaction Force: A Powerful Method to Discriminate Normal and Abnormal Gait and Assess Treatment. 28th Annual International Conference of the IEEE on Engineering in Medicine and Biology Society, Aug. 30 2006--Sept. 3 2006 Page(s):2683 -- 2686
• 10: P . Akashi , I . Sacco , R . Watari , E . Hennig. The effect of diabetic neuropathy and previous foot ulceration in EMG and ground reaction forces during gait. Clinical Biomechanics , 23(5) :584 -- 592
• 11: Isabelle Guyon , André Elisseeff, An introduction to variable and feature selection, The Journal of Machine Learning Research, 3, 3/1/2003
• 12: Feng Tan , Xuezheng Fu , Yanqing Zhang , Anu G. Bourgeois, A genetic algorithm-based method for feature subset selection, Soft Computing - A Fusion of Foundations, Methodologies and Applications, v.12 n.2, p.111-120, September 2007 [doi>10.1007/s00500-007-0193-8]
• 13: Jihoon Yang , Vasant G. Honavar, Feature Subset Selection Using a Genetic Algorithm, IEEE Intelligent Systems, v.13 n.2, p.44-49, March 1998 [doi>10.1109/5254.671091]
• 14: Melanie Mitchell, An introduction to genetic algorithms, MIT Press, Cambridge, MA, 1996
• 15: Randall S. Sexton , Robert E. Dorsey, Reliable classification using neural networks: a genetic algorithm and backpropagation comparison, Decision Support Systems, v.30 n.1, p.11-22, Dec. 15 2000 [doi>10.1016/S0167-9236(00)00086-5]

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.5 PATTERN RECOGNITION
      I.5.2 Design Methodology

General Terms:
Algorithms, Experimentation

Keywords:
biometric identification, genetic algorithm, ground reaction force