Support vector machine for classification of walking conditions using miniature kinematic sensors.

Publisher: Springer Country of Publication: United States NLM ID: 7704869 Publication Model: Print-Electronic Cited Medium: Print ISSN: 0140-0118 (Print) Linking ISSN: 01400118 NLM ISO Abbreviation: Med Biol Eng Comput Subsets: MEDLINE

Publication: New York, NY : Springer
Original Publication: Stevenage, Eng., Peregrinus.

Activities of Daily Living* ; Artificial Intelligence*; Walking/*physiology; Adult ; Biomechanical Phenomena ; Humans ; Male ; Movement/physiology ; Neural Networks, Computer

A portable gait analysis and activity-monitoring system for the evaluation of activities of daily life could facilitate clinical and research studies. This current study developed a small sensor unit comprising an accelerometer and a gyroscope in order to detect shank and foot segment motion and orientation during different walking conditions. The kinematic data obtained in the pre-swing phase were used to classify five walking conditions: stair ascent, stair descent, level ground, upslope and downslope. The kinematic data consisted of anterior-posterior acceleration and angular velocity measured from the shank and foot segments. A machine learning technique known as support vector machine (SVM) was applied to classify the walking conditions. SVM was also compared with other machine learning methods such as artificial neural network (ANN), radial basis function network (RBF) and Bayesian belief network (BBN). The SVM technique was shown to have a higher performance in classification than the other three methods. The results using SVM showed that stair ascent and stair descent could be distinguished from each other and from the other walking conditions with 100% accuracy by using a single sensor unit attached to the shank segment. For classification results in the five walking conditions, performance improved from 78% using the kinematic signals from the shank sensor unit to 84% by adding signals from the foot sensor unit. The SVM technique with the portable kinematic sensor unit could automatically recognize the walking condition for quantitative analysis of the activity pattern.

IEEE Trans Biomed Eng. 2005 Mar;52(3):486-94. (PMID: 15759579)
IEEE Trans Biomed Eng. 2006 Jul;53(7):1385-93. (PMID: 16830942)
Obes Res. 2003 Jan;11(1):33-40. (PMID: 12529483)
J Rehabil Res Dev. 1999 Jan;36(1):8-18. (PMID: 10659890)
Arch Phys Med Rehabil. 2004 Dec;85(12):1997-2001. (PMID: 15605339)
Hum Mov Sci. 2004 Nov;23(5):605-20. (PMID: 15589624)
IEEE Trans Biomed Eng. 2005 May;52(5):828-38. (PMID: 15887532)
Ergonomics. 2001 Jan 15;44(1):48-62. (PMID: 11214898)
Gait Posture. 2002 Feb;15(1):32-44. (PMID: 11809579)
J Pediatr Orthop. 2006 Mar-Apr;26(2):245-9. (PMID: 16557143)
Med Eng Phys. 1999 Mar;21(2):87-94. (PMID: 10426508)
Gait Posture. 2005 Dec;22(4):287-94. (PMID: 16274909)
Tohoku J Exp Med. 2005 Nov;207(3):197-202. (PMID: 16210830)
Med Biol Eng Comput. 2003 Nov;41(6):710-7. (PMID: 14686597)
J Biomech. 2002 Apr;35(4):537-42. (PMID: 11934425)
IEEE Trans Rehabil Eng. 1996 Jun;4(2):63-72. (PMID: 8798073)
IEEE Trans Neural Syst Rehabil Eng. 2004 Mar;12(1):81-8. (PMID: 15068191)
IEEE Trans Neural Syst Rehabil Eng. 2001 Jun;9(2):113-25. (PMID: 11474964)
Med Biol Eng Comput. 2005 Mar;43(2):273-82. (PMID: 15865139)
Gait Posture. 2001 Feb;13(1):49-66. (PMID: 11166554)
IEEE Trans Biomed Eng. 2006 Dec;53(12 Pt 1):2479-90. (PMID: 17153205)
J Biomech. 2005 Mar;38(3):401-8. (PMID: 15652537)
IEEE Trans Biomed Eng. 2002 Aug;49(8):843-51. (PMID: 12148823)
Gait Posture. 2001 Apr;13(2):102-20. (PMID: 11240358)
IEEE Trans Rehabil Eng. 2000 Sep;8(3):312-9. (PMID: 11001511)
Med Sci Sports Exerc. 1999 Jul;31(7):1053-9. (PMID: 10416569)
Gait Posture. 2008 Feb;27(2):248-57. (PMID: 17513111)

Date Created: 20080319 Date Completed: 20080924 Latest Revision: 20211020

20231215

10.1007/s11517-008-0327-x

18347832