Display options
Cite
Zhang Y, Liao Y, Wu X, et al. Non-Uniform Sample Assignment in Training Set Improving Recognition of Hand Gestures Dominated with Similar Muscle Activities. Front Neurorobot. 2018;12:3doi: 10.3389/fnbot.2018.00003.
Zhang, Y., Liao, Y., Wu, X., Chen, L., Xiong, Q., Gao, Z., Zheng, X., Li, G., & Hou, W. (2018). Non-Uniform Sample Assignment in Training Set Improving Recognition of Hand Gestures Dominated with Similar Muscle Activities. Frontiers in neurorobotics, 123. https://doi.org/10.3389/fnbot.2018.00003
Zhang, Yao, et al. "Non-Uniform Sample Assignment in Training Set Improving Recognition of Hand Gestures Dominated with Similar Muscle Activities." Frontiers in neurorobotics vol. 12 (2018): 3. doi: https://doi.org/10.3389/fnbot.2018.00003
Zhang Y, Liao Y, Wu X, Chen L, Xiong Q, Gao Z, Zheng X, Li G, Hou W. Non-Uniform Sample Assignment in Training Set Improving Recognition of Hand Gestures Dominated with Similar Muscle Activities. Front Neurorobot. 2018 Feb 12;12:3. doi: 10.3389/fnbot.2018.00003. eCollection 2018. PMID: 29483866; PMCID: PMC5816264.
Copy Download .nbib Format: NLM
Share it on

Front Neurorobot. 2018 Feb 12;12:3. doi: 10.3389/fnbot.2018.00003. eCollection 2018.

Non-Uniform Sample Assignment in Training Set Improving Recognition of Hand Gestures Dominated with Similar Muscle Activities.

Frontiers in neurorobotics

Yao Zhang, Yanjian Liao, Xiaoying Wu, Lin Chen, Qiliang Xiong, Zhixian Gao, Xiaolin Zheng, Guanglin Li, Wensheng Hou

Affiliations

  1. Key Laboratory of Biorheological Science and Technology, Ministry of Education, Bioengineering College, Chongqing University, Chongqing, China.
  2. Chongqing Engineering Research Center of Medical Electronics Technology, Chongqing, China.
  3. Key Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China.

PMID: 29483866 PMCID: PMC5816264 DOI: 10.3389/fnbot.2018.00003

Abstract

So far, little is known how the sample assignment of surface electromyogram (sEMG) features in training set influences the recognition efficiency of hand gesture, and the aim of this study is to explore the impact of different sample arrangements in training set on the classification of hand gestures dominated with similar muscle activation patterns. Seven right-handed healthy subjects (24.2 ± 1.2 years) were recruited to perform similar grasping tasks (fist, spherical, and cylindrical grasping) and similar pinch tasks (finger, key, and tape pinch). Each task was sustained for 4 s and followed by a 5-s rest interval to avoid fatigue, and the procedure was repeated 60 times for every task. sEMG were recorded from six forearm hand muscles during grasping or pinch tasks, and 4-s sEMG from each channel was segmented for empirical mode decomposition analysis trial by trial. The muscle activity was quantified with zero crossing (ZC) and Wilson amplitude (WAMP) of the first four resulting intrinsic mode function. Thereafter, a sEMG feature vector was constructed with the ZC and WAMP of each channel sEMG, and a classifier combined with support vector machine and genetic algorithm was used for hand gesture recognition. The sample number for each hand gesture was designed to be rearranged according to different sample proportion in training set, and corresponding recognition rate was calculated to evaluate the effect of sample assignment change on gesture classification. Either for similar grasping or pinch tasks, the sample assignment change in training set affected the overall recognition rate of candidate hand gesture. Compare to conventional results with uniformly assigned training samples, the recognition rate of similar pinch gestures was significantly improved when the sample of finger-, key-, and tape-pinch gesture were assigned as 60, 20, and 20%, respectively. Similarly, the recognition rate of similar grasping gestures also rose when the sample proportion of fist, spherical, and cylindrical grasping was 40, 30, and 30%, respectively. Our results suggested that the recognition rate of hand gestures can be regulated by change sample arrangement in training set, which can be potentially used to improve fine-gesture recognition for myoelectric robotic hand exoskeleton control.

Keywords: myoelectric control; pattern recognition; sample proportion; similar hand gestures; training set

References

  1. Med Eng Phys. 2014 Jul;36(7):975-80 - PubMed
  2. Ann Phys Rehabil Med. 2009 Apr;52(3):269-93 - PubMed
  3. Comput Methods Programs Biomed. 2014 Mar;113(3):736-48 - PubMed
  4. IEEE Trans Neural Syst Rehabil Eng. 2015 Sep;23(5):827-36 - PubMed
  5. Biomed Eng Online. 2014 Nov 25;13:155 - PubMed
  6. J Neuroeng Rehabil. 2011 May 09;8:25 - PubMed
  7. Biomed Eng Online. 2016 Dec 19;15(Suppl 3):140 - PubMed
  8. Hum Mov Sci. 2010 Oct;29(5):853-70 - PubMed
  9. Biomed Eng Online. 2015 Aug 14;14:78 - PubMed
  10. Exp Brain Res. 2006 Jan;168(3):450-4 - PubMed
  11. Sci Rep. 2017 Jan 31;7:41011 - PubMed
  12. Biomed Eng Online. 2014 Jul 25;13:102 - PubMed
  13. Biomed Eng Online. 2015 Jun 06;14:54 - PubMed
  14. J Rehabil Res Dev. 2011;48(6):719-37 - PubMed
  15. PLoS One. 2013;8(1):e53946 - PubMed
  16. IEEE Trans Haptics. 2015 Apr-Jun;8(2):140-51 - PubMed
  17. Food Chem. 2017 Apr 15;221:1206-1213 - PubMed
  18. IEEE Trans Biomed Eng. 2012 Mar;59(3):645-52 - PubMed
  19. NeuroRehabilitation. 2008;23 (1):29-41 - PubMed
  20. Biomed Eng Online. 2016 May 26;15(1):60 - PubMed
  21. Conf Proc IEEE Eng Med Biol Soc. 2013;2013:5754-7 - PubMed
  22. Biomed Eng Online. 2007 Dec 03;6:45 - PubMed
  23. Biomed Eng Online. 2015 Apr 09;14:30 - PubMed
  24. IEEE Trans Neural Syst Rehabil Eng. 2016 Jun;24(6):662-73 - PubMed
  25. JAMA. 2004 Oct 20;292(15):1853-61 - PubMed

Publication Types