Human Motion Recognition Using E-textile Sensor and Adaptive Neuro-Fuzzy Inference System

다국어 초록 (Multilingual Abstract)

The present paper is intended to introduce a new approach in order to classify human body movements by using textile sensor embedded fabrics. An intelligent processing model embedded in muscle activity pants has been developed based on adaptive neuro-fuzzy inference System (ANFIS) in order to recognize the types of several standard human motions. The processing circuit would digitize motion data from the fabric stretch sensor developed in previous research. Data were continuously flowed into the memory of microcontroller chip and processed in order to get important factors like as input variables of the classification model. The parameters chosen for developing the ANFIS system are the average of amplitude (AMP), the standard deviation of amplitude (STD), and the average cycle (CYC). The final decision on the types of the motions would be stored or transmitted to nearby monitoring devices. In this study, laboratory scale experiments were conducted for four different types of human motions such as walking, jumping, running, and sprinting in order to examine the feasibility of the ANFIS model developed. The accuracy of ANFIS model was compared with results of fuzzy inference system (FIS) model and artificial neural network (ANN) model. As expected, the results indicated that the adaptive neurofuzzy expert system developed could be used as one of the smart simulators in order to recognize human motions with robust and high accuracy classification rate. Based on the test statistics, ANFIS model has been proved to be superior to ANN and FIS in terms of classification rate.

참고문헌 (Reference)

1 V. Custodio, 12 : 13907-, 2012

2 F. Zhu, 18 : 369-, 2017

3 Y. Wang, 24 : 4666-, 2014

4 T. Yamada, 6 : 296-, 2011

5 B. J. Munro, 131 : 541-, 2008

6 W. Zeng, 26 : 5310-, 2014

7 K. Cherenack, 22 : 5178-, 2010

8 V. Kaushik, 5 : 1493-, 2015

9 L. M. Castano, 23 : 53001-, 2014

10 S. Patel, 9 : 1743-, 2012

11 T. Cheng, 27 : 3349-, 2015

12 Y. Meng, 25 : 2326-, 2013

13 S. Pei, 48 : 4466-, 2010

14 C. Mattmann, 8 : 3719-, 2008

15 K. Javed, 193 : 41-, 2014

16 L. Qu, 80 : 565-, 2014

17 J. Molina, 93 : 44-, 2013

18 E. Skrzetuska, 14 : 16816-, 2014

19 C. H. Lim, 48 : 1773-, 2015

20 V. K. Ojha, 60 : 97-, 2017

21 G. Bosque, 32 : 283-, 2014

22 A. Bulsari, 5 : 401-, 1992

23 R. J. P. Alejo, 26 : 1881-, 2013

24 A. Balbinot, 13 : 2613-, 2013

25 P. M. Granitto, 163 : 139-, 2005

26 J. Han, 9 : 109-, 1996

27 P. Koprinkova, 12 : 281-, 1999

28 F. M. Dias, 17 : 945-, 2004

29 C. L. Hui, 74 : 375-, 2004

30 D. Teichmann, 34 : 963-, 2013

31 S. -Y. Chiang, 16 : 2053-, 2016

32 W. Caesarendra, 1007 : 012005-, 2018

33 C. Vu, 18 : 1931-, 2017

34 Z. Chen, 44 : 2902-, 2011

35 L. Wang, 36 : 585-, 2003

36 Y. Y. Jhun, 29 : 2213-, 2008

37 O. D. Lara, 15 : 1192-, 2013

38 R. -E. Precup, 62 : 213-, 2011

39 Z. Zhang, 18 : 334-, 2017

40 K. Liu, 17 : 1522-, 2016

41 J. Kim, 17 : 963-, 2016

42 S. Miyamoto, "Algorithms for Fuzzy Clustering" Springer Berlin Heidelberg 9-42, 2008