Gait Type Classification Based on Deep Learning Using Smart Insole 


Vol. 43,  No. 8, pp. 1378-1381, Aug.  2018
10.7840/kics.2018.43.8.1378


PDF
  Abstract

We propose a method to classify gait types using a sensor embedded in smart insole. A pressure sensor array was used for gait measurement, and the features of gait pattern were extracted using deep convolution neural network (DCNN). The measurement data for the continuous walking is divided into unit steps. Then preprocessed data is used as the input of the DCNN. Using the feature map obtained from the DC NN output, a final complete connection network for classification was constructed to classify the types of gait. Through the experiments for the 7 types of gait, we confirmed that the proposed method showed high classification rate of 88% or more.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Cite this article

[IEEE Style]

S. Lee, S. Chang, S. Choi, "Gait Type Classification Based on Deep Learning Using Smart Insole," The Journal of Korean Institute of Communications and Information Sciences, vol. 43, no. 8, pp. 1378-1381, 2018. DOI: 10.7840/kics.2018.43.8.1378.

[ACM Style]

Sung-Sin Lee, Seok-Ho Chang, and Sang-Il Choi. 2018. Gait Type Classification Based on Deep Learning Using Smart Insole. The Journal of Korean Institute of Communications and Information Sciences, 43, 8, (2018), 1378-1381. DOI: 10.7840/kics.2018.43.8.1378.

[KICS Style]

Sung-Sin Lee, Seok-Ho Chang, Sang-Il Choi, "Gait Type Classification Based on Deep Learning Using Smart Insole," The Journal of Korean Institute of Communications and Information Sciences, vol. 43, no. 8, pp. 1378-1381, 8. 2018. (https://doi.org/10.7840/kics.2018.43.8.1378)

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880