Development of an Artificial Intelligence Model for Dumbbell Curl Motion Analysis Using IMU Data 


Vol. 47,  No. 9, pp. 1341-1352, Sep.  2022
10.7840/kics.2022.47.9.1341


PDF
  Abstract

With the increasing awareness of the importance of health among modern people, interest in exercise is increasing. Recently, after COVID-19, the demand for so-called home training, where you exercise alone at home, is increasing. The purpose of this study is to reduce the risk of injury by providing feedback during exercise at home. However, products on the market do not provide feedback, or trainers provide feedback on live streams. Also, even if you receive feedback through the video, you cannot get feedback on small movements. To solve this problem, we studied the motion analysis AI model of dumbbell curl exercise using IMU sensor data. We compared and analyzed SVM, RNN, LSTM, and ConvLSTM models, and presented a motion recognition artificial intelligence model for optimal dumbbell curl exercise using Confusion Matrix, Roc Curve, and AUC.

  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.


  Related Articles
  Cite this article

[IEEE Style]

H. Kim, S. Kim, J. Han, Y. Cho, "Development of an Artificial Intelligence Model for Dumbbell Curl Motion Analysis Using IMU Data," The Journal of Korean Institute of Communications and Information Sciences, vol. 47, no. 9, pp. 1341-1352, 2022. DOI: 10.7840/kics.2022.47.9.1341.

[ACM Style]

Hyolin Kim, Sun-A Kim, Ju-Hyuck Han, and YongSeok Cho. 2022. Development of an Artificial Intelligence Model for Dumbbell Curl Motion Analysis Using IMU Data. The Journal of Korean Institute of Communications and Information Sciences, 47, 9, (2022), 1341-1352. DOI: 10.7840/kics.2022.47.9.1341.

[KICS Style]

Hyolin Kim, Sun-A Kim, Ju-Hyuck Han, YongSeok Cho, "Development of an Artificial Intelligence Model for Dumbbell Curl Motion Analysis Using IMU Data," The Journal of Korean Institute of Communications and Information Sciences, vol. 47, no. 9, pp. 1341-1352, 9. 2022. (https://doi.org/10.7840/kics.2022.47.9.1341)