Window Selection Impact in Human Activity Recognition

Authors

  • Nurul Retno Nurwulan Department of Industrial Engineering Sampoerna University, Indonesia
  • Bernard C. Jiang Department of Industrial Management, National Taiwan University of Science and Technology, Taipei, Taiwan (R.O.C.)

DOI:

https://doi.org/10.15157/IJITIS.2020.3.1.381-394

Keywords:

Activity recognition, signal segmentation, windowing, window selection, human movement

Abstract

Signal segmentation is usually applied in the pre-processing step to make the data analysis easier. Windowing approach is commonly used for signal segmentation. However, it is unclear which type of window should be used to get optimum accuracy in human activity recognition. This study aimed to evaluate which window type yields the optimum accuracy in human activity recognition. The acceleration data of walking, jogging, and running were collected from 20 young adults. Then, the recognition accuracy of each window types is evaluated and compared to determine the impact of window selection in human movement data. From the evaluation, the overlapping 75% window with 0.1 s length provides the highest accuracy with mean, standard deviation, maximum, minimum, and energy as the features. The result of this study could be used for future researches in relation to human activity recognition.

Downloads

Published

2020-03-01

How to Cite

Retno Nurwulan, N., & C. Jiang, B. (2020). Window Selection Impact in Human Activity Recognition. International Journal of Innovative Technology and Interdisciplinary Sciences, 3(1), 381–394. https://doi.org/10.15157/IJITIS.2020.3.1.381-394

Issue

Vol. 3 No. 1 (2020): International Journal of Innovative Technology and Interdisciplinary Sciences

Section

Articles

License

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.