Resizing Method for Applying RF-based Data to ViT in Human Activity Recognition 


Vol. 50,  No. 5, pp. 725-727, May  2025
10.7840/kics.2025.50.5.725


PDF Full-Text
  Abstract

This paper applies RF-based data, obtained through the commonly used Radio Frequency (RF) approach in human activity recognition (HAR), to the Vision Transformer (ViT), a state-of-the-art machine learning method for image classification. Through this process, we analyze the challenges arising from applying RF-based data, which have different sizes compared to standard image dimensions, to ViT. To address these challenges, we propose various input resizing methods. Furthermore, through a comparison of these resizing methods, we identify the most effective resizing approach for RF-based data, achieving an average accuracy improvement of 9.57%.

  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]

J. Park and S. Bahk, "Resizing Method for Applying RF-based Data to ViT in Human Activity Recognition," The Journal of Korean Institute of Communications and Information Sciences, vol. 50, no. 5, pp. 725-727, 2025. DOI: 10.7840/kics.2025.50.5.725.

[ACM Style]

Jeongjun Park and Saewoong Bahk. 2025. Resizing Method for Applying RF-based Data to ViT in Human Activity Recognition. The Journal of Korean Institute of Communications and Information Sciences, 50, 5, (2025), 725-727. DOI: 10.7840/kics.2025.50.5.725.

[KICS Style]

Jeongjun Park and Saewoong Bahk, "Resizing Method for Applying RF-based Data to ViT in Human Activity Recognition," The Journal of Korean Institute of Communications and Information Sciences, vol. 50, no. 5, pp. 725-727, 5. 2025. (https://doi.org/10.7840/kics.2025.50.5.725)
Vol. 50, No. 5 Index

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880