Class Imbalance in UWB-Based Backward Driving Detection 


Vol. 50,  No. 11, pp. 1683-1686, Nov.  2025
10.7840/kics.2025.50.11.1683


PDF Full-Text
  Abstract

Backward driving in highway Hi-Pass lanes poses serious safety risks due to limited space and sudden maneuvers. This study proposes a deep learning framework that classifies forward and backward driving using Ultra-Wideband (UWB) Channel Impulse Response (CIR) data. Experiments conducted in a real tunnel environment show that a narrow segment of the CIR sequence was found to contain the most discriminative features for direction detection. To address this limitation, the concept of the Discriminative Signal Ratio (DSR) and analyze the impact of class imbalance. CNN, LSTM, and Transformer models are compared under varying class ratios, and results show that oversampling the minority class at a 1:6 ratio yields optimal performance. The findings demonstrate the feasibility of CIR-based direction detection and provide insights for future deployment in intelligent transportation systems.

  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]

K. Lee and Y. Ko, "Class Imbalance in UWB-Based Backward Driving Detection," The Journal of Korean Institute of Communications and Information Sciences, vol. 50, no. 11, pp. 1683-1686, 2025. DOI: 10.7840/kics.2025.50.11.1683.

[ACM Style]

Kyungbo Lee and Young-Bae Ko. 2025. Class Imbalance in UWB-Based Backward Driving Detection. The Journal of Korean Institute of Communications and Information Sciences, 50, 11, (2025), 1683-1686. DOI: 10.7840/kics.2025.50.11.1683.

[KICS Style]

Kyungbo Lee and Young-Bae Ko, "Class Imbalance in UWB-Based Backward Driving Detection," The Journal of Korean Institute of Communications and Information Sciences, vol. 50, no. 11, pp. 1683-1686, 11. 2025. (https://doi.org/10.7840/kics.2025.50.11.1683)
Vol. 50, No. 11 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