.png){kind=icon}
.png){kind=icon}
Return
Freeway traffic state classification using vehicle trajectory data
.png){kind=icon}
OA
AI
C
L
S
L
L
W
Y
Y
DOI：10.3389/ffutr.2026.1662480.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This study proposes the FCM-RF-SMOTE framework to resolve the issue of data imbalance in real-time freeway traffic state classification. The framework integrates Fuzzy C-Means (FCM), Random Forest (RF), and the Synthetic Minority Over-sampling Technique (SMOTE). Traffic states are classified into four categories (smooth, stable, congested, and severely congested) based on quantitative thresholds derived from FCM clustering centers. The validation utilizes SUMO simulation with Gaussian noise and a 10 Hz sampling rate to approximate millimeter-wave radar characteristics. Results show that the proposed framework significantly increases the representation of the severe congestion class from 3.67% to 19.83%. Consequently, the overall classification accuracy is enhanced from 77.67% to 97.80%, demonstrating superior performance in handling imbalanced datasets compared to baseline methods. The findings demonstrate the robustness of the algorithm for traffic monitoring systems, particularly in identifying minority traffic states, with future work planned for physical sensor validation.
Keywords:
freeway
fuzzy c-means
random forest
SMOTE
traffic state classification
vehicle trajectory data
Journal
F
IF:
1.5
Papers:
19
Citations:
194
Organization
Cited Papers