MCT-CNN-LSTM: A Driver Behavior Wireless Perception Method Based on an Improved Multi-Scale Domain-Adversarial Neural Network
Driving behavior recognition based on Frequency-Modulated Continuous-Wave (FMCW) radar systems has become a widely adopted paradigm. Numerous methods have been developed to accurately identify driving behaviors. Recently, deep learning has gained significant attention in radar signal processing due...
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-04-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/7/2268 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Driving behavior recognition based on Frequency-Modulated Continuous-Wave (FMCW) radar systems has become a widely adopted paradigm. Numerous methods have been developed to accurately identify driving behaviors. Recently, deep learning has gained significant attention in radar signal processing due to its ability to eliminate the need for intricate signal preprocessing and its automatic feature extraction capabilities. In this article, we present a network that incorporates multi-scale and channel-time attention modules, referred to as MCT-CNN-LSTM. Initially, a multi-channel convolutional neural network (CNN) combined with a Long Short-Term Memory Network (LSTM) is employed. This model captures both the spatial features and the temporal dependencies from the input radar signal. Subsequently, an Efficient Channel Attention (ECA) module is utilized to allocate adaptive weights to the feature channels that carry the most relevant information. In the final step, domain-adversarial training is applied to extract common features from both the source and target domains, which helps reduce the domain shift. This approach enables the accurate classification of driving behaviors by effectively bridging the gap between domains. Evaluation results show that our method reached an accuracy of 97.3% in a real measured dataset. |
|---|---|
| ISSN: | 1424-8220 |