CSI-based Vehicle target recognition and Collaborative CNN with Data-Importance-Aware
Shuo Li, Dingquan Liu, Xin Liu, Yunfei Ma, Xin Gu, Yunsheng Fan, Pingping Wang, Yao Lu, Bowen Liu · 2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC) · 2022
The introduction of orthogonal frequency division multiplexing (OFDM) and multiple input multiple output (MIMO) technology enables the new generation of the Internet of Vehicles to have the ability to integrate wireless communication and target tracking. Based on the new Internet of Vehicles, a cooperative convolutional neural network with data-importance-aware (DIA) is proposed.We use wireless channel state information (CSI) to construct a micro Doppler feature data set. A distributed collaborative machine learning method of DIA is proposed to realize the target recognition of the vehicle. Experimental results show that the vehicle recognition accuracy of the proposed method is higher than 95%, and the convergence speed of the machine learning model is improved.