基于脑电多尺度特征和图神经网络的紧急制动行为识别

闫光辉,黄霄,常文文

Emergency braking behavior recognition based on EEG multi-scale features and graph neural networks

Guanghui YAN,Xiao HUANG,Wenwen CHANG

表 3 不同模型的分类性能参数对比

Tab.3 Comparison of classification performance metrics across different models

算法 Acc/% P/% R/% F1/% AUC/% tt/min EEGNet 91.46 91.53 91.45 91.45 91.45 40.26 DeepConvNet 90.83 91.13 90.81 90.82 90.81 466.09 BiRNN 86.67 86.67 86.67 86.67 89.29 129.60 DGCNN 91.08 91.09 91.08 92.08 91.08 10.42 本研究 93.38 93.44 93.36 93.37 93.36 48.72