A Mental Workload Evaluation Model Based on Improved Multibranch LSTM Network with Attention Mechanism

Table 4

2-classification experimental results.

Model\Index	Acc	P	R	F-score
CNN	0.7937 ± 0.1125	0.8084 ± 0.1226	0.8114 ± 0.1310	0.7878 ± 0.1063
RNN	0.7620 ± 0.1281	0.7821 ± 0.1118	0.7553 ± 0.1332	0.7573 ± 0.1451
LSTM	0.8218 ± 0.1054	0.8446 ± 0.1213	0.8092 ± 0.1219	0.8114 ± 0.1067
Reference [31]	0.8882 ± 0.0805	0.8789 ± 0.1154	0.8467 ± 0.1026	0.8755 ± 0.1100
Reference [32]	0.8637 ± 0.0993	0.8606 ± 0.0412	0.8620 ± 0.0317	0.8479 ± 0.0924
Proposed	0.9533 ± 0.0334	0.9721 ± 0.0 215	0.9329 ± 0.0281	0.9448 ± 0.0332