Skip to main content
. 2022 Jan 1;22(1):323. doi: 10.3390/s22010323

Table 4.

Shows the accuracy of our hybrid approach as compared to other deep learning models.

No. Model Name Frames Sequence
30 60 90 120 150
1 MLP 85.45 83.64 83.47 87.05 71.51
2 CNN 88.82 88.22 87.65 83.74 75.47
3 LSTM 83.31 80.64 74.69 82.92 66.09
4 BiLSTM 90.15 85.39 89.30 82.02 66.26
5 CNN-LSTM 90.89 88.98 90.44 87.94 76.50