Table 4 Comparative outcomes of GRHIP-EDLIBWO methodology with existing models20,21,36,37,38.
Methodology | \(Acc{u}_{y}\) | \(Pre{c}_{n}\) | \(Rec{a}_{l}\) | \({F1}_{score}\) |
|---|---|---|---|---|
2DCNN and LSTM-LMS | 89.50 | 82.67 | 83.09 | 81.28 |
CNN-2layer LSTM | 94.00 | 76.25 | 73.91 | 86.63 |
3DCNN-SL-GCN | 98.00 | 78.61 | 74.36 | 76.15 |
CNN + RNN | 75.11 | 69.46 | 71.13 | 70.21 |
Pose Estimation + LSTM | 94.99 | 79.90 | 86.87 | 83.02 |
LiST-LFCISLT | 96.92 | 84.91 | 78.35 | 80.32 |
ANN Algorithm | 89.45 | 74.44 | 86.00 | 81.80 |
MLP Model | 90.04 | 76.97 | 84.16 | 73.29 |
hDNN-SLR | 97.10 | 74.99 | 81.69 | 75.55 |
Bi-LSTM | 92.84 | 81.55 | 82.01 | 84.09 |
HNN | 91.58 | 75.78 | 85.70 | 85.55 |
VA-E | 92.05 | 73.00 | 85.54 | 78.21 |
GRHIP-EDLIBWO | 98.72 | 87.37 | 87.14 | 87.04 |
