Table 6 Comparative analysis of OMHSA-IDPRGO model on Edge-IIoT and ToN-IoT datasets22,23,25,26,40,41,42,43.
Technique | \(Accu_{y}\) | \(\Pr ec_{n}\) | \({\text{Re}} ca_{l}\) | \(F1_{Score}\) |
|---|---|---|---|---|
Edge-IIoT dataset | ||||
LSTM-CSAE | 96.35 | 89.58 | 93.79 | 93.55 |
MhSaBiGRNN | 98.19 | 91.63 | 93.21 | 89.67 |
FL | 95.32 | 94.00 | 93.62 | 89.92 |
EECA-LSTM | 91.35 | 90.47 | 92.98 | 93.90 |
LSTM-KPCA | 95.81 | 89.02 | 93.23 | 93.04 |
ML-PCC and IF | 98.60 | 90.95 | 92.53 | 89.09 |
Shallow ANN | 94.76 | 93.81 | 92.97 | 89.34 |
Baseline DNN | 98.65 | 93.75 | 92.18 | 89.49 |
DAE-LSTM | 91.56 | 93.87 | 90.05 | 91.58 |
XCT-DF | 89.04 | 90.59 | 92.02 | 93.61 |
OMHSA-IDPRGO | 99.11 | 94.67 | 94.66 | 94.66 |
ToN-IoT dataset | ||||
MNBD | 90.56 | 90.76 | 83.71 | 82.34 |
NFA | 98.26 | 89.83 | 82.88 | 80.69 |
GNN | 90.46 | 91.36 | 84.31 | 82.84 |
CNN method | 90.05 | 90.24 | 83.20 | 81.60 |
DNN algorithm | 97.59 | 89.13 | 82.36 | 80.08 |
LSTM | 89.76 | 90.59 | 83.64 | 82.19 |
Decision tree | 98.15 | 89.03 | 80.75 | 80.29 |
kNN algorithm | 97.18 | 90.03 | 80.76 | 84.44 |
PCA model | 89.23 | 90.01 | 80.14 | 80.54 |
Naïve Bayes | 96.29 | 89.92 | 82.53 | 85.11 |
OMHSA-IDPRGO | 99.18 | 91.34 | 84.72 | 86.47 |
