Table 7 A comparative analysis of MTECM-FOSS performance against contemporary techniques for dataset 2.
From: Fractional-order state space reconstruction: a new frontier in multivariate complex time series
Study | Methods | Number of labels | Feature | Accuracy (%) | Prediction time (s) | ||
|---|---|---|---|---|---|---|---|
Size(MB) | Number | ||||||
Deep learning methods | Cui et al.36 | GAF-CBAM-CNN | 10 | 2.26 | NAN | 98.9 | 104 |
EMD- Resnet50 | 10 | 90.5 | NAN | 96.3 | 78 | ||
Zhong et al.37 | ShuffleNet-V2 | 10 | 7.39 | NAN | 98.2 | 0.081 | |
VGG-16 | 10 | 138.35 | NAN | 99.2 | 15.34 | ||
SLCNN-n | 10 | 0.95–4.75 | NAN | 95.6–99.5 | 0.085 | ||
Entropy Methods | Dhandapani et al.38 | MDE(NCDF) | 10 | NAN | 20 | 97.8 | NAN |
RCMDE(NCDF) | 10 | NAN | 20 | 99.6 | NAN | ||
MSE | 10 | NAN | 20 | 97.8 | NAN | ||
GGD-RCMDE | 10 | NAN | 20 | 99.6 | NAN | ||
Proposed method | MTECM-FOSS | 10 | NAN | 14 | 99.5 | 1.15 | |
