Table 11.
Competitive results from other methods.
| Authors | Year | Data Size | Number of Classes | Method | Accuracy (%) |
|---|---|---|---|---|---|
| Meena et al. [143] | 2019 | 259,627 | 4 | Decision Tree | 97.35 |
| Sow et al. [144] | 2019 | 6935 | 4 | ANN, SVM, RF, and NB | 94.74 |
| Laengsri et al. [67] | 2019 | 186 | 2 | DT, KNN, RF, ANN, and SVM | 98.03 |
| Ayyildiz and Tuncer [35] | 2019 | 342 | 2 | SVM and KNN | 96.20 |
| Kilicarslan et al. [74] | 2020 | 15,300 | 5 | GA-CNN and GA-SAE | 98.50 |
| Çil et al. [58] | 2020 | 342 | 2 | ELM, RELM, SVM, and KNN | 95.59 |
| Tyas et al. [145] | 2020 | 7108 | 9 | Multilayer Perceptron | 93.77 |
| De and Chakraborty [146] | 2021 | 200 | 2 | LR, RF, NB, MLP, DT, and KNN | 92.00 |
| Fu Yi-Kai et al. [147] | 2021 | 350 | 3 | Support Vector Machine | 76.00 |
| Dejene et al. [148] | 2022 | 11,174 | 4 | RF, Extreme Gradient Boosting, and Cat Boost | 97.56 |
| Memmolo et al. [149] | 2022 | 1000 | 2 | DT, DA, NB, SVM, KNN, and Ensemble Learning | 84.30 |
| Memmolo et al. [149] | 2022 | 1000 | 5 | DT, DA, NB, SVM, KNN, and Ensemble Learning | 69.50 |
| Islam et al. [30] | 2022 | 3020 | 2 | LR, LDA, KNN, SVM, QDA, NN, CART, and RF | 81.29 |
| Proposed Model | 2023 | 190 | 4 | ELM | 99.21 |