From: Fractal feature selection model for enhancing high-dimensional biological problems
Refs | Name of proposed models | Datasets | Accuracy |
---|---|---|---|
[2] | hybrid feature selection method Dynamic Feature Importance (DFI) | Biological data Face image data Biological data Other data | 85.01 ± 0.12 98.33 ± 0.54 98.86 ± 0.87 87.32 ± 0.80 |
[12] | A robust dictionary learning based on total least squares (ITLS-Robust) | SMK-CAN-187 TOX-171 GLI-85 CLL-SUB-111 | 65.8 65.6 87.5 62.3 |
[25] | Support vector machine-recursive feature elimination (SVM-RFE) | N/A | N/A |
[26] | Extended particle swarm optimization | Biomedical data | 100 |
[27] | Modified Harris Hawks optimizer for feature selection | Real biomedical datasets | 100 |
[28] | a hybrid feature selection method named Minimal Redundancy-Maximal New Classification Information (MR-MNCI) | Biomedical data | 94.89 |
[29] | min-redundancy and max-dependency (MRMD) | N/A | N/A |
[30] | Maximal independent classification information and minimal redundancy (MICIMR) | Biomedical data | 100 |
[31] | FSPFRdr and FRSLLE | Biomedical data | 95.88 ± 0.41 |
[32] | fusion of statistical importance using Standard Deviation and Difference of Mean and Median | NSL-KDD, UNSW_NB-15, CIC-IDS-2017 | 99.84 89.03 99.80 |
[33] | A semi-supervised feature selection based on ant colony optimization | Biomedical data | N/A |