Research Article
Breast Cancer Detection in the IOT Health Environment Using Modified Recursive Feature Selection
Table 9
Proposed study classification performance and results of other previously proposed methods.
| Reference | Method | Accuracy (%) |
| [38] | PCA-AE-Ada | 85 | [39] | ACO-SVM | 95.98 | [35] | GA-SVM | 97.19 | [35] | PSO-SVM | 97.37 | [26] | GA-MOO-NN | 98.85 | [14] | PCA-SVM | 96.84 | [40] | Breast cancer diagnosis techniques using SVM, PNN, and MLP | 97.80 | [11] | Classification system using fuzzy-GA method | 97.36 | [20] | Classification system using mixture ensemble of convolutional neural network | 96.39 | [41] | SAE-SVM | 98.25 | [42] | Prediction of breast cancer using SVM and K-NN | 98.57 | [43] | Breast cancer diagnosis using adaptive voting ensemble machine learning algorithm | 98.50 | [44] | Cost sensitivity SVM with IG for FS and breast cancer diagnosis | 98.83 | Proposed method | REF-SVM | 99 |
|
|