Table 5 A comparison of our model performance with several models used for gene expression data classification.
Author | Dataset | Methods | Result |
|---|---|---|---|
Danaee et al.21 | TCGA BRCA | SDAE method with SVM-RBF | Accuracy of 98.26% |
Jia et al.22 | TCGA BRCA | SVM, DT, BN, ANN, CNN-leNet and CNN-alexNet | Average accuracy of 97.36% |
MotieGhader et al.33 | mRNA and micro-RNA expression data | (WCC, LCA, GA, PSO, ACO, ICA, LA, HTS, FOA, DSOS, and CUK) with an SVM classifier | All algorithms achieved accuracy above 90% for the miRNA |
Elbashir et al.41 | TCGA BRCA | Lightweight CNN model | Accuracy of 98.76%, Sensitivity of 91.43%, and F-measure of 95.5% |
Proposed method | TCGA BRCA | EOSA-CNN | Accuracy of 98.3%, precision of 99%, f1-score of 99%, kappa of 90.3%, specificity of 92.8%, recall of 99%, and sensitivity of 98.9% |
