Table 8 Comparison with state-of-the-art methods
From: Optimizing diabetes classification with a machine learning-based framework
Authors | Models | Classification accuracy (%) |
|---|---|---|
Krishnamoorthi et al. [7] | LR, KNN, SVM, RF | 83 |
Saxena et al. [6] | KNN, RF, DT, MLP | 79 |
Garcia-Ordas et al. [13] | VAE, SAE, CNN | 92.31 |
Bukhari et al. [15] | ABP-SCGNN | 93 |
Gnanadass [18] | NB, LR, RF, AB, GBM, XGB | 77.54 |
Maniruzzaman et al. [10] | LDA, QDA, NB, GPC, SVM, ANN, AB, LR, DT, RF | 92.26 |
Hayashi and Yukita [19] | Re-RX with J 48 graft | 83.83 |
Alneamy et al. [20] | TLBO, FWNN, FLNN, FFWNN | 88.67 |
Chang et al. [21] | NB, RF, J48 | 79.57 |
Ours | DCSGAN | 96.27 |