Table 5 Comparison Analysis of our proposed model with existing works.

From: A hybrid cardiovascular arrhythmia disease detection using ConvNeXt-X models on electrocardiogram signals

Author

Data type

Dataset

Proposed model

Accuracy (%)

Bechinia et al.15

ECG

MIT-BIH Arrhythmia

CNN

99.22

Zhang et al.16

ECG

MIT-BIH Arrhythmia

2d-CNN

99.12

Zubair et al.17

ECG

MIT-BIH Arrhythmia

CNN

96.19

Chen et al.18

ECG

MIT-BIH Arrhythmia

MPR-STSGCN

99.71

Tahmid et al.19

ECG

MIT-BIH Arrhythmia

CNN

97.30

Aphale et al.20

ECG

MIT-BIH Arrhythmia

ArrhyNet

92.73

Katal et al.21

ECG

MIT-BIH Arrhythmia

CNN

91.20

Shi et al.22

ECG

MIT-BIH Arrhythmia

CNN+LSTM

94.20

Banos et al.23

ECG

MIT-BIH Arrhythmia

CNN+PSO

97.00

Sabor et al.25

ECG

MIT-BIH Arrhythmia

CNN

97.83

Farag et al.26

ECG

MIT-BIH Arrhythmia

CNN

99.10

Singh et al.27

ECG

MIT-BIH Arrhythmia

ACDAE

98.88

Bhattacharyya et al.28

ECG

MIT-BIH Arrhythmia

RF + SVM

98.21

Pokaprakarn et al.29

ECG

MIT-BIH Arrhythmia

CNN + RNN

97.60

Gill et al.30

ECG

MIT-BIH Arrhythmia

DenseNet121

80.00

Proposed model

ECG

MIT-BIH Arrhythmia

STL+ConvNeXtTiny

99.75