Research Article
Classification of Electrocardiography Hybrid Convolutional Neural Network-Long Short Term Memory with Fully Connected Layer
Table 2
Comparison of proposed method with existing methods.
| | Authors | Approach | Year | Num. of classes | Accuracy (%) | F1 score | Precision | Recall |
| | [9] | Wavelet + BiLSTM | 2018 | 5 | 99.25 | — | — | — | | [10] | NB, SVM, MLP, and OPF | 2019 | 5 | 94.30 | — | — | — | | [21] | CAE and LSTM | 2019 | 5 | 99.00 | — | — | 99.00% | | [23] | Deep residual network | 2020 | 5 | 99.06 | — | 96.76 | 93.21% | | [35] | LSTM | 2020 | 5 | 99.37 | 95.77% | 96.73% | 94.89% | | [43] | CNN-LSTM | 2020 | 8 | 99.01 | — | — | — | | Proposed method | Fully connected CNN-LSTM | 2022 | 5 | 99.43 | 96.27% | 94.85% | 92.85% |
|
|
