|
ECG based cardiac disorder classification using MobileNetV3 and LSTM |
|---|---|
| รหัสดีโอไอ | |
| Creator | Kusuma Sreenivasa |
| Title | ECG based cardiac disorder classification using MobileNetV3 and LSTM |
| Contributor | Kusuma Sreenivasa |
| Publisher | Asia-Pacific Journal of Science and Technology |
| Publication Year | 2566 |
| Journal Title | Asia-Pacific Journal of Science and Technology |
| Journal Vol. | 28 |
| Journal No. | 5 |
| Page no. | 7 |
| Keyword | Cardiovascular disease, CNN, ECG, MobileNetV3, LSTM |
| URL Website | https://www.tci-thaijo.org/index.php/APST |
| Website title | https://so01.tci-thaijo.org/index.php/APST/article/view/257271 |
| ISSN | 2539-6293 |
| Abstract | The early recognition of cardiovascular diseases is very important to stave off their development. An effective test such as the electrocardiogram (ECG) can be performed at the first sign of a problem. The objective of this study is to foster a framework that can classify heart disease using MobileNetV3 and Long Short-Term Memory (LSTM). The proposed framework is proficient in keeping up with stateful data for exact predictions. The performance has been analyzed with other extended convolutional neural network (CNN) architectures. The presented methodology is performed on the Research Resource for Complex Physiologic Signals dataset and beat other methods by achieving more than 89.62% accuracy. Its robustness in perceiving the abnormalities is a lot quicker with practically 3 times lesser calculations than the traditional MobileNet architecture outcomes in insignificant analytical endeavors. The experiments conducted on the system revealed that it performed well in terms of classification and dimensionality reduction, also indicated that it could help diagnose and monitor patients efficiently. |
