TY - GEN
T1 - Real Time ECG Classification System Based on DWT and SVM
AU - Liu, Yanze
AU - Dong, Li
AU - Zhang, Bing
AU - Xin, Youze
AU - Geng, Li
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/11/23
Y1 - 2020/11/23
N2 - Electrocardiogram (ECG) signal reflects the state of the heart. Arrhythmia detection in the ECG record plays a critical role in the clinical diagnosis of heart diseases. With the development of artificial intelligence technology in recent years, machine learning algorithms represented by Support Vector Machine (SVM) have been used for the classification of ECG signal. Based on the discrete wavelet transform (DWT) and SVM classification algorithm, this work implements a hardware system including ECG signal acquisition, feature extraction and the classification on the Xilinx ZYNQ SoC. Especially, a power efficient DWT acceleration module is proposed. The system classification accuracy is 98.7% and the classification time of each heartbeat is 280 \mu s with on-chip power of 2.059 W, which meets the requirement of real-time system.
AB - Electrocardiogram (ECG) signal reflects the state of the heart. Arrhythmia detection in the ECG record plays a critical role in the clinical diagnosis of heart diseases. With the development of artificial intelligence technology in recent years, machine learning algorithms represented by Support Vector Machine (SVM) have been used for the classification of ECG signal. Based on the discrete wavelet transform (DWT) and SVM classification algorithm, this work implements a hardware system including ECG signal acquisition, feature extraction and the classification on the Xilinx ZYNQ SoC. Especially, a power efficient DWT acceleration module is proposed. The system classification accuracy is 98.7% and the classification time of each heartbeat is 280 \mu s with on-chip power of 2.059 W, which meets the requirement of real-time system.
KW - Electrocardiogram (ECG)
KW - arrhythmia detection
KW - discrete wavelet transform (DWT)
KW - support vector machine (SVM)
UR - https://www.scopus.com/pages/publications/85100966238
U2 - 10.1109/ICTA50426.2020.9332052
DO - 10.1109/ICTA50426.2020.9332052
M3 - 会议稿件
AN - SCOPUS:85100966238
T3 - Proceedings of 2020 IEEE International Conference on Integrated Circuits, Technologies and Applications, ICTA 2020
SP - 155
EP - 156
BT - Proceedings of 2020 IEEE International Conference on Integrated Circuits, Technologies and Applications, ICTA 2020
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 3rd IEEE International Conference on Integrated Circuits, Technologies and Applications, ICTA 2020
Y2 - 23 November 2020 through 25 November 2020
ER -