ECG Feature Wave Recognition Based on Adaptive Wavelet Thresholding Algorithm

ECG signal is an important basis for the diagnosis of cardiovascular diseases, which contains a lot of information related to disease treatment. Therefore, it is of great significance to process and identify the important characteristics of ECG signal in clinic. Extracorporeal counterpulsation is a kind of equipment to exert pressure on the lower limbs to treat cardiovascular diseases according to the characteristics of ECG signals. In view of the low accuracy of the existing external counterpulsator in the pressure process, based on the traditional medical signal processing methods, an algorithm based on adaptive wavelet threshold is designed to identify the characteristics of ECG signal, and the accuracy of the algorithm is verified by using the data of MIT -BIB standard database. Then, using the ECG signal collected from the negative collector of the external counterpulsation device, the experimental simulation analysis of noise removal and R-wave feature recognition is carried out to verify the feasibility of the algorithm in the application of external counterpulsation. The results show that the recognition accuracy of the wavelet threshold algorithm designed in this paper can reach 99.9%, which is 0.8% higher than other algorithms, which lays a good foundation for the detection and recognition of other wave groups. The application of this algorithm in external counterpulsation device has high safety and reliability.