A ECG Signal Compression and Recognition Method Based on Singular Value Decomposition

Abstract

The invention discloses a method for compressing and identifying an ECG signal based on singular value decomposition. The R wave is used as the reference point, the first 100 sample points and the last 150 sample points are used as the heartbeat, and the ECG signal is intercepted by the heartbeat to obtain the experimental data; the SVM model is established by the method of feature extraction and numerical standardization; Establishment of the CNN model; S2. For the data in the MIT-BIH database, obtain the position of the R-wave in the ECG signal through R-wave detection; make the length of the R-R segment of the ECG signal equal through period standardization; perform SVD decomposition and reconstruction to obtain compression Signal; compressed test data is obtained through R wave detection and heartbeat interception, and it is applied to the established SVM model and CNN model to test the accuracy.

Description

technical field [0001] The invention relates to the field of biomedical information processing, in particular to a method for compressing and identifying electrocardiographic signals based on singular value decomposition. Background technique [0002] Remote ECG monitoring system - composed of ECG monitoring mobile phone terminal, hospital monitoring center server and network communication support, has been widely used in medical treatment, collects ECG signals through wearable electronic devices, transmits them to the server through the network, and ensures the patient's heart health Conditions can be monitored and classified in real-time under the server-side ECG classification system, and medical professionals can respond more quickly and effectively to some acute heart diseases. This makes the transmission of ECG signals an indispensable and important part of the entire operation. However, due to multiple cycles and high resolution, the amount of collected ECG data is t...

AI Technical Summary

Problems solved by technology

However, due to multiple cycles and high resolution, the amount of collected ECG data is too large to affect the transmission efficiency and portability of ECG data, which requires ECG signals to be compressed

[0003] In order to ensure the accuracy of diagnostic results, lossless compression is often used in the field of ECG monitoring and diagnosis. The advantage of lossless compression is that it can compress signals without data loss. The disadvantage is that it cannot obtain a high compression rate, which inevitably leads to a reduction in transmission efficiency.

Images