An effective method for identification of ECG signals before and after exercise

Abstract

The invention discloses an effective method for identification of ECG signals before and after exercise. The method comprises the following steps: collecting ECG signals of several subjects before andafter exercise, using half of the subjects' ECG signal data as an auxiliary data set for selecting optimal features, and the taking other half of the subjects as an experimental data set for verifying the validity of the selected optimal feature; performing various feature extraction on the collected ECG signal data; standardizing the extracted features; using a KL divergence indicator to sort the various features after standardization on the auxiliary data set to find the optimal feature combination; on the experimental data set, using the selected optimal feature combination and ECG signaldata before exercise for training a classifier, classifying and evaluating the ECG signal data after exercise, and verifying the validity of the optimal feature combination; registering the ECG signalof ordinary person before exercise, and performing the ECG signal identification according to the optimal feature combination after exercise.

Description

technical field [0001] The invention relates to the field of biomedical information processing, in particular to an effective method for identification of ECG signals before and after exercise. Background technique [0002] Biometric identification technology is based on the unique and difficult-to-forge anatomical, physiological or behavioral characteristics between people, and realizes personal identification through digital processing. Common biometric identification methods mainly include faces, fingerprints, and voices. Although these recognition methods are mature in technology and have a high recognition rate, they are not invulnerable. For example, human faces can be deciphered by taking pictures and makeup, fingerprints can be copied, stolen and recreated with latex, and voices can be deciphered by recording or imitating. In order to strengthen the reliability and security of biometric identification technology, experts and scholars at home and abroad, on the one ...

AI Technical Summary

Problems solved by technology

[0003] However, the weak nature of ECG signals makes it difficult to use ECG signals for identification

Weak ECG signals are highly susceptible to noise interference

The accuracy of ECG signal identification collected outside the laboratory is far from satisfactory

In addition, changes in people's emotions and exercise status will also have a great impact on ECG signals, especially changes in exercise status will not only significantly change heart rate, but also affect P, Q, R, S, and T waves in different ways. There are differences, which makes it very difficult to deal with, and it is difficult to find features that remain relatively stable before and after the change of motion state for high-quality identification

Images