Cardiac beat automatic identification method and system

Abstract

The invention discloses a cardiac beat automatic identification method, which comprises the following steps: S1, pre-processing electrocardiogram signals, so that pure electrocardiogram signals are obtained; dividing the obtained pure electrocardiogram signals into to-be-classified cardiac beat signals, and storing the cardiac beat signals for later use; S2, reading cardiac beat signals which are selected from a data set and classified in known categories, and setting a training set; S3, extracting and storing the cardiac beat signals of the various categories, conducting hierarchical combination and training on the stored signals, and storing a classifier which is obtained from the training; and S4, classifying and identifying the to-be-classified cardiac beats. The invention discloses a cardiac beat automatic identification system, which comprises a memory in which a program is saved and a processor, wherein the processor is used for executing the method by operating the program. With the implementation of the identification method and the identification system disclosed by the invention, the number of support vector machines required by multi-classification of the cardiac beats is reduced, computing complexity is reduced and the practical value of the classification is improved. The identification method and the identification system are widely applicable to the field of medical signal processing.

Description

technical field [0001] The invention relates to the field of medical signal processing, in particular to a method and system for automatic heart beat recognition through medical equipment. Background technique [0002] ECG: Abbreviation for electrocardiogram, electrocardiogram. [0003] An electrocardiogram is a recording of the heart's activity signals. Among them, the category of heartbeat is an important basis for diagnosing heart disease. According to the "Pharmaceutical Industry Standard of the People's Republic of China: Medical Electrical Equipment, Part II, Special Requirements for Safety and Basic Performance of Holter Electrocardiogram System" (YY0885-2013), Holter ECG equipment should have the function of automatically identifying the type of heartbeat. The technical approach of heartbeat automatic recognition is to extract the feature vector that characterizes the effective information of the electrocardiogram, and input it to the classifier algorithm to obtain...

AI Technical Summary

Problems solved by technology

However, these classification methods have the problems of high computational complexity and ignoring the classification cost. Although classifiers can have high classification accuracy, with the increase of classification categories, the number of support vector machines that need to be designed increases rapidly, and the computational complexity is greatly increased. increase, have a great impact on the actual

Images