LSTM-based automatic multi-classification identification method for ballistocardiogram signals

Abstract

The invention discloses a ballistocardiogram signal automatic multi-classification identification method based on LSTM. The method comprises the steps of acquiring a data set training sample; preprocessing the obtained data set training sample by adopting a wavelet threshold denoising method to obtain a pure ballistocardiogram signal; matching the obtained ballistocardiogram signals with a self-adaptive threshold value to complete positioning of IJK waves, and obtaining heart beat interception of the ballistocardiogram signals; constructing an LSTM network model, intercepting a heart beat of the obtained ballistocardiogram signal as input data of the LSTM model, and training and testing the network model; in the training process, a back propagation algorithm is used for carrying out weightoptimization on the constructed LSTM network model, so that the network is converged to global optimum; and outputting an identification rate by the LSTM network model to obtain a classification accuracy rate, calculating a kapaa coefficient according to the correctness of confusion matrix classification, and evaluating the classification accuracy of the model. According to the method, the problems of long-range dependence of RNN and excessive dependence on manual design and low classification precision of a traditional method can be solved, and a good classification effect is obtained.

Description

technical field [0001] The invention relates to the field of physiological signal classification of deep learning, in particular to an LSTM-based automatic multi-classification recognition method for cardiac shock signals. Background technique [0002] Cardiovascular Disease (CVD), also known as circulatory system disease, is a series of diseases involving the circulatory system. It has the characteristics of high prevalence, high disability rate and high mortality rate. "Number One Killer". In my country, cardiovascular disease seriously threatens people's health. According to the 2017 "China Cardiovascular Disease Report", there are currently about 290 million CVD patients nationwide, and an average of 1 in every 5 people suffers from cardiovascular disease. Therefore, the prevention, diagnosis and treatment of cardiovascular diseases have become one of the medical topics related to the national health of our country. [0003] For heart rate acquisition, ECG signals are ...

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to use RNN to deal with the defects existing in the time series data of BCG signals, and provide an automatic multi-classification recognition method for heart shock signals based on LSTM, which provides a long-range dependence problem that can solve the problem of RNN , as well as a method to solve the problems of traditional methods relying too much on manual design and low classification accuracy, and obtain better classification results

Images