Feature extraction and state recognition of one-dimensional physiological signal based on depth learning

Abstract

The present invention discloses a feature extraction and state recognition method for one-dimensional physiological signal based on depth learning. The method comprises: establishing a feature extraction and state recognition analysis model DBN of a on-dimensional physiological signal based on depth learning, wherein the DBN model adopts a "pre-training+fine-tuning" training process, and in a pre-training stage, a first RBM is trained firstly and then a well-trained node is used as an input of a second RBM, and then the second RBM is trained, and so forth; and after training of all RBMs is finished, using a BP algorithm to fin-tune a network, and finally inputting an eigenvector output by the DBN into a Softmax classifier, and determining a state of an individual that is incorporated into the one-dimensional physiological signal. The method provided by the present invention effectively solves the problem that in the conventional one-dimensional physiological signal classification process, feature inputs need to be selected manually so that classification precision is low; and through non-linear mapping of the deep confidence network, highly-separable features / feature combinations are automatically obtained for classification, and a better classification effect can be obtained by keeping optimizing the structure of the network.

Description

technical field [0001] The present invention relates to the technical field of medical data processing, in particular to a physiological signal feature extraction and classification recognition method, in particular to feature extraction and state recognition of one-dimensional physiological signals based on deep learning. Background technique [0002] Physiological signals are dominated by the autonomic nervous system and endocrine system, not controlled by subjective consciousness, and can objectively and truly reflect the individual's physiological, mental, and emotional states, so they have been more and more widely studied and applied. Physiological signals are the external manifestations of the individual's physiological, mental, emotional and other states, and can directly and truly reflect changes in these states. Therefore, many researchers have used different classifiers to classify data based on physiological signals (EEG, EEG, EEG, etc.) electrocardiogram, myoele...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the problems that traditional shallow classifiers need to manually extract features and the recognition effect is unstable, the present invention aims to provide a one-dimensional physiological signal feature extraction and state recognition method based on deep learning, which can effectively solve the traditional one-dimensional physiological signal classification process. In the problem that manual selection of feature input is required, resulting in low classification accuracy, it automatically obtains highly separable features and feature combinations for classification through the nonlinear mapping of the deep belief network, and continuously optimizes the network structure to obtain better classification results

Images