EEG relaxation recognition method and device based on time domain and frequency domain space

Abstract

The invention discloses a method and device for identifying EEG relaxation based on time domain and frequency domain space. The method includes: filtering the EEG sequence signal to be processed to extract signal waves; slicing each signal wave, and calculating The maximum value and minimum value of the projection of the signal wave on the y-axis of the corresponding slice, at least two equal-length intervals are formed according to the maximum value and the minimum value, and the grid of the signal wave is obtained according to the number of projections located in each interval Project the variability to obtain the characteristic quantity in the time domain space; calculate the energy of the signal wave, calculate the energy ratio between any two signal waves according to the frequency range of each brain wave and the energy of the signal wave, and obtain the energy ratio in the frequency domain space Feature quantity: Classify and identify the feature quantity in the time domain space and the feature quantity in the frequency domain space to obtain the degree of EEG relaxation. The present invention can extract feature quantities of different dimensions and spaces of each brainwave, thereby realizing accurate recognition of brainwave relaxation.

Description

technical field [0001] The present invention relates to the field of relaxation therapy, in particular to a method and device for identifying EEG relaxation based on time domain and frequency domain space. Background technique [0002] Relaxation training is one of the most widely used techniques in behavior therapy. It is a consultation and treatment method established and developed on the basis of psychological experiments. Good curative effects have been achieved in menopausal syndrome and changing bad behavior patterns. [0003] Existing relaxation training mainly includes recording guidance, oral guidance and biofeedback guidance. Among them, the recording instruction method is rigid and unchanged, and cannot change the content according to the state of the trainee; the oral instruction requires high requirements for the object of the oral instruction, and is limited by time and place; the biofeedback instruction is mainly based on EEG feedback, which can Combining th...

AI Technical Summary

Problems solved by technology

[0005] The existing feature extraction methods generally can only extract the features of brain waves from a single angle, and the evaluation method is single, which cannot guarantee the accuracy of the classification results

Moreover, the calculation and processing process of the existing feature extraction algorithm is complicated. On the one hand, it increases the requirements for hardware. On the other hand, due to the complicated calculation, the classification result cannot be obtained in time, which affects the effect of relaxation therapy.

Images