Music feedback depressive emotion adjusting system based on electroencephalogram signals

Abstract

The invention provides a music feedback depressive emotion adjusting system based on electroencephalogram signals. Corresponding feedback music training is carried out on a trainee by analyzing a mapping relation between electroencephalogram signals and music signals, and the purpose of improving the emotion of a depressive patient is achieved. The system comprises: an electroencephalogram signalacquisition module used for acquiring resting-state electroencephalogram signals of the trainee; an electroencephalogram signal data processing module used for preprocessing the acquired electroencephalogram signals; a feedback music generation module used for segmenting and integrating the preprocessed electroencephalogram signals to obtain the mapping relation between the electroencephalogram signals and the music signals and performing comparing in a built feedback music type reference library to obtain a feedback music type for music feedback training; a feedback training adjustment moduleused for performing feedback training on the trainee by adopting feedback music adaptive to the feedback music type to realize adjustment of depressive emotion; and a data storage and analysis moduleused for storing and analyzing the process and result of emotion adjustment of the trainee.

Description

technical field [0001] The invention relates to a music feedback depression emotion adjustment system based on electroencephalogram signals, which belongs to the technical field of medical assistance systems. Background technique [0002] When the brain nerves are active, there will be weak electric field fluctuations. When tens of thousands of nerves are active at the same time, the electric field will produce rhythmic fluctuations. This fluctuation can be measured from the scalp, which is the brain wave. EEG has the following characteristics: it is a spontaneous potential generated by brain nerve activity and always exists in the central nervous system; the EEG signal is very weak; the anti-interference performance is weak and the robustness is poor; it is a random signal with non-stationary Gaussian and nonlinear characteristics; able to reflect the state and changes of the nervous system. [0003] EEG signals can reflect human emotional changes in real time. The study...

AI Technical Summary

Problems solved by technology

[0012] 1) There are defects in the treatment of depression: the existing treatment methods for depression include Chinese and Western drug treatment, psychological counseling therapy, etc., and these treatment methods have side effects to varying degrees

Mainstream psychotherapy for depression, such as cognitive-behavioral therapy, ignores the richness of the patient's life and the importance of emotional experience to a certain extent, and overemphasizes rationality and objectivity, and the process and effect of treatment mainly depend on the therapist ;

[0013] 2) Usually, the EEG-based music therapy method mainly intervenes on the emotions of the subjects by listening to music. This kind of music therapy method related to listening is called receptive music therapy method. The stress response to music is different, this method is not universal

Moreover, this intervention method is a low-level intervention method, which is likely to make patients "immune" and cannot achieve good results;

[0014] 3) EEG signal acquisition equipment is not universal: medical EEG signal acquisition equipment is complex and expensive, and a special person is required to be responsible for the acquisition; portable EEG acquisition equipment, the number and location of EEG acquisition electrodes are uncertain, and brain The methods of electrical collection electrodes and data transmission, as well as the cost and application fields are different, the power consumption is large, and the number of A / D conversion bits is low;

[0015] 4) Data modeling and analysis lack relative reliability: the modeling data is small, and the amount of information contained is small, so that the data model does not have good balance and effectiveness

The EEG extraction algorithm is not good enough to obtain pure physiological EEG signals

A single data analysis method makes the results of feature extraction and selection lack representativeness and accuracy

These shortcomings make it impossible to give rationalized adjuvant treatment based on the characteristic information of the subjects

Images