Electroencephalogram signal artifact removing method and computer readable storage medium

Abstract

The invention provides an electroencephalogram artifact removing method and a computer readable storage medium. The electroencephalogram signal artifact removing method comprises the steps of: acquiring an electroencephalogram signal containing crymodynia information as a target signal, and performing iterative noise reduction on the target signal to obtain a pure mode function; performing short-time Fourier time-frequency analysis on the pure mode function to obtain a time-frequency diagram, determining effective features according to the time-frequency diagram, constructing a mode function corresponding to the effective features so as to obtain effective signals, and screening out a pure signal from the effective signals; inputting the test data set of the pure signal into a classification model to obtain precision evaluation parameters of the pure signal; and determining that the pure signal is a qualified signal when the detection precision evaluation parameters of the pure signalmeet the precision requirement. VMD decomposition and noise reduction are carried out on multichannel electroencephalogram signals with crymodynia information, so that the problems of modal aliasing and endpoint effect are solved, the decomposition precision and the noise reduction precision are improved, and meanwhile, the precision of extracting the effective features is also improved.

Description

technical field [0001] The present invention relates to the technical field, in particular to a method for removing artifacts of electroencephalogram signals and a computer-readable storage medium. Background technique [0002] Acute pain has long been studied extensively as a way to elicit signals of brain activity and as a laboratory method for the clinical diagnosis of pain-induced diseases. Most pain studies are assessed by multi-channel acquisition of scalp EEG (electroencephalogram) followed by signal processing. In the study, it was found that pain can modulate the synchronicity of the cerebral cortex, with well-defined non-rhythmic "oscillations" between the constituent nodes in the neural network. Moreover, the pain-induced EEG signal has strong non-stationarity and low signal-to-noise ratio, and the robustness is difficult to grasp, and it is very difficult to extract features from the EEG signal. Especially under acute cold-tender conditions, the evoked transien...

AI Technical Summary

Problems solved by technology

And the above-mentioned method detects cold pain sensation brain activity accuracy is not high, is unfavorable for practical application and medical clinical detection

Images