Artifact removal and electroencephalogram signal quality evaluation method based on wearable electroencephalogram equipment

Abstract

The invention discloses an artifact removal and electroencephalogram signal quality evaluation method based on wearable electroencephalogram equipment. The method comprises the following steps: original electroencephalogram signals on the scalp surface layer are collected through the wearable electroencephalogram equipment; equipment noises in the original electroencephalogram signal are filtered;various artifact noises in the original electroencephalogram signal, comprising motion artifacts, burr artifacts, eye movement artifacts and myoelectricity artifacts, are recognized; adaptive artifact clipping and signal splicing are carried out based on the artifact recognition result to obtain a clean electroencephalogram signal; and comprehensive quality evaluation is carried out on the cleanelectroencephalogram signal by adopting neural network classification and index parameters. The problems that artifacts of the wearable electroencephalogram equipment are difficult to remove due to channel number limitation and real-time performance, and an electroencephalogram signal quality evaluation method is lacked are solved.

Description

technical field [0001] The invention belongs to the field of electroencephalogram signal monitoring, and in particular relates to a method for evaluating the quality of electroencephalogram signals. Background technique [0002] EEG signals are produced by the discharge of neurons in the brain and reflect the weak bioelectrical signals of brain activity. Due to the characteristics of easy acquisition, non-invasiveness, and high temporal resolution, EEG is playing an increasingly important role in scientific research and disease diagnosis. With the continuous development of EEG monitoring technology, a large number of wearable EEG devices have appeared on the market, which are mainly used in business, medical and education fields. However, these wearable EEG devices face many problems in the actual application process. The two main problems are: the difficulty of real-time removal of noise and the lack of signal quality. The EEG signal is a low-amplitude unsteady signal, wh...

AI Technical Summary

Problems solved by technology

However, these wearable EEG devices face many problems in the actual application process, the most important two problems are: the noise is difficult to remove in real time and the lack of signal quality

In scientific research, all EEG data will be artificially screened by researchers to eliminate data segments with poor signal quality, but artificial screening cannot be done in the actual application process, so there is an urgent need for a technology that automatically evaluates the quality of EEG signals

Images