Neural network-based magnetoencephalogram eye movement artifact detection and elimination method and electronic device

Abstract

The invention provides a neural network-based magnetoencephalogram eye movement artifact detection and a elimination method and an electronic device. The method comprises the following steps: cuttinga to-be-detected magnetoencephalogram signal, and drawing a plurality of magnetoencephalogram signal views according to a signal segment and a magnetoencephalogram sensor detection signal position; extracting signal space distribution characteristics of the magnetoencephalogram, and classifying the signal space distribution characteristics; obtaining an eye movement signal interference segment according to a fixed ratio and the eye movement electrooculogram signal segment at the corresponding time point of the magnetoencephalogram signal segment containing the eye movement artifact noise signal; subtracting the magnetoencephalogram signal segment containing the eye movement artifact noise signal from the eye movement signal interference segment, and restoring the obtained signal segment with removed the eye movement artifact noise signal to a corresponding position. According to the invention, the electrooculogram signal measured by an electrode is not needed during detection, and themagnetoencephalogram signal that is not influenced by the electrooculogram signal is not interfered during elimination, so that the information in the original magnetoencephalogram signal can be reserved to the maximum extent.

Description

technical field [0001] The invention relates to the field of removing magnetoencephalogram artifact signals in the field of biological feature recognition, in particular to a neural network-based method for detecting and removing magnetoencephalogram eye movement artifacts and an electronic device. Background technique [0002] Magnetoencephalography is a kind of brain function image detection technology that uses extremely sensitive magnetic sensors to detect the weak magnetic signals emitted by the human brain. It has the advantages of being completely non-invasive and non-invasive. At present, magnetoencephalography technology has been used in the research of advanced brain functions such as thinking and emotion, and is widely used in neurosurgery for brain function localization, epilepsy focus surgical localization, surgery for functional diseases such as Parkinson's disease, mental illness and drug withdrawal. At the same time, it also has important clinical medical app...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the shortcomings of the above-mentioned traditional methods for removing eye movement artifacts in magnetoencephalography, the present invention provides a neural network-based method for detecting and removing eye movement artifacts in magnetoencephalography and an electronic device, which can effectively and accurately identify Noisy signal of eye movement artifacts in magnetoencephalogram and its removal

Images