Scalp electroencephalogram collection site sorting method and system

Abstract

The invention discloses a scalp electroencephalogram collection site sorting method and system. The collection site sorting method includes the steps of reading of data; preprocessing of the data, wherein original electroencephalogram signals are subjected to artifact removal and noise suppression processing, and processed electroencephalogram signals of a three-dimensional matrix are output; extraction of features, wherein the time domain features and the frequency domain features are extracted, and feature numbers, test frequency numbers and channel numbers constitute electroencephalogram feature data of the three-dimensional matrix; signature of the features, wherein the electroencephalogram feature data is subjected to feature pooling, feature clustering and data reorganization to obtain electroencephalogram signature data, recorded by the test frequency numbers and the channel numbers, of a two-dimensional matrix; correlation sorting, wherein correlations between the electroencephalogram signature data and electroencephalogram signal categories are calculated and sorted, and the channel numbers of one-dimensional vectors are output; output of results. By means of the method, arandom and divergent calculation process cannot be caused, the performance of an EEG-BCI system is improved, the data scale is reduced, the universality is high, and convenience is provided for incorporating other methods into the system.

Description

technical field [0001] The invention belongs to the technical field of EEG signal acquisition, and in particular relates to a method and system for sorting the acquisition sites of scalp EEG. Background technique [0002] Brain-computer interface (brain-computer interface, BCI) is a new way of direct brain-computer interaction, which can collect brain activity signals related to mental activities, then parse these signals into appropriate instructions, and send these instructions to the computer . The EEG signal collected on the human scalp is called electroencephalography (EEG). Non-invasive scalp EEG has the advantages of low risk, low cost, and high flexibility and is suitable for practical applications. It has been widely used in BCI. . Generally speaking, EEG data is a multi-channel signal collected from electrodes placed at multiple points on the scalp, which reflects the activity characteristics of multiple cortical layers of the brain. [0003] The core of an EEG-...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a sorting method and system for scalp EEG collection sites, so as to overcome the shortcomings of the existing EEG-BCI such as too long application time, low signal-to-noise ratio, random calculation process and poor versatility

Images