Electroencephalogram(EEG) signal online identification method with data structure information being fused

Abstract

The invention relates to an electroencephalogram (EEG) signal online identification method with data structure information being fused. The method comprises the following steps: S1) establishing a classification model based on an online sequential extreme learning machine (OS-ELM) algorithm by utilizing a small training set formed by a small number of labeled EEG samples to serve as an initial classification model in semi-supervised learning; S2) establishing a structure learning model by utilizing an on-line fuzzy clustering method, and estimating a global structure of data distribution afterbatch increase of EEG samples collected online based on prior information of the labeled EEG samples; S3)carrying out labeling on the EEG samples collected online by utilizing the classification model, and through a batch learning mode and based on the structure information estimated by a structural learning model, selecting a batch of EEG samples collected online and meeting a certain conditionsto add to a training set, and re-training the classification model by utilizing the updated training set; and S4) carrying out online identification on the collected EEG signals through the updated classification model.

Description

technical field [0001] The invention belongs to the technical field of electroencephalogram signal processing, and in particular relates to an on-line recognition method of electroencephalogram signals fused with data structure information. Background technique [0002] Brain-computer interface (brain-computer interface, BCI), as a new communication system based on electrophysiological measurement of brain function, realizes information exchange and control between human and the outside world. It has extremely high application value and broad application prospects in many fields such as life and entertainment, and has become one of the current research hotspots. Among them, non-invasive BCI based on scalp EEG signals is the mainstream model in BCI research today. [0003] Researchers have conducted extensive research on BCI based on scalp EEG signals. But in the process of realizing the present invention, the inventor finds that there are following deficiencies in the key ...

AI Technical Summary

Problems solved by technology

[0004] 1. The method of supervised learning to achieve pattern classification is the mainstream mode, but the supervised method requires a large number of labeled EEG samples to build an effective classifier, and the classifier is solidified during work and does not have online adaptability

[0005] 2. At present, there are a few studies using semi-supervised classification methods, which can use unlabeled EEG samples to train and update classifiers, but the existing methods use samples for classifier learning one by one, which has blindness and error in learning. Problems that affect the performance of online signal recognition, such as the cumulative effect of markers and low generalization ability

Images