Intelligent classification method for distinguishing electroencephalogram blink artifacts and frontal electrode epilepsy discharge

Abstract

The invention discloses an intelligent classification method for distinguishing electroencephalogram blink artifacts and frontal electrode epilepsy discharge. The method comprises the following steps: firstly, carrying out filtering processing and signal cutting on electroencephalogram EEG signals; then performing smooth nonlinear energy operator (SNEO) signal conversion and variational modal extraction (VME) signal conversion on the processed EEG signal to obtain an SNEO data set and a VME data set; performing 20-dimensional feature extraction on signals corresponding to the three data sets; then performing binary unsupervised clustering through a K-means algorithm, and constructing an unsupervised classification model; and finally, realizing the classification of blink artifacts and epilepsy discharge signals through the established unsupervised classification model. According to the method, the difficulty of low blink artifact detection precision under the background containing epilepsy discharge signals is overcome, the problem that an existing model neglects epilepsy discharge can be solved, and accurate and automatic classification of the blink artifacts and the frontal electrode epilepsy discharge can be realized.

Description

technical field [0001] The invention belongs to the field of EEG signal processing and intelligent medical treatment, and relates to a K-means-based unsupervised clustering algorithm for strong noise EEG signals containing frontal pole epileptiform discharges and fusion of multi-dimensional feature representations of multiple types of signals classification method. In the field of EEG analysis and artifact filtering in epilepsy, it is very important to effectively distinguish frontal pole epileptiform discharges from blink artifacts. The invention is an automatic classification method for epileptiform discharge signals and eye blink artifact signals based on EEG data under the background of epileptiform discharges. Background technique [0002] Electroencephalogram (EEG) is the overall response of the electrophysiological activity of brain nerve cells on the surface of the cerebral cortex or scalp. It contains a wealth of brain activity information and is widely used in bra...

AI Technical Summary

Problems solved by technology

However, in epilepsy auxiliary detection and analysis research, the epileptiform discharge signal waveform in the background of epileptic patients is very similar to the EEG artifact caused by eye blinking, and the location of the two is also highly consistent, both concentrated in the EEG forehead channel, which tends to interfere greatly with blink artifact signal detection

The current traditional blink artifact detection methods usually ignore the key issue of high similarity between blink artifacts and frontal pole epileptiform discharges, and only focus on the identification of blink artifacts while ignoring the classification of epileptiform discharge signals and blink artifact signals. Conventional blink artifact detection models fail in EEG of patients with frontal lobe epilepsy

Images