Epileptic seizure EEG signal classification system based on nonlinear dynamics features

Abstract

The invention provides an epileptic seizure EEG signal classification system based on nonlinear dynamics features and belongs to the technical field of neural information. The system comprises a preprocessing module, a feature extraction module, a feature sequencing module, a feature selection module and a classification module, wherein the preprocessing module removes noise in EEG data by discrete wavelet transform and acquires effective EEG data containing no noise; the feature extraction module calculates nonlinear dynamics features of each EEG signal by multiple entropy algorithms; the feature sequencing module sequences features by variance analysis; the feature selection module selects an optimized feature subset having the most significant influence on model accuracy by a front andback sequential algorithm; and the classification module converts judgment of epileptic seizure and seizure diapauses into binary classification problems by a least square support vector machine algorithm. The classification system can classify EEG signals of epileptic seizure with low calculation complexity, good timeliness and high accuracy.

Description

technical field [0001] The invention relates to a classification system of epileptic seizure EEG signals based on nonlinear dynamic features, specifically relates to the use of various entropy to extract nonlinear dynamic features of EEG to classify epileptic seizure EEG signals, which belongs to neural information technology field. Background technique [0002] Epilepsy is a common, multiple, chronic neurological disease in which seizures are caused by irregular and irregular discharges of neurons caused by synchronous or excessive neuronal activity in the brain. During the seizure process, dysfunction of motor, behavior, consciousness and sensation is caused, and therefore, seizures can lead to various fatal consequences. Worldwide, more than 50 million people live with epilepsy, and more than 200,000 new cases are diagnosed each year. The treatment methods for epilepsy include surgery, drugs, electrical stimulation and other methods. Before determining the treatment met...

AI Technical Summary

Problems solved by technology

However, in the field of EEG signal analysis of epileptic seizures, most studies use a single entropy to measure the characteristics of EEG, which cannot cover most of the characteristics of epileptic EEG, resulting in the accuracy, sensitivity and specificity of various algorithms. There are shortcomings in the aspect, lack of a method to fuse different entropy together to extract epileptic EEG features, and cannot fully characterize the large number of nonlinear dynamic features contained in EEG signals

Images