Spike wave detection method based on sequential features and stacked Bi-LSTM network

Abstract

The invention discloses a spike wave detection method based on sequential feature extraction and a stacked Bi-LSTM network. The method comprises the steps of firstly, preprocessing an input original single-channel electroencephalogram signal, segmenting the preprocessed electroencephalogram signal to obtain electroencephalogram signal segments, obtaining smooth nonlinear energy features and morphological features through two time sequence feature extraction algorithms, cutting the obtained two time sequence features to ensure that the length is consistent with the length of the electroencephalogram signal segment, splicing with the electroencephalogram signal segment to obtain a feature matrix, and training a stacked Bi-LSTM network model by using the obtained feature matrix and annotation information; and finally, testing the trained stacked Bi-LSTM network model by adopting test data, and performing model performance optimization according to a test result. According to the method, effective learning is carried out on electroencephalogram time sequence features through a recurrent neural network model to achieve the effect of accurately detecting spike wave discharge; and spike waves and channel positions generated by the spike waves can be detected at the same time.

Description

technical field [0001] The invention belongs to the field of electroencephalogram signal processing, and relates to a spike wave detection method based on time series feature extraction and stacked bidirectional long-short-term memory (stack Bi-LSTM) network. Background technique [0002] Epilepsy is a common chronic neurological disease that seriously threatens the life and health of children and adults. Spikes and their complex waveforms are the pathological basis of epileptic seizures. The relevant parameters such as spike discharge time and discharge position are of great significance. The first step to determine these parameters is spike detection. [0003] The existing spike detection methods are mainly divided into two types. The traditional method is often biased towards feature engineering. After designing one or more features that can characterize the characteristics of spikes, the signals are classified into spikes by threshold method and other relatively simple c...

AI Technical Summary

Problems solved by technology

[0004] 1. Due to the weak performance of the classifier in the traditional method, the characterization ability of the extracted features is relatively harsh. In order to improve the performance of the model, it is often necessary to extract multiple features, and the computational complexity is high;

[0005] 2. Deep learning methods generally use fully connected neural networks or convolutional neural networks, which cannot effectively use the characteristics of EEG signals as a sequential signal

Images