基于注意力机制RNN模型的癫痫患者脑电信号识别方法

doi:10.12068/j.issn.1005-3026.2023.08.005

东北大学学报（自然科学版） ›› 2023, Vol. 44 ›› Issue (8): 1098-1103.DOI: 10.12068/j.issn.1005-3026.2023.08.005

基于注意力机制RNN模型的癫痫患者脑电信号识别方法

周嵩，高天寒

(东北大学软件学院，辽宁沈阳110169)

发布日期:2023-08-15
通讯作者: 周嵩
作者简介:周嵩(1989-)，男，山东济南人，东北大学博士研究生；高天寒(1978-)，男，辽宁沈阳人，东北大学教授，博士生导师.
基金资助:
国家自然科学基金资助项目(52130403)；中央高校基本科研业务费专项资金资助项目(N2017003).

EEG Recognition Method for Epileptic Patients Based on RNN Model with Attention Mechanism

ZHOU Song， GAO Tian-han

School of Software， Northeastern University， Shenyang 110169， China.

Published:2023-08-15
Contact: GAO Tian-han
About author:-
Supported by:
-

摘要/Abstract

摘要： 针对癫痫患者脑电信号(electroencephalogram，EEG)数据识别提出了一种基于注意力机制的RNN(recurrent neural networks) 模型.传统EEG特征分析耗时巨大且过度依赖专家经验，极大限制了脑活动识别方法的应用推广.因此，提出一种新的EEG识别方法以解决上述问题.首先对癫痫患者EEG的基本特征进行分析，进而采用基于注意力机制RNN模型消除各种干扰信号，利用XGBoost分类器识别EEG数据的类别，达到自动细化识别原始EEG的目的，最后在公共EEG数据集上进行大量实验，验证所提方法对EEG识别的准确性.实验结果表明，与一些成熟的EEG识别方法相比，本文所提方法在识别精度上有了进一步提升.

关键词: 脑电信号；注意力机制；RNN模型；XGBoost分类器；癫痫患者

Abstract: A RNN (recurrent neural networks) model based on attention mechanism is proposed for EEG (electroencephalogram) data recognition in epilepsy patients. Traditional EEG feature analysis is time-consuming and excessively dependent on expert experience， which greatly limits the application and popularization of brain activity recognition methods. A new EEG recognition method to solve the above problems is proposed. Firstly， the basic characteristics of EEG from epilepsy patients are analyzed. Then， the RNN model based on attention mechanism is designed to eliminate various interference signals and the XGBoost classifier is used to identify the categories of EEG data， so as to achieve the purpose of automatic refinement and recognition of the original EEG. Finally， a large number of experiments are carried out on the public EEG data set to verify the accuracy of the proposed method. The experimental results show that compared with the mature EEG recognition methods， the proposed method has higher recognition accuracy.

Key words: EEG(electroencephalogram); attention mechanism; RNN (recurrent neural networks) model; XGBoost classifier; epileptic patient

中图分类号:

TP391

周嵩，高天寒. 基于注意力机制RNN模型的癫痫患者脑电信号识别方法[J]. 东北大学学报（自然科学版）, 2023, 44(8): 1098-1103.

ZHOU Song， GAO Tian-han. EEG Recognition Method for Epileptic Patients Based on RNN Model with Attention Mechanism[J]. Journal of Northeastern University(Natural Science), 2023, 44(8): 1098-1103.

参考文献

[1]Sukriti，Chakraborty M，Mitra D.Epilepsy seizure detection using kurtosis based VMDs parameters selection and bandwidth features［J］.Biomedical Signal Processing and Control，2021，64(9971):102255.
[2]Wijayanto I，Hartanto R，Nugroho H A .Comparison of empirical mode decomposition and coarse-grained procedure for detecting pre-ictal and ictal condition in electro-encephalo graphy signal［J］.Informatics in Medicine Unlocked，2020，19:100325.
[3]Lcdna B，Dt B，Raa B，et al.Classification of EEG signals for epileptic seizures detection and eye states identification using Jacobi polynomial transforms-based measures of complexity and least-square support vector machine［J］.Informatics in Medicine Unlocked，2021，23:47-61.
[4]赵艳娜.癫痫脑电信号识别方法及系统:202110564684.8［P］.2021-12-5.(Zhao Yan-na.Method and system for identify epileptic EEG signals:202110564684.8［P］.2021-12-5.)
[5]Wolpaw J R，Birbaumer N，Heetderks W J，et al.Brain-computer interface technology:a review of the first international meeting［J］.Rehabilitation Engineering IEEE Transactions，2000，8(2):164-173.
[6]Brari Z，Belghith S .A novel machine learning model for the detection of epilepsy and epileptic seizures using electroencephalographic signals based on chaos and fractal theories［J］.Mathematical Problems in Engineering，2021，2021:1-10.
[7]Schirrmeister R T，Springenberg J T，Fiederer L，et al.Deep learning with convolutional neural networks for brain mapping and decoding of movement-related information from the human EEG［J］.Human Brain Mapping，2017(5):341-355.
[8]Correa A G，Orosco L L，Diez P，et al.Adaptive filtering for epileptic event detection in the EEG［J］.Journal of Medical and Biological Engineering，2019(1):82-93.
[9]Brari Z，Belghith S .A new method for the detection of epilepsy and epileptic seizures based on the variance of EEG signals and its derivatives with a simple kernel trick［C］//2020 4th International Conference on Advanced Systems and Emergent Technologies(IC_ASET).Zhuhai，2020:105-114.
[10]Yang J F.Applying a locally linear embedding algorithm for feature extraction and visualization of MI-EEG［J］.Journal of Sensors，2016，16(4):1-9.
[11]Slimen I B，Boubchir L，Mbarki Z，et al.EEG epileptic seizure detection and classification based on dual-tree complex wavelet transform and machine learning algorithms［J］.Journal of Biomedical Research，2020，34(3):21-39.
[12]Xiao J，Gui B.Removal of artifacts from EEG signals:a review［J］.Sensors，2019，34(3):14-26.
[13]Tanveer M，Pachori R B，Angami N V.Entropy based features in FAWT framework for automated detection of epileptic seizure EEG signals［C］//IEEE Symposium Series on Computational Intelligence(SSCI).Cape Town，2018:23-31.
[14]Delimayanti M K，Purnama B，Nguyen N G，et al.Classification of brainwaves for sleep stages by high-dimensional FFT features from EEG signals［J］.Applied Sciences，2020，10(5):17-26.
[15]Baig M Z，Aslam N，Shum H.Filtering techniques for channel selection in motor imagery EEG applications:a survey［J］.Artificial Intelligence Review，2020，53(3):25-40.

基于注意力机制RNN模型的癫痫患者脑电信号识别方法

EEG Recognition Method for Epileptic Patients Based on RNN Model with Attention Mechanism

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	杨丹，刘国如，任梦成，裴宏杨. 多尺度卷积核U-Net模型的视网膜血管分割方法[J]. 东北大学学报（自然科学版）, 2021, 42(1): 7-14.
[2]	韩东红，张宏亮，朱帅伟，齐孝龙. 面向新浪微博的情感社区检测算法[J]. 东北大学学报（自然科学版）, 2021, 42(1): 21-31.
[3]	原培新，陈鼎夫. 双能X射线高动态范围安检图像压缩算法[J]. 东北大学学报（自然科学版）, 2021, 42(1): 96-101.
[4]	魏颖, 徐楚翘, 刁兆富, 李伯群. 基于生成对抗网络的多目标行人跟踪算法[J]. 东北大学学报（自然科学版）, 2020, 41(12): 1673-1680.
[5]	李稷，徐安军. 炼钢车间多天车动态调度仿真方案[J]. 东北大学学报:自然科学版, 2020, 41(12): 1699-1707.
[6]	李占山，吕艾娜. 基于新冗余度的特征选择方法[J]. 东北大学学报:自然科学版, 2020, 41(11): 1550-1556.
[7]	王鑫，王翠荣，王聪，苑迎. 双通道多感知卷积神经网络图像超分辨率重建[J]. 东北大学学报:自然科学版, 2020, 41(11): 1564-1570.
[8]	张春雷，戴丽，刘宇，李鹤. 基于三点法和ICP算法的手术导航系统患者配准[J]. 东北大学学报:自然科学版, 2020, 41(11): 1584-1590.
[9]	陈剑，何涛，闻英友，马林涛. 基于BERT模型的司法文书实体识别方法[J]. 东北大学学报:自然科学版, 2020, 41(10): 1382-1387.
[10]	张田，田勇，王子，王昭东. 基于清晰度评价的自适应阈值图像分割法[J]. 东北大学学报:自然科学版, 2020, 41(9): 1231-1238.
[11]	张丽杰，刘建昌，谭树彬. 复杂建筑火灾中的人员疏散路径多目标规划[J]. 东北大学学报:自然科学版, 2020, 41(6): 761-766.
[12]	赵海，周冰玲，朱宏博，窦圣昶. 基于连续最大流的三维肺实质快速分割算法[J]. 东北大学学报:自然科学版, 2020, 41(4): 470-474.
[13]	徐久强，张金鹏，贾玉其，邵建新. 基于集成学习的束支传导阻滞识别方法[J]. 东北大学学报:自然科学版, 2020, 41(3): 321-326.
[14]	孟琭，钟健平，李楠. 基于GAN的医学图像仿真数据集生成算法[J]. 东北大学学报:自然科学版, 2020, 41(3): 332-336.
[15]	徐礼胜，宋代远，刘文彦，王瑜璠. 用不同外周动脉波形重建主动脉波形的对比研究[J]. 东北大学学报:自然科学版, 2020, 41(2): 188-192.