计算机工程 ›› 2020, Vol. 46 ›› Issue (2): 298-303.doi: 10.19678/j.issn.1000-3428.0053501

• 开发研究与工程应用 • 上一篇    下一篇

基于局部模式的癫痫脑电信号自动分类方法

齐永锋, 李陇强   

  1. 西北师范大学 计算机科学与工程学院, 兰州 730070
  • 收稿日期:2018-12-27 修回日期:2019-03-14 发布日期:2019-04-22
  • 作者简介:齐永锋(1972-),男,教授、博士,主研方向为数字图像处理、模式识别;李陇强,硕士研究生。
  • 基金项目:
    甘肃省科技计划项目(18JR3RA097);甘肃省高等学校科研项目(2016A-004)。

Automatic Classification Method for Epilepsy EEG Signals Based on Local Pattern

QI Yongfeng, LI Longqiang   

  1. College of Computer Science and Engineering, Northwest Normal University, Lanzhou 730070, China
  • Received:2018-12-27 Revised:2019-03-14 Published:2019-04-22

摘要: 为有效地检测脑电图(EEG)中的癫痫信号,设计一维局部三值模式(1D-LTP)算子提取信号特征,并结合主成分分析(PCA)和极限学习机(ELM)对特征进行分类。通过1D-LTP算子计算信号点的顶层模式和底层模式下的特征变换码以准确滤除干扰信号,并对变换码直方图PCA降维后采用ELM进行分类,以10折交叉验证评估分类性能。实验结果表明,该方法能有效识别在癫痫发作期的EEG信号,其准确率可达99.79%。

关键词: 脑电图, 局部三值模式算子, 特征提取, 分类, 癫痫

Abstract: In order to effectively detect epileptic signals in Electroencephalogram(EEG),this paper proposes a one-dimensional Local Ternary Pattern(1D-LTP) operator to extract signal features,and the features are classified by combing Principal Component Analysis(PCA) and Extreme Learning Machine(ELM).The 1D-LTP operator is used to calculate the feature-transformation code in the top-level and bottom-level modes of the signal points,so as to accurately filter out the interference signals.Then the histogram of transformation code is dimensionally reduced by PCA and classified by ELM,and the classification performance is evaluated by 10-fold cross validation.Experimental results show that the proposed method can identify EEG signals during seizures,and the recognition accuracy can reach 99.79%.

Key words: Electroencephalogram(EEG), Local Ternary Pattern(LTP) operator, feature extraction, classification, epilepsy

中图分类号: