《计算机应用研究》|Application Research of Computers

基于改进遗传模拟退火K-means的心电波形的分类研究

Research of ECG waveforms classification based on improved genetic simulated annealing K-means

免费全文下载 (已被下载 次)  
获取PDF全文
作者 何云斌,张晓瑞,万静,李松
机构 哈尔滨理工大学 计算机科学与技术学院,哈尔滨 150080
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2014)11-3328-05
DOI 10.3969/j.issn.1001-3695.2014.11.029
摘要 针对心电图自动诊断困难这一问题,提出了一种新的聚类算法:基于均方差属性加权的遗传模拟退火K-means改进聚类算法,用于改进心电图(ECG)信号的自动识别技术。利用小波变换的多分辨率和抗干扰能力好的特点,检测QRS波、P波、T波,提高了特征检测的准确性;利用聚类分析具有较好的鲁棒性和适合于大数据量分析的特点,对心电信号进行波形分类。采用MIT-BIH标准心电数据库中的部分数据对识别结果进行判断,改进后的K-means聚类算法的准确率高于传统的K-means聚类算法,实验表明该算法对心电信号可以进行有效分类。
关键词 心电图信号;聚类;特征提取;K-means;遗传算法;模拟退火;属性权重;均方差;小波变换
基金项目 黑龙江省教育厅科学技术研究项目(12511100)
黑龙江省自然科学基金资助项目(F201014,F201134)
本文URL http://www.arocmag.com/article/01-2014-11-029.html
英文标题 Research of ECG waveforms classification based on improved genetic simulated annealing K-means
作者英文名 HE Yun-bin, ZHANG Xiao-rui, WAN Jing, LI Song
机构英文名 School of Computer Science & Technology, Harbin University of Science & Technology, Harbin 150080, China
英文摘要 In view of the difficulties to recognize ECG signal automatically, this paper presented a new clustering algorithm, which was proposed based on the MSE attribute weights genetic simulated annealing to improve K-means clustering algorithm , in order to improve the ECG signal automatic identification technology. It used wavelet transform and multi-resolution and good anti-jamming capability to detect QRS complex, P wave, T wave, improved the accuracy of feature detection. Because of the cluster method had more robust and suitable for large data volume analysis, it classified the ECG signals by using this method to analyze large data volume. It adopted the parts of data from the MIT-BIH standard ECG database to judge the result of the identification. The improved K-means clustering algorithm is more accurate than the traditional K-means clustering algorithm, experiments indicate that this algorithm is effective and accurate to classify ECG signals.
英文关键词 ECG signal; clustering; feature extraction; K-means; genetic algorithms; simulated annealing; attribute weights; MSE; wavelet transform
参考文献 查看稿件参考文献
  [1] 王丽苹, 董军. 心电图模式分类方法研究进展与分析[J] . 中国生物医学工程学报, 2010, 29(6):916-926.
[2] 葛丁飞, 翁剑枫. 基于2D-LDA和高频心电信号的心肌梗死特征提取和分类[J] . 航天医学与医学工程, 2013, 26(2):125-130.
[3] WANG Wen-june, YE Yun-chi. Feature selection algorithm for ECG signals using range-overlaps method[J] . Expert Systems with Applications, 2010, 37(4):2088-2096.
[4] 牟善玲, 郑刚. 动态心电波形数据的聚类有效性评价方法研究[J] . 计算机工程与应用, 2011, 47(32):148-150.
[5] MARTIS R J, CHAKRABORTY C, RAY A J. A two-stage mechanism for registration and classification of ECG using Gaussian mixture model[J] . Pattern Recognition, 2009, 42(11):2979-2988.
[6] 蒋德育, 刘光远. 基于心电P-QRS-T波的特征提取及情感识别[J] . 计算机工程与应用, 2009, 45(8):213-215.
[7] 刘彤彤, 戴敏, 李忠义. 基于窗口斜率表示法的心电波形相似性分析[J] . 计算机应用, 2012, 32(10):2969-2972.
[8] 马永杰, 云文霞. 遗传算法研究进展[J] . 计算机应用研究, 2012, 29(4):1201-1206.
[9] UBEYLI E D. ECG beats classification using multiclass support vector machines with error correcting output codes[J] . Digital Signal Processing, 2006, 17(3):675-684.
[10] YU Sung-nien, CHOU Kuan-to. Selection of significant independent components for ECG beat classification[J] . Expert Systems with Applications, 2009, 36(2):2088-2096.
[11] 练仕榴, 郑刚, 牟善玲. 用于心电波形分析的相似性度量策略[J] . 计算机工程, 2011, 37(9):263-265.
[12] EBRAHIMZADEH A A, KHAZAEE A. Detection of premature ventricular contractions using MLP neural networks:a comparative study[J] . Measurement, 2010, 43(1):103-112.
[13] 张扬, 杨松涛, 张香芝. 一种模拟退火遗传算法的传感器网络数据融合技术研究[J] . 计算机应用研究, 2012, 29(5):1860-1862.
[14] KORUREK M, DOGAN B. ECG beat classification using particle swarm optimization and radial basis function neural network[J] . Expert Systems with Applications, 2010, 37(12):7563-7569.
[15] WEI Jiang, KONG Song. Block based neural networks for personalized ECG signal classification[J] . IEEE Trans on Neural Networks, 2007, 18(6):1750-1761.
[16] ZHAO Zhi-dong, YANG Lei, CHEN Dian-dian. Research of ECG identification based on FFT-matching pursuit algorithm[J] . 传感技术学报, 2013, 26(3):307-314.
[17] 王庆荣, 袁占亭, 张秋余. 基于改进遗传—模拟退火算法的公交排班优化研究[J] . 计算机应用研究, 2012, 29(7):2461-2463.
[18] 景波, 刘莹, 黄兵. 基于遗传算法的Job-Shop调度问题研究[J] . 计算机应用研究, 2013, 30(3):688-691.
收稿日期 2013/10/23
修回日期 2013/12/3
页码 3328-3332
中图分类号 TP391.4
文献标志码 A