摘要
心血管疾病是当今危害人类健康的主要疾病之一,心电图检查是临床上诊断心血管疾病的重要方法。心电图准确的自动分类对于心血管疾病的诊断起着关键作用。
聚类分析是非监督模式识别的一个重要分支,它是用数学的方法研究和处理给定对象分类。
模糊聚类建立在样本对于类别的不确定性描述的基础上,更能客观的反映现实世界,从而成为聚类分析研究的主流,并在许多领域得到了广泛的应用。
目前,已提出了许多模糊聚类算法,其中最常用的是基于目标函数的模糊c-均值聚类算法(FCM)。针对此算法中存在的需要聚类先验知识的问题,采用SOM神经网络算法作为FCM算法的先导级,先将样本经过SOM神经网络的训练,得到聚类类别数,但此方法得到的类别数与实际结果存在较大偏差。因此提出了一种改进方法,即将SOM神经网络、优化的系统聚类法和FCM算法相结合的聚类方法。首先对系统聚类法进行优化,然后使用优化后的系统聚类法分析SOM神经网络初始分类的结果,最终得到更合理的聚类类别数和聚类中心,将此聚类数和聚类中心用于FCM算法的输入进行进一步聚类,从而得到精确的聚类信息。
最后,采用MIT/BIH心电数据库中的数据来仿真,结果说明此种方法具有很好的聚类效果。
Cardiovascular disease is one of major disease which endangers human’s health. The analysis of ECG(Electrocardiogram) is an important means for diagnosing cardiovascular disease in clinic. The accurate automatic classification of ECG plays a key role for the diagnosis of cardiovascular disease.
The cluster analysis is an important branch of non-supervision pattern recognition, which uses the methods of mathematics to research and deal with given classification of objects.
Fuzzy clustering based on the uncertain description for sample to category, which can more objectively reflect the real world, thus becoming the mainstream of cluster analysis, and has been widely used in many areas.
At present, many algorithms for fuzzy clustering are proposed, in which the most commonly used is the fuzzy c-means clustering algorithm based on the objective function.For the problem of the algorithm which requires clustering prior knowledge, we take the SOM neural network algorithm as the forerunner of FCM algorithm. Using the SOM neural network to train samples, and get the number of clustering categories. But it has a big deviation in the actual results and the results for using this method. Therefore, this paper proposes an improved method, which is a combination clustering method of the SOM neural network, the optimizing system algorithm and the FCM algorithm. First, optimizing the system clustering method, then using the optimized system clustering method to analyze the initial classification results of SOM neural network, ultimately get more reasonable number of cluster categories and cluster centers, through using the number of cluster categories and cluster centers as the input of FCM clustering algorithm to further cluster, so that get accurate clustering information.
Finally, take the data in the MIT / BIH ECG database to simulate, and show that this method has good clustering effect through the results.
引文
[1]陈长亮.心电图的计算机智能分析系统[D].山东:山东大学,2006
[2]许丽利.聚类分析的算法及应用[D].吉林:吉林大学,2010
[3]孔攀.模糊聚类分析及其有效性研究[D].南京:东南大学,2009
[4] ZadehLA. Fuzzy sets[J]. Information and Control,1965,8(46):338~335
[5] Han J,Kamber M,范明,孟小峰.数据挖掘概念与技术[M].北京:机械工业出版社,2002,88~107
[6]惠周利.聚类分析中的若干问题研究及应用[D].山西:中北大学,2008
[7]汪永成.模糊聚类算法研究及其在web日志挖掘中的应用[D].辽宁:辽宁工程技术大学,2005
[8] Xiangyang Li,Nong Ye. A Supervised Clustering and Classification Algorithm for Mining Data With Mixed Variables[J]. Man and Cybernetics-Part A: Systems and Humans,2005,24(78):1~11
[9]赖玉霞,刘建平. K-means算法的初始聚类中心的优化[J].计算机工程与应用,2008,44(10):62~64
[10] Gokcay E,Principe JC. Information theoretic clustering[J]. IEEE Trans.PAMI,2002,24(2):158~171
[11] K.Sugihara,H.Tanaka. Interval evaluations in the analytic hierarchy process by possibility analysis[J]. Computational intelligence,2001,17(3):567~579
[12] Lagerholm M,Peterson C,Braccini G. Clustering ECG complexes using hermite functions and self-organizing maps[J]. IEEE Transations on Biomedical Engineering,2000,47(7):838~848
[13] Y.Tan,L. Du. Study on Wavelet Transform in the Processing for ECG Signals[C]. 2009,515~518
[14] Guleral,Ubeyl ED. A modified mixture of experts network structure for ECG beats classification with diverse features[J]. Engineering Applications of Artificial Intelligence,2005,18(5):845~856
[15] Gulera I,Ubeyh ED. ECG beat classifier designed by combined neural network model[C]. Pattern Recognition,2005,38(2):199~208
[16]栾龙源.基于自组织神经网络与模糊算法的彩色图像聚类分割系统[D].西安:西安电子科技大学,2010
[17]施红鑫.基于附加敏感参数SOM神经网络的自动聚类系统的研究[D].河北:燕山大学,2009
[18]吴春旭,鲍满园等.自组织映射聚类算法在电信客户细分中的应用[J].计算机系统应用,2010,19(8):95~98
[19]魏丽.数据挖掘中聚类算法比较研究[J].数据库及信息管理,2007,5(8):537~639
[20]姜丽.模糊C均值聚类的理论与应用研究[D].杭州:浙江工商大学,2010
[21] Lun-ping Hung. A personalized recommendation system based on product taxonomy for one-to-one marketing online[J]. Expert systems with applications,2005,9(2):383~392
[22]高新波.模糊聚类分析及其应用[M].西安:西安电子科技大学出版社,2004.49~61
[23]齐淼.改进的模糊C-均值聚类算法研究[J].计算机工程与应用,2009,13(6):62~67
[24]陈春明.一种改进的模糊C-均值算法[J].情报探索,2009,45(9):109~111
[25]季虎.心电信号自动分析关键技术研究[D].湖南:国防科学技术大学,2006
[26] Willems JL,Arnaud P,van Belmmel JH,et al. Common standards for Quantitative electrocardiography: goals and main results[J]. Methods of Information in Medicine,1990,29(4):263~271
[27] Hermes RE,Geselowitz DB, Oliver GC. Development, distribution, and use of The American Heart Association database for ventricular arrhythmia detector evaluation[J]. Computers in Cardiology,1980,59(47):263~266
[28] Cambridge. MIT-BIH Database distribution, Massachusetts Institute of Technology[J]. MA02139,2007,3(9):1996~2005
[29] G.Moody,R.Mark. The impact of the MIT-BIH arrhythmia database on CD-ROM and software for use with it[J]. Computers in Cardiology,1990,17:185~188
[30]宋春丽.怎样识读MIT-BIH中的心电信号[J].科技资讯,2010,9(4):405~406
[31]杨庭树,卢喜烈.心电图基础理论[M].天津:天津科学技术版社,2005.2~3
[32]李雪飞.心电自动分析系统的研究[D].重庆:重庆大学,2007
[33]刘世雄.基于模糊聚类算法对心电数据典型特征分类研究[D].杭州:浙江大学,2006
[34]张泾周.基于神经网络的心电信号波形自动分类算法研究[J].北京生物医学工程,2008,34(4):145~147
[35]齐志.基于SOM神经网络的聚类可视化方法研究[D].东北:东北师范大学,2009
[36] Chip-Hong Chang. New Adaptive Color Quantization Method Based on Self-Organizing Maps[J]. IEEE Transactions on Neural Networks,2005,16(1),276~278
[37] Fedja Hadz. CSOM: Self-Organizing Map for Continuous Data[J]. IEEE International Conference on Industrial Informatics (INDIN),2005,2 (5):23~25
[38]林泽涛,葛耀峥.心律失常的聚类分析研究[J].生物医学工程杂志,2006,23(5):999~1002
[39]岳清华,郑刚.一种动态心电图波形聚类策略的研究[J].天津理工大学学报,2008,24(8):49~52
[40] Szilagyi L,Szilagyi S M,et al. Quick ECG analysis for on-line holter monitoring systems[C]. In Proceedings of the 28th IEEE EMBS Annual International Conference. New York City:2006,1678~1681
[41]郭伟业,赵晓丹.数据挖掘中SOM神经网络的聚类方法研究[J].情报科学,2009,29(4):675~678
[42]白耀辉.利用自组织特征映射神经网络进行可视化聚类[J].计算机仿真,2006,183(4):870~872
[43]郭明.基于SOM网和K-means的聚类算法[J].计算机与数字工程,2008,46(9):263-265
[44] ]Li Jie,Gao Xinbo,Jiao Licheng. A new feature weighted fuzzy clustering algorithm[R]. RSFDGr 2005
[45]张询,邓辉文.基于减法聚类与聚类有效性评判的FCM聚类[J].重庆工学院学报,2006,20(5):59~62
[46]齐淼,张化祥.基于FCM的两级集成分类器算法[J].计算机工程与设计,2010,31(16):56~58
[47]寇英信,王琳,全勇.自组织特征映射网络在目标分类识别中的应用[J].火力与指挥控制,2009,34(1):277~280
[48]薛年喜. MATLAB在数字信号处理中的应用[M].北京:清华大学出版社,2008.94~100
[49] R.cereghino,Y-S.Park. Review of the Self-Organizing Map(SOM)approach in Water Resource: Commentary[J]. Environmental Systemling & Software,2009,50(1):945~947.
[50] Dan Tian,Linan Fan. A Brain MR images Segmentation Method Based on SOM Neural Network[J]. IEEE Transactions on Neural Networks,2007,43(6):25~28
[51] Kalteh,A.M.,Hjorth,BerndtssonR. Review of the self-organizing map(SOM) approach in water resources: analysis, systemling and application[J]. Environmental Systemling and Software,2008,23(6):835~845
[52]于迪,李义杰.基于减法聚类改进的模糊c均值算法的模糊聚类研究[J].微型机与应用,2010,9(16):49~51
[53]袁正.基于SOM及k均值聚类方法的分布式入侵检测模型的研究[D].天津:天津理工大学,2009
[54]王继光,张韧.卫星云图样本集的FCM优化调整与云类判别[J].防灾减灾工程学报,2005,25(2):162~167
[55]马华,张西学.数据压缩的FCM算法用于人脑MRI图像的分割[J].信息与电子工程,2006,4(3):222~224