智能远程健康监护系统生理参数数据分析及预报的研究
|
摘要
随着人民生活水平的提高,人类平均寿命普遍延长,人口老龄化日益明显。提高老年人健康生活质量是今后卫生工作重点。远程健康监护是我国近十年来蓬勃发展起来的课题,它与医学、信息科学、计算机、网络与通信等密切相关,是社会发展的必然需求。国内外学者已对监护系统做了大量的工作,并且已经提出了许多监护信息处理方法。然而在实际应用中,传统的监护信息处理方法,大多都存在各自的缺陷或受到适用条件的限制。随着社会的进步,希望所开发的监护系统具有更准确更综合的功能。因此,研究远程健康监护系统监护信息分析处理方法具有重要的现实意义和推广价值。
本文在对监护信息的特点及相关的技术进行了分析,以及国内外研究现状进行分析研究的基础上,提出了远程健康监护系统中监护信息数据分析方法。针对监护过程所采集的海量数据,采用小波分析、神经网络、支持向量机等数据挖掘技术对用户的多生理参数进行分析处理,消除冗余数据,对影响分析的异常数据进行识别处理,采用预报技术实现监护信息的预报。
本文的主要工作和贡献有以下几方面：
1.提出了对监护信息去除干扰信号的处理方法。由于监护信号常受到如噪声、伪迹的干扰,造成监护信号参数的估值错误,从而导致监护仪错误报警。由于小波变换能有效的抑制监护对象参数中所含的噪声和干扰信号,对微弱的噪声等干扰信息,本文提出基于改进阀值的小波变换对其进行处理；对噪声等干扰信号较强的,采用小波变换和Hampel相结合的方法降噪,并分别与采用传统小波阀值去噪方法进行对比实验,结果表明所提出的降噪方法能达到较好的效果,以提高诊断报警的准确性和有效性。
2.提出了远程健康监护系统的监护信息异常值识别处理方法。对多种处理异常值的方法进行研究,针对监护信息异常值识别问题,提出了利用改进统计量的假设检验方法与基于Kalman滤波的AR(p)模型的缺失值重构的监护信息异常值识别处理方法,首先采用改进统计量的假设检验方法识别出监护数据中可能的异常值,并将可能的异常点进行直接删除处理。然后视已删除的异常点为缺失值,采用基于Kalman滤波算法的AR(p)模型对缺失值进行预测,以该时刻的预测值添补缺失值,为下一步的准确预报做准备。
3.为实现监护系统的报警功能,建立了基于小波分解与最小二乘支持向量回归机的监护信息综合预报模型。首先对监护信息进行小波分解,得到各分解层序列；然后对各分解层序列应用最小二乘支持向量回归机对各序列进行回归预测,最后对各序列预测结果进行叠加,实现监护信息的预报。同时采用PSO寻参方法对最小二乘支持向量机进行参数寻优,对提出的方法进行了实验验证,并与其他预报方法进行对比,证明所提出的方法能取得较好的预报结果。
4.研制了智能远程健康监护系统实验平台。给出了智能远程健康监护系统的总体结构、硬件平台及系统的软件设计,利用Windows NT操作系统,SQL Server 2000数据库,Windows visual studio.net 2005为工具开发了智能远程健康监护系统软件,实验结果表明健康监护系统能有效的降低噪声干扰,对异常值进行识别处理并对监护信息进行预报,进一步证实了提出的方法的有效性。
With the improvement of the people's lives, the expectation of life is longing, and the old people is becoming more and more. To meet with the health of old people and improve the living quality, Community medical service should be strengthened aiming at the focus on sanitation of old people's healthy life. In China, tele-monitoring of health has been developed in recent decade, it is the inevitable result with the development of society, and it is closely related with medicine, information science, computer, network and communication. Many methods of monitoring information process have been put forward as a lot of work for monitoring system has been done by scholars both at home and abroad. However, the traditional processing methods have its defects or suitable conditions in the actual application. The hope of monitoring system is more accurate and more comprehensive with the progress of the society. Therefore, the study on the tele-monitoring system and the processing methods of health information has important realistic meaning and extension value.
The analyzing methods of monitoring information have been put forward on the basis of analysis of the characteristics of monitoring information and its related technologies, and the recent studies. According to the mass monitoring data, the technologies of data mining for physical parameters, such as wavelet analysis, support vector machines and neural networks, have been used to eliminate redundant data, identify abnormal data in physical parameters which will influence diagnosis, and forecast techniques have been used to realize forecast of monitoring information.
The main work and contributions of the paper are as follows.
1. The signal processing methods for monitoring information have been brought forward. As the monitoring signals are disturbed by noise, artifact and data loss, the error valuations of signal parameter, and it leads to the error alarm of guardianship. Because of wavelet transform can restrain jamming signal and noise contained in monitoring information effectively, the method of wavelet transform based on improved threshold is put forward to handle faint noise interference. While the combined method of wavelet transform and Hampel is adopted to strong noise signal. The experiment results show that the proposed denoising method can achieve good results compared with traditional wavelet threshold, and it can improve the accuracy and validity of alarm.
2. The methods of identifying abnormal values of monitoring information have been raised. According to the problem of identifying abnormal monitoring information, the abnormal recognition method of monitoring information is put forward, which is combined hypothesis based on improved statistics with AR(p) based on Kalman filter, after studying on many other deposing method of abnormal. First, the abnormal monitoring data has been identified by means of improving hypothesis, and it will be delete directly. Then the deleted points are took as missing value, and the abnormal values are be predicted with AR(p) model based on Kalman filtering algorithm, and we fill the abnormal values with the predicted values, which is the preparation for next prediction.
3. To realize the alarm of monitoring system, the integrated forecast model of monitoring information based on wavelet decomposition and least squares supports vector regression are established. Firstly, obtaining each decomposed layers sequence of monitoring information with wavelet decomposition. Secondly, the each decomposed layers sequence are predicted by using the least square support vector regression machine. Finally, realizing the prediction of monitoring information through composing the forecast results of each sequence. Meanwhile, the LS-SVMs are optimized by using PSO, and the related experiments are conducted and the results show the integrated method can obtain better forecasting results than other forecast methods.
4. The article develops the experiment platform of intelligent health monitoring system. System structure, hardware and software architecture are designed. Healthy monitoring system is programmed on the operation system Windows NT. SQL Server 2000 is used as database, and Windows visual studio.net 2005 is adopted as development tool. Experiment results show that health monitoring system has the function of reducing noise effectively, identification of unusual values and prediction. The efficiency of proposed methods are intensified by experiment results.
本文在对监护信息的特点及相关的技术进行了分析,以及国内外研究现状进行分析研究的基础上,提出了远程健康监护系统中监护信息数据分析方法。针对监护过程所采集的海量数据,采用小波分析、神经网络、支持向量机等数据挖掘技术对用户的多生理参数进行分析处理,消除冗余数据,对影响分析的异常数据进行识别处理,采用预报技术实现监护信息的预报。
本文的主要工作和贡献有以下几方面：
1.提出了对监护信息去除干扰信号的处理方法。由于监护信号常受到如噪声、伪迹的干扰,造成监护信号参数的估值错误,从而导致监护仪错误报警。由于小波变换能有效的抑制监护对象参数中所含的噪声和干扰信号,对微弱的噪声等干扰信息,本文提出基于改进阀值的小波变换对其进行处理；对噪声等干扰信号较强的,采用小波变换和Hampel相结合的方法降噪,并分别与采用传统小波阀值去噪方法进行对比实验,结果表明所提出的降噪方法能达到较好的效果,以提高诊断报警的准确性和有效性。
2.提出了远程健康监护系统的监护信息异常值识别处理方法。对多种处理异常值的方法进行研究,针对监护信息异常值识别问题,提出了利用改进统计量的假设检验方法与基于Kalman滤波的AR(p)模型的缺失值重构的监护信息异常值识别处理方法,首先采用改进统计量的假设检验方法识别出监护数据中可能的异常值,并将可能的异常点进行直接删除处理。然后视已删除的异常点为缺失值,采用基于Kalman滤波算法的AR(p)模型对缺失值进行预测,以该时刻的预测值添补缺失值,为下一步的准确预报做准备。
3.为实现监护系统的报警功能,建立了基于小波分解与最小二乘支持向量回归机的监护信息综合预报模型。首先对监护信息进行小波分解,得到各分解层序列；然后对各分解层序列应用最小二乘支持向量回归机对各序列进行回归预测,最后对各序列预测结果进行叠加,实现监护信息的预报。同时采用PSO寻参方法对最小二乘支持向量机进行参数寻优,对提出的方法进行了实验验证,并与其他预报方法进行对比,证明所提出的方法能取得较好的预报结果。
4.研制了智能远程健康监护系统实验平台。给出了智能远程健康监护系统的总体结构、硬件平台及系统的软件设计,利用Windows NT操作系统,SQL Server 2000数据库,Windows visual studio.net 2005为工具开发了智能远程健康监护系统软件,实验结果表明健康监护系统能有效的降低噪声干扰,对异常值进行识别处理并对监护信息进行预报,进一步证实了提出的方法的有效性。
With the improvement of the people's lives, the expectation of life is longing, and the old people is becoming more and more. To meet with the health of old people and improve the living quality, Community medical service should be strengthened aiming at the focus on sanitation of old people's healthy life. In China, tele-monitoring of health has been developed in recent decade, it is the inevitable result with the development of society, and it is closely related with medicine, information science, computer, network and communication. Many methods of monitoring information process have been put forward as a lot of work for monitoring system has been done by scholars both at home and abroad. However, the traditional processing methods have its defects or suitable conditions in the actual application. The hope of monitoring system is more accurate and more comprehensive with the progress of the society. Therefore, the study on the tele-monitoring system and the processing methods of health information has important realistic meaning and extension value.
The analyzing methods of monitoring information have been put forward on the basis of analysis of the characteristics of monitoring information and its related technologies, and the recent studies. According to the mass monitoring data, the technologies of data mining for physical parameters, such as wavelet analysis, support vector machines and neural networks, have been used to eliminate redundant data, identify abnormal data in physical parameters which will influence diagnosis, and forecast techniques have been used to realize forecast of monitoring information.
The main work and contributions of the paper are as follows.
1. The signal processing methods for monitoring information have been brought forward. As the monitoring signals are disturbed by noise, artifact and data loss, the error valuations of signal parameter, and it leads to the error alarm of guardianship. Because of wavelet transform can restrain jamming signal and noise contained in monitoring information effectively, the method of wavelet transform based on improved threshold is put forward to handle faint noise interference. While the combined method of wavelet transform and Hampel is adopted to strong noise signal. The experiment results show that the proposed denoising method can achieve good results compared with traditional wavelet threshold, and it can improve the accuracy and validity of alarm.
2. The methods of identifying abnormal values of monitoring information have been raised. According to the problem of identifying abnormal monitoring information, the abnormal recognition method of monitoring information is put forward, which is combined hypothesis based on improved statistics with AR(p) based on Kalman filter, after studying on many other deposing method of abnormal. First, the abnormal monitoring data has been identified by means of improving hypothesis, and it will be delete directly. Then the deleted points are took as missing value, and the abnormal values are be predicted with AR(p) model based on Kalman filtering algorithm, and we fill the abnormal values with the predicted values, which is the preparation for next prediction.
3. To realize the alarm of monitoring system, the integrated forecast model of monitoring information based on wavelet decomposition and least squares supports vector regression are established. Firstly, obtaining each decomposed layers sequence of monitoring information with wavelet decomposition. Secondly, the each decomposed layers sequence are predicted by using the least square support vector regression machine. Finally, realizing the prediction of monitoring information through composing the forecast results of each sequence. Meanwhile, the LS-SVMs are optimized by using PSO, and the related experiments are conducted and the results show the integrated method can obtain better forecasting results than other forecast methods.
4. The article develops the experiment platform of intelligent health monitoring system. System structure, hardware and software architecture are designed. Healthy monitoring system is programmed on the operation system Windows NT. SQL Server 2000 is used as database, and Windows visual studio.net 2005 is adopted as development tool. Experiment results show that health monitoring system has the function of reducing noise effectively, identification of unusual values and prediction. The efficiency of proposed methods are intensified by experiment results.
引文
[1]林兆花,谢存禧.基于视频的社区智能远程健康监护系统研究.微计算机信息.2008.2：77-79.
[2]沈若玲。人口老龄化与老年社区护理现状[J].现代护理,2007,13(12)：1117-1119.
[3]周海旺。上海老年人享受医疗保障的现状与问题。中国社会保障,2002,6：1-33.
[4]陈洁君。对老年人医疗保险制度的探讨。河南大学学报哲学社会科学版,2004,6(2)：45-48.
[5]Vlaskamp FJM. SAFE 21-NEW social alarm servies via a person infrastructure[C]. Proceedings of the 3rd TIDE Congress; Technology for Inclusive Design and Equality Improving the Quality of life for the Eurpean Citizen, Helsinki, Finland, 1998,(6):23-25
[6]Williams G, Doughty K, Bradley DA. A system approach to achieving Carernet an integrated and Information Technology in Biomedicine,1998,(20):1-9
[7]Riseborough M. Community Alarm services Today and Toworrow[M]. Oxford: Anchor Research,1997
[8]Frank G, Misklly. Assitive technology in elderly care[J]. Age and aging, 2001,(30):455-458
[9]Ohta S, Nakamoto H, Shinagawa Y etc. A health monitoring system for elderly people living alone[J]. Journal of Telemedicine and Telecare,2002,(8):151-156
[10]Bashshur RL. Telemedicine and Health Care[J]. Telemedicine Journal and e-Health,2002,(8):5-12
[11]Doughty K, Cameron K, Garner P. Three generations of telecare,1996,(2):71-80
[12]Scalvini S, Zanelli E, Volterrani M etc. A pilot study of nurse-led, home-based telecardiology for patients with chronic heart failure[J]. Journal of Telemedicine and Telecare,2004(10):113-117
[13]Alfredo I. Hernandez, Fernando Mora, etc. Real-Time ECG Transmission Via Internet for Nonclinical Applications IEEE. Transcations on Information Technology in Biomedicine,2001,5(3):253-257.
[14]Sadiq, M.A., Hoshiba, Y., Usman, K. etc. Telemedicine in Remote Areas of Bhutan via PSTN. Enterprise Networking and Computing in Healthcare Industry, 2004, Healthcom 2004. Proceedings.6th International Workshop on 28-29 June 2004: 44-47.
[15]Yuechun Chu, Aura Ganz. A Mobile Teletrauma System Using 3G Networks. IEEE Transcations on Information Technology in Biomedicine.2004,8(4):456-462.
[16]M Clarke, RW Jones, AIDMAN-Telecardiology Over a High-speed Satellite Network. Computers in Cardiology.2000,27:657-660.
[17]Kevin Hung, Yuan-Ting Zhang. Implementation of a WAP-Based Telemedicine System for Patient Monitoring. IEEE Transcations on Information Technology in Biomedicine.2003,7(2):101-107.
[18]PAN J, TOMPKINSW J. A real-time QRS detection algorithm [J]. IEEE Trans. on BME 1985,32 (3):230-236.
[19]ZHU LY, WU B M, WANG ZH G, et a.l A real-time QRS complex detection algorithm formobile ECG telemonitoring system[J]. Chinese Journal of Scientific Instrument,2005,26(6):603-607.
[20]VALTINO X, AFONSO, TOMPKINSW J. Filter bank based ECG beat detection[C]. Proceedings of 19th AnnualConference of IEEE/EMBS,1996: 1037-1038.
[21]VIJAYA G, KUMAR V, VERMAH K. ANN-based QRS complex analysis of ECG[J]. J.Med. Eng. Techno.1,1998,22(4):160-167.
[22]于学鸿,许小汉.,基于神经网络的波型检测方法[J].生物医学工程学杂志,2000,17(1)：59-62.
[23]LI C W. Detection of ECG characterstic points using wavelet transforms [J]. IEEE Trans on BME,1995,42(1):21-28.
[24]姬军,董秀珍.心电信号QRS波的识别算法及程序设计[J].北京生物医学工程,2001,20(2)：119-125.
[25]WANG X K, QIN SH R, LIANG X R. The application of wavelet transform in ECG feature extraction[J]. Beijing Biomedical Engineering,2005,24(6):410-413.
[26]PARK K L, LEE K J, YOON H R. Application of a wavelet adaptive filter to minimize distortion of the ST segment[J]. Med. Bio.l Eng. Comput.1998, 36(5):581-586.
[27]LIX Y, WANG T. ST-T complex automatic analysis of the electrocardiogram signals based on wavelet transform[C]. Bioengineering Conference,2003 IEEE 29th Annua,12003:144-145.
[28]芦继来,胡广书.基于小波变换的运动心电ST段检测方法[J].北京生物医学工程,2005,24(6)：329-350.
[29]Ercelebi E. Electrocardiogram signals de-noising using lifting-based descrete wavelet transform[J]. Comput Biol Med.2004,34(6):479-493.
[30]He T, Clifford GD, Tarassenko L. Application of independent component analysis in removing artifacts from the electrocardiogram[J]. Neural Comput. Appl. 2006,15:105-116.
[31]Sittig D F and Factor M. Physiologic trend detection and artifact rejection:a parallel implementation of a multi-state Kalman filtering algorithm[J]. Comput. Methods Programs biomed.1990,31(1):1-10.
[32]Cao C, Kohane IS, McIntosh N. Artifact detection in cardiovascular time series monitoring data from preterm infants[C]. Proc AMIA Symp.1999,207-211.
[33]Tsien CL, Kohane IS, Mclntosh N, Multiple signal integration by decision tree induction to detect artifacts in the neonatal intensive care unit[J]. Artificial Intelligence in Medicine,2000(19):189-202.
[34]Tsien CL, Kohane IS, McIntosh N. Building ICU artifact detection models with more data in less time[C]. Proc AMIA Symp.2001,706-710.
[35]David J.Christini, Frederick M.Bennett, Kenneth R.Lutchen, etc. Application of linear and nonlinear time series modeling to heart rate dynamics analysis. IEEE Transactions on biomedical engineering.1995, Vol.42,No 4:411-415.
[36]Martin Daumer, Markus Falk. On-line change-point detection (for state space models) using multijprocess Kalman filters. Linear Algebra and its application. 1998,284:125-135.
[37]P.L. Davies, R.Fried, U.Gather. Robust signal extraction for on-line monitoring data. Journal of Statistical Planning and Inference 122 (2004) 65-78.
[38]Sylvie Charbonnier, Guillaume Beeq, Loic Biot. On-Line segmentation algorithm for continuously monitored data in intensive care units. IEEE Transactions on biomedical engineering.2004, Vol.51,No 3:484-492.
[39]Sylvie Charbonnier, Garcia-Beltan C, Cadet C, etc. Trends extraction and analysis for complex system monitoring and decision support. Engineer Applications of artificial Intelligence 18 (2005) 21-36.
[40]Sylvie Charbonnier. On line extraction of temporal episodes from ICU high-frequency data: A visual support for signal interpretation. Computer Methods and Programs in Biomedicine (2005) 78,115-132.
[41]Roland Fried, Ursula Gather, Michael Imhoff. Online pattern recognition in intensive care medicine. Journal of the American medical informatics association. 2001, Suppl.S:184-188.
[42]Gather, U., Imhoff, M., and Fried, R., Graphical models for multivariate time series from intensive care monitoring. STATISTICS IN MEDICINE 21 (18): 2685-2701 SEP 30 2002
[43]邹焱飚.基于机器人多功能护理床的智能社区远程监护系统研究.华南理工大学博士学位论文.2005,6.
[44]M.Imhoff, M.Bauer, U.Gather, R.Fried. Pattern detection in intensive care monitoring time series with autoregressive models:Influence of the model order. Biometrical Journal.2002,44,6:746-761.
[45]Box and Jenkins,时间序列分析预测与控制。顾岚,范金城译.第三版.中国统计出版社.2003.
[46]Zellner, A. An Introduction to Bayesian Inference in Econometrics. Wiley, New York.197i.
[47]Newbold。P. Bayesian estimation of Box—Jenkins transfer function models, J. R. Stat. Soc. Ser.1973, B 35(2):323—336.
[48]Monohan, J. F. Full Bayesian analysis of ARMA time series models, J. Econometrics.1983,21:307-331.
[49]Ho1dlen K, Broomhead A. An rxamination of vertorauto—regressive forecasts for the U. K[J]. Economy.1990,6(1):11-23.
[50]Phi 11 ip P C B. Bayes model and forecasts of Australian macroeconomic time series[J]. Journal of Time Series.1994,15(2):241-246.
[51]王文玉,时间序列的AR及ARMA模型的阶数的贝叶斯判据,应用数学学报,1984,185-195.
[52]朱慧敏,韩玉启,郑进成.基于正态—Gamma共轭先验分布的贝叶斯AR(p) 预测模型.统计与决策.2005,(1)：8-9.
[53]LUA C, GESTEL TV, SUYKENS J, etal.PreoPerative prediction of malignancy of ovarian tumors using least squares support vector machines [J].Arficial Intelligence in Medieine,2003,28:281-306.
[54]KE Y, YIYU C, Discriminating the genuineness of Chinese medicines using least squares support vector machines[J], Chinese Journal of Analytical Chemistry,2006, 34(4):561-564.
[55]COMAK E, POLAT K, GUNES S, etal.A new medical decision making system: Least square support vector machine(lssvm) with fuzzy weighting preprocessing[J]. Expert Systems with Applications,2007,32:409-414.
[56]POLAT K, GINES S.Breast cancer diagnosis using least square support vector machine[J]. Digital Signal Processing,2007,17:694-701.
[57]POLAT K, AKDEMIR B, GINES S.Computer aided diagnosis of ecg data on the Least square support vector machine[J].Digital Signal processing,2008,18:25-32
[58]HANBAY D.An expert system based on least square support vector machines for diagnosis of the valvular heart disease [J].Expert Systems with Applications,2008, In press.
[59]A.Kawamura, K.Fujii, Y.Itoh and Y.Fukui, "A new noise reduction method based on linear prediction", Proc. ISPACS, vol2, pp.742-745, Nov.2000.
[60]J.Benesty, J.Chen and Y.Huang, "On widely linear Wiener and tradeoff filters for noise reduction" Speech Commun., submitted for publication.
[61]J.Benesty, J.Chen and Y.Huang, "A Widely Linear Distortionless Filter for Single-Channel Noise Reduction", IEEE signal processing letters, vol.17, No.5, MAY 2010.
[62]Hammel S M. A noise reduction method for chaotic system [J]. Physics Letter A, 1990,148(8-9):421-428.
[63]吴洪艳,黄道平.基于特征向量提取的核主元分析法.计算机科学,2009,36(7)：185-187.
[64]王大凯,彭进业.《小波分析及其在信号处理中的应用》.电子工业出版社,2006.
[65]乐全明,郁惟镛.基于提升算法的电力系统故障录波数据压缩新方案.电力系统自动化.2005,29(5)：74-78
[66]王宏宝.电子测量.北京：科学出版社,2005
[67]苏丽.远程心电监护诊断系统心电信号处理方法研究.哈尔滨工程大学博士学位论文,2006
[68]周伟编.《MATLAB小波分析高级技术》,西安电子科技大学出版社,2006.1
[69]Astola Jaakko, Kuosmanen Pauli. Fundamentals of nonlinear digital filtering[M]. Boca Raton, New York:CRC Press,1997.
[70]邹焱飚,林兆花,谢存禧.监护信息系统中异常值的识别和处理方法,测试技术学报,2007,21(6)：530-535.
[71]Moody GB, Mark RG, Goldberger AL. PhysioNet: A web-based resource for the study of physiologic signals[J]. IEEE Engineering in Medicine and Biology Magazine(S0739-5175),2001,20(3):70-75.
[72]O'Carrol T M. Survey of alarm in an intensive therapy unit[J]. Anaesthsia, 1986(41):742-744.
[73]Cook. R.D. Detection of influential observation in linear regression. Technometrics.1977,19:15-18.
[74]Barrett. B.E. and Ling. R.F. General classes of influence measures for multivariate regression. J.Am. Statist. Assoc.1992,87:184-191.
[75]Bruce. A.G. and Martin. R.D. Leave-k-out diagnostics for time series(with discussion). J.R. Statist. Soc. B.1989,51:363-424.
[76]Christensen. R., Person. L.M. and Johnson. W. Case-deletion diagnostics for mixed models. Technometrics.1992(34):38-45.
[77]Bannerjee. M. and Frees. E.W. Influence diagnostics for linear longitudinal models. J.Am. Statist. Assoc.,1997(92):999-1005.
[78]Preisser. J.S. and Qaqish, B.F. Deletion diagnostics for generalised estimating equations. Biometrika.1996(83):551-562.
[79]Christensen, R. and Pearson, L.M. Prediction diagnostics for spatial linear models. Biometrika.1992(79):583-591.
[80]Christensen, R. and Pearson, L.M. Convariance function diagnostics for spatial linear models. Math. Geol.,1993(25):145-160.
[81]Huber. P. Robust Statistics, New York:Wiley and Sons.1981.
[82]Elashoff, J.D. A model for quadratic outliers in linear regression. J.Am. Statist. Assoc.,1972(67):478-485.
[83]Aitkin, M. and Wilson, G.T. Mixture models. Outliers and the EM algorithm. Technometrics.1980(22):325-332.
[84]Box, G.E.P. and Tiao, G.C. A bayesian approach to some outlier problems. Biometrika.1968(55):119-129.
[85]Guttman,I. Care and handling of univariate or multivariate outliers in detecting spuriosity-a bayesian approach. Technometrics.1973(15):732-738.
[86]Guttman,I., Dutter, R. and Freeman, P.R. Care and handling of univariate outliers in the general linear model to detect spuriosity-a bayesian approach. Technometrics.1978(20):187-193.
[87]Cook. R.D. Assessment of local influence(with discussion). J.R. Statist. Soc.B 1986(48):133-169.
[88]Wu, X. and Luo, Z. Residual sum of squares and multiple potential. Diagnostics by a second order local approach. Statist. Probab. Lett.,1993(16):289-293.
[89]王彤,何大卫.线性回归中多个异常点的稳健诊断及医学应用[J].中国卫生统计,1988,15(5)：1-4.
[90]Roland Fried, Ursula Gather, Michael Imhoff, and Marcus Bauer. Some Statistical Methods in Intensive Care Online Monitoring A Review. Medical data analysis, proceeding lecture notes in computer science 1933,2000. springer-verlag berlin:67-77.
[91]韦博成,鲁国斌,史建清.统计诊断引论[M].南京：东南大学出版社,1991.28-30.
[92]王彤,何大卫.线性回归中多个异常点的诊断[J],中国卫生统计1997,14(6)：7-10.
[93]Mickey MR, Dunn OJ, Clark V. Computers and Biomedicine Research, 1967,1:105-111.
[94]Gentleman JF, Wilk MB. Biometrics,1975,31:387-410.
[95]Paul SR, Fung KY. Technometrics,1991,33:339-348.
[96]程博.对几个统计模型的构造和数据分析.南开大学博士学位论文,2001
[97]Hampel, F.R. The influence curve and its role in robust estimation. J.Am. Statist. Assoc.,1974(69):383-393.
[98]Mcleod, A.I. On the distribution of residual autocorrelations in Box-Jenkins models. J.R. Statist. Soc.B.1978(40):296-302.
[99]Li, W.K. and Hui, Y.V. On the empirical influence functions of residual autocorrelations in time series. Proc. Busi. Econom. Statist. Sec, Amer. Statist. Assoc, 1987:465-468.
[100]温雯,郝志峰,杨晓伟等.基于假设检验及异常点剔除的稳健LS-SVM回归,模式识别与人工智能,2010,4：241-249.
[101]邓勃.分析测试数据的统计处理方法[M].北京：清华大学出版社,1994,48-49.
[102]陶澍.应用数理统计方法[M].北京：中国环境科学出版社,1995.
[103]王太勇,王国锋,吴振勇等,加工状态下实测信号的AR最优建模,天津大学学报.2002.3(2)：159-161.
[104]李清泉,杨蜀江,陀螺经纬仪逆转点观测数据随机模型的研究,测绘工程,1999,5(2)：39-44
[105]杨位钦,顾岚编.时间序列分析与动态数据建模[M].修订版.北京：北京理工大学出版社,1988：98-111.
[106]Paulo S. R. Diniz.自适应滤波算法与实现(第二版)[M].北京：电子工业出版社,2004.7：49-61.
[107]陈希孺.最小一乘线性回归(上)[J].数理统计与管理,1989,(5)：48-55.
[108]Birkes.D. and Dodge.Y. Alternative Methods of Resression. New York:Wiley. 1993:191-192.
[109]Cade.B.S. and Richards.J.D. Permutation tests for least absolute deviation regression. Biometrics.1996(52):886-902.
[110]邓自立.卡尔曼滤波与维纳滤波[M].哈尔滨：哈尔滨工业大学出版社,2001.
[111]贾沛璋,朱征桃.最优估计及其应用[M].北京：科学出版社,1994
[112]西蒙·赫金著.《自适应滤波器原理》,电子工业出版社,2006.11
[113]YANG S K, LIU T S. State estimation for predictive maintenance using Kalman filter[J]. Reliability Engineering and System Safety,1999,66(1):29-39.
[114]Zhao J, Xu L, Liu L. Equipment Fault Forecasting Based on ARMA Model[J]. ICMA,2007:3514-3518.
[115]Guizhong Tang, Guangming Zhang, etc. Turbo-Generator Vibration Fault Prediction Using Gray Prediction Model[A]. Proceedings of the 7th World Congress on Intelligent Control and Automation[C], WCICA.2008:25-27.
[116]Zhang Zhengdao, Hu Shousong. Fault prediction of fighter based on nonparametric density estimation[J]. Journal of Systems Engineering and Electronics, 2005,16(4):831-836.
[117]Tse P W, Atherton D P. Prediction of machine deterioration using vibration based fault trends and recurrent neural networks [J]. Journal of Vibration and Acoustics,1999,121(7):355-362.
[118]Xu K, Xie M, etc. Application of Neural Networks in forecasting Engine Systems Reliability [J], Applied Soft Computing.2003,2:255-268.
[119]Policker S, Geva A. B. A New Algorithm for Time Series Prediction by Temporal Fuzzy Clustering[A]. Proceedings of 15th International Conference on Pattern Recognition[C], ICPR.2000:732-735.
[120]Vapnik V.N. The Nature of Statistical Learning Theory[M]. New York, Springer-Verlag,1995.
[121]Vapnik V.N. An overview of statistical learning theory[J]. IEEE Trans Neural Network,1999,10(5):988-999.
[122]M. Dominique and B. Alistair. Nonlinear blind source separation using kernels[J]. IEEE Trans. On Neural Networks,2003,14(1):228-235.
[123]邵信光,杨慧中,陈刚.基于粒子群优化算法的支持向量机参数选择及其应用[J].控制理论与应用,2006,23(5)：740-743.
[124]闻新,周露等.《MATLAB神经网络应用设计》,科学出版社,2002.9
[125]何仁斌.《MATLAB6工程计算及应用》,重庆大学出版社,2001.12
[2]沈若玲。人口老龄化与老年社区护理现状[J].现代护理,2007,13(12)：1117-1119.
[3]周海旺。上海老年人享受医疗保障的现状与问题。中国社会保障,2002,6：1-33.
[4]陈洁君。对老年人医疗保险制度的探讨。河南大学学报哲学社会科学版,2004,6(2)：45-48.
[5]Vlaskamp FJM. SAFE 21-NEW social alarm servies via a person infrastructure[C]. Proceedings of the 3rd TIDE Congress; Technology for Inclusive Design and Equality Improving the Quality of life for the Eurpean Citizen, Helsinki, Finland, 1998,(6):23-25
[6]Williams G, Doughty K, Bradley DA. A system approach to achieving Carernet an integrated and Information Technology in Biomedicine,1998,(20):1-9
[7]Riseborough M. Community Alarm services Today and Toworrow[M]. Oxford: Anchor Research,1997
[8]Frank G, Misklly. Assitive technology in elderly care[J]. Age and aging, 2001,(30):455-458
[9]Ohta S, Nakamoto H, Shinagawa Y etc. A health monitoring system for elderly people living alone[J]. Journal of Telemedicine and Telecare,2002,(8):151-156
[10]Bashshur RL. Telemedicine and Health Care[J]. Telemedicine Journal and e-Health,2002,(8):5-12
[11]Doughty K, Cameron K, Garner P. Three generations of telecare,1996,(2):71-80
[12]Scalvini S, Zanelli E, Volterrani M etc. A pilot study of nurse-led, home-based telecardiology for patients with chronic heart failure[J]. Journal of Telemedicine and Telecare,2004(10):113-117
[13]Alfredo I. Hernandez, Fernando Mora, etc. Real-Time ECG Transmission Via Internet for Nonclinical Applications IEEE. Transcations on Information Technology in Biomedicine,2001,5(3):253-257.
[14]Sadiq, M.A., Hoshiba, Y., Usman, K. etc. Telemedicine in Remote Areas of Bhutan via PSTN. Enterprise Networking and Computing in Healthcare Industry, 2004, Healthcom 2004. Proceedings.6th International Workshop on 28-29 June 2004: 44-47.
[15]Yuechun Chu, Aura Ganz. A Mobile Teletrauma System Using 3G Networks. IEEE Transcations on Information Technology in Biomedicine.2004,8(4):456-462.
[16]M Clarke, RW Jones, AIDMAN-Telecardiology Over a High-speed Satellite Network. Computers in Cardiology.2000,27:657-660.
[17]Kevin Hung, Yuan-Ting Zhang. Implementation of a WAP-Based Telemedicine System for Patient Monitoring. IEEE Transcations on Information Technology in Biomedicine.2003,7(2):101-107.
[18]PAN J, TOMPKINSW J. A real-time QRS detection algorithm [J]. IEEE Trans. on BME 1985,32 (3):230-236.
[19]ZHU LY, WU B M, WANG ZH G, et a.l A real-time QRS complex detection algorithm formobile ECG telemonitoring system[J]. Chinese Journal of Scientific Instrument,2005,26(6):603-607.
[20]VALTINO X, AFONSO, TOMPKINSW J. Filter bank based ECG beat detection[C]. Proceedings of 19th AnnualConference of IEEE/EMBS,1996: 1037-1038.
[21]VIJAYA G, KUMAR V, VERMAH K. ANN-based QRS complex analysis of ECG[J]. J.Med. Eng. Techno.1,1998,22(4):160-167.
[22]于学鸿,许小汉.,基于神经网络的波型检测方法[J].生物医学工程学杂志,2000,17(1)：59-62.
[23]LI C W. Detection of ECG characterstic points using wavelet transforms [J]. IEEE Trans on BME,1995,42(1):21-28.
[24]姬军,董秀珍.心电信号QRS波的识别算法及程序设计[J].北京生物医学工程,2001,20(2)：119-125.
[25]WANG X K, QIN SH R, LIANG X R. The application of wavelet transform in ECG feature extraction[J]. Beijing Biomedical Engineering,2005,24(6):410-413.
[26]PARK K L, LEE K J, YOON H R. Application of a wavelet adaptive filter to minimize distortion of the ST segment[J]. Med. Bio.l Eng. Comput.1998, 36(5):581-586.
[27]LIX Y, WANG T. ST-T complex automatic analysis of the electrocardiogram signals based on wavelet transform[C]. Bioengineering Conference,2003 IEEE 29th Annua,12003:144-145.
[28]芦继来,胡广书.基于小波变换的运动心电ST段检测方法[J].北京生物医学工程,2005,24(6)：329-350.
[29]Ercelebi E. Electrocardiogram signals de-noising using lifting-based descrete wavelet transform[J]. Comput Biol Med.2004,34(6):479-493.
[30]He T, Clifford GD, Tarassenko L. Application of independent component analysis in removing artifacts from the electrocardiogram[J]. Neural Comput. Appl. 2006,15:105-116.
[31]Sittig D F and Factor M. Physiologic trend detection and artifact rejection:a parallel implementation of a multi-state Kalman filtering algorithm[J]. Comput. Methods Programs biomed.1990,31(1):1-10.
[32]Cao C, Kohane IS, McIntosh N. Artifact detection in cardiovascular time series monitoring data from preterm infants[C]. Proc AMIA Symp.1999,207-211.
[33]Tsien CL, Kohane IS, Mclntosh N, Multiple signal integration by decision tree induction to detect artifacts in the neonatal intensive care unit[J]. Artificial Intelligence in Medicine,2000(19):189-202.
[34]Tsien CL, Kohane IS, McIntosh N. Building ICU artifact detection models with more data in less time[C]. Proc AMIA Symp.2001,706-710.
[35]David J.Christini, Frederick M.Bennett, Kenneth R.Lutchen, etc. Application of linear and nonlinear time series modeling to heart rate dynamics analysis. IEEE Transactions on biomedical engineering.1995, Vol.42,No 4:411-415.
[36]Martin Daumer, Markus Falk. On-line change-point detection (for state space models) using multijprocess Kalman filters. Linear Algebra and its application. 1998,284:125-135.
[37]P.L. Davies, R.Fried, U.Gather. Robust signal extraction for on-line monitoring data. Journal of Statistical Planning and Inference 122 (2004) 65-78.
[38]Sylvie Charbonnier, Guillaume Beeq, Loic Biot. On-Line segmentation algorithm for continuously monitored data in intensive care units. IEEE Transactions on biomedical engineering.2004, Vol.51,No 3:484-492.
[39]Sylvie Charbonnier, Garcia-Beltan C, Cadet C, etc. Trends extraction and analysis for complex system monitoring and decision support. Engineer Applications of artificial Intelligence 18 (2005) 21-36.
[40]Sylvie Charbonnier. On line extraction of temporal episodes from ICU high-frequency data: A visual support for signal interpretation. Computer Methods and Programs in Biomedicine (2005) 78,115-132.
[41]Roland Fried, Ursula Gather, Michael Imhoff. Online pattern recognition in intensive care medicine. Journal of the American medical informatics association. 2001, Suppl.S:184-188.
[42]Gather, U., Imhoff, M., and Fried, R., Graphical models for multivariate time series from intensive care monitoring. STATISTICS IN MEDICINE 21 (18): 2685-2701 SEP 30 2002
[43]邹焱飚.基于机器人多功能护理床的智能社区远程监护系统研究.华南理工大学博士学位论文.2005,6.
[44]M.Imhoff, M.Bauer, U.Gather, R.Fried. Pattern detection in intensive care monitoring time series with autoregressive models:Influence of the model order. Biometrical Journal.2002,44,6:746-761.
[45]Box and Jenkins,时间序列分析预测与控制。顾岚,范金城译.第三版.中国统计出版社.2003.
[46]Zellner, A. An Introduction to Bayesian Inference in Econometrics. Wiley, New York.197i.
[47]Newbold。P. Bayesian estimation of Box—Jenkins transfer function models, J. R. Stat. Soc. Ser.1973, B 35(2):323—336.
[48]Monohan, J. F. Full Bayesian analysis of ARMA time series models, J. Econometrics.1983,21:307-331.
[49]Ho1dlen K, Broomhead A. An rxamination of vertorauto—regressive forecasts for the U. K[J]. Economy.1990,6(1):11-23.
[50]Phi 11 ip P C B. Bayes model and forecasts of Australian macroeconomic time series[J]. Journal of Time Series.1994,15(2):241-246.
[51]王文玉,时间序列的AR及ARMA模型的阶数的贝叶斯判据,应用数学学报,1984,185-195.
[52]朱慧敏,韩玉启,郑进成.基于正态—Gamma共轭先验分布的贝叶斯AR(p) 预测模型.统计与决策.2005,(1)：8-9.
[53]LUA C, GESTEL TV, SUYKENS J, etal.PreoPerative prediction of malignancy of ovarian tumors using least squares support vector machines [J].Arficial Intelligence in Medieine,2003,28:281-306.
[54]KE Y, YIYU C, Discriminating the genuineness of Chinese medicines using least squares support vector machines[J], Chinese Journal of Analytical Chemistry,2006, 34(4):561-564.
[55]COMAK E, POLAT K, GUNES S, etal.A new medical decision making system: Least square support vector machine(lssvm) with fuzzy weighting preprocessing[J]. Expert Systems with Applications,2007,32:409-414.
[56]POLAT K, GINES S.Breast cancer diagnosis using least square support vector machine[J]. Digital Signal Processing,2007,17:694-701.
[57]POLAT K, AKDEMIR B, GINES S.Computer aided diagnosis of ecg data on the Least square support vector machine[J].Digital Signal processing,2008,18:25-32
[58]HANBAY D.An expert system based on least square support vector machines for diagnosis of the valvular heart disease [J].Expert Systems with Applications,2008, In press.
[59]A.Kawamura, K.Fujii, Y.Itoh and Y.Fukui, "A new noise reduction method based on linear prediction", Proc. ISPACS, vol2, pp.742-745, Nov.2000.
[60]J.Benesty, J.Chen and Y.Huang, "On widely linear Wiener and tradeoff filters for noise reduction" Speech Commun., submitted for publication.
[61]J.Benesty, J.Chen and Y.Huang, "A Widely Linear Distortionless Filter for Single-Channel Noise Reduction", IEEE signal processing letters, vol.17, No.5, MAY 2010.
[62]Hammel S M. A noise reduction method for chaotic system [J]. Physics Letter A, 1990,148(8-9):421-428.
[63]吴洪艳,黄道平.基于特征向量提取的核主元分析法.计算机科学,2009,36(7)：185-187.
[64]王大凯,彭进业.《小波分析及其在信号处理中的应用》.电子工业出版社,2006.
[65]乐全明,郁惟镛.基于提升算法的电力系统故障录波数据压缩新方案.电力系统自动化.2005,29(5)：74-78
[66]王宏宝.电子测量.北京：科学出版社,2005
[67]苏丽.远程心电监护诊断系统心电信号处理方法研究.哈尔滨工程大学博士学位论文,2006
[68]周伟编.《MATLAB小波分析高级技术》,西安电子科技大学出版社,2006.1
[69]Astola Jaakko, Kuosmanen Pauli. Fundamentals of nonlinear digital filtering[M]. Boca Raton, New York:CRC Press,1997.
[70]邹焱飚,林兆花,谢存禧.监护信息系统中异常值的识别和处理方法,测试技术学报,2007,21(6)：530-535.
[71]Moody GB, Mark RG, Goldberger AL. PhysioNet: A web-based resource for the study of physiologic signals[J]. IEEE Engineering in Medicine and Biology Magazine(S0739-5175),2001,20(3):70-75.
[72]O'Carrol T M. Survey of alarm in an intensive therapy unit[J]. Anaesthsia, 1986(41):742-744.
[73]Cook. R.D. Detection of influential observation in linear regression. Technometrics.1977,19:15-18.
[74]Barrett. B.E. and Ling. R.F. General classes of influence measures for multivariate regression. J.Am. Statist. Assoc.1992,87:184-191.
[75]Bruce. A.G. and Martin. R.D. Leave-k-out diagnostics for time series(with discussion). J.R. Statist. Soc. B.1989,51:363-424.
[76]Christensen. R., Person. L.M. and Johnson. W. Case-deletion diagnostics for mixed models. Technometrics.1992(34):38-45.
[77]Bannerjee. M. and Frees. E.W. Influence diagnostics for linear longitudinal models. J.Am. Statist. Assoc.,1997(92):999-1005.
[78]Preisser. J.S. and Qaqish, B.F. Deletion diagnostics for generalised estimating equations. Biometrika.1996(83):551-562.
[79]Christensen, R. and Pearson, L.M. Prediction diagnostics for spatial linear models. Biometrika.1992(79):583-591.
[80]Christensen, R. and Pearson, L.M. Convariance function diagnostics for spatial linear models. Math. Geol.,1993(25):145-160.
[81]Huber. P. Robust Statistics, New York:Wiley and Sons.1981.
[82]Elashoff, J.D. A model for quadratic outliers in linear regression. J.Am. Statist. Assoc.,1972(67):478-485.
[83]Aitkin, M. and Wilson, G.T. Mixture models. Outliers and the EM algorithm. Technometrics.1980(22):325-332.
[84]Box, G.E.P. and Tiao, G.C. A bayesian approach to some outlier problems. Biometrika.1968(55):119-129.
[85]Guttman,I. Care and handling of univariate or multivariate outliers in detecting spuriosity-a bayesian approach. Technometrics.1973(15):732-738.
[86]Guttman,I., Dutter, R. and Freeman, P.R. Care and handling of univariate outliers in the general linear model to detect spuriosity-a bayesian approach. Technometrics.1978(20):187-193.
[87]Cook. R.D. Assessment of local influence(with discussion). J.R. Statist. Soc.B 1986(48):133-169.
[88]Wu, X. and Luo, Z. Residual sum of squares and multiple potential. Diagnostics by a second order local approach. Statist. Probab. Lett.,1993(16):289-293.
[89]王彤,何大卫.线性回归中多个异常点的稳健诊断及医学应用[J].中国卫生统计,1988,15(5)：1-4.
[90]Roland Fried, Ursula Gather, Michael Imhoff, and Marcus Bauer. Some Statistical Methods in Intensive Care Online Monitoring A Review. Medical data analysis, proceeding lecture notes in computer science 1933,2000. springer-verlag berlin:67-77.
[91]韦博成,鲁国斌,史建清.统计诊断引论[M].南京：东南大学出版社,1991.28-30.
[92]王彤,何大卫.线性回归中多个异常点的诊断[J],中国卫生统计1997,14(6)：7-10.
[93]Mickey MR, Dunn OJ, Clark V. Computers and Biomedicine Research, 1967,1:105-111.
[94]Gentleman JF, Wilk MB. Biometrics,1975,31:387-410.
[95]Paul SR, Fung KY. Technometrics,1991,33:339-348.
[96]程博.对几个统计模型的构造和数据分析.南开大学博士学位论文,2001
[97]Hampel, F.R. The influence curve and its role in robust estimation. J.Am. Statist. Assoc.,1974(69):383-393.
[98]Mcleod, A.I. On the distribution of residual autocorrelations in Box-Jenkins models. J.R. Statist. Soc.B.1978(40):296-302.
[99]Li, W.K. and Hui, Y.V. On the empirical influence functions of residual autocorrelations in time series. Proc. Busi. Econom. Statist. Sec, Amer. Statist. Assoc, 1987:465-468.
[100]温雯,郝志峰,杨晓伟等.基于假设检验及异常点剔除的稳健LS-SVM回归,模式识别与人工智能,2010,4：241-249.
[101]邓勃.分析测试数据的统计处理方法[M].北京：清华大学出版社,1994,48-49.
[102]陶澍.应用数理统计方法[M].北京：中国环境科学出版社,1995.
[103]王太勇,王国锋,吴振勇等,加工状态下实测信号的AR最优建模,天津大学学报.2002.3(2)：159-161.
[104]李清泉,杨蜀江,陀螺经纬仪逆转点观测数据随机模型的研究,测绘工程,1999,5(2)：39-44
[105]杨位钦,顾岚编.时间序列分析与动态数据建模[M].修订版.北京：北京理工大学出版社,1988：98-111.
[106]Paulo S. R. Diniz.自适应滤波算法与实现(第二版)[M].北京：电子工业出版社,2004.7：49-61.
[107]陈希孺.最小一乘线性回归(上)[J].数理统计与管理,1989,(5)：48-55.
[108]Birkes.D. and Dodge.Y. Alternative Methods of Resression. New York:Wiley. 1993:191-192.
[109]Cade.B.S. and Richards.J.D. Permutation tests for least absolute deviation regression. Biometrics.1996(52):886-902.
[110]邓自立.卡尔曼滤波与维纳滤波[M].哈尔滨：哈尔滨工业大学出版社,2001.
[111]贾沛璋,朱征桃.最优估计及其应用[M].北京：科学出版社,1994
[112]西蒙·赫金著.《自适应滤波器原理》,电子工业出版社,2006.11
[113]YANG S K, LIU T S. State estimation for predictive maintenance using Kalman filter[J]. Reliability Engineering and System Safety,1999,66(1):29-39.
[114]Zhao J, Xu L, Liu L. Equipment Fault Forecasting Based on ARMA Model[J]. ICMA,2007:3514-3518.
[115]Guizhong Tang, Guangming Zhang, etc. Turbo-Generator Vibration Fault Prediction Using Gray Prediction Model[A]. Proceedings of the 7th World Congress on Intelligent Control and Automation[C], WCICA.2008:25-27.
[116]Zhang Zhengdao, Hu Shousong. Fault prediction of fighter based on nonparametric density estimation[J]. Journal of Systems Engineering and Electronics, 2005,16(4):831-836.
[117]Tse P W, Atherton D P. Prediction of machine deterioration using vibration based fault trends and recurrent neural networks [J]. Journal of Vibration and Acoustics,1999,121(7):355-362.
[118]Xu K, Xie M, etc. Application of Neural Networks in forecasting Engine Systems Reliability [J], Applied Soft Computing.2003,2:255-268.
[119]Policker S, Geva A. B. A New Algorithm for Time Series Prediction by Temporal Fuzzy Clustering[A]. Proceedings of 15th International Conference on Pattern Recognition[C], ICPR.2000:732-735.
[120]Vapnik V.N. The Nature of Statistical Learning Theory[M]. New York, Springer-Verlag,1995.
[121]Vapnik V.N. An overview of statistical learning theory[J]. IEEE Trans Neural Network,1999,10(5):988-999.
[122]M. Dominique and B. Alistair. Nonlinear blind source separation using kernels[J]. IEEE Trans. On Neural Networks,2003,14(1):228-235.
[123]邵信光,杨慧中,陈刚.基于粒子群优化算法的支持向量机参数选择及其应用[J].控制理论与应用,2006,23(5)：740-743.
[124]闻新,周露等.《MATLAB神经网络应用设计》,科学出版社,2002.9
[125]何仁斌.《MATLAB6工程计算及应用》,重庆大学出版社,2001.12