基于K-means和MTLS-SVM算法的生理参数监测系统

doi:10.11959/j.issn.1000-0801.2017286

电信科学 ›› 2017, Vol. 33 ›› Issue (10): 43-49.doi: 10.11959/j.issn.1000-0801.2017286

• 专题：物联网技术与应用 • 上一篇下一篇

基于K-means和MTLS-SVM算法的生理参数监测系统

夏景明,唐玲玲,谈玲,郑晗

南京信息工程大学，江苏南京 210044

修回日期:2017-09-30 出版日期:2017-10-01 发布日期:2017-11-13
作者简介:夏景明（1980-），男，博士，南京信息工程大学电子与信息工程学院副教授，主要研究方向为信号处理。|唐玲玲（1992-），女，南京信息工程大学电子与信息工程学院硕士生，主要研究方向为智能仪器。|谈玲（1979-），女，博士，南京信息工程大学计算机与软件学院副教授，主要研究方向为物联网大数据及气候变化。|郑晗（1994-），男，南京信息工程大学计算机与软件学院硕士生，主要研究方向为物联网。
基金资助:
国家自然科学基金资助项目(41505017);江苏省自然科学基金资助项目(BK20160951)

Biometric monitoring system based on K-means ＆MTLS-SVM algorithm

Jingming XIA,Lingling TANG,Ling TAN,Han ZHENG

Nanjing University of Information Science ＆Technology,Nanjing 210044,China

Revised:2017-09-30 Online:2017-10-01 Published:2017-11-13
Supported by:
The National Natural Science Foundation of China(41505017);The National Natural Science Foundation of Jiangsu Province of China(BK20160951)

摘要/Abstract

摘要：

在非医模式的生理参数监测系统中，对监测参数进行学习，可以提高诊断和预测精度。针对多任务时间序列中存在的信息挖掘不充分、预测精度低等问题，将机器学习中的监督和半监督学习方式结合起来对远程健康监护对象进行生理状况预测。该方法用 K-means 算法将相同类别的数据集群，并使用多任务最小二乘支持向量机（MTLS-SVM）来训练历史数据来进行趋势预测。为了评估该方法的有效性，将MTLS-SVM方法与K-means、MTLS-SVM方法比较，实验结果表明该方法具有较高的预测精度。

关键词: 生理参数, 时间序列预测, K-means聚类, 多任务学习

Abstract:

In a nonmedical biometric monitoring system,the monitoring parameters are preceded with machine learning for precision promotion of diagnosis and prediction.Considering the problems of insufficient information mining and low prediction accuracy in multi task time series,both supervised and unsupervised machine learning techniques were applied to predict the physical condition of the remote health care.These techniques were K-means for clustering the similar group of data and MTLS-SVM model for training and testing historical data to perform a trend prediction.In order to evaluate the effectiveness of the method,the proposed method was compared with MTLS-SVM method.The experimental results show that the proposed method has higher prediction accuracy.

Key words: physiological parameter, time series prediction, K-means clustering, multi-task learning

中图分类号:

TN919

夏景明,唐玲玲,谈玲,郑晗. 基于K-means和MTLS-SVM算法的生理参数监测系统[J]. 电信科学, 2017, 33(10): 43-49.

Jingming XIA,Lingling TANG,Ling TAN,Han ZHENG. Biometric monitoring system based on K-means ＆MTLS-SVM algorithm[J]. Telecommunications Science, 2017, 33(10): 43-49.

图/表 9

图1

图2

图3

图4

表1

表2

表3

图5

图6

参考文献 14

[1]	褚航, 曾碧 . 非接触式心跳监控系统——面向社区医疗服务的物联网应用系统研究与开发[J]. 计算机系统应用, 2012,21(8): 233-235.
	CHU H , ZENG B . Non contact heartbeat monitoring system—research and development of internet of things application system for community medical service[J]. Computer System ＆Applications, 2012,21(8): 233-235.
[2]	谈玲, 张琭 . 交互式多生物特征识别技术在电子商务中的应用[J]. 电信科学, 2015,31(10): 124-129.
	TAN L , ZHANG L . Application of interactive multi-biometrics recognition on E-commerce[J]. Telecommunications Science, 2015,31(10): 124-129.
[3]	PALANIAPPAN S , AWANG R . Intelligent heart disease prediction system using data mining techniques[C]// International Conference on Computer Systems ＆ Applications,March 30-April 3,2008,Doha,Qatar. New Jersey:IEEE Press, 2008: 108-115.
[4]	TSIPOURAS M G , EXARCHOS T P , FOTIADIS D I ,et al. Automated diagnosis of coronary artery disease based on data mining and fuzzy modeling[J]. IEEE Transactions on Information Technology in Biomedicine, 2008,12(4): 447-458.
[5]	PATIL S B , KUMARASWAMY Y S . Intelligent and effective heart attack prediction system using data mining and artificial neural network[J]. European Journal of Scientific Research, 2009,31(4): 642-656.
[6]	SRINIVAS K , KAVITHA R B K , GOVRDHAN A . Applications of data mining techniques in healthcare and prediction of heart attacks[J]. International Journal on Computer Science and Engineering, 2010,2(2): 250-255.
[7]	RESUL D , TURKOGLU I , SENGUR A . Effective diagnosis of heart disease through neural networks ensembles[J]. International Journal of Expert Systems with Applications, 2009(36): 7675-7680.
[8]	VAPNIK V . The nature of statistical learning theory[M]. New York: SpringerPress, 1995.
[9]	SAPANKEVYCH N I , SANKAR R . Time series prediction using support vector machines:a survey[J]. IEEE Computational Intelligence Magazine, 2009,4(2): 24-38.
[10]	KAYTEZ F , TAPLAMACIOGLU M C , CAM E ,et al. Forecasting electricity consumption:a comparison of regression analysis,neural networks and least squares support vector machines[J]. International Journal of Electrical Power ＆ Energy Systems, 2015(67): 431-438.
[11]	VAN G T , SUYKENS J K , BAESTAENS D E ,et al. Financial time series prediction using least squares support vector machines within the evidence framework[J]. IEEE Transactions on Neural Networks, 2001,12(4): 809-821.
[12]	YE M Y , WANG X D . Chaotic time series prediction using least squares support vector machines[J]. Chinese Physics, 2004,13(4):454.
[13]	CARUANA R . Multitask learning[M]. New York: SpringerPress, 1998: 95-133.
[14]	HAN J W , KAMBER M . Data mining:concepts and techniques:2nd edition[J]. San Francisco:Morgan Kaufman Publishers, 2006.

	k=2			k=3			k=4			k=5
	数据集1	数据集2	数据集3	数据集1	数据集2	数据集3	数据集1	数据集2	数据集3	数据集1	数据集2	数据集3
心电情况	82.5%	78.1%	79.4%	80.6%	79.3%	79.8%	80.2%	77.9%	78.9%	79.7%	77.2%	77.4%
血压情况	78.7%	80.2%	79.7%	77.9%	80.8%	80.2%	76.5%	79.1%	77.8%	77.6%	79.2%	79.1%

	下降			平缓			上升
	数据集1	数据集2	数据集3	数据集1	数据集2	数据集3	数据集1	数据集2	数据集3
心电情况	15	13	11	18	16	19	17	21	20
血压情况	10	12	14	18	15	17	22	23	19

	误差	MTLS-SVM	基于K-means+MTLS-SVM	精度提高
心电情况	RMSE	4.36	3.46	20%
血压情况	MAE	3.68	2.87	22%
	RMSE	4.03	3.25	19%
	MAE	3.79	3.07	19%

基于K-means和MTLS-SVM算法的生理参数监测系统

Biometric monitoring system based on K-means ＆MTLS-SVM algorithm

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献 14

相关文章 1

Metrics

推荐阅读 0