正在加载图片...
第8卷第6期 智能系统学报 Vol.8 No.6 2013年12月 CAAI Transactions on Intelligent Systems Dec.2013 D0:10.3969/j.issn.1673-4785.201306035 网络出版地址:http://www.enki..net/kcms/detail/23.1538.TP.20131012.1814.007.html 基于小波HMM的UUV传感器数据孤立点检测 移岩,侯怒萍2,迟冬南 (1.海军驻沈阳地区舰船配套军事代表室,辽宁沈阳110031;2.哈尔滨工程大学机电工程学院,黑龙江哈尔滨 150001;3.哈尔滨工程大学自动化工程学院,黑龙江哈尔滨150001) 摘要:针对水下无人潜航器(UV)预测跟踪过程中传感器所采集数据的不准确问题,提出了一种利用小波隐马尔 可夫模型进行UUV预测跟踪数据孤立点检测的方法利用改进递归小波变换,对原始数据进行重构,小波系数中孤 立点处的系数得到局部放大小波系数的更新基于历史时刻的数据,因此,可以利用正常数据与孤立点的差异对数据 进行实时处理利用隐马尔可夫模型定义异常值分布判定函数,并以其作为依据,检测特征明显异于正常数据的孤立 点将准孤立点利用惰性算法进行重检测,提高孤立点检测的准确性.湖试数据验证了该方法能够有效地检测出UUV 预测跟踪中的数据孤立点. 关键词:水下无人潜航器:预测跟踪:小波变换:隐马尔可夫;孤立点检测 中图分类号:TP18:TN96711文献标志码:A文章编号:1673-4785(2013)06-0551-07 中文引用格式:穆岩,侯恕萍,迟冬南.基于小波HMM的UUV传感器数据孤立点检测[J].智能系统学报,2013,8(6):551-557. 英文引用格式:MU Yan,HOU Shuping,CHI Dongnan.UUV sensor data outlier detection using wavelet HMM[J].CAAI Transac- tions on Intelligent Systems,2013,8(6):551-557. UUV sensor data outlier detection on the basis of wavelet HMM MU Yan',HOU Shuping',CHI Dongnan? (1.Representative Department for Forming Complete Sets of Naval Ships in the Area of Shenyang,Shenyang 110031,China;2.Col- lege of Mechanical and Electrical Engineering,Harbin Engineering University,Harbin 150001,China;3.College of Aotomation,Har- bin Engineering University,Harbin 150001,China) Abstract:A method for outlier detection based on wavelet HMM hidden Markov model)is proposed in this paper in order to deal with the inaccurate original data collected from sensors during UUV forecast tracing.The improved recursive wavelet transform (IRWT)is used to reconstruct the original data and locally amplify the wavelet coeffi- cients of the outliers.The update of wavelet coefficients are based on the data at the historical moment,thus,data may be processed in real time by utilizing the difference between normal data and outliers.The judgment function on the distribution of abnormal values is defined by HMM.In addition,on the basis of this,the outliers with features obviously different from the normal data are detected.The quasi-outliers are redetected by using a lazy algorithm for improving the accuracy of the detection results.The data from the lake experiment verify that the method may effec- tively detect the data outliers in UUV forecast tracing. Keywords:underwater unmanned vehicle;forecast tracing;wavelet transform;hidden Markov model;outlier de- tection UUV(underwater unmanned vehicle)的预测跟踪 主要应用于其在未知环境中航行、对环境进行感知 并完成既定任务的过程中在感知未知环境的过程 收稿日期:2013-06-20.网络出版日期:2013-10-12 中,传感器所采集的数据成为UUV自主决策的惟一 基金项目:国家自然科学基金资助项目(51109043). 通信作者:侯恕萍.E-mail:houshuping@hrbeu.cdu.cn 依据.因此,原始数据的准确性直接影响着UUV的第 8 卷第 6 期 智 能 系 统 学 报 Vol.8 №.6 2013 年 12 月 CAAI Transactions on Intelligent Systems Dec. 2013 DOI:10.3969 / j.issn.1673⁃4785.201306035 网络出版地址:http: / / www.cnki.net / kcms/ detail / 23.1538.TP.20131012.1814.007.html 基于小波 HMM 的 UUV 传感器数据孤立点检测 穆岩1 ,侯恕萍2 ,迟冬南3 (1.海军驻沈阳地区舰船配套军事代表室,辽宁 沈阳 110031; 2. 哈尔滨工程大学 机电工程学院,黑龙江 哈尔滨 150001; 3. 哈尔滨工程大学 自动化工程学院,黑龙江 哈尔滨 150001) 摘 要:针对水下无人潜航器(UUV)预测跟踪过程中传感器所采集数据的不准确问题,提出了一种利用小波隐马尔 可夫模型进行 UUV 预测跟踪数据孤立点检测的方法.利用改进递归小波变换,对原始数据进行重构,小波系数中孤 立点处的系数得到局部放大.小波系数的更新基于历史时刻的数据,因此,可以利用正常数据与孤立点的差异对数据 进行实时处理.利用隐马尔可夫模型定义异常值分布判定函数,并以其作为依据,检测特征明显异于正常数据的孤立 点.将准孤立点利用惰性算法进行重检测,提高孤立点检测的准确性.湖试数据验证了该方法能够有效地检测出 UUV 预测跟踪中的数据孤立点. 关键词:水下无人潜航器;预测跟踪;小波变换;隐马尔可夫;孤立点检测 中图分类号: TP18;TN96711 文献标志码:A 文章编号:1673⁃4785(2013)06⁃0551⁃07 中文引用格式:穆岩,侯恕萍,迟冬南. 基于小波 HMM 的 UUV 传感器数据孤立点检测[J]. 智能系统学报, 2013, 8(6): 551⁃557. 英文引用格式:MU Yan,HOU Shuping, CHI Dongnan. UUV sensor data outlier detection using wavelet HMM[J]. CAAI Transac⁃ tions on Intelligent Systems, 2013, 8(6): 551⁃557. UUV sensor data outlier detection on the basis of wavelet HMM MU Yan 1 , HOU Shuping 2 , CHI Dongnan 3 (1. Representative Department for Forming Complete Sets of Naval Ships in the Area of Shenyang, Shenyang 110031, China; 2. Col⁃ lege of Mechanical and Electrical Engineering, Harbin Engineering University, Harbin 150001, China; 3. College of Aotomation, Har⁃ bin Engineering University, Harbin 150001, China) Abstract:A method for outlier detection based on wavelet HMM (hidden Markov model) is proposed in this paper in order to deal with the inaccurate original data collected from sensors during UUV forecast tracing. The improved recursive wavelet transform (IRWT) is used to reconstruct the original data and locally amplify the wavelet coeffi⁃ cients of the outliers. The update of wavelet coefficients are based on the data at the historical moment, thus, data may be processed in real time by utilizing the difference between normal data and outliers. The judgment function on the distribution of abnormal values is defined by HMM. In addition, on the basis of this, the outliers with features obviously different from the normal data are detected. The quasi-outliers are redetected by using a lazy algorithm for improving the accuracy of the detection results. The data from the lake experiment verify that the method may effec⁃ tively detect the data outliers in UUV forecast tracing. Keywords: underwater unmanned vehicle; forecast tracing; wavelet transform; hidden Markov model; outlier de⁃ tection 收稿日期:2013⁃06⁃20. 网络出版日期:2013⁃10⁃12. 基金项目:国家自然科学基金资助项目(51109043). 通信作者:侯恕萍. E⁃mail:houshuping@ hrbeu.edu.cn. UUV(underwater unmanned vehicle)的预测跟踪 主要应用于其在未知环境中航行、对环境进行感知 并完成既定任务的过程中.在感知未知环境的过程 中,传感器所采集的数据成为 UUV 自主决策的惟一 依据.因此,原始数据的准确性直接影响着 UUV 的
向下翻页>>
©2008-现在 cucdc.com 高等教育资讯网 版权所有