光纤安防监测信号的特征提取与识别研究综述
|
摘要
光纤安防监测系统信号的特征提取与识别方法是当前的研究热点。光纤振动信号的随机性、非平稳性,以及各种信号的相似性,导致信号的识别容易产生误报现象。识别入侵事件类型的关键是信号的特征提取和高效的识别方法。对光纤振动信号的各种特征提取方法和识别方法进行分析和比较,把特征提取方法分为基于小波分解的特征提取法、基于其他分解模型的特征提取方法和基于波形统计参数的特征提取法;把对光纤振动信号的识别方法分为经验阈值识别方法、支持向量机识别方法和神经网络识别方法,最后对特征提取方法和识别方法进行总结和展望。
The feature extraction and recognition method of optical fiber security monitoring system is the current research hotspot. The randomness, nonstationarity and similarity of various incident signals of optical fiber vibration signals cause false identification. The key to identify the types of intrusion event is signal feature extraction and efficient recognition. The characteristics extraction methods and recognition methods of optical fiber vibration signals are analyzed and compared. Feature extraction methods are divided into feature extraction based on wavelet decomposition, feature extraction based on other decomposition models and feature extraction based on waveform statistical parameters. The identification methods of optical fiber vibration signals are divided into empirical threshold recognition, support vector machine recognition and neural network recognition. Finally, the feature extraction methods and recognition methods are summarized and prospected.
The feature extraction and recognition method of optical fiber security monitoring system is the current research hotspot. The randomness, nonstationarity and similarity of various incident signals of optical fiber vibration signals cause false identification. The key to identify the types of intrusion event is signal feature extraction and efficient recognition. The characteristics extraction methods and recognition methods of optical fiber vibration signals are analyzed and compared. Feature extraction methods are divided into feature extraction based on wavelet decomposition, feature extraction based on other decomposition models and feature extraction based on waveform statistical parameters. The identification methods of optical fiber vibration signals are divided into empirical threshold recognition, support vector machine recognition and neural network recognition. Finally, the feature extraction methods and recognition methods are summarized and prospected.
引文
[1]周正仙,肖石林,仝芳轩.基于M-Z干涉原理的定位式光纤振动传感器[J].光通信研究,2009,155(5):67-70.
[2]朱程辉,瞿永中,王建平.基于时频特征的光纤周界振动信号识别[J].光电工程,2014,41(1):16-22.
[3]周正仙,段绍辉,田杰,等.分布式光纤振动传感器及振动信号模式识别技术研究[J].光学仪器,2013,35(6):11-15.
[4]杨正理.采用小波变换的周界报警信号辨识[J].光电工程,2013,40(1):84-89.
[5] Hussain Z M,Boashash B.Adaptive instantaneous frequency estimation of multi-component FM signals using quadratic time frequency distributions[J].IEEE Transactions on Signal Processing,2002,50(8):1866-1876.
[6] Mahmoud S S,Hussain Z M,Cosic I,et al.Time-frequency analysis of normal and abnormal biological signals[J].Journal of Biomedical Signal Processing and Control,2006,1(1):33-43.
[7] De Vries J.A low cost fence impact classification system with neural networks[C]//IEEE 7th Africon Conference in Africa,2004:131-136.
[8] Cohen L.Time-frequency analysis[M].Englewood Cliffs,New Jersey:Prentice Hall PTR,1995.
[9]万遂人,彭丽成.安防系统光纤信号特征提取与分类算法研究[J].科技导报,2012,30(36):24-28.
[10]饶云江,吴敏,冉曾令,等.基于准分布式FBG传感器的光纤入侵报警系统[J].传感技术学报,2007,20(5):45-49.
[11] Jiang Lihui,Liu Xiangming,Zhang Feng.Multi-target recognition used in airpoty fiber fence warning system[C]//Proceeding of the Ninth International Conference on Machine Learning and Cybernetics,Qingdao,China,July11-14 2010:l126-l129.
[12]赵杰,丁吉,万遂人,等.全光纤安防系统模式识别混合编程的实现[J].东南大学学报(自然科学版),2011,41(1):41-46.
[13]罗光明,李枭,崔平贵,等.分布式光纤传感器的周界安防入侵信号识别[J].光电工程,2012,39(10):71-77.
[14]喻骁芒,罗光明,朱珍民,等.分布式光纤传感器周界安防入侵信号的多目标识别[J].光电工程,2014,41(1):36-41.
[15]杨正理,孙书芳.基于小波能量熵的光纤周界安防系统信号识别[J].光电子·激光,2016,27(12):1328-1333.
[16]李凯彦,赵兴群,孙小菡,等.一种用于光纤链路振动信号模式识别的规整化复合特征提取方法[J].物理学报,2015,64(5):243-249.
[17]朱程辉,王建平,李奇越,等.基于时频特征的光纤周界入侵振动信号识别与定位[J].中国激光,2016,43(6):301-309.
[18]陶沛琳,延凤平,刘鹏,等.基于Mach-Zehnder干涉仪的光纤人侵行为识别系统[J].量子电子学报,201l,28(2):183-190.
[19]王思远,娄淑琴,梁生,等.M-Z干涉仪型光纤分布式扰动传感系统模式识别方法[J].红外与激光工程,2014,43(8):2613-2618.
[20]邹柏贤,苗军,许少武,等.基于ELM算法的光纤振动信号识别研究[J].计算机工程与应用,2017,53(16):126-133.
[21]蒋立辉,盖井艳,王维波,等.基于总体平均经验模态分解的光纤周界预警系统模式识别方法[J].光学学报,2015,35(10):52-58.
[22]张燕君,刘文哲,付兴虎,等.基于EMD-AWPP和HOSASVM算法的分布式光纤振动入侵信号的特征提取与识别[J].光谱学与光谱分析,2016,36(2):577-582.
[23]毕福昆,周良欣,李雪莲.基于基音特征分析的光纤振动信号识别算法[J].北方工大学报,2017,29(2):39-44.
[24]盛智勇,张新燕,王彦平,等.光纤振动信号特征提取及线性分类方法[J].光电子·激光,2018,29(7):760-768.
[25] Wang Liang,Guo Yubin,Sun Tiegang,et al.Signal recognition of the optical fiber vibration sensor based on two-level feature extraction[C]//8th International Congress on Image and Signal Processing,2015:1484-1488.
[26] Seedahmed S M,Jim K.Elimination of rain-induced nuisance alarms in distributed fiber optic perimeter intrusion detection systems[J].Proceedings of SPIE,2009,7316:731604.
[27] Mahmoud S S,Katsifolis J.Robust event classification for a fiber optic perimeter intrusion detection system using level crossing features and artificial neural networks[J].Proceedings of SPIE,2010,7677:767708.
[28] Seedahmed S M,Jim K,Yuvaraja V.Real-time distributed fiber optic sensor for security systems:performance,event classification and nuisance mitigation[J].Photonie Sensors(S1674-9251),2012,2(3):225-236.
[2]朱程辉,瞿永中,王建平.基于时频特征的光纤周界振动信号识别[J].光电工程,2014,41(1):16-22.
[3]周正仙,段绍辉,田杰,等.分布式光纤振动传感器及振动信号模式识别技术研究[J].光学仪器,2013,35(6):11-15.
[4]杨正理.采用小波变换的周界报警信号辨识[J].光电工程,2013,40(1):84-89.
[5] Hussain Z M,Boashash B.Adaptive instantaneous frequency estimation of multi-component FM signals using quadratic time frequency distributions[J].IEEE Transactions on Signal Processing,2002,50(8):1866-1876.
[6] Mahmoud S S,Hussain Z M,Cosic I,et al.Time-frequency analysis of normal and abnormal biological signals[J].Journal of Biomedical Signal Processing and Control,2006,1(1):33-43.
[7] De Vries J.A low cost fence impact classification system with neural networks[C]//IEEE 7th Africon Conference in Africa,2004:131-136.
[8] Cohen L.Time-frequency analysis[M].Englewood Cliffs,New Jersey:Prentice Hall PTR,1995.
[9]万遂人,彭丽成.安防系统光纤信号特征提取与分类算法研究[J].科技导报,2012,30(36):24-28.
[10]饶云江,吴敏,冉曾令,等.基于准分布式FBG传感器的光纤入侵报警系统[J].传感技术学报,2007,20(5):45-49.
[11] Jiang Lihui,Liu Xiangming,Zhang Feng.Multi-target recognition used in airpoty fiber fence warning system[C]//Proceeding of the Ninth International Conference on Machine Learning and Cybernetics,Qingdao,China,July11-14 2010:l126-l129.
[12]赵杰,丁吉,万遂人,等.全光纤安防系统模式识别混合编程的实现[J].东南大学学报(自然科学版),2011,41(1):41-46.
[13]罗光明,李枭,崔平贵,等.分布式光纤传感器的周界安防入侵信号识别[J].光电工程,2012,39(10):71-77.
[14]喻骁芒,罗光明,朱珍民,等.分布式光纤传感器周界安防入侵信号的多目标识别[J].光电工程,2014,41(1):36-41.
[15]杨正理,孙书芳.基于小波能量熵的光纤周界安防系统信号识别[J].光电子·激光,2016,27(12):1328-1333.
[16]李凯彦,赵兴群,孙小菡,等.一种用于光纤链路振动信号模式识别的规整化复合特征提取方法[J].物理学报,2015,64(5):243-249.
[17]朱程辉,王建平,李奇越,等.基于时频特征的光纤周界入侵振动信号识别与定位[J].中国激光,2016,43(6):301-309.
[18]陶沛琳,延凤平,刘鹏,等.基于Mach-Zehnder干涉仪的光纤人侵行为识别系统[J].量子电子学报,201l,28(2):183-190.
[19]王思远,娄淑琴,梁生,等.M-Z干涉仪型光纤分布式扰动传感系统模式识别方法[J].红外与激光工程,2014,43(8):2613-2618.
[20]邹柏贤,苗军,许少武,等.基于ELM算法的光纤振动信号识别研究[J].计算机工程与应用,2017,53(16):126-133.
[21]蒋立辉,盖井艳,王维波,等.基于总体平均经验模态分解的光纤周界预警系统模式识别方法[J].光学学报,2015,35(10):52-58.
[22]张燕君,刘文哲,付兴虎,等.基于EMD-AWPP和HOSASVM算法的分布式光纤振动入侵信号的特征提取与识别[J].光谱学与光谱分析,2016,36(2):577-582.
[23]毕福昆,周良欣,李雪莲.基于基音特征分析的光纤振动信号识别算法[J].北方工大学报,2017,29(2):39-44.
[24]盛智勇,张新燕,王彦平,等.光纤振动信号特征提取及线性分类方法[J].光电子·激光,2018,29(7):760-768.
[25] Wang Liang,Guo Yubin,Sun Tiegang,et al.Signal recognition of the optical fiber vibration sensor based on two-level feature extraction[C]//8th International Congress on Image and Signal Processing,2015:1484-1488.
[26] Seedahmed S M,Jim K.Elimination of rain-induced nuisance alarms in distributed fiber optic perimeter intrusion detection systems[J].Proceedings of SPIE,2009,7316:731604.
[27] Mahmoud S S,Katsifolis J.Robust event classification for a fiber optic perimeter intrusion detection system using level crossing features and artificial neural networks[J].Proceedings of SPIE,2010,7677:767708.
[28] Seedahmed S M,Jim K,Yuvaraja V.Real-time distributed fiber optic sensor for security systems:performance,event classification and nuisance mitigation[J].Photonie Sensors(S1674-9251),2012,2(3):225-236.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |