基于时/频域综合特征提取的分布式光纤入侵监测系统事件识别方法
|
摘要
针对分布式光纤入侵监测系统在室外复杂环境下误报率过高的问题,提出了一种基于时/频域综合特征提取的入侵事件识别方法。使用自适应幅值门限信号切分算法找出有效振动信号片段,在此基础上提取平均片段间隔特征。选取最大能量片段作为主要研究对象,提取片段长度和峰均比特征,并对其进行小波包分解,生成频域能量分布特征,组成时/频域复合特征向量,使用高性能的支持向量机多分类算法进行模式识别。实验结果表明:该方法对行人脚踩、自行车轧过、拍击围栏和剪切光缆这4种典型入侵事件的平均识别正确率达到了98.33%,相比于仅提取时域或频域特征方法的识别正确率均有显著提高。该方法对光路光功率变化不敏感,能有效提升系统的实用性。
To reduce the high false alarm rate of the distributed fiber intrusion monitoring system in outdoor complex environment, this study proposes and demonstrates an intrusion event discrimination method based on integrated time/frequency domain feature extraction. First, a vibration fragment segmentation algorithm based on a self-adaptive amplitude threshold is developed to distinguish the vibrating part. On this basis, the average fragment interval feature is extracted. Next, the vibration fragment with the maximum energy is chosen as the research target, and the length and peak-to-average ratio are extracted in the time domain, whose energy distribution in the frequency domain is calculated according to wavelet packet decomposition and an integrated time/frequency domain feature vector is formed. Finally, one-versus-one support vector machine is used to classify four common intrusion events: footsteps of a passerby, bicycle rolling, knocking on the fence, and cutting of an optical cable. The experimental results show that the proposed method recognizes the abovementioned four common intrusion events with an average accuracy of 98.33%, which is much more accurate than the methods that only extract the time or frequency domain features. Moreover, the proposed method is immune to the optical power variation in light path. Thus, the proposed method is helpful to improve the utility of the system.
To reduce the high false alarm rate of the distributed fiber intrusion monitoring system in outdoor complex environment, this study proposes and demonstrates an intrusion event discrimination method based on integrated time/frequency domain feature extraction. First, a vibration fragment segmentation algorithm based on a self-adaptive amplitude threshold is developed to distinguish the vibrating part. On this basis, the average fragment interval feature is extracted. Next, the vibration fragment with the maximum energy is chosen as the research target, and the length and peak-to-average ratio are extracted in the time domain, whose energy distribution in the frequency domain is calculated according to wavelet packet decomposition and an integrated time/frequency domain feature vector is formed. Finally, one-versus-one support vector machine is used to classify four common intrusion events: footsteps of a passerby, bicycle rolling, knocking on the fence, and cutting of an optical cable. The experimental results show that the proposed method recognizes the abovementioned four common intrusion events with an average accuracy of 98.33%, which is much more accurate than the methods that only extract the time or frequency domain features. Moreover, the proposed method is immune to the optical power variation in light path. Thus, the proposed method is helpful to improve the utility of the system.
引文
[1] Liu D M,Sun Q Z,Lu P,et al.Research progress in the key device and technology for fiber optic sensor network[J].Photonic Sensors,2016,6(1):1-25.
[2] Allwood G,Wild G,Hinckley S.Optical fiber sensors in physical intrusion detection systems:a review[J].IEEE Sensors Journal,2016,16(14):5497-5509.
[3] Huang S C,Lin W W,Tsai M T,et al.Fiber optic in-line distributed sensor for detection and localization of the pipeline leaks[J].Sensors and Actuators A:Physical,2007,135(2):570-579.
[4] Lopez-Higuera J M,Rodriguez Cobo L,Quintela Incera A,et al.Fiber optic sensors in structural health monitoring[J].Journal of Lightwave Technology,2011,29(4):587-608.
[5] Liao Y B,Yuan L B,Tian Q.The 40 years of optical fiber sensors in China[J].Acta Optica Sinica,2018,38(3):0328001.廖延彪,苑立波,田芊.中国光纤传感40年[J].光学学报,2018,38(3):0328001.
[6] Li P C,Liu K,Jiang J F,et al.Research on polarization control of distributed optical fiber sensing system based on FPGA[J].Chinese Journal of Lasers,2018,45(5):0510002.李鹏程,刘琨,江俊峰,等.基于FPGA的分布式光纤传感系统偏振控制研究[J].中国激光,2018,45(5):0510002.
[7] Ghafoori-Shiraz H,Okoshi T.Fault location in optical fibers using optical frequency domain reflectometry[J].Journal of Lightwave Technology,1986,4(3):316-322.
[8] Huang X D,Wang Y D,Liu K,et al.Event discrimination of fiber disturbance based on filter bank in DMZI sensing system[J].IEEE Photonics Journal,2016,8(3):1-14.
[9] Liu K,Tian M,Liu T G,et al.A high-efficiency multiple events discrimination method in optical fiber perimeter security system[J].Journal of Lightwave Technology,2015,33(23):4885-4890.
[10] Jiang L H,Gai J Y,Wang W B,et al.Ensemble empirical mode decomposition based event classification method for the fiber-optic intrusion monitoring system[J].Acta Optica Sinica,2015,35(10):1006002.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):1006002.
[11] Jiang L H,Liu X M,Yang R Y.Application of the HHT method to the airport fiber fence warning[C]//2011 International Conference on Electronics,Communications and Control (ICECC),September 9-11,2011,Ningbo,China.New York:IEEE,2011:1337-1340.
[12] Mahmoud S S,Visagathilagar Y,Katsifolis J.Real-time distributed fiber optic sensor for security systems:performance,event classification and nuisance mitigation[J].Photonic Sensors,2012,2(3):225-236.
[13] Li K Y,Zhao X Q,Sun X H,et al.A regular composite feature extraction method for vibration signal pattern recognition in optical fiber link system[J].Acta Physica Sinica,2015,64(5):054304.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):054304.
[14] Huang X D,Zhang H J,Liu K,et al.High-efficiency intrusion recognition by using synthesized features in optical fiber perimeter security system[J].Acta Physica Sinica,2017,66(12):124206.黄翔东,张皓杰,刘琨,等.基于综合特征的光纤周界安防系统高效入侵事件识别[J].物理学报,2017,66(12):124206.
[15] Wang H,Sun Q Z,Li X L,et al.Improved location algorithm for multiple intrusions in distributed Sagnac fiber sensing system[J].Optics Express,2014,22(7):7587-7597.
[16] Donoho D L.De-noising by soft-thresholding[J].IEEE Transactions on Information Theory,1995,41(3):613-627.
[17] Jansen M.Noise reduction by wavelet thresholding[M].New York:Springer-Verlag,2001:35-39.
[18] Hu G S.Modern digital signal processing tutorial[M].2nd ed.Beijing:Tsinghua University Press,2015:381-388.胡广书.现代数字信号处理教程[M].2版.北京:清华大学出版社,2015:381-388.
[19] Han L H,Wang B,Duan S F.Development of voice activity detection technology[J].Application Research of Computers,2010,27(4):1220-1226.韩立华,王博,段淑凤.语音端点检测技术研究进展[J].计算机应用研究,2010,27(4):1220-1226.
[20] Tanyer S G,Ozer H.Voice activity detection in nonstationary noise[J].IEEE Transactions on Speech and Audio Processing,2000,8(4):478-482.
[21] Jain A K,Duin R P W,Mao J C.Statistical pattern recognition:a review[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(1):4-37.
[22] Liu L,Sun W,Zhou Y,et al.Security event classification method for fiber-optic perimeter security system based on optimized incremental support vector machine[M]∥Li S,Liu C,Wang Y.Communications in Computer and Information Science.Berlin,Heidelberg:Springer,2014:595-603.
[23] Wang L K,Tan D J,Cai Y J,et al.Study on method of recognizing characteristics of pipeline leakage acoustic signals[C]//Pipeline Division.2006 International Pipeline Conference,September 25-29,2006,Calgary,Alberta,Canada.New York:ASME,2006:751-755.
[24] Sun J D,Jin S J.Feature extraction method based on wavelet packet energy and high-order spectrum[J].Journal of Tianjin University,2010,43(6):562-566.孙洁娣,靳世久.基于小波包能量及高阶谱的特征提取方法[J].天津大学学报,2010,43(6):562-566.
[25] Haykin S.Neural networks and learning machines[M].Shen F R,Xu Y,Zheng J,et al,Transl.3rd ed.Beijing:China Machine Press,2011:144-193.Simon Haykin.神经网络与机器学习[M].申富饶,徐烨,郑俊,等,译.3版.北京:机械工业出版社,2011:144-193.
[26] Hsu C W,Lin C J.A comparison of methods for multiclass support vector machines[J].IEEE Transactions on Neural Networks,2002,13(2):415-425.
[27] Lingras P,Butz C.Rough set based 1-v-1 and 1-v-r approaches to support vector machine multi-classification[J].Information Sciences,2007,177(18):3782-3798.
[28] Li Y C,Xue Q,Fu X J.Analysis on features of stealing oil signal of pipeline with wavelet transform[J].Journal of Wuhan University of Technology,2010,32(6):76-79,94.李迎春,薛琴,付兴建.管道盗警信号特征提取的小波分析[J].武汉理工大学学报,2010,32(6):76-79,94.
[2] Allwood G,Wild G,Hinckley S.Optical fiber sensors in physical intrusion detection systems:a review[J].IEEE Sensors Journal,2016,16(14):5497-5509.
[3] Huang S C,Lin W W,Tsai M T,et al.Fiber optic in-line distributed sensor for detection and localization of the pipeline leaks[J].Sensors and Actuators A:Physical,2007,135(2):570-579.
[4] Lopez-Higuera J M,Rodriguez Cobo L,Quintela Incera A,et al.Fiber optic sensors in structural health monitoring[J].Journal of Lightwave Technology,2011,29(4):587-608.
[5] Liao Y B,Yuan L B,Tian Q.The 40 years of optical fiber sensors in China[J].Acta Optica Sinica,2018,38(3):0328001.廖延彪,苑立波,田芊.中国光纤传感40年[J].光学学报,2018,38(3):0328001.
[6] Li P C,Liu K,Jiang J F,et al.Research on polarization control of distributed optical fiber sensing system based on FPGA[J].Chinese Journal of Lasers,2018,45(5):0510002.李鹏程,刘琨,江俊峰,等.基于FPGA的分布式光纤传感系统偏振控制研究[J].中国激光,2018,45(5):0510002.
[7] Ghafoori-Shiraz H,Okoshi T.Fault location in optical fibers using optical frequency domain reflectometry[J].Journal of Lightwave Technology,1986,4(3):316-322.
[8] Huang X D,Wang Y D,Liu K,et al.Event discrimination of fiber disturbance based on filter bank in DMZI sensing system[J].IEEE Photonics Journal,2016,8(3):1-14.
[9] Liu K,Tian M,Liu T G,et al.A high-efficiency multiple events discrimination method in optical fiber perimeter security system[J].Journal of Lightwave Technology,2015,33(23):4885-4890.
[10] Jiang L H,Gai J Y,Wang W B,et al.Ensemble empirical mode decomposition based event classification method for the fiber-optic intrusion monitoring system[J].Acta Optica Sinica,2015,35(10):1006002.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):1006002.
[11] Jiang L H,Liu X M,Yang R Y.Application of the HHT method to the airport fiber fence warning[C]//2011 International Conference on Electronics,Communications and Control (ICECC),September 9-11,2011,Ningbo,China.New York:IEEE,2011:1337-1340.
[12] Mahmoud S S,Visagathilagar Y,Katsifolis J.Real-time distributed fiber optic sensor for security systems:performance,event classification and nuisance mitigation[J].Photonic Sensors,2012,2(3):225-236.
[13] Li K Y,Zhao X Q,Sun X H,et al.A regular composite feature extraction method for vibration signal pattern recognition in optical fiber link system[J].Acta Physica Sinica,2015,64(5):054304.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):054304.
[14] Huang X D,Zhang H J,Liu K,et al.High-efficiency intrusion recognition by using synthesized features in optical fiber perimeter security system[J].Acta Physica Sinica,2017,66(12):124206.黄翔东,张皓杰,刘琨,等.基于综合特征的光纤周界安防系统高效入侵事件识别[J].物理学报,2017,66(12):124206.
[15] Wang H,Sun Q Z,Li X L,et al.Improved location algorithm for multiple intrusions in distributed Sagnac fiber sensing system[J].Optics Express,2014,22(7):7587-7597.
[16] Donoho D L.De-noising by soft-thresholding[J].IEEE Transactions on Information Theory,1995,41(3):613-627.
[17] Jansen M.Noise reduction by wavelet thresholding[M].New York:Springer-Verlag,2001:35-39.
[18] Hu G S.Modern digital signal processing tutorial[M].2nd ed.Beijing:Tsinghua University Press,2015:381-388.胡广书.现代数字信号处理教程[M].2版.北京:清华大学出版社,2015:381-388.
[19] Han L H,Wang B,Duan S F.Development of voice activity detection technology[J].Application Research of Computers,2010,27(4):1220-1226.韩立华,王博,段淑凤.语音端点检测技术研究进展[J].计算机应用研究,2010,27(4):1220-1226.
[20] Tanyer S G,Ozer H.Voice activity detection in nonstationary noise[J].IEEE Transactions on Speech and Audio Processing,2000,8(4):478-482.
[21] Jain A K,Duin R P W,Mao J C.Statistical pattern recognition:a review[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(1):4-37.
[22] Liu L,Sun W,Zhou Y,et al.Security event classification method for fiber-optic perimeter security system based on optimized incremental support vector machine[M]∥Li S,Liu C,Wang Y.Communications in Computer and Information Science.Berlin,Heidelberg:Springer,2014:595-603.
[23] Wang L K,Tan D J,Cai Y J,et al.Study on method of recognizing characteristics of pipeline leakage acoustic signals[C]//Pipeline Division.2006 International Pipeline Conference,September 25-29,2006,Calgary,Alberta,Canada.New York:ASME,2006:751-755.
[24] Sun J D,Jin S J.Feature extraction method based on wavelet packet energy and high-order spectrum[J].Journal of Tianjin University,2010,43(6):562-566.孙洁娣,靳世久.基于小波包能量及高阶谱的特征提取方法[J].天津大学学报,2010,43(6):562-566.
[25] Haykin S.Neural networks and learning machines[M].Shen F R,Xu Y,Zheng J,et al,Transl.3rd ed.Beijing:China Machine Press,2011:144-193.Simon Haykin.神经网络与机器学习[M].申富饶,徐烨,郑俊,等,译.3版.北京:机械工业出版社,2011:144-193.
[26] Hsu C W,Lin C J.A comparison of methods for multiclass support vector machines[J].IEEE Transactions on Neural Networks,2002,13(2):415-425.
[27] Lingras P,Butz C.Rough set based 1-v-1 and 1-v-r approaches to support vector machine multi-classification[J].Information Sciences,2007,177(18):3782-3798.
[28] Li Y C,Xue Q,Fu X J.Analysis on features of stealing oil signal of pipeline with wavelet transform[J].Journal of Wuhan University of Technology,2010,32(6):76-79,94.李迎春,薛琴,付兴建.管道盗警信号特征提取的小波分析[J].武汉理工大学学报,2010,32(6):76-79,94.