SNR Bağımlı Veri Üretimi kullanılarak Fiber Optik Dağıtılmış Akustik Algılama için Derin Öğrenmeye Dayalı Tehdit Sınıflandırması

Year 2020, , 4 - 12, 21.12.2020

Emre Uzundurukan , Ali Kara

https://doi.org/10.5281/zenodo.3977620

Abstract

Bu çalışmada, SNR bağımlı veri tabanı oluşturmak ve fiber optik dağıtılmış akustik algılama (DAS) sistemler için sismik olayları sınıflandırmak yöntemi önerilmiştir. DAS sinyallerini almak için optik zaman alanı reflektometrisi (OTDR) kullanılmıştır. Önerilen veri oluşturma yöntemi, gerçek kanal gürültü özelliklerine dayanan farklı SNR değerlerine sahip sinyaller üretir. Bu şekilde, sınırlı veri kümesinden, çekiç vuruşu, kazma ile kazma ve kürekle kazma gibi üç farklı sismik olaydan oluşan büyük veri kümesi elde edilmiştir. Sınıflandırma bölümünde, üç farklı sismik olayı tanımlamak için iki farklı Derin Öğrenme algoritması (Evrişimsel Sinir Ağları ve tam bağlantılı sinir ağları) kullanılır. Sonuçlar, üç farklı SNR aralığı için dikkate değer tanımlama doğruluğunun elde edildiğini göstermektedir

Keywords

Dağıtık akustik algılama, Derin öğrenme sınıflandırması, Optik zaman-alanı yansıtma ölçüsü, Sismik olay sınıflandırması

Deep Learning Based Threat Classification for Fiber Optic Distributed Acoustic Sensing Using SNR Dependent Data Generation

Abstract

In this study, a novel method is proposed to generate SNR dependent database and classify seismic events for fiber optic distributed acoustic sensing (DAS) systems. Optical time-domain reflectometry (OTDR) is used to acquire DAS signals. Proposed data creation method generates signals with different SNR values which is based on real channel noise characteristics. By this way, from the limited dataset, huge dataset consists of three different seismic events such as hammer hit, digging with pickaxe and digging with shovel is generated. In the classification part, two different Deep Learning algorithm (Convolutional Neural Network and fully connected neural networks) are used to identify three different seismic events. Results show that remarkable identification accuracy for the three different SNR ranges is achieved.

Keywords

Deep Learning, Distributed acoustic sensing, Optical time-domain reflectometry, Seismic event classification

References

• D. Hill, “Distributed acoustic sensing (das): Theory and applications,” In Frontiers in Optics (pp. FTh4E-1). Optical Society of America, Oct. 2015.
• J. Tejedor et al., “Towards prevention of pipeline integrity threats using a smart fiber optic surveillance system,” Journal of Lightwave Technology, vol. 34, no. 19, pp. 4445–4453, 2016.
• J. C. Juarez and H. F. Taylor, “Field test of a distributed fiber-optic intrusion sensor system for long perimeters,” Applied Optics, vol. 46, no. 11, pp. 1968–1971, 2007.
• J. Tejedor et al., “A novel fiber optic based surveillance system for prevention of pipeline integrity threats,” Sensors, 17(2), 355, 2017.
• M. Aktas, et al., “Deep learning based multi-threat classification for phase-OTDR fiber optic distributed acoustic sensing applications,” In Fiber Optic Sensors and Applications XIV International Society for Optics and Photonics, Vol. 10208, p. 102080G Apr. 2017.
• J. Tejedor, et al.,” Machine learning methods for pipeline surveillance systems based on distributed acoustic sensing: A review,” Applied Sciences, 7(8), 841, 2017.
• Y. Wang, et al., “Real-Time Distributed Vibration Monitoring System Using $\Phi $-OTDR,” IEEE Sensors Journal, 17(5), 1333-1341. 2017.
• J. Tejedor, et al., “Real field deployment of a smart fiber-optic surveillance system for pipeline integrity threat detection: Architectural issues and blind field test results,” Journal of Lightwave Technology, 36(4), 1052-1062, 2018.
• G. Duckworth et al., “OptaSense® distributed acoustic and seismic sensing performance for multi-threat, multi-environment border monitoring,” In 2013 European Intelligence and Security Informatics Conference, pp. 273-276, Aug. 2013.
• A. Faria and N. Morgan, “Corrected tandem features for acoustic model training,” In Proceedings of the 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, Las Vegas, NV, USA, pp. 4737–4740, 31 March–4 April 2008.
• Q. Sun et al., “Recognition of a phase-sensitivity OTDR sensing system based on morphologic feature extraction,” Sensors, 15(7), 15179-15197, 2015.
• Y. Kim et al., “GMM-based Target Classification Scheme for a Node in Wireless Sensor Networks,” IEICE Trans. Commun, E91-B, 3544–3551, 2008.
• X. Qi et al., “An Approach of Passive Vehicle Type Recognition by Acoustic Signal Based on SVM,” In Proceedings of the International Conference on Genetic and Evolutionary Computing 2009, Guilin, China, 14–17, pp. 545–548, Oct. 2009.
• G. Jobin et al., “Vehicle Detection and Classification from Acoustic Signal Using ANN and KNN,” In Proceedings of the International Conference on Control Communication and Computing 2013, Thiruvananthapuram, India, pp. 436–439, 13–15 December 2013.
• E. Lewis et al., “Principal component analysis and artificial neural network based approach to analysing optical fibre sensors signals,” Sensors and Actuators A: Physical, 136(1), pp. 28-38, 2007.
• B.F. Necioglu et al., “Vehicle Acoustic Classification in Netted Sensor Systems Using Gaussian Mixture Models; Technical Report,” The MITRE Corporation: McLean, VA, USA, 2005.
• W. B. Lyons et al.,”Interrogation of multipoint optical fibre sensor signals based on artificial neural network patternrecognition techniques,” Sensors and Actuators A: Physical, 114(1), pp. 7-12. 2004.
• M. Barnoski et al., “Optical time domain reflectometer,” Applied optics, 16(9), pp. 2375-2379, 1977.
• I. Ölçer and A. Öncü, “Adaptive temporal matched filtering for noise suppression in fiber optic distributed acoustic sensing,” Sensors, 17(6), 1288, 2017.
• S. A. Abufana et al., “Variational Mode Decomposition-Based Threat Classification for Fiber Optic Distributed Acoustic Sensing,” IEEE Access, 2020
• A. V. Makarenko, “Deep learning algorithms for signal recognition in long perimeter monitoring distributed fiber optic sensors,” In 2016 IEEE 26th International Workshop on Machine Learning for Signal Processing (MLSP), pp. 1-6, Sept. 2016
• B. Wang et al., “Improved wavelet packet classification algorithm for vibrational intrusions in distributed fiber-optic monitoring systems,” Optical Engineering, 54(5), 055104, 2015.