Skip to main content
Top

Hint

Swipe to navigate through the chapters of this book

2020 | OriginalPaper | Chapter

Proactive Fiber Break Detection Based on Quaternion Time Series and Automatic Variable Selection from Relational Data

Authors : Vincent Lemaire, Fabien Boitier, Jelena Pesic, Alexis Bondu, Stéphane Ragot, Fabrice Clérot

Published in: Advanced Analytics and Learning on Temporal Data

Publisher: Springer International Publishing

share
SHARE

Abstract

We address the problem of event classification for proactive fiber break detection in high-speed optical communication systems. The proposed approach is based on monitoring the State of Polarization (SOP) via digital signal processing in a coherent receiver. We describe in details the design of a classifier providing interpretable decision rules and enabling low-complexity real-time detection embedded in network elements. The proposed method operates on SOP time series, which define trajectories on the 3D sphere; SOP time series are low-pass filtered (to reduce measurement noise), pre-rotated (to provide invariance to the starting point of trajectories) and converted to quaternion domain. Then quaternion sequences are recoded to relational data for automatic variable construction and selection. We show that a naïve Bayes classifier using a limited subset of variables can achieve an event classification accuracy of more than 99% for the tested conditions.
Footnotes
1
Invariance to the starting point is quite different from invariance to time scale that could be addressed using dynamic time warping (DTW). Here DTW would not solve the problem of invariance to the starting point.
 
2
Up to now this is an adhoc decision discussed in the last section of this paper.
 
Literature
1.
go back to reference Adewuyi, A.P., Wu, Z., Serker, N.K.: Assessment of vibration-based damage identification methods using displacement and distributed strain measurements. Struct. Health Monit. 8(6), 443–461 (2009) CrossRef Adewuyi, A.P., Wu, Z., Serker, N.K.: Assessment of vibration-based damage identification methods using displacement and distributed strain measurements. Struct. Health Monit. 8(6), 443–461 (2009) CrossRef
2.
go back to reference Bagnall, A., Lines, J., Hills, J., Bostrom, A.: Time-series classification with COTE: the collective of transformation-based ensembles. IEEE Trans. Knowl. Data Eng. 27(9), 2522–2535 (2015) CrossRef Bagnall, A., Lines, J., Hills, J., Bostrom, A.: Time-series classification with COTE: the collective of transformation-based ensembles. IEEE Trans. Knowl. Data Eng. 27(9), 2522–2535 (2015) CrossRef
3.
go back to reference Bagnall, A., Davis, L., Hills, J., Lines, J.: Transformation based ensembles for time series classification. In: Proceedings of the 12th SDM, April 2012 Bagnall, A., Davis, L., Hills, J., Lines, J.: Transformation based ensembles for time series classification. In: Proceedings of the 12th SDM, April 2012
4.
go back to reference Bagnall, A., Lines, J., Bostrom, A., Large, J., Keogh, E.: The great time series classification bake off: a review and experimental evaluation of recent algorithmic advances. Data Min. Knowl. Disc. 31(3), 606–660 (2017) MathSciNetCrossRef Bagnall, A., Lines, J., Bostrom, A., Large, J., Keogh, E.: The great time series classification bake off: a review and experimental evaluation of recent algorithmic advances. Data Min. Knowl. Disc. 31(3), 606–660 (2017) MathSciNetCrossRef
5.
go back to reference Boitier, F., et al.: Proactive fiber damage detection in real-time coherent receiver. In: Proceedings of the ECOC (2017) Boitier, F., et al.: Proactive fiber damage detection in real-time coherent receiver. In: Proceedings of the ECOC (2017)
6.
go back to reference Boitier, F., et al.: Seamless optical path restoration with just-in-time resource allocation leveraging machine learning. In: Proceeding of the ECOC, Demo Session (2018) Boitier, F., et al.: Seamless optical path restoration with just-in-time resource allocation leveraging machine learning. In: Proceeding of the ECOC, Demo Session (2018)
8.
go back to reference Boullé, M.: MODL: a Bayes optimal discretization method for continuous attributes. Mach. Learn. 65(1), 131–165 (2006) CrossRef Boullé, M.: MODL: a Bayes optimal discretization method for continuous attributes. Mach. Learn. 65(1), 131–165 (2006) CrossRef
9.
go back to reference Boullé, M.: Compression-based averaging of selective naive Bayes classifiers. J. Mach. Learn. Res. 8, 1659–1685 (2007) MathSciNetMATH Boullé, M.: Compression-based averaging of selective naive Bayes classifiers. J. Mach. Learn. Res. 8, 1659–1685 (2007) MathSciNetMATH
10.
go back to reference Boullé, M.: Tagging fireworkers activities from body sensors under distribution drift. In: Proceedings of Federated Conference on Computer Science and Information System, pp. 389–396 (2015) Boullé, M.: Tagging fireworkers activities from body sensors under distribution drift. In: Proceedings of Federated Conference on Computer Science and Information System, pp. 389–396 (2015)
11.
go back to reference Boullé, M.: Khiops: outil d’apprentissage supervisé automatique pour la fouille de grandes bases de données multi-tables. In: Extraction et Gestion des Connaissances, pp. 505–510 (2016). http://​www.​khiops.​com Boullé, M.: Khiops: outil d’apprentissage supervisé automatique pour la fouille de grandes bases de données multi-tables. In: Extraction et Gestion des Connaissances, pp. 505–510 (2016). http://​www.​khiops.​com
12.
go back to reference Boullé, M.: Predicting dangerous seismic events in coal mines under distribution drift. In: Ganzha, M., Maciaszek, L., Paprzycki, M. (eds.) Proceedings of Federated Conference on Computer Science and Information System, pp. 221–224 (2016) Boullé, M.: Predicting dangerous seismic events in coal mines under distribution drift. In: Ganzha, M., Maciaszek, L., Paprzycki, M. (eds.) Proceedings of Federated Conference on Computer Science and Information System, pp. 221–224 (2016)
13.
go back to reference Boullé, M., Charnay, C., Lachiche, N.: A scalable robust and automatic propositionalization approach for Bayesian classification of large mixed numerical and categorical data. Mach. Learn. 108, 229–266 (2018) MathSciNetCrossRef Boullé, M., Charnay, C., Lachiche, N.: A scalable robust and automatic propositionalization approach for Bayesian classification of large mixed numerical and categorical data. Mach. Learn. 108, 229–266 (2018) MathSciNetCrossRef
14.
16.
go back to reference Dutisseuil, E., et al.: 34 Gb/s PDM-QPSK coherent receiver using SiGe ADCs and a single FPGA for digital signal processing. In: Proceedings of the OFC, p. OM3H.7 (2012) Dutisseuil, E., et al.: 34 Gb/s PDM-QPSK coherent receiver using SiGe ADCs and a single FPGA for digital signal processing. In: Proceedings of the OFC, p. OM3H.7 (2012)
18.
go back to reference Dzeroski, S., Lavrac, N.: Inductive Logic Programming: Techniques and Applications. Prentice Hall, New York (1994) MATH Dzeroski, S., Lavrac, N.: Inductive Logic Programming: Techniques and Applications. Prentice Hall, New York (1994) MATH
19.
go back to reference Fawcett, T.: ROC graphs: notes and practical considerations for researchers. Technical Report HPL-2003-4, HP Laboratories (2004) Fawcett, T.: ROC graphs: notes and practical considerations for researchers. Technical Report HPL-2003-4, HP Laboratories (2004)
20.
go back to reference Gay, D., Guigourés, R., Boullé, M., Clérot, F.: Feature extraction over multiple representations for time series classification. In: International Workshop NFMCP held at ECML/PKDD, pp. 18–34 (2013) CrossRef Gay, D., Guigourés, R., Boullé, M., Clérot, F.: Feature extraction over multiple representations for time series classification. In: International Workshop NFMCP held at ECML/PKDD, pp. 18–34 (2013) CrossRef
21.
go back to reference Hamilton, W.R.: On a new species of imaginary quantities connected with a theory of quaternions. Proc. R. Ir. Acad. 2, 424–434 (1843) Hamilton, W.R.: On a new species of imaginary quantities connected with a theory of quaternions. Proc. R. Ir. Acad. 2, 424–434 (1843)
22.
go back to reference Hanson, A.J.: Visualizing Quaternions. Morgan Kaufmann Publishers, Burlington (2006) Hanson, A.J.: Visualizing Quaternions. Morgan Kaufmann Publishers, Burlington (2006)
23.
go back to reference Hauske, F.N., Kuschnerov, M., Spinnler, B., Lankl, B.: Optical performance monitoring in digital coherent receivers. J. Lightwave Technol. 27(16), 3623–3631 (2009) CrossRef Hauske, F.N., Kuschnerov, M., Spinnler, B., Lankl, B.: Optical performance monitoring in digital coherent receivers. J. Lightwave Technol. 27(16), 3623–3631 (2009) CrossRef
24.
go back to reference Hayford-Acquah, T., Asante, B.: Causes of fiber cut and the recommendation to solve the problem. IOSR J. Electron. Commun. Eng. 12, 46–64 (2017) CrossRef Hayford-Acquah, T., Asante, B.: Causes of fiber cut and the recommendation to solve the problem. IOSR J. Electron. Commun. Eng. 12, 46–64 (2017) CrossRef
25.
go back to reference Hills, J., Lines, J., Baranauskas, E., Mapp, J., Bagnall, A.: Classification of time series by shapelet transformation. Data Min. Knowl. Disc. 28(4), 851–881 (2014) MathSciNetCrossRef Hills, J., Lines, J., Baranauskas, E., Mapp, J., Bagnall, A.: Classification of time series by shapelet transformation. Data Min. Knowl. Disc. 28(4), 851–881 (2014) MathSciNetCrossRef
26.
go back to reference Kikuchi, K.: Fundamentals of coherent optical fiber communications. J. Lightwave Technol. 34(1), 157–179 (2016) CrossRef Kikuchi, K.: Fundamentals of coherent optical fiber communications. J. Lightwave Technol. 34(1), 157–179 (2016) CrossRef
30.
go back to reference Langley, P., Iba, W., Thompson, K.: An analysis of Bayesian classifiers. In: Proceedings of the Tenth National Conference on Artificial Intelligence (AAAI 1992), pp. 223–228 (1992) Langley, P., Iba, W., Thompson, K.: An analysis of Bayesian classifiers. In: Proceedings of the Tenth National Conference on Artificial Intelligence (AAAI 1992), pp. 223–228 (1992)
32.
go back to reference Layec, P., Dupas, A., Verchère, D., Sparks, K., Bigo, S.: Will metro networks be the playground for (true) elastic optical networks? J. Lightwave Technol. 35(6), 1260–1266 (2017) CrossRef Layec, P., Dupas, A., Verchère, D., Sparks, K., Bigo, S.: Will metro networks be the playground for (true) elastic optical networks? J. Lightwave Technol. 35(6), 1260–1266 (2017) CrossRef
34.
go back to reference Lines, J., Bagnall, A.: Time series classification with ensembles of elastic distance measures. Data Min. Knowl. Disc. 29(3), 565–592 (2015) MathSciNetCrossRef Lines, J., Bagnall, A.: Time series classification with ensembles of elastic distance measures. Data Min. Knowl. Disc. 29(3), 565–592 (2015) MathSciNetCrossRef
35.
go back to reference Liu, X., Jin, B., Bai, Q., Wang, D., Wang, Y.: Distributed fiber-optic sensors for vibration detection. Sensors 16, 1164 (2016) CrossRef Liu, X., Jin, B., Bai, Q., Wang, D., Wang, Y.: Distributed fiber-optic sensors for vibration detection. Sensors 16, 1164 (2016) CrossRef
37.
go back to reference Pesic, J., Le Rouzic, E., Brochier, N., Dupont, L.: Proactive restoration of optical links based on the classification of events. In: Proceedings of the ONDM, pp. 1–6 (2011) Pesic, J., Le Rouzic, E., Brochier, N., Dupont, L.: Proactive restoration of optical links based on the classification of events. In: Proceedings of the ONDM, pp. 1–6 (2011)
38.
go back to reference Pesic, J., Meuric, J., Le Rouzic, E., Dupont, L., Morvan, M.: Proactive failure detection for WDM carrying IP. In: Proceedings of IEEE INFOCOM, pp. 2971–2975 (2012) Pesic, J., Meuric, J., Le Rouzic, E., Dupont, L., Morvan, M.: Proactive failure detection for WDM carrying IP. In: Proceedings of IEEE INFOCOM, pp. 2971–2975 (2012)
39.
go back to reference Pesic, J.: Study of the mechanisms associated with the preventive network restoration in fiber optic core networks. Ph.D. thesis, Université de Bretagne-Sud (2012) Pesic, J.: Study of the mechanisms associated with the preventive network restoration in fiber optic core networks. Ph.D. thesis, Université de Bretagne-Sud (2012)
42.
go back to reference Schäfer, P., Leser, U.: Fast and accurate time series classification with WEASEL. In: Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, pp. 637–646 (2017) Schäfer, P., Leser, U.: Fast and accurate time series classification with WEASEL. In: Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, pp. 637–646 (2017)
43.
go back to reference Shoemake, K.: Animating rotation with quaternion curves. ACM SIGGRAPH Comput. Graph. 19(3), 245–254 (1985) CrossRef Shoemake, K.: Animating rotation with quaternion curves. ACM SIGGRAPH Comput. Graph. 19(3), 245–254 (1985) CrossRef
44.
go back to reference Simsarian, J.E., Winzer, P.J.: Shake before break: per-span fiber sensing with in-line polarization monitoring. In: Proceedings of OFC, p. M2E.6 (2017) Simsarian, J.E., Winzer, P.J.: Shake before break: per-span fiber sensing with in-line polarization monitoring. In: Proceedings of OFC, p. M2E.6 (2017)
46.
go back to reference Warren Liao, T.: Clustering of time series data - a survey. Pattern Recognit. 38(11), 1857–1874 (2005) CrossRef Warren Liao, T.: Clustering of time series data - a survey. Pattern Recognit. 38(11), 1857–1874 (2005) CrossRef
Metadata
Title
Proactive Fiber Break Detection Based on Quaternion Time Series and Automatic Variable Selection from Relational Data
Authors
Vincent Lemaire
Fabien Boitier
Jelena Pesic
Alexis Bondu
Stéphane Ragot
Fabrice Clérot
Copyright Year
2020
DOI
https://doi.org/10.1007/978-3-030-39098-3_3

Premium Partner