Contextual outlier detection for wireless sensor networks

  • Sourabh Bharti
  • K. K. Pattanaik
  • Anshul Pandey
Original Research


The quality of dataset measured and collected by wireless sensor networks (WSN) is often affected by noise and error that are inherent to resource-constrained sensor nodes. The affected data points deviating from the normal pattern are termed as outlier(s). However, detected outlier can be a result of the occurrence of an actual event. Outlier detection techniques developed for WSNs perform binary labelling of the data points and does not indicate the context stating whether the outlier is the result of an actual event or the noise/error. This paper proposes a contextual outlier detection framework specifically designed for WSNs named as in-network contextual outlier detection on edge (INCODE). The proposed framework also estimates the degree of outlierness associated with the detected outlier(s) to provide better insight into the measured data point. Algorithms used in INCODE are designed around the edge computing concept to minimize the communication and computational complexities to make it suitable for resource-constrained WSN. The results suggest an impressive 98% accuracy in identifying the context of the outlier(s). The low communication and computational complexity suggest INCODE’s suitability for resource constrained WSNs.


Wireless sensor networks Contextual outlier detection Edge computing 



We thank the editor and anonymous reviewers for their constructive comments and suggestions that helped improve the quality of this manuscript.


  1. Ayadi A, Ghorbel O, Obeida AM, Abid M (2017) Outlier detection approaches for wireless sensor networks: A survey. Comput Netw 129:319–333CrossRefGoogle Scholar
  2. Abid A, Masmoudi A, Kachouri A, Mahfoudhi A (2017) Outlier detection in wireless sensor networks based on OPTICS method for events and errors identification. Wirel Pers Commun 97(1):1503–1515CrossRefGoogle Scholar
  3. Boracchi G, Michaelides M, Roveri M (2018) A cognitive monitoring system for detecting and isolating contaminants and faults in intelligent buildings. IEEE Trans Syst Man Cybern Syst. 48(3):433–447CrossRefGoogle Scholar
  4. Bosman HH et al (2017) Spatial anomaly detection in sensor networks using neighbourhood information. Infor Fusion 33:41–56CrossRefGoogle Scholar
  5. Bhuiyan Z et al (2017) Dependable structural health monitoring using wireless sensor networks. IEEE Trans Dependable Secur Comput 14(4):363–376CrossRefGoogle Scholar
  6. Bharti S, Pattanaik KK (2016) Gravitational outlier detection for wireless sensor networks. Int J Commun Syst 29(13):2015–2027CrossRefGoogle Scholar
  7. Branch J, Giannella C, Szymanski B, Wolff R, Kargupta H (2013) In-network outlier detection in wireless sensor networks. Knowl Infor Syst 34(1):23–54CrossRefGoogle Scholar
  8. Bisdikian C, Kaplan LM, Srivastava MB (2013) On the quality and value of information in sensor networks. ACM Trans Sens Netw 9(4):48CrossRefGoogle Scholar
  9. Burdakis S, Deligiannakis A (2012) Detecting outlier(s) in sensor networks using the geometric approach. In: IEEE 28th international conference on data engineering, April 1-5 2012, pp 1108–1119Google Scholar
  10. Deligiannakis A et al. (2009) Another outlier bites the dust: computing meaningful aggregates in sensor networks. In: IEEE 25th international conference on data engineering, March 29-April 04 2009, pp 988–999Google Scholar
  11. Fong S et al (2018) Predicting unusual energy consumption events from smart home sensor network by data stream mining with misclassified recall. J Ambient Intell Human Comput 9(4):1197–1221CrossRefGoogle Scholar
  12. Flouri K, Lozano B, Tsakalides P (2008) Distributed consensus algorithms for SVM training in wireless sensor networks. In: 16th European conference on signal processing, August 25-29 2008Google Scholar
  13. Fawzy A, Mokhtar H, Hegazy O (2013) outlier(s) detection and classification in wireless sensor networks. Egypt Infor J 14:157–164CrossRefGoogle Scholar
  14. Giatrakos N et al (2018) Omnibus outlier detection in sensor networks using windowed locality sensitive hashing. Future Gener Computer Syst. Google Scholar
  15. Gaura EI et al (2014) Edge mining the internet of things. IEEE Sens J 13(10):3816–3825CrossRefGoogle Scholar
  16. Gil P, Santos A, Cardoso A (2014) Dealing with outlier(s) in wireless sensor networks: an oil refinery application. IEEE Trans Control Syst Technol 22(4):1589–1596CrossRefGoogle Scholar
  17. Giatrakos N et al (2013) In-network approximate computation of outlier(s) with quality guarantees. Inf Syst 38(8):1285–1308CrossRefGoogle Scholar
  18. Giatrakos N et al. (2010) Taco: tnable approximate computation of outlier(s) in wireless sensor networks. In: Proceedings of the 2010 ACM SIGMOD international conference on management of data, June 6-11 2010, pp 279-290Google Scholar
  19. Gao Q et al (2006) Radio range adjustment for energy efficient wireless sensor networks. Ad-hoc Netw 4(1):75–82CrossRefGoogle Scholar
  20. Intel Lab Data (2014). Accessed on 14 November 2014
  21. Liu N, Shin D, Hu X (2018) Contextual outlier interpretation. arXiv:1711.10589. Accessed on 16 April 2018
  22. LeBlanc HL, Zhang H, Sundaram S, Koutsoukos X (2012) Consensus of multi-agent networks in the presence of adversaries using only local information. Proceedings of the 1st international conference on High Confidence Networked Systems, April 17-18 2012, pp 1-10Google Scholar
  23. Lotfi A et al (2012) Smart homes for the elderly dementia sufferers: identification and prediction of abnormal behaviour. J Ambient Intell Human Comput 3(3):205–218CrossRefGoogle Scholar
  24. Lee S, Lee H (2010) Analysis of network lifetime in cluster-based sensor networks. IEEE Commun Lett 14:900–902CrossRefGoogle Scholar
  25. Liang J, Parthasarathy S (2006) Robust contextual outlier detection: where context meets sparsity. Accessed on 23 March 2018
  26. Morley T, Oram A (2016) The elements of anomaly detection in the internet of things. O’Reilly publishing. Accessed on 23 March 2018
  27. Malazil HT, Zamanifar K, Dulman S (2011) FED: fuzzy event detection model for wireless sensor networks. Int J Wirel Mob Netw 3(6):29–45CrossRefGoogle Scholar
  28. Nesa N, Ghosh T, Banerjee I (2018) Non-parametric sequence-based learning approach for outlier detection in IoT. Future Gener Comput Syst 82:412–421CrossRefGoogle Scholar
  29. O’Reilly C, Gluhak A, Imran MA, Rajasegarar S (2014) Anomaly detection in wireless sensor networks in a non-stationary environment. IEEE Commun Surv Tutor 16(3):1413–1432CrossRefGoogle Scholar
  30. Paola A, Gaglio S (2015) Adaptive distributed outlier detection for WSNs. IEEE Trans Cybern 45(5):888–899CrossRefGoogle Scholar
  31. Perera C, Zaslavsky A, Christen P, Georgakopoulos D (2014) Context aware computing for the internet of things : a survey. IEEE Commun Surv Tutor 16(1):414–454CrossRefGoogle Scholar
  32. Page L (2001) Method for node ranking in a linked database. US6285999 B1: 285-999Google Scholar
  33. Rajasegarar S, Leckie C, Palaniswami M, Bezdek J (2006) Distributed anomaly detection in wireless sensor networks. In: 10th IEEE Singapore international conference on communication systems, October 30-November 1 2006Google Scholar
  34. Rokach L, Maimon O (2005) Data mining and knowledge discovery handbook. Springer, Boston, MA. ISBN 978-0-387-09822-7, e-ISBN 978-0-387-09823-4zbMATHGoogle Scholar
  35. Radivojac P, Korad U, Sivalingam KM, Obradovic Z (2003) Learning from class-imbalanced data in wireless sensor networks. In: Proceedings of the IEEE 58th vehicular technology conference, October 6-9 2003, pp 3030-3034Google Scholar
  36. Shakya R, Singh Y, Verma N (2013) Generic correlation model for wireless sensor network applications. Wirel Sens Syst 3:266–276CrossRefGoogle Scholar
  37. Shahid N, Naqvi IH, Qaisar SB (2012) Real time energy efficient approach to outlier & event detection in wireless sensor networks. In: Proceedings of international conference on communication systems, November 21-23 2012, pp 162-166Google Scholar
  38. Sheng B, Li Q, Mao W, Jin W (2007) Outlier detection in sensor networks. In: Proceedings of the 8th ACM international symposium on mobile ad Hoc networking and computing, 9-14 September 2007, pp 219–228Google Scholar
  39. Shewhart WA (1939) Statistical Method from the viewpoint of quality control. The Graduate School, Department of Agriculture, Washington, D.C., 1939 editionGoogle Scholar
  40. Wong KBY, Zhang T, Aghajan H (2015) Extracting patterns of behaviour from a network of binary sensors. J Ambient Intell Human Comput. 6(1):83–105CrossRefGoogle Scholar
  41. Yuan F, Zhan Y, Wang Y (2014) Data density correlation degree clustering method for data aggregation in WSN. IEEE Sens J 14:1089–1098CrossRefGoogle Scholar
  42. Zang Y, Hamm N, Meratnia N, Stein A, Voort M, Havinga P (2012) Statistics-based outlier detection for wireless sensor networks. Int J Geographical Inf Sci 26(8):1373–1392CrossRefGoogle Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Department of Information TechnologyIndira Gandhi Delhi Technical University for WomenDelhiIndia
  2. 2.Wireless Sensor Networks LaboratoryABV-Indian Institute of Information Technology and ManagementGwaliorIndia
  3. 3.Department of Electronics and Communication EngineeringIndian Institute of Information TechnologyAllahabadIndia

Personalised recommendations