Efficient Signal Processing and Anomaly Detection in Wireless Sensor Networks

  • Markus Wälchli
  • Torsten Braun
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5484)


In this paper the node-level decision unit of a self-learning anomaly detection mechanism for office monitoring with wireless sensor nodes is presented. The node-level decision unit is based on Adaptive Resonance Theory (ART), which is a simple kind of neural networks. The Fuzzy ART neural network used in this work is an ART neural network that accepts analog inputs. A Fuzzy ART neural network represents an adaptive memory that can store a predefined number of prototypes. Any observed input is compared and classified in respect to a maximum number of M online learned prototypes. Considering M prototypes and an input vector size of N, the algorithmic complexity, both in time and memory, is in the order of O(MN). The presented Fuzzy ART neural network is used to process, classify and compress time series of event observations on sensor node level. The mechanism is lightweight and efficient. Based on simple computations, each node is able to report locally suspicious behavior. A system-wide decision is subsequently performed at a base station.


Sensor networks anomaly detection pattern recognition 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Li, D., Wong, K.D., Hu, Y.H., Sayeed, A.M.: Detection, classification and tracking of targets. IEEE Signal Processing Magazine 19(2), 17–29 (2002)CrossRefGoogle Scholar
  2. 2.
    Römer, K.: Discovery of frequent distributed event patterns in sensor networks. In: Verdone, R. (ed.) EWSN 2008. LNCS, vol. 4913, pp. 106–124. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  3. 3.
    Cai, J., Ee, D., Pham, B., Roe, P., Zhang, J.: Sensor network for the monitoring of ecosystem: Bird species recognition. In: Proc. of the 3rd International Conference on Intelligent Sensors, Sensor Networks and Information (ISSNIP 2007), Melbourne, Australia, pp. 293–298 (2007)Google Scholar
  4. 4.
    Wang, X.R., Lizier, J.T., Obst, O., Prokopenko, M., Wang, P.: Spatiotemporal anomaly detection in gas monitoring sensor networks. In: Verdone, R. (ed.) EWSN 2008. LNCS, vol. 4913, pp. 90–105. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  5. 5.
    Li, Y.Y., Parker, L.: Intruder detection using a wireless sensor network with an intelligent mobile robot response. In: Proc. of the IEEE Southeast Con. 2008, Huntsville, Alabama, USA, pp. 37–42 (2008)Google Scholar
  6. 6.
    Dasgupta, D., Forrest, S.: Novelty detection in time series data using ideas from immunology. In: Proc. of The Fifth International Conference on Intelligent Systems (IS 1996), Reno, Nevada, USA (1996)Google Scholar
  7. 7.
    Mazhar, N., Farooq, M.: BeeAIS: Artificial Immune System Security for Nature Inspired, MANET Routing Protocol, BeeAdHoc. In: de Castro, L.N., Von Zuben, F.J., Knidel, H. (eds.) ICARIS 2007. LNCS, vol. 4628, pp. 370–381. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  8. 8.
    Kulakov, A., Davcev, D.: Intelligent wireless sensor networks using fuzzyart neural-networks (iscc 2007). In: Proc. of the 12th IEEE Symposium on Computers and Communications, Aveiro, Portugal, pp. 569–574. IEEE, Los Alamitos (2007)Google Scholar
  9. 9.
    Carpenter, G., Grossberg, S.: Adaptive Resonance Theory. Bradford Books. MIT Press, Cambridge (2002)Google Scholar
  10. 10.
    Burwick, T., Joublin, F.: Optimal algorithmic complexity of fuzzy art. Neural Processing Letters 7(1), 37–41 (1998)CrossRefGoogle Scholar
  11. 11.
    Haar, A.: Zur theorie der orthogonalen funktionensysteme. Mathematische Annalen 69, 331–371 (1910)MathSciNetCrossRefMATHGoogle Scholar
  12. 12.
    Sentilla: Pervasive computing solutions (July 2008), http://www.sentilla.com/

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Markus Wälchli
    • 1
  • Torsten Braun
    • 1
  1. 1.Institute of Computer Science and Applied MathematicsUniversity of BernSwitzerland

Personalised recommendations