On the Effects of Input Unreliability on Classification Algorithms

  • Ardjan Zwartjes
  • Majid Bahrepour
  • Paul J. M. Havinga
  • Johann L. Hurink
  • Gerard J. M. Smit
Part of the Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering book series (LNICST, volume 104)


The abundance of data available on Wireless Sensor Networks makes online processing necessary. In industrial applications, for example, the correct operation of equipment can be the point of interest. The raw sampled data is of minor importance. Classification algorithms can be used to make state classifications based on the available data for devices such as industrial refrigerators.

The reliability through redundancy approach used in Wireless Sensor Networks complicates practical realizations of classification algorithms. Individual inputs are susceptible to multiple disturbances like hardware failure, communication failure and battery depletion. In order to demonstrate the effects of input failure on classification algorithms, we have compared three widely used algorithms in multiple error scenarios. The compared algorithms are Feed Forward Neural Networks, naive Bayes classifiers and decision trees.

Using a new experimental data-set, we show that the performance under error scenarios degrades less for the naive Bayes classifier than for the two other algorithms.


Sensor Node Wireless Sensor Network Feed Forward Neural Network Decision Tree Algorithm Receiver Operator Characteristic Analysis 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
  2. 2.
    Sun spot edemo technical datasheet. Technical datasheet, Sun Microsystems Inc., 16 Network Circle, Santa Clara, CA, USA (2010)Google Scholar
  3. 3.
    Akyildiz, I.F., Su, W., Sankarasubramamiam, Y., Cayirci, E.: A survey on sensor networks. IEEE Communications Magazine 40(8), 102–114 (2002)CrossRefGoogle Scholar
  4. 4.
    Alpaydin, E.: Introduction to machine learning. MIT Press (2004)Google Scholar
  5. 5.
    Bahrepour, M., Meratnia, N., Havinga, P.: Sensor fusion-based event detection in wireless sensor networks. Sensor Fusion, pp. 1–8 (2009)Google Scholar
  6. 6.
    Bahrepour, M., Meratnia, N., Havinga, P.J.: Automatic fire detection: A survey from wireless sensor network perspective. Technical report, Centre for Telematics and Information Technology (2007)Google Scholar
  7. 7.
    Bahrepour, M., Meratnia, N., Havinga, P.J.: Use of ai techniques for residential fire detection in wireless sensor networks. In: AIAI 2009 Workshop Proceedings (2009)Google Scholar
  8. 8.
    Bahrepour, M., Zhang, Y., Meratnia, N., Havinga, P.J.: Use of event detection approaches for outlier detection in wireless sensor networks. In: ISSNIP 2009 (2009)Google Scholar
  9. 9.
    Cayirci, E., Tezcan, H., Dogan, Y., Vedat, C.: Wireless sensor networks for underwater survelliance systems. Ad Hoc Networks 4, 431–446 (2006)CrossRefGoogle Scholar
  10. 10.
    Chohan, N.: Hardware assisted compression in wireless sensor networks (2007)Google Scholar
  11. 11.
    Evers, L., Bijl, M., Marin-Perianu, M., Marin-Perianu, R., Havinga, P.: Wireless sensor networks and beyond: A case study on transport and logistics (2005)Google Scholar
  12. 12.
    Evers, L., Havinga, P., Kuper, J.: Flexible sensor network reprogramming for logistics. In: IEEE International Conference on Mobile Adhoc and Sensor Systems, pp. 1–4 (2007)Google Scholar
  13. 13.
    Evers, L., Havinga, P.J., Kuper, J., Lijding, M.E., Meratnia, N.: Sensorscheme: Supply chain management automation using wireless sensor networks. In: IEEE Conference on Emerging Technologies and Factory Automation, pp. 448–455 (2007)Google Scholar
  14. 14.
    Fawcett, T.: An introduction to roc analysis. Pattern Recognition Letters 27, 861–874 (2006)CrossRefGoogle Scholar
  15. 15.
    Haykin, S.: Neural Networks: a comprehensive foundation, 2nd edn. Prentice Hall (1999)Google Scholar
  16. 16.
    Jin, G., Nittel, S.: Ned: An efficient noise-tolerant event and event boundary detection algorithm in wireless sensor networks. In: 7th International Conference on Mobile Data Management (2006)Google Scholar
  17. 17.
    Khelil, A., Shaikh, F.K., Ayari, B., Suri, N.: Mwm: A map-based world model for wireless sensor networks. Autonomics (2008)Google Scholar
  18. 18.
    Krishnamachari, B., Iyengar, S.: Distributed bayesian algorithms for fault-tolerant event region detection in wireless sensor networks. IEEE Transactions on Computers 53(3) (2004)Google Scholar
  19. 19.
    Li, D., Wong, K.D., Hu, Y.H., Sayeed, A.M.: Detection, classification and tracking of targets. IEEE Signal Processing Magazine 19, 17–29 (2002)Google Scholar
  20. 20.
    Lombriser, C., Roggen, D., Stäger, M., Tröster, G.: Titam: A tiny task network for dynamically reconfigurable heterogeneous sensor networks. Kommunikation in Verteilten Systemen 3, 127–138 (2006)Google Scholar
  21. 21.
    Luo, X., Dong, M., Huang, Y.: On distributed fault-tolerant detection in wireless sensor networks. IEEE Transactions on Computers 55(1), 58–70 (2006)CrossRefGoogle Scholar
  22. 22.
    Marin-Perianu, M., Havinga, P.: D-FLER – A Distributed Fuzzy Logic Engine for Rule-Based Wireless Sensor Networks. In: Ichikawa, H., Cho, W.-D., Satoh, I., Youn, H.Y. (eds.) UCS 2007. LNCS, vol. 4836, pp. 86–101. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  23. 23.
    Martincic, F., Schwiebert, L.: Distributed event detection in sensor networks. In: Proceedings of the International Conference on Systems and Networks Communications, p. 43 (2006)Google Scholar
  24. 24.
    Murthy, S.K.: Automatic construction of decision trees from data: A multi-disiplinary survey. Data Mining and Knnowledge Discovery 2, 345–389 (1998)CrossRefGoogle Scholar
  25. 25.
  26. 26.
    Russel, S., Norvig, P.: Artificial Intelligence A Modern Approach. Prentice Hall Series in Artificial Intelligence. Prentice Hall (1995)Google Scholar
  27. 27.
    Segal, M.L., Antonio, F.P., Elam, S., Erlenbach, J., de Paolo, K.R., Beach, S.: Method and apparatus for automatic event detection in a wireless communication system. US. Patent (2000)Google Scholar
  28. 28.
    Vu, C.T., Beyah, R.A., Li, Y.: Composite event detection in wireless sensor networks. In: Performance, Computing and Communications, pp. 264–271 (2007)Google Scholar
  29. 29.
    Werner-Allen, G., Lorincz, K., Welsh, M., Marcillo, O., Johnson, J., Ruiz, M., Lees, J.: Deploying a wireless sensor network on an active volcano. IEEE Internet Computing, 18–25 (2006)Google Scholar
  30. 30.
    Xue, W., Luo, Q., Chen, L., Liu, Y.: Contour map matching for event detection in sensor networks. In: Proceedings of the 2006 ACM SIGMOD International Conference on Management of Data (2006)Google Scholar
  31. 31.
    Zhang, H.: The optimality of naive bayes. In: 17th Florida Artificial Intelligence Research Society Conference (2004)Google Scholar
  32. 32.
    Zwartjes, A.: Fridge dataset,

Copyright information

© ICST Institute for Computer Science, Social Informatics and Telecommunications Engineering 2012

Authors and Affiliations

  • Ardjan Zwartjes
    • 1
  • Majid Bahrepour
    • 1
  • Paul J. M. Havinga
    • 1
  • Johann L. Hurink
    • 1
  • Gerard J. M. Smit
    • 1
  1. 1.University of TwenteEnschedeThe Netherlands

Personalised recommendations