Skip to main content

Learning and Self-organization for Spatiotemporal Systems

Abstract

This article deals with the modeling and management of spatiotemporal systems using machine learning and self-organization algorithms. Two application examples are the localization of objects from radio measurements using spatiotemporal models learned from data, and the self-organizing management of wireless multi-hop sensor networks. For both examples we show how machine learning and self-organization significantly increases accuracy and efficiency.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4

References

  1. 1.

    Bahl P, Padmanabhan VN (2000) RADAR: an in-building RF-based user location and tracking system. In: Proc IEEE joint conf IEEE computer communications societies (INFOCOM), pp 775–784

    Google Scholar 

  2. 2.

    Bak P (1996) How nature works: the science of self-organized criticality. Copernicus Books, New York

    MATH  Google Scholar 

  3. 3.

    Bishop CM (1995) Neural networks for pattern recognition. Oxford University Press, London

    Google Scholar 

  4. 4.

    Bishop CM (2007) Pattern recognition and machine learning. Springer, Berlin

    Google Scholar 

  5. 5.

    Cheung KW, So HC, Ma W-K, Chan YT (2004) Least squares algorithms for time-of-arrival based mobile location. IEEE Trans Signal Process 53(4):1121–1128

    MathSciNet  Article  Google Scholar 

  6. 6.

    Durrant-Whyte H, Bailey T (2006) Simultaneous localization and mapping (slam). Part I. The essential algorithms. IEEE Robot Autom Mag 13:99–110

    Article  Google Scholar 

  7. 7.

    Gardner M (1970) Mathematical games: the fantastic combinations of John Conway’s new solitaire game “life”. Sci Am 223:120–123

    Article  Google Scholar 

  8. 8.

    Höppner F, Klawonn F, Kruse R, Runkler TA (1999) Fuzzy cluster analysis—methods for image recognition, classification, and data analysis. Wiley, New York

    Google Scholar 

  9. 9.

    Olfati-Saber R, Franco E, Frazzoli E, Shamma JS (2006) Belief consensus and distributed hypothesis testing in sensor networks. In: Networked embedded sensing and control: workshop (NESC’05), University of Notre Dame, USA, October 2005. Springer, New York. Proceedings

    Google Scholar 

  10. 10.

    Olfati-Saber R (2003) Consensus protocols for networks of dynamic agents. In: Proceeding of the 2003 American control conference, June 2003

    Google Scholar 

  11. 11.

    Parodi BB, Lenz H, Szabo A, Wang H, Horn J, Bamberger J, Obradovic D (2006) Initialization and online-learning of RSS maps for indoor/campus localization. In: Proceedings of IEEE/ION PLANS 2006

    Google Scholar 

  12. 12.

    Parodi BB, Szabo A, Horn J, Bamberger J (2008) Spll: simultaneous probabilistic localization and learning. In: Proceedings of IFAC world congress, vol 17, part 1

    Google Scholar 

  13. 13.

    Reynolds CW (1987) Flocks, herds and schools: A distributed behavioral model. Comput Graph 21:25–34

    Article  Google Scholar 

  14. 14.

    Roos T, Myllymäki P, Tirri H, Misikangas P, Sievänen J (2002) A probabilistic approach to WLAN user location estimation. Int J Wirel Inf Netw 9(3):155–164

    Article  Google Scholar 

  15. 15.

    Tahbaz Salehi A, Jadbabaie A (2008) A necessary and sufficient condition for consensus over random networks. IEEE Trans Autom Control 53(3):791–796

    MathSciNet  Article  Google Scholar 

  16. 16.

    Schölkopf B, Smola AJ (2002) Learning with kernels. MIT Press, Cambridge

    Google Scholar 

  17. 17.

    Seow CK, Tan SY (2008) Non-line-of-sight localization in multipath environments. IEEE Trans Mob Comput 7(5):647–660

    Article  Google Scholar 

  18. 18.

    Sutton RS, Barto AG (1998) Reinforcement learning: an introduction. MIT Press, Cambridge

    Google Scholar 

  19. 19.

    Szabo A, Weiherer T, Bamberger J (2011) Unsupervised learning of propagation time for indoor localization. In: VTC spring, pp. 1–5. IEEE

    Google Scholar 

  20. 20.

    Torrieri DJ (2007) Statistical theory of passive location systems. IEEE Trans Aerosp Electron Syst 20(2):183–198

    Article  Google Scholar 

  21. 21.

    Yang L, Ho KC (2009) An approximately efficient TDOA localization algorithm in closed-form for locating multiple disjoint sources with erroneous sensor positions. IEEE Trans Signal Process 57(12):4598–4615

    MathSciNet  Article  Google Scholar 

Download references

Acknowledgements

Part of this work was done in the project ZESAN on reliable and energy efficient wireless sensor and actuator networks and was partially funded by German Ministry of Education and Research (BMBF) grant 01BN0712A.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Thomas A. Runkler.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Runkler, T.A., Sollacher, R. & Szabo, A. Learning and Self-organization for Spatiotemporal Systems. Künstl Intell 26, 269–274 (2012). https://doi.org/10.1007/s13218-012-0171-x

Download citation

Keywords

  • Sensor Node
  • Time Slot
  • Receive Signal Strength
  • Consensus Protocol
  • Receive Signal Strength Measurement