An Optimization Method of SNNs for Shortest Path Problem

  • Hong QuEmail author
  • Zhi Zeng
  • Changle Chen
  • Dongdong Wang
  • Nan Yao
Part of the Proceedings in Adaptation, Learning and Optimization book series (PALO, volume 1)


In this paper we propose a new optimization method of integrate-and-fire neural model for shortest path problem and compare it with Dijkstra algorithm. The proposed algorithm improves the speed of path planning by parallel property of spike spreading in the network and makes efficiency independent from the number of connections of the network which is only related to the length of the shortest path in the network with determined number of edges. Mathematical analysis and simulations demonstrate that planing shortest path by utilizing connections between transmission time in integrate-and-fire model and edge weights is feasible. The comparisons with Dijkstra algorithm manifest that the new algorithm does have superiority in some application scenarios.


Shortest path problem Spike spreading Integrate-and-fire model 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Bohte, S.M., Kok, J.N., La, P.H.: Error-backpropagation in temporally encoded networks of spiking neurons. Neurocomputing 48(1), 17–37 (2002)CrossRefzbMATHGoogle Scholar
  2. 2.
    Yan, G., Zhou, T., Hu, B., Fu, Z.Q., Wang, B.H.: Efficient routing on complex networks. Physical Review E 73(4), 046108 (2006)Google Scholar
  3. 3.
    Alazab, A., Venkatraman, S., Abawajy, J., Alazab, M.: An optimal transportation routing approach using GIS-based dynamic traffic flows. In: ICMTA 2010: Proceedings of the International Conference on Management Technology and Applications, pp. 172–178. Research Publishing Services (2010)Google Scholar
  4. 4.
    Xi, Y., Schwiebert, L., Shi, W.: Privacy preserving shortest path routing with an application to navigation. Pervasive and Mobile Computing (2013)Google Scholar
  5. 5.
    Kwon, S., Shroff, N.B.: Analysis of shortest path routing for large multi-hop wireless networks. IEEE/ACM Transactions on Networking (TON) 17(3), 857–869 (2009)CrossRefGoogle Scholar
  6. 6.
    Wang, X., Qu, H., Yi, Z.: A modified pulse coupled neural network for shortest-path problem. Neurocomputing 72(13), 3028–3033 (2009)CrossRefGoogle Scholar
  7. 7.
    Dijkstra, E.W.: A note on two problems in connexion with graphs. Numerische mathematik 1(1), 269–271 (1959)CrossRefzbMATHMathSciNetGoogle Scholar
  8. 8.
    Fuhao, Z., Jiping, L.: An algorithm of shortest path based on Dijkstra for huge data. In: Sixth International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2009, vol. 4, pp. 244–247. IEEE (August 2009)Google Scholar
  9. 9.
    Maass, W., Zador, A.M.: Dynamic stochastic synapses as computational units. Neural Computation 11(4), 903–917 (1999)CrossRefGoogle Scholar
  10. 10.
    Kasabov, N.: To spike or not to spike: A probabilistic spiking neuron model. Neural Networks 23(1), 16–19 (2010)CrossRefGoogle Scholar
  11. 11.
    Hu, J., et al.: A spike-timing-based integrated model for pattern recognition. Neural Computation 25(2), 450–472 (2013)CrossRefzbMATHMathSciNetGoogle Scholar
  12. 12.
    Kasabov, N., Feigin, V., Hou, Z.G., et al.: Evolving spiking neural networks for personalised modelling, classification and prediction of spatio-temporal patterns with a case study on stroke. Neurocomputing 134, 269–279 (2014)CrossRefGoogle Scholar
  13. 13.
    GMaass, W., Bishop, C.M. (eds.): Pulsed neural networks. MIT Press (2001)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Hong Qu
    • 1
    Email author
  • Zhi Zeng
    • 1
  • Changle Chen
    • 1
  • Dongdong Wang
    • 1
  • Nan Yao
    • 1
  1. 1.School of Computer Science and EngineeringUniversity of Electronic Science and Technology of ChinaChengduP.R. China

Personalised recommendations