Advertisement

Robust Adaptive SOMs Challenges in a Varied Datasets Analytics

  • Alaa Ali HameedEmail author
  • Naim Ajlouni
  • Bekir Karlik
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 976)

Abstract

The advancement of available technology in use cause the production of huge amounts of data which need to be categorised within an acceptable time for end users and decision makers to be able to make use of the data contents. Present unsupervised algorithms are not capable to process huge amounts of generated data in a short time. This increases the challenges posed by storing, analyzing, recognizing patterns, reducing the dimensionality and processing Data. Self-Organizing Map (SOM) is a specialized clustering technique that has been used in a wide range of applications to solve different problems. Unfortunately, it suffers from slow convergence and high steady-state error. The work presented in this paper is based on the recently proposed modified SOM technique introducing a Robust Adaptive learning approach to the SOM (RA-SOM). RA-SOM helps to overcome many of the current drawbacks of the conventional SOM and is able to efficiently outperform the SOM in obtaining the winner neuron in a lower learning process time. To verify the improved performance of the RA-SOM, it was compared against the performance of other versions of the SOM algorithm, namely GF-SOM, PLSOM, and PLSOM2. The test results proved that the RA-SOM algorithm outperformed the conventional SOM and the other algorithms in terms of the convergence rate, Quantization Error (QE), Topology Error (TE) preserving map using datasets of different sizes. The results also showed that RA-SOM maintained an efficient performance on all the different types of datasets used, while the other algorithms a more inconsistent performance, which means that their performance could be data type-related.

Keywords

Robust Adaptive-SOM Clustering Topology 

References

  1. 1.
    Kohonen T (1990) The self-organizing maps. Proc IEEE 78(9):1464–1480CrossRefGoogle Scholar
  2. 2.
    Kohonen T, Oja E, Simula O, Visa A, Kangas J (1996) Engineering applications of the self-organizing map. Proc IEEE 84(9):1358–1384CrossRefGoogle Scholar
  3. 3.
    Shieh SL, Liao IE (2012) A new approach for data clustering and visualization using self-organizing maps. Expert Syst Appl 39:11924–11933CrossRefGoogle Scholar
  4. 4.
    Kohonen T (2001) Self-organizing maps. Springer, BerlinCrossRefGoogle Scholar
  5. 5.
    Vesanto J, Alhoniemi E (2002) Clustering of the self-organizing map. IEEE Trans Neural Netw 11(3):586–600CrossRefGoogle Scholar
  6. 6.
    Lapidot I, Guterman H, Cohen A (2002) Unsupervised speaker recognition based on competition between self-organizing maps. IEEE Trans Neural Netw 13(4):877–887CrossRefGoogle Scholar
  7. 7.
    Kohonen T (1989) Self-organization and associative memory process. Springer, BerlinCrossRefGoogle Scholar
  8. 8.
    Hoffmann M (2005) Numerical control of Kohonen neural network for scattered data approximation. Numer Algorithms 39(1):175–186MathSciNetCrossRefGoogle Scholar
  9. 9.
    Marini F, Zupan J, Magri AL (2005) Class-modeling using Kohonen artificial neural networks. Anal Chim Acta 544(1):306–314CrossRefGoogle Scholar
  10. 10.
    Astel A, Tsakovski S, Barbieri P, Simeonov V (2007) Comparison of self-organizing maps classification approach with cluster and principal components analysis for large environmental data sets. Water Res 41(19):4566–4578CrossRefGoogle Scholar
  11. 11.
    Appiah K, Hunter A, Dickinson P, Meng H (2012) Implementation and applications of tri-state self-organizing maps on FPGA. IEEE Trans Circuits Syst Video Technol 22(8):1150–1160CrossRefGoogle Scholar
  12. 12.
    Brugger D, Bogdan M, Rosenstiel W (2008) Automatic cluster detection in Kohonen’s SOM. IEEE Trans Neural Netw 19(3):442–459CrossRefGoogle Scholar
  13. 13.
    Chi SC, Yang CC (2008) A two-stage clustering method combining ant colony SOM and k-means. J Inf Sci Eng 24(5):1445–1460Google Scholar
  14. 14.
    Cottrell M, Gaubert P, Eloy C, Francois D, Hallaux G, Lacaille J, Verleysen M (2009) Fault prediction in aircraft engines using self-organizing maps. In: International workshop on self-organizing maps, vol 5629. Springer, Heidelberg, pp 37–44Google Scholar
  15. 15.
    Tasdemir K, Milenov P, Tapsall B (2011) Topology-based hierarchical clustering of self-organizing maps. IEEE Trans Neural Netw 22(3):474–485CrossRefGoogle Scholar
  16. 16.
    Wong MLD, Jack LB, Nandi AK (2006) Modified self-organising map for automated novelty detection applied to vibration signal monitoring. Mech Syst Signal Process 20(3):593–610CrossRefGoogle Scholar
  17. 17.
    Yang L, Ouyang Z, Shi Y (2012) A modified clustering method based on self-organizing maps and its applications. Procedia Comput Sci 9:1371–1379CrossRefGoogle Scholar
  18. 18.
    Yen GG, Wu Z (2008) Ranked centroid projection: a data visualization approach with self-organizing maps. IEEE Trans Neural Netw 19(2):245–259CrossRefGoogle Scholar
  19. 19.
    Bogdan M, Rosenstiel W (2001) Detection of cluster in self-organizing maps for controlling a prostheses using nerve signals. In: Proceedings of 9th European symposium on artificial neural networks. ESANN, pp 131–136Google Scholar
  20. 20.
    Berglund E, Sitte J (2006) The parameterless self-organizing map algorithm. IEEE Trans Neural Netw 17(2):305–316CrossRefGoogle Scholar
  21. 21.
    Berglund E (2010) Improved PLSOM algorithm. Appl Intell 32(1):122–130CrossRefGoogle Scholar
  22. 22.
    Hameed AA, Karlik B, Salman MS, Eleyan G (2019) Robust adaptive learning approach to self-organizing maps. Knowl-Based Syst 171:25–36CrossRefGoogle Scholar
  23. 23.
    Hameed AA, Karlik B, Salman MS (2016) Back-propagation algorithm with variable adaptive momentum. Knowl Based Syst 114:79–87CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Department of Mathematics and Computer ScienceIstanbul Aydin UniversityIstanbulTurkey
  2. 2.Department of Computer EngineeringIstanbul Aydin UniversityIstanbulTurkey
  3. 3.Neurosurgical Simulation Research and Training CentreMcGill UniversityMontrealCanada

Personalised recommendations