Advertisement

Fuzzy Classification on the Base of Convolutional Neural Networks

  • A. PuchkovEmail author
  • M. Dli
  • M. Kireyenkova
Conference paper
  • 139 Downloads
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 902)

Abstract

The paper deals with the algorithm of object classification based on the method of fuzzy logic and the application of artificial convolutional neural networks. Every object can be characterized by a set of data presented in the numerical form and in the form of images (photographs in different parts of the light spectrum). In this case, one object can be matched with a few images associated with it; they can be received by different methods and from different sources. In the algorithm, this generalized totality of images is recognized by convolutional neural networks. A separate neural network is formed for every channel of data receiving. Then, the network outputs are combined for processing in the system of classification on the basis of fuzzy logic output. The normalized outputs of convolutional neural networks are used as values of a membership function to terms of outputs variables when a fuzzy classifier works. For the first adjustment of the convolution neural network hyperparameters, the gradient method is applied. The algorithm is realized in Python language with the use of Keras deep learning library and Tensor Flow library of parallel computation with CUDA technology from NVIDIA company. This paper presents the results of practical application of the developed neuro-fuzzy classifier to forecast the problem of working time losses.

Keywords

Fuzzy logic Classification Image recognition Convolutional neural networks 

References

  1. 1.
    Hkalilov, D.: Marketing in Social Networks, 2nd edn. Mann, Ivanov and Febber, Moscow (2014)Google Scholar
  2. 2.
    Zlobina, N., Zavrazhina, K.: Marketing in social networks: modern tendencies and outlook. Sci. Tech. Bull. 6(233), 166–172 (2015)Google Scholar
  3. 3.
    Kasim, A.A., Wardoyo, R., Harjoko, A.: Batik classification with artificial neural network based on texture-shape feature of main ornament. Int. J. Intell. Syst. Appl. (IJISA) 9(6), 55–65 (2017).  https://doi.org/10.5815/ijisa.2017.06.06CrossRefGoogle Scholar
  4. 4.
    Ostrovsky, A.: Fuzzy clastarization of electronic information resources of project repository at automatic designing. Dissertation, State Technical University in Ulyanovsk (2010)Google Scholar
  5. 5.
    Dli, M., Puchkov, A., Malevich, E.: The solving of inverse problems on the base of fuzzy inverse Kalman’s algorithm. Software products, systems and algorithms. Electron. J. 2 (2016)Google Scholar
  6. 6.
    Kosko, B.: Fuzzy systems as universal approximators. IEEE Trans. Comput. 43(11) (2004)Google Scholar
  7. 7.
    Boyarinov, Y., Stoyanov, O., Dli, M.: The application of neuro-fuzzy method of group argument account for building the models of social economic systems. Softw. Prod. Syst. 3, 7–11 (2006)Google Scholar
  8. 8.
    Puchkov, A., Dli, M.: The improvement of diagnostic system of a boiler unit on the base of neuro-fuzzy algorithms. Int. Sci. Technol. J. 7, 47–50 (2016)Google Scholar
  9. 9.
    Korchagin, V., Krossovsky, V.: Neuron networks classification in destribution of the repairing fund of units according to the test results. News State Univ. Tula. Tech. Sci. 5, 127–133 (2013)Google Scholar
  10. 10.
    Zhuravlyov, Y., Ryazanov, V., Senko, O.: Detection. Mathematical Methods, Software System. Practical Application. Phases, Moscow (2005)Google Scholar
  11. 11.
    Fedotova, N.: The Theory of Features of Images Detection on the Base of Stochastic Geometry and Functional Analysis. PHYSMATLIT, Moscow (2010)Google Scholar
  12. 12.
    Kumar, S., Tripathi, B.K.: On the root-power mean aggregation based neuron in quaternionic domain. Int. J. Intell. Syst. Appl. (IJISA) 10(7), 11–26 (2018).  https://doi.org/10.5815/ijisa.2018.07.02CrossRefGoogle Scholar
  13. 13.
    Nayak, S.C.: Development and performance evaluation of adaptive hybrid higher order neural networks for exchange rate prediction. Int. J. Intell. Syst. Appl. (IJISA) 9(8), 71–85 (2017).  https://doi.org/10.5815/ijisa.2017.08.08CrossRefGoogle Scholar
  14. 14.
    Hinton, G., Deng, L., Yu, D., Dahl, G., Mohamed, A., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T., Kingsbury, B.: Deep neural networks for acoustic modeling in speech recognition. IEEE Signal Process. Mag. 29(6), 82–97 (2012)CrossRefGoogle Scholar
  15. 15.
    LeCun, Y., Kavukcuoglu, K., Farabet, C.: Convolutional networks and applications in vision. In: Proceedings of 2010 IEEE International Symposium on Circuits and Systems (ISCAS), pp. 253–256. IEEE (2010)Google Scholar
  16. 16.
    Lee, H., Grosse, R., Ranganath, R., Ng, A.Y.: Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations. In: Proceedings of the 26th Annual International Conference on Machine Learning, pp. 609–616. ACM (2009)Google Scholar
  17. 17.
    Capsule networks from Hinton, images processing, machine learning. https://habr.com/company/recognitor/blog/343726/. Accessed 2018/05/05
  18. 18.
    Candrot, E., Sanders, J.: CUDA Technology on Examples. Introduction to Programming of Graphic Processes. DMK Press, Moscow (2016)Google Scholar
  19. 19.
    Oppenheim, A.V., Schafer, R.W.: From frequency to quefrency: a history of the cepstrum. IEEE Signal Process. Mag. 21(5), 95–106 (2004)CrossRefGoogle Scholar
  20. 20.
    Ostapets, A.: Decision rules for the sets of networks of probable classifiers while solving the problems of classifications with intersection classes. Mach. Learn. Data Anal. 2(3), 276–285 (2016)CrossRefGoogle Scholar
  21. 21.
    Kruglov, V., Dli, M., Golunov, R.: Fuzzy Logic and Artificial Neuron Networks. Physics and Mathematics Publ, Moscow (2001)Google Scholar
  22. 22.
    Zhang, M.L., Zhou, Z.H.: ML-KNN: a lazy learning approach to multi-label learning. Pattern Recogn. 40(7), 2038–2048 (2007)CrossRefGoogle Scholar
  23. 23.
    Kotomin, A.: Recognition of voice command with the use of convolutional neuron networks. In: Digest of Annual Youth Conference: Knowledge-Intensive Information Technologies, SIT-2012, pp. 17–28, Pereslavl-Zalesky (2012)Google Scholar
  24. 24.
    Smith, S.: Digital Signal Processing: Practical Handbook for Engineers and Scientists. Dodeka-XXI, Moscow (2008)Google Scholar
  25. 25.
    Ha, L.M.: Convolutional neuron network for solving the problem of classification. MFTI Works 8(3), 91–97, https://mipt.ru/upload/medialibrary/659/91_97.pdf. Accessed 2018/04/30
  26. 26.
    Geron, A.: The Applied Machine Learning with the Help of Scikit-Learn and Conceptions, Tools and Techniques for Intetellectual Systems Creation. Dialektika, Moscow (2018)Google Scholar
  27. 27.
    Izotov, P., Suhkonov, S., Golovashkin, D.: The technology of realization of neural networks algorithm in CUDA environment on the example of handwritten digit recognition. Comput. Opt. 34(2), 243–251 (2010)Google Scholar
  28. 28.
    Classifier evaluation (accuracy, completeness, F-measure). http://bazhenov.me/blog/2012/07/21/classification-performance-evaluation.html/. Accessed 2018/05/15

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.National Research University “Moscow Power Engineering Institute” (Branch) in SmolenskSmolenskRussia

Personalised recommendations