Evaluation of Neural Network Output Results Reliability in Pattern Recognition

  • Daniil V. MarshakovEmail author
  • Vasily V. Galushka
  • Vladimir A. Fathi
  • Denis V. Fathi
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 874)


Artificial neural networks (ANN) are well-known effective parallel systems which have successfully approved themselves in solving of complicated artificial intelligence problems. The practice of the widespread ANN application due to their high efficiency in solving non-formalized or hard-formalized problems associated with the need for ANN training on experimental material particularly in pattern recognition. In solving problems of pattern recognition the feedforward neural network is usually used due to the simplicity of algorithmic implementation, the availability of advanced training methods, the possibilities of multi-parallel computations. When neural network classifier implementing within decision support systems, it is necessary to assess the ANN results reliability based upon interpretation of the output signals to establish trust between users and the neural network algorithm. In this paper the ANN output results reliability evaluation method in terms of the degree of belonging of the recognized patterns to the originally specified classes is considered. The proposed method is based on the computation of Euclidean distance between the actual ANN output vector characterizing the class of the object recognition and a set of sample vectors defining a priori known classes at the training stage followed by its evaluation by the curve construction of the normal probability distribution law coinciding with the Gaussian function. A feature of this method is the construction of an individual probability distribution curve computed for each ANN output vector. An experimental research of the proposed method in MATLAB is presented on the example of solving the known Fisher’s Iris Database classification for input data without noise and with noise. The obtained results confirm the adequacy of the proposed method which can be used both in independent neural network pattern recognition systems and within decision support complexes.


Artificial neural network Pattern recognition Classification Reliability 


  1. 1.
    Khong, L.M.D., Gale, T.J., Jiang, D., Olivier, J.C., Ortiz-Catalan, M.: Multi-layer perceptron training algorithms for pattern recognition of myoelectric signals. In: Proceedings of 6th Biomedical Engineering International Conference (BMEiCON-2013), pp. 1–5. IEEE, Piscataway (2013)Google Scholar
  2. 2.
    Al-Fatlawi, A.H., Ling, S.H., Lam, H.K.: A comparison of neural classifiers for graffiti recognition. J. Intell. Learn. Syst. Appl. 6(2), 94–112 (2014)Google Scholar
  3. 3.
    Lipton, Z.C.: The mythos of model interpretability. In: Proceedings of the 2016 ICML Workshop on Human Interpretability in Machine Learning (WHI-2016), New York, NY (2016). arXiv:1606.03490
  4. 4.
    Kotenko, I.V., Shorov, A.V., Nesteruk, P.G.: Analysis of bio-inspired approaches for protection of computer systems and networks. SPIIRAS Proc. 3(18), 19–73 (2011). (in Russian)Google Scholar
  5. 5.
    Benitez, J.M., Castro, J.L., Requena, I.: Are artificial neural networks black boxes? IEEE Trans. Neural Netw. 8(5), 1156–1164 (1997)CrossRefGoogle Scholar
  6. 6.
    Chorowski, J., Zurada, J.M.: Extracting rules from neural networks as decision diagrams. IEEE Trans. Neural Netw. 22(12), 2435–2446 (2011)CrossRefGoogle Scholar
  7. 7.
    Marshakov, D.V.: About the method of probabilistic interpretation for the results of the artificial neural network. In: Proceedings of the VII International Workshop “Sistemnyy analiz, upravleniye i obrabotka informatsii”, pp. 102–106. Don State Technical University, Rostov-on-Don, Russian Federation (2016). (in Russian)Google Scholar
  8. 8.
    Kachaykin, E.I., Ivanov, A.I., Bezyaev, A.V., Perfilov, K.A.: Reliability estimation of the automated neural network expertise of authorship hand-written handwriting. Voprosy kiberbezopasnosti 2(10), 43–48 (2015). (in Russian)Google Scholar
  9. 9.
    Savchenko, A.V.: Statistical pattern recognition based on probabilistic neural network with homogeneity testing. Knowl. Acquis. Autom. Reason. 4, 45–56 (2013). (in Russian)Google Scholar
  10. 10.
    Chauhan, S., Goel, V., Dhingra, S.: Pattern recognition system using MLP neural networks. IOSR J. Eng. 2(5), 990–993 (2012)CrossRefGoogle Scholar
  11. 11.
    Sharma, L., Sharma, U.: Neural network based classifier (pattern recognition) for classification of iris data set. Int. J. Recent Dev. Eng. Technol. 3(2), 64–66 (2014)Google Scholar
  12. 12.
    Kohonen, T.: Self-Organizing Maps, 3rd edn. Springer, Heidelberg (2001)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Daniil V. Marshakov
    • 1
    Email author
  • Vasily V. Galushka
    • 1
  • Vladimir A. Fathi
    • 1
  • Denis V. Fathi
    • 1
  1. 1.Don State Technical UniversityRostov on DonRussian Federation

Personalised recommendations