Use of neural networks in the problems of operation and repair of rolling stock of electric transport

Authors

  • D. Zubenko O.M. Beketov National University of Urban Economy in Kharkiv
  • S. Zakurday O.M. Beketov National University of Urban Economy in Kharkiv
  • O. Donets O.M. Beketov National University of Urban Economy in Kharkiv

Keywords:

electric transport operation, multi-level learning, neural networks, deep learning, rolling stock repair.

Abstract

Deep neural networks have achieved great success in controlled learning problems, and MIL as a typical poorly controlled learning method is effective for many applications in computer vision, biometrics, natural language processing, etc. In this article, we review several neural networks with multiple instances ( MINN), which neural networks seek to solve MIL problems. MINNs perform MILs in the end, which take bags with different numbers of instances as input and directly output the tags of the bags. All parameters in MINN can be optimized by back propagation. In addition to revising old MINNs, we offer a new type of MINN for exploring bag representations, which differs from existing MINNs that focus on the evaluation of an instance label. In addition, recent tricks developed in deep learning have been studied in MINN; we find that deep supervision is effective for a better understanding of bag views. In experiments, the proposed MINNs achieve the most advanced or competitive performance on several MIL tests. Moreover, for testing and learning it is very fast, for example, it takes only 0.0.0 03 s to predict the bag and a few seconds to learn on the MIL datasets on a moderate processor.

Initially, several instances (MILs) were proposed to predict bounce activity [1]. Now it is widely applied to many domains and is an important problem in computer training. Many multimedia data have a multiplier (MI) structure; For example, a text article contains several paragraphs, the image can be divided into several local areas, and gene expression data contains several genes. MIL is useful for processing and understanding MI data.

Studying multiple instances is a type of weak controlled learning (WSL). Each sample is executed in the form of labeled data, which consist of a wide variety of instances associated with the functions of input. The purpose of MIL in the dual task is to prepare a classifier for prediction of test packet labels, based on the assumption that there is a positive packet and contains at least one positive instance, while the data is negative if it consists only of negative instances.

References

[1] T.G. Dietterich, R.H. Lathrop, T. Lozano-Pérez Solving the multiple instance problem with axis-parallel rectangles, Artif. Intell. 89 (1) (1997) 31–71.
[2] J. Amores Multiple instance classification: review, taxonomy and comparative study, Artif. Intell. 201 (2013) 81–105.
[3] G. Hinton, S. Osindero, Y.W. Teh A fast learning algorithm for deep belief nets, Neural Comput. 18 (7) (2006) 1527–1554.
[4] Y. LeCun, L. Bottou, Y. Bengio, P. Haffner Gradient-based learning applied to document recognition, Proc. IEEE 86 (11) (1998) 2278–2324.
[5] A. Krizhevsky, I. Sutskever, G.E. Hinton Imagenet classification with deep con- volutional neural networks, in: NIPS, 2012, pp. 1097–1105.
[6] R.J. Williams, D. Zipser A learning algorithm for continually running fully recurrent neural networks, Neural Comput. 1 (2) (1989) 270–280.
[7] S. Hochreiter, J. Schmidhuber Long short-term memory, Neural Comput. 9 (8) (1997) 1735–1780.
[8] J. Ramon, L. De Raedt Multi instance neural networks, in: Proceedings of the ICML-20 0 0 Workshop on Attribute-Value and Relational Learning, 20 0 0, pp. 53–60.
[9] Z.-H. Zhou, M.-L. Zhang Neural networks for multi-instance learning, in: Pro- ceedings of the International Conference on Intelligent Information Technology, Beijing, China, 2002, pp. 455–459.
[10] S. Andrews, I. Tsochantaridis, T. Hofmann Support vector machines for multiple-instance learning, in: NIPS, 2002, pp. 561–568 .
[11] N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, R. Salakhutdinov Dropout: a simple way to prevent neural networks from overfitting, JMLR 15 (1) (2014) 1929–1958.
[12] V. Nair, G. Hinton Rectified linear units improve restricted Boltzmann ma- chines, in: ICML, 2010, pp. 807–814.
[13] C.Y. Lee, S. Xie, P. Gallagher, Z. Zhang, Z. Tu Deeply-supervised nets, in: AIS- TATS, 2015, pp. 562–570.
[14] K. He, X. Zhang, S. Ren, J. Sun Deep residual learning for image recognition, arXiv:1512.03385 (2015).
[15] Mykhalkiv S., Ravlyuk V., Khodakivskyi A., Bereznyi V. Identification of axle-box bearing faults of freight cars based on minimum entropy deconvolution and squared envelope spectra // International Journal of Engineering & Technology. — 2018. Vol. 7(4.3). P. 167–173. https://doi.org/10.14419/ijet.v7i4.3.19729

Downloads

Published

2020-09-30

How to Cite

Zubenko, D., Zakurday, S., & Donets, O. (2020). Use of neural networks in the problems of operation and repair of rolling stock of electric transport. Lighting Engineering & Power Engineering, 2(58), 55–57. Retrieved from https://lepe.kname.edu.ua/index.php/lepe/article/view/442

Issue

Vol. 2 No. 58 (2020): Lighting Engineering & Power Engineering

Section

Articles

License

The authors that are published in this journal agree with the following terms:

  • The authors reserve the right of authorship of his work and pass to the journal the right of first publication of this work is licensed under a Creative Commons Attribution License, which allows others to freely distribute published work with reference to authors of original works and works first published in this journal.
  • The authors have the right to enter into a separate additional agreement for non-exclusive distribution of work in the form in which it was published in the magazine (for example, to place work in electronic storage agencies or publish as part of the monograph), providing the reference to the first publication in this journal.
  • Journal policy allows and encourages the placement by the authors on the Internet (eg, in storage facilities or personal websites) the manuscript of the works before the submission of the manuscript to the editor as well as during its editorial processing, as it contributes to productive scientific discussion and has a positive impact on efficiency and dynamics citing published work (see. The Effect of Open Access).