Classification of Dangerous Situations for Small Sample Size Problem in Maintenance Decision Support Systems

Conference paper

DOI: 10.1007/978-3-319-52920-2_31

Part of the Communications in Computer and Information Science book series (CCIS, volume 661)
Cite this paper as:
Milov V.R., Savchenko A.V. (2017) Classification of Dangerous Situations for Small Sample Size Problem in Maintenance Decision Support Systems. In: Ignatov D. et al. (eds) Analysis of Images, Social Networks and Texts. AIST 2016. Communications in Computer and Information Science, vol 661. Springer, Cham

Abstract

In this paper we examine the task of maintenance decision support in classification of the dangerous situations discovered by the monitoring system. This task is reduced to the contextual multi-armed bandit problem. We highlight the small sample size problem appeared in this task due to the rather rare failures. The novel algorithm based on the nearest neighbor search is proposed. An experimental study is provided for several synthetic datasets with the situations described by either simple features or grayscale images. It is shown, that our algorithm outperforms the well-known contextual multi-armed methods with the Upper Confidence Bound and softmax stochastic search strategies.

Keywords

Maintenance decision support systems Classification Small sample size problem Nearest neighbor Contextual multi-armed bandit 

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.Nizhny Novgorod State Technical University n.a. R.E. AlekseevNizhny NovgorodRussia
  2. 2.Laboratory of Algorithms and Technologies for Network AnalysisNational Research University Higher School of EconomicsNizhny NovgorodRussia

Personalised recommendations