Deep Learning Inspired Prognostics Scheme for Applications Generating Big Data
Abstract
In this paper, the relevance of deep neural network (DNN) is studied in big data scenarios, specifically for prognostics applications. It is observed that fault predictions can be performed more efficiently when DNN is used with a pre-processing step. A novel hierarchical dimension reduction (HDR) approach is therefore proposed as a pre-processing step to DNN. This two-step approach is shown to be effective in extracting value from complex and uncertain big data. It is shown that use of HDR prior to DNN improves convergence and allows for the possibility of reduction in model size without any drop in accuracy. A comprehensive methodology is developed to facilitate prognostics using DNN. Simulation results are included to demonstrate the overall methodology using big data-sets.
Recommended Citation
R. Krishnan et al., "Deep Learning Inspired Prognostics Scheme for Applications Generating Big Data," Proceedings of the 2017 International Joint Conference on Neural Networks (2017, Anchorage, AK), pp. 3296 - 3302, Institute of Electrical and Electronics Engineers (IEEE), May 2017.
The definitive version is available at https://doi.org/10.1109/IJCNN.2017.7966269
Meeting Name
2017 International Joint Conference on Neural Networks, IJCNN (2017: May 14-19, Anchorage, AK)
Department(s)
Electrical and Computer Engineering
Second Department
Mathematics and Statistics
Research Center/Lab(s)
Intelligent Systems Center
Second Research Center/Lab
Center for High Performance Computing Research
Keywords and Phrases
Data mining; Deep learning; Deep neural networks; Systems engineering; Dimension reduction; Fault prediction; Model size; Pre-processing step; Two-step approach; Big data
International Standard Book Number (ISBN)
978-1-5090-6182-2
International Standard Serial Number (ISSN)
2161-4407
Document Type
Article - Conference proceedings
Document Version
Citation
File Type
text
Language(s)
English
Rights
© 2017 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.
Publication Date
01 May 2017
Comments
This research was supported in part by NSF I/UCRC awards IIP 1134721 and CMMI #1547042.