search for




 

Monitoring procedure of autocorrelated processes using the deep learning-based LSTM model
Journal of the Korean Data & Information Science Society 2022;33:237-48
Published online March 31, 2022;  https://doi.org/10.7465/jkdi.2022.33.2.237
© 2022 Korean Data and Information Science Society.

Sujeong Lee1 · Jaeheon Lee2

12Department of Applied Statistics, Chung-Ang University
Correspondence to: 1 Graduate student, Department of Applied Statistics, Chung-Ang University, Seoul 06974, Korea.
2 Professor, Department of Applied Statistics, Chung-Ang University, Seoul 06974, Korea. E-mail: jaeheon@cau.ac.kr
This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (No. 2020R1F1A1A01050674).
Received February 11, 2022; Revised February 21, 2022; Accepted February 24, 2022.
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
Abstract
Many researches have been conducted on procedures to monitor autocorrelated processes, and the most used method among them is to calculate the residual by estimating the predicted value and to monitor the residual data. That is, the autocorrelation problem is solved by using the residual. In this paper, we propose a procedure for monitoring autocorrelated processes using a long short-term memory (LSTM) model based on deep learning. The performance of the proposed procedure is compared with that of using a vanilla recurrent neural network (RNN) model and that of fitting a time series model, by performing simulations. The procedure using the LSTM and RNN models shows good overall performance, and when compared to the procedure for fitting a time series model, it is considered an efficient procedure in that it does not require accurate model fitting.
Keywords : Autocorrelated process, deep learning, LSTM, RNN.