Reducing Uncertainty in Failure Prediction Using Singular Value Decomposition Feature Selection

Nor, A.K.M. and Pedapati, S.R. and Muhammad, M. (2022) Reducing Uncertainty in Failure Prediction Using Singular Value Decomposition Feature Selection. Lecture Notes in Electrical Engineering, 758. pp. 775-796. ISSN 18761100

Full text not available from this repository.
Official URL: https://www.scopus.com/inward/record.uri?eid=2-s2....

Abstract

Uncertainty is one of the indicators to evaluate the prediction of deep learning models. In real-world prognostic domain, predicting failure with uncertainty provides users with powerful argument when important decisions related to safety, security and monetary must be made. While quantifying uncertainty has slowly becoming a norm in deep learning, no work has been dedicated in formulating the appropriate feature selection framework that lessens the prediction uncertainties. Much of the available techniques have only been proven to improve point estimate predictions, without considering its effect on uncertainty. In this paper, a feature selection method based on elimination of noisy data is proposed to reduce the Aleatoric uncertainty in a Remaining Useful Life (RUL) prediction problem. Singular Value Decomposition (SVD) technique is employed to denoise sensor data in SVD matrix by filtering higher SVD modes susceptible to contain noise. Then, the �cleaned� Signal to Noise Ratio (SNR) of each feature is calculated and ranked. Features with low SNR, thus with higher noise, are eliminated. We compare the uncertainty level and behavior between a full feature dataset and different percentage of features selected using SVD and SNR. The same comparison is done between our approach and other feature selection methods such as Pearson and Spearman correlations as well as F Regression. The results show that our approach achieved a lower uncertainty degree with generally better prediction performance than the other mentioned methods. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Item Type: Article
Additional Information: cited By 0; Conference of 1st International Conference on Artificial Intelligence for Smart Community, AISC 2020 ; Conference Date: 17 December 2020 Through 18 December 2020; Conference Code:286319
Uncontrolled Keywords: Deep learning; Feature Selection; Forecasting; Signal to noise ratio; Uncertainty analysis, CMAPSS; Failures prediction; Feature selection methods; Features selection; Learning models; PHM; Real-world; Remaining useful lives; Selection framework; Uncertainty, Singular value decomposition
Depositing User: Mr Ahmad Suhairi UTP
Date Deposited: 19 Dec 2023 03:23
Last Modified: 19 Dec 2023 03:23
URI: https://khub.utp.edu.my/scholars/id/eprint/17389

Actions (login required)

View Item
View Item