Generative pseudorehearsal strategy for fault classification under an incremental learning

Subin Lee; Jun Geol Baek

doi:10.1109/CSE/EUC.2019.00035

Generative pseudorehearsal strategy for fault classification under an incremental learning

Subin Lee, Jun Geol Baek

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

3 Citations (Scopus)

Abstract

As fault classification becomes more important in manufacturing industry, the state-of-art machine learning methods have been utilized. However, owing to the problem called catastrophic forgetting, the networks tend to forget the former knowledge. Thus, it is evident that overall classification performance has fallen, when training the existing model with new classes. We propose classification model that retains previous information using generative pseudorehearsal networks. In this method, newly arrived fault classes could be trained on same network which is parameterized by former data. The proposed method shows significant experimental results comparing to non-incremental methods, while achieving memory efficiency and solving the class imbalance problem.

Original language	English
Title of host publication	Proceedings - 22nd IEEE International Conference on Computational Science and Engineering and 17th IEEE International Conference on Embedded and Ubiquitous Computing, CSE/EUC 2019
Editors	Meikang Qiu
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	138-140
Number of pages	3
ISBN (Electronic)	9781728116631
DOIs	https://doi.org/10.1109/CSE/EUC.2019.00035
Publication status	Published - 2019 Aug
Event	22nd IEEE International Conference on Computational Science and Engineering and 17th IEEE International Conference on Embedded and Ubiquitous Computing, CSE/EUC 2019 - New York, United States Duration: 2019 Aug 1 → 2019 Aug 3

Publication series

Name	Proceedings - 22nd IEEE International Conference on Computational Science and Engineering and 17th IEEE International Conference on Embedded and Ubiquitous Computing, CSE/EUC 2019

Conference

Conference	22nd IEEE International Conference on Computational Science and Engineering and 17th IEEE International Conference on Embedded and Ubiquitous Computing, CSE/EUC 2019
Country/Territory	United States
City	New York
Period	19/8/1 → 19/8/3

Bibliographical note

Publisher Copyright:
© 2019 IEEE.

Keywords

Fault diagnostics and classification
Generative networks
Incremental learning
Pseudorehearsal strategy

ASJC Scopus subject areas

Computer Networks and Communications
Computer Science Applications
Computer Vision and Pattern Recognition
Hardware and Architecture
Human-Computer Interaction
Artificial Intelligence

Access to Document

10.1109/CSE/EUC.2019.00035

Cite this

Lee, S., & Baek, J. G. (2019). Generative pseudorehearsal strategy for fault classification under an incremental learning. In M. Qiu (Ed.), Proceedings - 22nd IEEE International Conference on Computational Science and Engineering and 17th IEEE International Conference on Embedded and Ubiquitous Computing, CSE/EUC 2019 (pp. 138-140). Article 8919543 (Proceedings - 22nd IEEE International Conference on Computational Science and Engineering and 17th IEEE International Conference on Embedded and Ubiquitous Computing, CSE/EUC 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CSE/EUC.2019.00035

Generative pseudorehearsal strategy for fault classification under an incremental learning. / Lee, Subin; Baek, Jun Geol.
Proceedings - 22nd IEEE International Conference on Computational Science and Engineering and 17th IEEE International Conference on Embedded and Ubiquitous Computing, CSE/EUC 2019. ed. / Meikang Qiu. Institute of Electrical and Electronics Engineers Inc., 2019. p. 138-140 8919543 (Proceedings - 22nd IEEE International Conference on Computational Science and Engineering and 17th IEEE International Conference on Embedded and Ubiquitous Computing, CSE/EUC 2019).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Lee, S & Baek, JG 2019, Generative pseudorehearsal strategy for fault classification under an incremental learning. in M Qiu (ed.), Proceedings - 22nd IEEE International Conference on Computational Science and Engineering and 17th IEEE International Conference on Embedded and Ubiquitous Computing, CSE/EUC 2019., 8919543, Proceedings - 22nd IEEE International Conference on Computational Science and Engineering and 17th IEEE International Conference on Embedded and Ubiquitous Computing, CSE/EUC 2019, Institute of Electrical and Electronics Engineers Inc., pp. 138-140, 22nd IEEE International Conference on Computational Science and Engineering and 17th IEEE International Conference on Embedded and Ubiquitous Computing, CSE/EUC 2019, New York, United States, 19/8/1. https://doi.org/10.1109/CSE/EUC.2019.00035

Lee S, Baek JG. Generative pseudorehearsal strategy for fault classification under an incremental learning. In Qiu M, editor, Proceedings - 22nd IEEE International Conference on Computational Science and Engineering and 17th IEEE International Conference on Embedded and Ubiquitous Computing, CSE/EUC 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 138-140. 8919543. (Proceedings - 22nd IEEE International Conference on Computational Science and Engineering and 17th IEEE International Conference on Embedded and Ubiquitous Computing, CSE/EUC 2019). doi: 10.1109/CSE/EUC.2019.00035

Lee, Subin ; Baek, Jun Geol. / Generative pseudorehearsal strategy for fault classification under an incremental learning. Proceedings - 22nd IEEE International Conference on Computational Science and Engineering and 17th IEEE International Conference on Embedded and Ubiquitous Computing, CSE/EUC 2019. editor / Meikang Qiu. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 138-140 (Proceedings - 22nd IEEE International Conference on Computational Science and Engineering and 17th IEEE International Conference on Embedded and Ubiquitous Computing, CSE/EUC 2019).

@inproceedings{6cd667d75b124de1bba01c03067a8378,

title = "Generative pseudorehearsal strategy for fault classification under an incremental learning",

abstract = "As fault classification becomes more important in manufacturing industry, the state-of-art machine learning methods have been utilized. However, owing to the problem called catastrophic forgetting, the networks tend to forget the former knowledge. Thus, it is evident that overall classification performance has fallen, when training the existing model with new classes. We propose classification model that retains previous information using generative pseudorehearsal networks. In this method, newly arrived fault classes could be trained on same network which is parameterized by former data. The proposed method shows significant experimental results comparing to non-incremental methods, while achieving memory efficiency and solving the class imbalance problem.",

keywords = "Fault diagnostics and classification, Generative networks, Incremental learning, Pseudorehearsal strategy",

author = "Subin Lee and Baek, {Jun Geol}",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 22nd IEEE International Conference on Computational Science and Engineering and 17th IEEE International Conference on Embedded and Ubiquitous Computing, CSE/EUC 2019 ; Conference date: 01-08-2019 Through 03-08-2019",

year = "2019",

month = aug,

doi = "10.1109/CSE/EUC.2019.00035",

language = "English",

series = "Proceedings - 22nd IEEE International Conference on Computational Science and Engineering and 17th IEEE International Conference on Embedded and Ubiquitous Computing, CSE/EUC 2019",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "138--140",

editor = "Meikang Qiu",

booktitle = "Proceedings - 22nd IEEE International Conference on Computational Science and Engineering and 17th IEEE International Conference on Embedded and Ubiquitous Computing, CSE/EUC 2019",

}

TY - GEN

T1 - Generative pseudorehearsal strategy for fault classification under an incremental learning

AU - Lee, Subin

AU - Baek, Jun Geol

PY - 2019/8

Y1 - 2019/8

N2 - As fault classification becomes more important in manufacturing industry, the state-of-art machine learning methods have been utilized. However, owing to the problem called catastrophic forgetting, the networks tend to forget the former knowledge. Thus, it is evident that overall classification performance has fallen, when training the existing model with new classes. We propose classification model that retains previous information using generative pseudorehearsal networks. In this method, newly arrived fault classes could be trained on same network which is parameterized by former data. The proposed method shows significant experimental results comparing to non-incremental methods, while achieving memory efficiency and solving the class imbalance problem.

AB - As fault classification becomes more important in manufacturing industry, the state-of-art machine learning methods have been utilized. However, owing to the problem called catastrophic forgetting, the networks tend to forget the former knowledge. Thus, it is evident that overall classification performance has fallen, when training the existing model with new classes. We propose classification model that retains previous information using generative pseudorehearsal networks. In this method, newly arrived fault classes could be trained on same network which is parameterized by former data. The proposed method shows significant experimental results comparing to non-incremental methods, while achieving memory efficiency and solving the class imbalance problem.

KW - Fault diagnostics and classification

KW - Generative networks

KW - Incremental learning

KW - Pseudorehearsal strategy

UR - http://www.scopus.com/inward/record.url?scp=85077037210&partnerID=8YFLogxK

U2 - 10.1109/CSE/EUC.2019.00035

DO - 10.1109/CSE/EUC.2019.00035

M3 - Conference contribution

AN - SCOPUS:85077037210

T3 - Proceedings - 22nd IEEE International Conference on Computational Science and Engineering and 17th IEEE International Conference on Embedded and Ubiquitous Computing, CSE/EUC 2019

SP - 138

EP - 140

BT - Proceedings - 22nd IEEE International Conference on Computational Science and Engineering and 17th IEEE International Conference on Embedded and Ubiquitous Computing, CSE/EUC 2019

A2 - Qiu, Meikang

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 22nd IEEE International Conference on Computational Science and Engineering and 17th IEEE International Conference on Embedded and Ubiquitous Computing, CSE/EUC 2019

Y2 - 1 August 2019 through 3 August 2019

ER -

Generative pseudorehearsal strategy for fault classification under an incremental learning

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this