Autoencoder with Spiking in Frequency Domain for Anomaly Detection of Uncertainty Event

Authors
Umaporn Yokkampon1, *, Sakmongkon Chumkamon1, Abbe Mowshowitz2, Eiji Hayashi1
1Department of Computer Science and Systems Engineering, Kyushu Institute of Technology, 680-4 Kawazu, Iizuka, Fukuoka 820-8502, Japan
2Department of Computer Science, The City College of New York, 160 Convent Avenue, New York, NY 10031, USA
*Corresponding author. Email: [email protected]
Corresponding Author
Umaporn Yokkampon
Received 11 November 2019, Accepted 21 December 2019, Available Online 29 February 2020.
DOI
https://doi.org/10.2991/jrnal.k.200222.005
Keywords
Anomaly detection; autoencoder; data mining; factory automation
Abstract
This paper proposes the autoencoder method with spiking raw data to the frequency domain to analyze and predict the anomaly case among the standard data set and compare it with original data. The dataset is the real-world data from factory automation. The combination of frequency domain and original data can improve the validity and accuracy in detecting an anomaly data. Therefore, analyzing time-series data using combination of autoencoder and the frequency domain can be efficient in detecting anomalies.
Copyright
© 2020 The Authors. Published by ALife Robotics Corp. Ltd.
Open Access
This is an open access article distributed under the CC BY-NC 4.0 license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)