Nonlinear Theory and Its Applications, IEICE
Online ISSN : 2185-4106
ISSN-L : 2185-4106
Regular Section
Reconstructive reservoir computing for anomaly detection in time-series signals
Junya KatoGouhei TanakaRyosho NakaneAkira Hirose
Author information

2024 Volume 15 Issue 1 Pages 183-204


We propose reconstructive reservoir computing (RRC) which performs better anomaly detection in time-series signals than forecasting-based methods. In this paper, reconstruction means that a neural network generates past input signals. RRC reconstructs a past normal signal for anomaly detection using an echo state network which can learn quickly and stably. We expect that it is easier to restore a past normal signal than to predict an unknown future normal signal. For anomaly detection, we compute an instantaneous reconstruction error. The reconstruction error larger than a threshold is a sign of anomaly. We conduct experiments using sound data obtained from a pump. In the experiments, we pay attention to a time lag between input and output to be reconstructed since we assume that an excessive time lag makes reconstruction difficult due to signal attenuation in the network. Experimental results show that if the time lag is moderate, the reconstruction error of the normal signal is lower than the forecasting error of the same signal. Furthermore, we show that RRC with the appropriate time lag has a better anomaly detection performance index than forecasting-based methods.

Content from these authors
© 2024 The Institute of Electronics, Information and Communication Engineers

This article is licensed under a Creative Commons [Attribution-NonCommercial-NoDerivatives 4.0 International] license.
Previous article