JSAI2019

Presentation information

General Session

General Session » [GS] J-3 Data mining

[4A2-J-3] Data mining: analysis of changes and accidents

Fri. Jun 7, 2019 12:00 PM - 1:40 PM Room A (2F Main hall A)

Chair:Yusuke Kumagai Reviewer:Hikaru Kajino

12:20 PM - 12:40 PM

[4A2-J-3-02] Collective Anomaly Detection using Generative Adversarial Networks

〇Chihiro Maru1, Ichiro Kobayashi1 (1. Ochanomizu University)

Keywords:Anomaly detection, GAN, Collective anomaly, Time-series

Generative adversarial network (GAN) is now being applied to anomaly detection.
However, the existing approaches to GAN-based anomaly detection cannot detect collective anomalies that change the behavior of some data instances because they deal with individual data instances.
This study aims to determine how collective anomalies that are commonly associated with time-series data can be detected using GAN models.
We developed a GAN model for time-series data by adopting a decoder side of sequence to sequence (seq2seq) to a generator, an encoder side of seq2seq to an encoder, recurrent neural networks and fully connected neural network to a discriminator.
We conducted several experiments on datasets, regarded as anomaly datasets, that we generated by swapping data instances at different time points.
The results suggest that our GAN model can compete effectively with existing approaches for detecting collective anomalies.