[2S4-GS-2] Machine learning:

[2S4-GS-2-01] An Autoencoder incorporating frequencies in time series data

〇Daichi Fushihara¹, Yuka Hashimoto¹, Yoichi Matsuo¹ (1. NTT)

Keywords:Anomaly detection, Autoencoder, Time-series data

Anomaly detection in time series data is essential across various industries, such as communication networks. Recently, Autoencoder (AE) has been widely used for anomaly detection. However, the training of AE heavily depends on the geometric features of input data, which makes it challenging to train AE for time series data with complicated periodic patterns. In this paper, we propose an Autoencoder that uses the frequencies of time series data, which we call AE-FED(AE with Frequency-Encoded Decoder). We prove that AE-FED can reconstruct the input time series data with periods. Experimental results on synthetic time series datasets demonstrate that AE-FED outperforms existing approaches in detecting anomalies in periodic time series data, achieving the highest AUC scores.