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

Journal of Robotics, Networking and Artificial Life (JRNAL)

关键词: Anomaly detection;    autoencoder;    data mining;    factory automation;   

DOI  :  10.2991/jrnal.k.200222.005

来源: DOAJ

【 摘 要 】

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.

【 授权许可】

Unknown