Experiments on city train vibration anomaly detection Using deep learning approaches

Abstract

Anomaly detection is widely in demand in the field where automated detection of anomalous conditions in many observation tasks. While conventional data science approaches have shown interesting results, deep learning approaches to anomaly detection problems reveal new perspectives of possibilities especially where massive amount of data need to be handled. We develop anomaly detection applications on city train vibration data using deep learning approaches. We carried out preliminary research on anomaly detection in general and applied our real world data to existing solutions. In this paper, we provide a survey on anomaly detection and analyse our results of experiments using deep learning approaches.

Three level intrusion detection system based on conditional generative adversarial network

“…Kim et al [41] performed anomaly detection for the vibration data city train using generative adversarial network. For vibration data analysis, spectral density evaluation was carried out.…”