Exploring Deep Time-Series Imaging for Anomaly Detection of Building Energy Consumption

A Comprehensive Survey of Deep Transfer Learning for Anomaly Detection in Industrial Time Series: Methods, Applications, and Directions

“…It is important to note that when the target data is already sufficient, transferring knowledge can be detrimental as it can decrease prediction accuracy on the final task. Copiaco et al aims to detect anomalies for building energy consumption via transfer learning from pre-trained CNN models [128]. First, they convert 1D time series signals to 2D image representations.…”