DeepTimeAnomalyViz: A Tool for Visualizing and Post-processing Deep Learning Anomaly Detection Results for Industrial Time-Series
This is an incremental tool for engineers and data scientists working on industrial monitoring to streamline anomaly detection implementation.
The paper tackles the complexity of implementing deep learning anomaly detection for industrial time-series by introducing DeTAVIZ, a web-based visualization tool that enables quick exploration and assessment of feasibility, allowing users to iterate through post-processing options and compare models with manual optimization.
Industrial processes are monitored by a large number of various sensors that produce time-series data. Deep Learning offers a possibility to create anomaly detection methods that can aid in preventing malfunctions and increasing efficiency. But creating such a solution can be a complicated task, with factors such as inference speed, amount of available data, number of sensors, and many more, influencing the feasibility of such implementation. We introduce the DeTAVIZ interface, which is a web browser based visualization tool for quick exploration and assessment of feasibility of DL based anomaly detection in a given problem. Provided with a pool of pretrained models and simulation results, DeTAVIZ allows the user to easily and quickly iterate through multiple post processing options and compare different models, and allows for manual optimisation towards a chosen metric.