DeepVATS: Deep Visual Analytics for Time Series

TL;DR

DeepVATS introduces a deep learning-based visual analytics tool for time series data, enabling pattern and anomaly detection through self-supervised autoencoder embeddings in an interactive interface.

Contribution

It presents an open-source framework that applies deep visual analytics to time series, combining self-supervised learning with interactive visualization.

Findings

Effective detection of patterns and anomalies in time series

Validated on synthetic and real datasets

Open-source implementation available

Abstract

The field of Deep Visual Analytics (DVA) has recently arisen from the idea of developing Visual Interactive Systems supported by deep learning, in order to provide them with large-scale data processing capabilities and to unify their implementation across different data and domains. In this paper we present DeepVATS, an open-source tool that brings the field of DVA into time series data. DeepVATS trains, in a self-supervised way, a masked time series autoencoder that reconstructs patches of a time series, and projects the knowledge contained in the embeddings of that model in an interactive plot, from which time series patterns and anomalies emerge and can be easily spotted. The tool includes a back-end for data processing pipeline and model training, as well as a front-end with a interactive user interface. We report on results that validate the utility of DeepVATS, running experiments on both synthetic and real datasets. The code is publicly available on https://github.com/vrodriguezf/deepvats