Timage -- A Robust Time Series Classification Pipeline
This addresses the problem of robust and efficient time series classification for researchers and practitioners, though it is incremental by building on existing methods like ResNet and recurrence plots.
The paper tackles time series classification by proposing a pipeline that uses transfer learning with ResNet on recurrence plots, simplifying preprocessing and enabling multi-dataset classification with a single network, achieving competitive results on the UCR 2018 archive.
Time series are series of values ordered by time. This kind of data can be found in many real world settings. Classifying time series is a difficult task and an active area of research. This paper investigates the use of transfer learning in Deep Neural Networks and a 2D representation of time series known as Recurrence Plots. In order to utilize the research done in the area of image classification, where Deep Neural Networks have achieved very good results, we use a Residual Neural Networks architecture known as ResNet. As preprocessing of time series is a major part of every time series classification pipeline, the method proposed simplifies this step and requires only few parameters. For the first time we propose a method for multi time series classification: Training a single network to classify all datasets in the archive with one network. We are among the first to evaluate the method on the latest 2018 release of the UCR archive, a well established time series classification benchmarking dataset.