RTFN: Robust Temporal Feature Network

TL;DR

The paper introduces RTFN, a novel neural network architecture combining temporal feature extraction and attention-based LSTM to improve time series analysis in various applications.

Contribution

It proposes a new robust temporal feature network (RTFN) that effectively captures basic and complex features for time series analysis, outperforming existing methods.

Findings

RTFN-based supervised structure wins 40 out of 85 datasets.

RTFN-based unsupervised clustering outperforms on 4 out of 11 datasets.

Demonstrates effectiveness in diverse time series tasks.

Abstract

Time series analysis plays a vital role in various applications, for instance, healthcare, weather prediction, disaster forecast, etc. However, to obtain sufficient shapelets by a feature network is still challenging. To this end, we propose a novel robust temporal feature network (RTFN) that contains temporal feature networks and attentional LSTM networks. The temporal feature networks are built to extract basic features from input data while the attentional LSTM networks are devised to capture complicated shapelets and relationships to enrich features. In experiments, we embed RTFN into supervised structure as a feature extraction network and into unsupervised clustering as an encoder, respectively. The results show that the RTFN-based supervised structure is a winner of 40 out of 85 datasets and the RTFN-based unsupervised clustering performs the best on 4 out of 11 datasets in the UCR2018 archive.