RTFN: A Robust Temporal Feature Network for Time Series Classification

TL;DR

This paper introduces RTFN, a novel neural network combining local feature extraction and relation modeling for time series classification, achieving state-of-the-art results in both supervised and unsupervised settings.

Contribution

The paper proposes RTFN, integrating a residual convolutional network with an LSTM-based attention mechanism to better capture local and relational features in time series data.

Findings

RTFN achieves superior accuracy on UCR2018 datasets.

RTFN performs well in both supervised and unsupervised learning.

The model effectively captures local and global features.

Abstract

Time series data usually contains local and global patterns. Most of the existing feature networks pay more attention to local features rather than the relationships among them. The latter is, however, also important yet more difficult to explore. To obtain sufficient representations by a feature network is still challenging. To this end, we propose a novel robust temporal feature network (RTFN) for feature extraction in time series classification, containing a temporal feature network (TFN) and an LSTM-based attention network (LSTMaN). TFN is a residual structure with multiple convolutional layers. It functions as a local-feature extraction network to mine sufficient local features from data. LSTMaN is composed of two identical layers, where attention and long short-term memory (LSTM) networks are hybridized. This network acts as a relation extraction network to discover the intrinsic relationships among the extracted features at different positions in sequential data. In experiments, we embed RTFN into a supervised structure as a feature extractor and into an unsupervised structure as an encoder, respectively. The results show that the RTFN-based structures achieve excellent supervised and unsupervised performance on a large number of UCR2018 and UEA2018 datasets.