Attention-based LSTM-CNNs For Time-series Classification
Lists
Only you see this
Abstract
Time series classification is a critical problem in the machine learning field, which spawns numerous research works on it. In this work, we propose AttLSTM-CNNs, an attention-based LSTM network and convolution network that jointly extracts the underlying pattern among the time-series for the classification. The attention-based LSTM automatically captures the long-term temporal dependency among the series, and the CNN describes the spatial sparsity and heterogeneity in the data. The extensive experiments show that the proposed model outperforms the other methods for time-series classification.
BibTeX
@inproceedings{du2018attention,
author = {Qianjin Du and Weixi Gu and Lin Zhang and Shao-Lun Huang},
title = {{Attention-based LSTM-CNNs For Time-series Classification}},
booktitle = {SenSys},
year = {2018},
url = {https://openreview.net/forum?id=ANMx6pOqzETJ},
}Loading related content...