Guozhong Li
Shapenet: A shapelet-neural network approach for multivariate time series classification
Li, Guozhong; Choi, Byron; Xu, Jianliang; Bhowmick, Sourav S; Chun, Kwok-Pan; Wong, Grace LH
Authors
Byron Choi
Jianliang Xu
Sourav S Bhowmick
Dr Kwok Chun Kwok.Chun@uwe.ac.uk
Lecturer in Environmental Managment
Grace LH Wong
Abstract
Time series shapelets are short discriminative subsequences that recently have been found not only to be accurate but also interpretable for the classification problem of univariate time series (UTS). However, existing work on shapelets selection cannot be applied to multivariate time series classification (MTSC) since the candidate shapelets of MTSC may come from different variables of different lengths and thus cannot be directly compared. To address this challenge, in this paper, we propose a novel model called ShapeNet, which embeds shapelet candidates of different lengths into a unified space for shapelet selection. The network is trained using cluster-wise triplet loss, which considers the distance between anchor and multiple positive (negative) samples and the distance between positive (negative) samples, which are important for convergence. We compute representative and diversified final shapelets rather than directly using all the embeddings for model building to avoid a large fraction of non-discriminative shapelet candidates. We have conducted experiments on ShapeNet with competitive state-of-the-art and benchmark methods using UEA MTS datasets. The results show that the accuracy of ShapeNet is the best of all the methods compared. Furthermore, we illustrate the shapelets’ interpretability with two case studies.
Presentation Conference Type | Conference Paper (Published) |
---|---|
Conference Name | The 35th AAAIConferenceonArtificial Intelligence(AAAI-21) |
Start Date | May 18, 2021 |
Acceptance Date | Mar 18, 2021 |
Online Publication Date | May 18, 2021 |
Publication Date | May 18, 2021 |
Deposit Date | Jan 18, 2022 |
Volume | 35 |
Pages | 8375-8383 |
Book Title | Proceedings of the AAAI Conference on Artificial Intelligence |
ISBN | 9781713835974 |
Keywords | Time-Series/Data Streams; Data Stream Mining; Representation Learning; Unsupervised & Self-Supervised Learning |
Public URL | https://uwe-repository.worktribe.com/output/8545887 |
You might also like
Spatiotemporal vegetation variations and projections driven by atmosphere-ocean oscillations at multiple time scales: A case study in Gansu, China
(2020)
Presentation / Conference Contribution
Visualet: Visualizing shapelets for time series classification
(2020)
Presentation / Conference Contribution
Analysing and projecting spatial drought conditions of the Seine catchment based on ocean-atmosphere oscillations over interannual and decadal scales
(2020)
Presentation / Conference Contribution
Downloadable Citations
About UWE Bristol Research Repository
Administrator e-mail: repository@uwe.ac.uk
This application uses the following open-source libraries:
SheetJS Community Edition
Apache License Version 2.0 (http://www.apache.org/licenses/)
PDF.js
Apache License Version 2.0 (http://www.apache.org/licenses/)
Font Awesome
SIL OFL 1.1 (http://scripts.sil.org/OFL)
MIT License (http://opensource.org/licenses/mit-license.html)
CC BY 3.0 ( http://creativecommons.org/licenses/by/3.0/)
Powered by Worktribe © 2024
Advanced Search