Time series data augmentation for neural networks by time warping with a discriminative teacher

研究成果: Chapter in Book/Report/Conference proceedingConference contribution

3 被引用数 (Scopus)

抄録

Neural networks have become a powerful tool in pattern recognition and part of their success is due to generalization from using large datasets. However, unlike other domains, time series classification datasets are often small. In order to address this problem, we propose a novel time series data augmentation called guided warping. While many data augmentation methods are based on random transformations, guided warping exploits the element alignment properties of Dynamic Time Warping (DTW) and shapeDTW, a high-level DTW method based on shape descriptors, to deterministically warp sample patterns. In this way, the time series are mixed by warping the features of a sample pattern to match the time steps of a reference pattern. Furthermore, we introduce a discriminative teacher in order to serve as a directed reference for the guided warping. We evaluate the method on all 85 datasets in the 2015 UCR Time Series Archive with a deep convolutional neural network (CNN) and a recurrent neural network (RNN). The code with an easy to use implementation can be found at https://github.com/uchidalab/time_series_augmentation.

本文言語英語
ホスト出版物のタイトルProceedings of ICPR 2020 - 25th International Conference on Pattern Recognition
出版社Institute of Electrical and Electronics Engineers Inc.
ページ3558-3565
ページ数8
ISBN(電子版)9781728188089
DOI
出版ステータス出版済み - 2020
イベント25th International Conference on Pattern Recognition, ICPR 2020 - Virtual, Milan, イタリア
継続期間: 1 10 20211 15 2021

出版物シリーズ

名前Proceedings - International Conference on Pattern Recognition
ISSN(印刷版)1051-4651

会議

会議25th International Conference on Pattern Recognition, ICPR 2020
国/地域イタリア
CityVirtual, Milan
Period1/10/211/15/21

All Science Journal Classification (ASJC) codes

  • コンピュータ ビジョンおよびパターン認識

フィンガープリント

「Time series data augmentation for neural networks by time warping with a discriminative teacher」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル