ON MINI-BATCH TRAINING WITH VARYING LENGTH TIME SERIES

研究成果: 書籍/レポート タイプへの寄稿会議への寄与

抄録

In real-world time series recognition applications, it is possible to have data with varying length patterns. However, when using artificial neural networks (ANN), it is standard practice to use fixed-sized mini-batches. To do this, time series data with varying lengths are typically normalized so that all the patterns are the same length. Normally, this is done using zero padding or truncation without much consideration. We propose a novel method of normalizing the lengths of the time series in a dataset by exploiting the dynamic matching ability of Dynamic Time Warping (DTW). In this way, the time series lengths in a dataset can be set to a fixed size while maintaining features typical to the dataset. In the experiments, all 11 datasets with varying length time series from the 2018 UCR Time Series Archive are used. We evaluate the proposed method by comparing it with 18 other length normalization methods on a Convolutional Neural Network (CNN), a Long-Short Term Memory network (LSTM), and a Bidirectional LSTM (BLSTM). The code is publicly available at https://github.com/uchidalab/vary length time series.

本文言語英語
ホスト出版物のタイトル2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings
出版社Institute of Electrical and Electronics Engineers Inc.
ページ4483-4487
ページ数5
ISBN(電子版)9781665405409
DOI
出版ステータス出版済み - 2022
イベント47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Virtual, Online, シンガポール
継続期間: 5月 23 20225月 27 2022

出版物シリーズ

名前ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
2022-May
ISSN(印刷版)1520-6149

会議

会議47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022
国/地域シンガポール
CityVirtual, Online
Period5/23/225/27/22

!!!All Science Journal Classification (ASJC) codes

  • ソフトウェア
  • 信号処理
  • 電子工学および電気工学

フィンガープリント

「ON MINI-BATCH TRAINING WITH VARYING LENGTH TIME SERIES」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