arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1809.04356cs.LGcs.AIstat.ML
收藏

时间序列分类的深度学习研究进展

Deep learning for time series classification: a review

Université Haute Alsace(上阿尔萨斯大学);Monash University(莫纳什大学)

Hassan Ismail Fawaz, Germain Forestier, Jonathan Weber, Lhassane Idoumghar, Pierre-Alain Muller

摘要:

时间序列分类是数据采掘中一个重要而又具有挑战性的问题。随着时间序列数据可用性的提高,人们提出了数百种TSC算法。在这些方法中,只有少数考虑使用深度神经网络(DNN)来执行此任务。这是令人惊讶的,因为深度学习在过去几年中已经看到了非常成功的应用。DNN确实彻底改变了计算机视觉领域,特别是随着残差和卷积神经网络等新型更深层次架构的出现。除了图像之外,文本和音频等序列数据也可以使用DNN进行处理,以达到文档分类和语音识别的最新性能。在本文中,我们通过对最新的TSC DNN架构进行实证研究,研究了TSC深度学习算法的当前最先进性能。我们给出了一个概述的最成功的深度学习应用程序在各种时间序列域的统一分类的DNN TSC。我们还为TSC社区提供了一个开源的深度学习框架,我们在其中实现了每种比较方法,并在单变量TSC基准(UCR/UEA存档)和12个多变量时间序列数据集上对其进行了评估。通过在97个时间序列数据集上训练8,730个深度学习模型,我们提出了迄今为止对TSC DNN最详尽的研究。

英文摘要:

Time Series Classification (TSC) is an important and challenging problem in data mining. With the increase of time series data availability, hundreds of TSC algorithms have been proposed. Among these methods, only a few have considered Deep Neural Networks (DNNs) to perform this task. This is surprising as deep learning has seen very successful applications in the last years. DNNs have indeed revolutionized the field of computer vision especially with the advent of novel deeper architectures such as Residual and Convolutional Neural Networks. Apart from images, sequential data such as text and audio can also be processed with DNNs to reach state-of-the-art performance for document classification and speech recognition. In this article, we study the current state-of-the-art performance of deep learning algorithms for TSC by presenting an empirical study of the most recent DNN architectures for TSC. We give an overview of the most successful deep learning applications in various time series domains under a unified taxonomy of DNNs for TSC. We also provide an open source deep learning framework to the TSC community where we implemented each of the compared approaches and evaluated them on a univariate TSC benchmark (the UCR/UEA archive) and 12 multivariate time series datasets. By training 8,730 deep learning models on 97 time series datasets, we propose the most exhaustive study of DNNs for TSC to date.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑