arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1909.09149cs.LGstat.ML
收藏

Timage --一种鲁棒的时间序列分类流水线

Timage -- A Robust Time Series Classification Pipeline

Rosenheim Technical University of Applied Sciences(罗森海姆应用技术大学);Technische Hochschule Nürnberg Georg Simon Ohm(纽伦堡格奥尔格·西蒙·欧姆应用技术大学)

Marc Wenninger, Sebastian P. Bayerl, Jochen Schmidt, Korbinian Riedhammer

摘要:

时间序列是按时间排序的值的序列。这种数据可以在许多现实世界中找到。时间序列分类是一项艰巨的任务,也是一个活跃的研究领域。本文研究了迁移学习在深度神经网络和称为递归图的时间序列的2D表示中的使用。为了利用在图像分类领域所做的研究,其中深度神经网络已经取得了非常好的结果,我们使用了一种称为ResNet的残差神经网络架构。由于时间序列的预处理是每一个时间序列分类流水线的主要部分,所提出的方法简化了这一步骤,只需要很少的参数。我们首次提出了一种多时间序列分类的方法:训练一个网络来分类归档中的所有数据集。我们是第一批在最新的2018年发布的UCR档案中评估该方法的公司之一,这是一个完善的时间序列分类基准数据集。

英文摘要:

Time series are series of values ordered by time. This kind of data can be found in many real world settings. Classifying time series is a difficult task and an active area of research. This paper investigates the use of transfer learning in Deep Neural Networks and a 2D representation of time series known as Recurrence Plots. In order to utilize the research done in the area of image classification, where Deep Neural Networks have achieved very good results, we use a Residual Neural Networks architecture known as ResNet. As preprocessing of time series is a major part of every time series classification pipeline, the method proposed simplifies this step and requires only few parameters. For the first time we propose a method for multi time series classification: Training a single network to classify all datasets in the archive with one network. We are among the first to evaluate the method on the latest 2018 release of the UCR archive, a well established time series classification benchmarking dataset.

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。

↑