当前位置: X-MOL 学术Integr. Comput. Aided Eng. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Pattern discovery in time series using autoencoder in comparison to nonlearning approaches
Integrated Computer-Aided Engineering ( IF 6.5 ) Pub Date : 2021-01-29 , DOI: 10.3233/ica-210650
Fabian Kai-Dietrich Noering 1 , Yannik Schroeder 2 , Konstantin Jonas 1, 3 , Frank Klawonn 1, 4, 5
Affiliation  

In technical systems the analysis of similar situations is a promising technique to gain information about the system’s state, its health or wearing. Very often, situations cannot be defined but need to be discovered as recurrent patterns within time series data of the system under consideration. This paper addresses the assessment of different approaches to discover frequent variable-length patterns in time series. Because of the success of artificial neural networks (NN) in various research fields, a special issue of this work is the applicability of NNs to the problem of pattern discovery in time series. Therefore we applied and adapted a Convolutional Autoencoder and compared it to classical nonlearning approaches based on Dynamic Time Warping, based on time series discretization as well as based on the Matrix Profile. These nonlearning approaches have also been adapted, to fulfill our requirements like the discovery of potentially time scaled patterns from noisy time series. We showed the performance (quality, computing time, effort of parametrization) of those approaches in an extensive test with synthetic data sets. Additionally the transferability to other data sets is tested by using real life vehicle data. We demonstrated the ability of Convolutional Autoencoders to discover patterns in an unsupervised way. Furthermore the tests showed, that the Autoencoder is able to discover patterns with a similar quality like classical nonlearning approaches.

中文翻译:

与非学习方法相比,使用自动编码器在时间序列中进行模式发现

在技​​术系统中,对相似情况的分析是一种有前途的技术,可用于获取有关系统状态,健康或磨损的信息。很多情况下,情况无法定义,但需要作为正在考虑的系统的时间序列数据内的循环模式来发现。本文介绍了在时间序列中发现频繁的可变长度模式的不同方法的评估。由于人工神经网络(NN)在各个研究领域都取得了成功,因此这项工作的一个特殊问题是神经网络在时间序列模式发现问题中的适用性。因此,我们应用并改编了卷积自动编码器,并将其与基于动态时间规整,基于时间序列离散化以及基于矩阵概要文件的经典非学习方法进行了比较。还修改了这些非学习方法,以满足我们的要求,例如从嘈杂的时间序列中发现潜在的时间标度模式。我们在综合数据集的广泛测试中展示了这些方法的性能(质量,计算时间,参数化工作)。另外,通过使用现实生活中的车辆数据来测试对其他数据集的可传递性。我们展示了卷积自动编码器以无监督方式发现模式的能力。此外,测试表明,自动编码器能够发现质量类似经典非学习方法的模式。在综合数据集的广泛测试中对这些方法的参数化工作)。另外,通过使用现实生活中的车辆数据来测试对其他数据集的可传递性。我们展示了卷积自动编码器以无监督方式发现模式的能力。此外,测试表明,自动编码器能够发现质量类似经典非学习方法的模式。在综合数据集的广泛测试中对这些方法的参数化工作)。另外,通过使用现实生活中的车辆数据来测试对其他数据集的可传递性。我们展示了卷积自动编码器以无监督方式发现模式的能力。此外,测试表明,自动编码器能够发现质量类似经典非学习方法的模式。
更新日期:2021-02-03
down
wechat
bug