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 2009.11705cs.LG
收藏

用于多变量时间序列分析的门控Res2Net

Gated Res2Net for Multivariate Time Series Analysis

Ocean University of China(中国海洋大学)

Chao Yang, Mingxing Jiang, Zhongwen Guo, Yuan Liu

摘要:

多元时间序列分析因其广泛的应用而成为数据采掘中的一个重要问题。随着可用于训练的时间序列数据的增加,在时间序列分析领域实现深度神经网络变得越来越普遍。Res2Net是最近提出的一种骨干网络,它可以进一步改善最先进的网络,因为它通过连接不同的过滤器组来提高多尺度表示能力。然而,Res2Net忽略了特征图之间的相关性,缺乏对信息交互过程的控制。针对这一问题,本文提出了一种基于门控机制和Res2Net思想的骨干卷积神经网络,即Gated Res2Net(GRes2Net),用于多变量时间序列分析。分层残差类连接受到门的影响,门的值基于原始特征图、前一个输出特征图和下一个输入特征图来计算,从而更有效地考虑特征图之间的相关性。通过利用门控机制,网络可以控制信息发送的过程,从而可以更好地捕获和利用时间信息和特征图之间的相关性。我们在四个多变量时间序列数据集上评估了GRes2Net,包括两个分类数据集和两个预测数据集。结果表明,GRes2Net具有更好的性能比国家的最先进的方法,从而表明优越性

英文摘要:

Multivariate time series analysis is an important problem in data mining because of its widespread applications. With the increase of time series data available for training, implementing deep neural networks in the field of time series analysis is becoming common. Res2Net, a recently proposed backbone, can further improve the state-of-the-art networks as it improves the multi-scale representation ability through connecting different groups of filters. However, Res2Net ignores the correlations of the feature maps and lacks the control on the information interaction process. To address that problem, in this paper, we propose a backbone convolutional neural network based on the thought of gated mechanism and Res2Net, namely Gated Res2Net (GRes2Net), for multivariate time series analysis. The hierarchical residual-like connections are influenced by gates whose values are calculated based on the original feature maps, the previous output feature maps and the next input feature maps thus considering the correlations between the feature maps more effectively. Through the utilization of gated mechanism, the network can control the process of information sending hence can better capture and utilize the both the temporal information and the correlations between the feature maps. We evaluate the GRes2Net on four multivariate time series datasets including two classification datasets and two forecasting datasets. The results demonstrate that GRes2Net have better performances over the state-of-the-art methods thus indicating the superiority

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。

↑