计算机科学与探索 ›› 2019, Vol. 13 ›› Issue (6): 916-927.DOI: 10.3778/j.issn.1673-9418.1812059

• 学术研究 • 上一篇    下一篇

采用CNN和Bidirectional GRU的时间序列分类研究

张国豪,刘  波+   

  1. 暨南大学 信息科学技术学院,广州 510632
  • 出版日期:2019-06-01 发布日期:2019-06-14

Research on Time Series Classification Using CNN and Bidirectional GRU

ZHANG Guohao, LIU Bo+   

  1. College of Information Science and Technology, Jinan University, Guangzhou 510632, China
  • Online:2019-06-01 Published:2019-06-14

摘要: 时间序列数据具有非离散性、数据之间的时序相关性、特征空间维度大等特点,当前大多数分类方法需要经过复杂的数据处理或特征工程,未考虑到时间序列具有不同时间尺度特征以及序列数据之间的时序依赖。通过结合卷积神经网络和循环神经网络中的双向门控循环单元,提出了一个新的端对端深度学习神经网络模型BiGRU-FCN,不需要对数据进行复杂的预处理,并且通过不同的网络运算来获取多种特征信息,如卷积神经网络在时序信息上的空间特征以及双向循环神经网络在序列上的双向时序依赖特征,对单维时间序列进行分类。在大量的基准数据集上对模型进行实验与评估,实验结果表明,与现有的多种方法相比,所提出的模型具有更高的准确率,具有很好的分类效果。

关键词: 时间序列分类, 深度学习, 卷积神经网络, 循环神经网络, 双向门控循环单元

Abstract: Time series data have the characteristics of non-discreteness, correlation between data and large feature space dimensions. Most current classification methods require complex data processing or feature engineering, which don??t take into account different time scale features and the timing dependencies between sequence data. In this paper, a new end-to-end deep learning neural network model named BiGRU-FCN is proposed by combining convolutional neural network and bidirectional gated recurrent unit of recurrent neural network. It does not require complex preprocessing of data. A plurality of features can be obtained through different networks operations, such as the spatial characteristics of convolutional neural networks on time series information and the bidirectional time-dependent characteristics of bidirectional recurrent neural networks in sequence, which can be used to classify the univariate time series data. The model is tested and evaluated on a large number of benchmark datasets. The experimental results show that the proposed model has higher accuracy than the existing methods and has preferable ability of classification.

Key words: time series classification, deep learning, convolutional neural network, recurrent neural network, bidirectional gated recurrent unit