IEEE Trans Neural Netw Learn Syst. 2020 Aug;31(8):2879-2888. doi: 10.1109/TNNLS.2019.2934110. Epub 2019 Sep 4.
This article focuses on a problem important to automatic machine learning: the automatic processing of a nonpreprocessed time series. The convolutional neural network (CNN) is one of the most popular neural network (NN) algorithms for pattern recognition. Seasonal time series with trends are the most common data sets used in forecasting. Both the convolutional layer and the pooling layer of a CNN can be used to extract important features and patterns that reflect the seasonality, trends, and time lag correlation coefficients in the data. The ability to identify such features and patterns makes CNN a good candidate algorithm for analyzing seasonal time-series data with trends. This article reports our experimental findings using a fully connected NN (FNN), a nonpooling CNN (NPCNN), and a CNN to study both simulated and real time-series data with seasonality and trends. We found that convolutional layers tend to improve the performance, while pooling layers tend to introduce too many negative effects. Therefore, we recommend using an NPCNN when processing seasonal time-series data with trends. Moreover, we suggest using the Adam optimizer and selecting either a rectified linear unit (ReLU) function or a linear activation function. Using an NN to analyze seasonal time series with trends has become popular in the NN community. This article provides an approach for building a network that fits time-series data with seasonality and trends automatically.
对未经预处理的时间序列的自动处理。卷积神经网络（CNN）是用于模式识别的最流行的神经网络（NN）算法之一。具有趋势的季节性时间序列是预测中最常用的数据集。CNN 的卷积层和池化层都可用于提取反映数据季节性、趋势和时间滞后相关系数的重要特征和模式。识别这些特征和模式的能力使得 CNN 成为分析具有趋势的季节性时间序列数据的优秀候选算法。本文报告了使用全连接神经网络（FNN）、非池化 CNN（NPCNN）和 CNN 对具有季节性和趋势的模拟和真实时间序列数据进行研究的实验结果。我们发现卷积层往往会提高性能，而池化层往往会带来太多负面影响。因此，我们建议在处理具有趋势的季节性时间序列数据时使用 NPCNN。此外，我们建议使用 Adam 优化器，并选择修正线性单元（ReLU）函数或线性激活函数。使用 NN 分析具有趋势的季节性时间序列在 NN 社区中已经很流行。本文提供了一种自动构建适合季节性和趋势时间序列的网络的方法。
