基于改进VAE的时间序列数据增强方法  

A Time Series Data Enhancement Method Based on Improved VAE

作　　者：范振杰 罗娜[1] FAN Zhenjie;LUO Na(Key Laboratory of Smart Manufacturing in Energy Chemical Process,Ministry of Education,East China University of Science and Technology,Shanghai 200237,China)

机构地区：[1]华东理工大学能源化工过程智能制造教育部重点实验室,上海200237

出　　处：《华东理工大学学报（自然科学版）》2024年第3期400-410,共11页Journal of East China University of Science and Technology

基　　金：杭州市萧山区2022年高层次人才创业创新“5213”计划项目。

摘　　要：基于数据驱动的时间序列预测模型通常需要大量的训练数据,当数据量不足时将导致建模的准确性下降。本文针对时间序列预测中的小样本问题,提出了一种基于改进变分自编码器(Variational Auto-Encoder,VAE)的时间序列数据增强方法,旨在生成和原始数据不同但分布相似的虚拟数据。通过在编码网络中引入多头自注意力机制挖掘原始数据深层特征,为解码网络生成数据时提供全面的特征信息;引入残差连接避免模型出现梯度消失的问题。由于时间序列数据具有趋势与周期性,故在解码网络中引入趋势组件和季节性组件,以准确表示原始数据的时间特性,并且为数据的生成过程赋予时间上的可解释性。为了验证本文方法的有效性,和当前常用的时序数据增强方法进行比较,实验结果表明,该方法在虚拟样本的生成和时间序列回归预测上均具有较好表现。Data-driven time series prediction models usually require a large amount of training data,and the accuracy of modeling will decline when the amount of data is insufficient.Aiming at the problem of few shot in time series prediction,this paper proposed a method to enhance time series data based on the improved Variational Auto-Encoder(VAE),which aims to generate virtual data different from the original data but similar in distribution.The Multi-head self-attention mechanism was introduced into the coding network to mine the deep features of the original data and provide comprehensive feature information for the decoding network to generate data.The residual connection was introduced to avoid the problem of disappearing gradient.Due to the trend and periodicity of time series data,the trend component and seasonal component were introduced into the decoding network to accurately represent the time characteristics of original data,and to endow the generation process of data with time interpretability.In order to verify the effectiveness of the proposed method,the experimental comparison was made with the current commonly used time series data enhancement methods.The experimental results showed that the proposed method had good performance in virtual sample generation and time series regression prediction.

关 键 词：小样本 数据增强 时间序列数据 VAE 可解释性 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]