4.7 Article

Adversarial Recurrent Time Series Imputation

出版社

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TNNLS.2020.3010524

关键词

Time series analysis; Gallium nitride; Task analysis; Correlation; Generative adversarial networks; Data models; Estimation; Generative adversarial learning; missing data imputation; time series analysis

向作者/读者索取更多资源

In this article, a generative adversarial learning framework for time series imputation is proposed, which leverages the idea of conditional generative adversarial networks. The generator G, based on a modified bidirectional RNN structure, aims to generate missing values by utilizing temporal and nontemporal information extracted from the observed time series. The discriminator D is designed to differentiate between generated and real values in order to assist the generator in producing more authentic imputation results. Experimental results demonstrate significant improvements compared to state-of-the-art baseline models on various real-world time series datasets.
For the real-world time series analysis, data missing is a ubiquitously existing problem due to anomalies during data collecting and storage. If not treated properly, this problem will seriously hinder the classification, regression, or related tasks. Existing methods for time series imputation either impose too strong assumptions on the distribution of missing data or cannot fully exploit, even simply ignore, the informative temporal dependencies and feature correlations across different time steps. In this article, inspired by the idea of conditional generative adversarial networks, we propose a generative adversarial learning framework for time series imputation under the condition of observed data (as well as the labels, if possible). In our model, we employ a modified bidirectional RNN structure as the generator G, which is aimed at generating the missing values by taking advantage of the temporal and nontemporal information extracted from the observed time series. The discriminator D is designed to distinguish whether each value in a time series is generated or not so that it can help the generator to make an adjustment toward a more authentic imputation result. For an empirical verification of our model, we conduct imputation and classification experiments on several real-world time series data sets. The experimental results show an eminent improvement compared with state-of-the-art baseline models.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.7
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据