.png){kind=icon}
返回
MAGAN: A masked autoencoder generative adversarial network for processing missing IoT sequence data
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patrec.2020.07.025.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Missing sequence data prevent local data from reflecting the overall distribution of a sample, hindering data analysis. The problem of missing data during actual production is a serious issue and results in a high defect rate, low dimensionality, and high noise level. In this study, a Masked Generative Adversarial Network (MAGAN) model is proposed that is less affected by the data loss rate than a baseline comparison model, and at an 80% missing data rate, the model can still better reflect the distribution of real data. MAGAN shows better results than a traditional processing method for dealing with missing data. (C) 2020 Elsevier B.V. All rights reserved.
Keyword:
Missing data
Time series data
Sensor data
GAN
Deep learning
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3.3
论文数:
8.0K
被引数:
1.6W
机构
引用论文
.png){kind=icon}
Multiple imputation of missing values was not necessary before performing a longitudinal mixed-model analysis在执行纵向混合模型分析之前，不需要对缺失值进行多重插补
PREAI
分享收藏
Chemical synthesis and structural characterization of the substitution compound LaFe1−Cu O3 (x= 0–0.40)取代化合物LaFe1-cu O3 (x = 0-0.40) 的化学合成与结构表征
PREAI
分享收藏 没有更多内容
没有更多内容