Supervised Variational Autoencoders for Soft Sensor Modeling With Missing Data

Autoencoder (AE) is a deep neural network that has been widely utilized in process industry owing to its superior abilities of feature extraction and data reconstruction. Recently, assuming the latent variables to be random variables, a probabilistic variant of it called variational autoencoder (VAE...

Full description

Saved in:

Bibliographic Details
Published in:	IEEE transactions on industrial informatics Vol. 16; no. 4; pp. 2820 - 2828
Main Authors:	Xie, Ruimin, Jan, Nabil Magbool, Hao, Kuangrong, Chen, Lei, Huang, Biao
Format:	Journal Article
Language:	English
Published:	Piscataway IEEE 01.04.2020 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:	Artificial neural networks Coders Data models Decoding Feature extraction Industries Melt viscosity index (MVI) Missing data modified unsupervised DVAE (MUDVAE) Neural networks Probabilistic logic Process control Random variables Reconstruction Sensors soft sensor frameworks supervised deep VAE (SDVAE) variationan autoencoder (VAE)
ISSN:	1551-3203, 1941-0050
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Be the first to leave a comment!