[HTML][HTML] Latent variable models in the era of industrial big data: Extension and beyond

X Kong, X Jiang, B Zhang, J Yuan, Z Ge - Annual Reviews in Control, 2022 - Elsevier
A rich supply of data and innovative algorithms have made data-driven modeling a popular
technique in modern industry. Among various data-driven methods, latent variable models …

When deep learning-based soft sensors encounter reliability challenges: a practical knowledge-guided adversarial attack and its defense

R Guo, H Liu, D Liu - IEEE Transactions on Industrial …, 2023 - ieeexplore.ieee.org
Deep learning-based soft sensors (DLSSs) have been demonstrated to exhibit significantly
improved sensing accuracy; however, their vulnerability to adversarial attacks affects their …

Evasion Attack and Defense On Machine Learning Models in Cyber-Physical Systems: A Survey

S Wang, RKL Ko, G Bai, N Dong… - … Surveys & Tutorials, 2023 - ieeexplore.ieee.org
Cyber-physical systems (CPS) are increasingly relying on machine learning (ML)
techniques to reduce labor costs and improve efficiency. However, the adoption of ML also …

A self-interpretable soft sensor based on deep learning and multiple attention mechanism: From data selection to sensor modeling

R Guo, H Liu, G **e, Y Zhang… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
For deep learning-based soft sensors, the lack of interpretability and the consequent
unreliability has become one of the most important problems. In this article, a neural network …

Cloud-fog automation: Vision, enabling technologies, and future research directions

J **, K Yu, J Kua, N Zhang, Z Pang… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
The Industry 4.0 digital transformation envisages future industrial systems to be fully
automated, including the control, upgrade, and configuration processes of a large number of …

Deep PLS: A lightweight deep learning model for interpretable and efficient data analytics

X Kong, Z Ge - IEEE transactions on neural networks and …, 2022 - ieeexplore.ieee.org
The salient progress of deep learning is accompanied by nonnegligible deficiencies, such
as: 1) interpretability problem; 2) requirement for large data amounts; 3) hard to design and …

Adversarial attacks for neural network based industrial soft sensors: Mirror output attack and translation mirror output attack

L Chen, QX Zhu, YL He - IEEE Transactions on Industrial …, 2023 - ieeexplore.ieee.org
Soft sensing using the neural network technique has been increasingly applied to industrial
processes. Recently, the security and robustness of neural network-based soft sensors have …

Neural network weight comparison for industrial causality discovering and its soft sensing application

Y He, X Kong, L Yao, Z Ge - IEEE Transactions on Industrial …, 2022 - ieeexplore.ieee.org
Due to the complex reaction mechanisms of industrial process units, causality and
correlations exist between industrial process variables. Causal discovery algorithms have …

Adversarial Attacks on Regression Systems via Gradient Optimization

X Kong, Z Ge - IEEE Transactions on Systems, Man, and …, 2023 - ieeexplore.ieee.org
Adversarial attack can fabricate imperceptible fake samples to cheat a well-trained artificial
intelligence (AI) model, and it has shown strong destructive power in many classification …

A zero-shot soft sensor modeling approach using adversarial learning for robustness against sensor fault

ZY Ding, JY Loo, SG Nurzaman, CP Tan… - IEEE Transactions …, 2022 - ieeexplore.ieee.org
Soft sensors are widely used in many industrial systems to monitor key variables that are
difficult to measure, using measurements from other available physical sensors. Because …