Rapid trust calibration through interpretable and uncertainty-aware AI
Artificial intelligence (AI) systems hold great promise as decision-support tools, but we must
be able to identify and understand their inevitable mistakes if they are to fulfill this potential …
be able to identify and understand their inevitable mistakes if they are to fulfill this potential …
Towards trustworthy rotating machinery fault diagnosis via attention uncertainty in transformer
To enable researchers to fully trust the decisions made by deep diagnostic models,
interpretable rotating machinery fault diagnosis (RMFD) research has emerged. Existing …
interpretable rotating machinery fault diagnosis (RMFD) research has emerged. Existing …
Out-of-distribution detection-assisted trustworthy machinery fault diagnosis approach with uncertainty-aware deep ensembles
Recent intelligent fault diagnosis technologies can effectively identify the machinery health
condition, while they are learnt based on a closed-world assumption, ie, the training and …
condition, while they are learnt based on a closed-world assumption, ie, the training and …
Towards trustworthy machine fault diagnosis: A probabilistic Bayesian deep learning framework
Fault diagnosis is efficient to improve the safety, reliability, and cost-effectiveness of
industrial machinery. Deep learning has been extensively investigated in fault diagnosis …
industrial machinery. Deep learning has been extensively investigated in fault diagnosis …
Explainable machine learning in image classification models: An uncertainty quantification perspective
X Zhang, FTS Chan, S Mahadevan - Knowledge-Based Systems, 2022 - Elsevier
The poor explainability of deep learning models has hindered their adoption in safety and
quality-critical applications. This paper focuses on image classification models and aims to …
quality-critical applications. This paper focuses on image classification models and aims to …
Uncertainty-aware deep learning for reliable health monitoring in safety-critical energy systems
In recent years, significant advancements in deep learning technology have facilitated the
development of intelligent health monitoring approaches for energy systems. However …
development of intelligent health monitoring approaches for energy systems. However …
Explaining bayesian neural networks
To make advanced learning machines such as Deep Neural Networks (DNNs) more
transparent in decision making, explainable AI (XAI) aims to provide interpretations of DNNs' …
transparent in decision making, explainable AI (XAI) aims to provide interpretations of DNNs' …
[PDF][PDF] 基于不确定性感知网络的可信机械故障诊断
邵海东， 肖一鸣， 邓乾旺， 任颖莹， 韩特 - 机械工程学报, 2024 - qikan.cmes.org
基于深度学习的故障诊断方法受其黑箱特性限制难以给出可信赖和可解释的诊断结果.
现有可解释故障诊断研究多集中在开发可解释模块并嵌入深度学习模型以赋予诊断结果一定 …
现有可解释故障诊断研究多集中在开发可解释模块并嵌入深度学习模型以赋予诊断结果一定 …
E2-MIL: An explainable and evidential multiple instance learning framework for whole slide image classification
Multiple instance learning (MIL)-based methods have been widely adopted to process the
whole slide image (WSI) in the field of computational pathology. Due to the sparse slide …
whole slide image (WSI) in the field of computational pathology. Due to the sparse slide …
A new metric for reliable diagnosis of rotating machines applied to a multi-fault rotor using Bayesian neural networks
O Belli, HF de Castro - Journal of the Brazilian Society of Mechanical …, 2024 - Springer
This paper dedicates itself to filling the gap in reliable data-driven diagnoses through
uncertainty quantification for different rotor fault identifications. Three signal-processing …
uncertainty quantification for different rotor fault identifications. Three signal-processing …