Learning uncertainty with artificial neural networks for predictive process monitoring

Weytjens, Hans; Weerdt, Jochen De

doi:10.1016/j.asoc.2022.109134

Cited by 19 publications

(9 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Aleatoric uncertainty is an irreducible uncertainty that captures the non-deterministic nature of real-world occurrences. Recently, method development acknowledged the existence of both types of uncertainty and incorporated their quantification in its output [317]. Uncertainty quantification can build trust for the prediction method by measuring confidence metrics [337] that accompany probabilistic outputs and improves the subsequent actions, as the user can decide to wait for more certain prediction results that are more likely to occur.…”

Section: Assessment Scheme For Event Prediction Methodsmentioning

confidence: 99%

A Survey on Event Prediction Methods from a Systems Perspective: Bringing Together Disparate Research Areas

Benzin¹,

Rinderle-Ma²

2023

Preprint

View full text Add to dashboard Cite

Event prediction is the ability of anticipating future events, i.e., future real-world occurrences, and aims to support the user in deciding on actions that change future events towards a desired state. An event prediction method learns the relation between features of past events and future events. It is applied to newly observed events to predict corresponding future events that are evaluated with respect to the user's desired future state. If the predicted future events do not comply with this state, actions are taken towards achieving desirable future states. Evidently, event prediction is valuable in many application domains such as business and natural disasters.The diversity of application domains results in a diverse range of methods that are scattered across various research areas which, in turn, use different terminology for event prediction methods. Consequently, sharing methods and knowledge for developing future event prediction methods is restricted. To facilitate knowledge sharing on account of a comprehensive classification, integration, and assessment of event prediction methods, we combine taxonomies and take a systems perspective to integrate event prediction methods into a single system, elicit requirements and assess existing work with respect to the requirements. Based on the assessment, we identify open challenges and discuss future research directions.

show abstract

Section: Assessment Scheme For Event Prediction Methodsmentioning

confidence: 99%

A Survey on Event Prediction Methods from a Systems Perspective: Bringing Together Disparate Research Areas

Benzin¹,

Rinderle-Ma²

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Uncertainty estimation for NNs has been investigated in different domains of OR: predictive maintenance (Kraus & Feuerriegel, 2019), recommender systems (Nahta et al, 2021), finance (Ghahtarani, 2021), stress-level prediction (Oh et al, 2021), transportation (Zhang & Mahadevan, 2020;Feng et al, 2022), predictive process monitoring (Weytjens & De Weerdt, 2022), and educational data mining (Yu et al, 2021). In the available work, however, uncertainty estimates are merely monitored as an additional metric, not used in combination with a human expert such as in classification with rejection (i.e., shortcoming 1).…”

Section: Uncertainty and Neural Network In Operations Researchmentioning

confidence: 99%

Explainability through uncertainty: Trustworthy decision-making with neural networks

Thuy,

Benoit

2024

European Journal of Operational Research

View full text Add to dashboard Cite

“…Effective process monitoring is crucial in ensuring the safe production and product quality [1,2]. In addition, the complexity of process mechanisms and the maturity of data science have also led to the rapid development of data-driven process monitoring methods, especially multivariate statistical * Author to whom any correspondence should be addressed.…”

Section: Introductionmentioning

confidence: 99%

“…Although the above methods can solve the problem of coexistence of multiple characteristics in process data to a certain extent, there are still some problems to be solved: (1) these methods usually only consider two data characteristics, and require prior knowledge to determine the modeling methods in advance. In practical industrial processes, there are usually multiple data characteristics at the same time [25]; (2) in the process of serial feature extraction, the determination of latent variables has an impact on the performance of the model [26];…”

Section: Introductionmentioning

confidence: 99%

A novel monitoring method based on multi-model information extraction and fusion

Li,

Shen,

Tian

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Modern industrial processes are increasingly complex, where multiple characteristics usually coexist in process data. Therefore, traditional monitoring methods based on a single model may ignore other data characteristics and obtain poor monitoring performance. Aiming at this problem, a novel monitoring method based on multi-model information extraction and fusion is proposed in this paper. Firstly, several methods are used to extract different characteristics from process data. For example, principal component analysis, independent component analysis and slow features analysis can be used to extract Gaussian, non-Gaussian and dynamic characteristics respectively. Secondly, features extracted from multiple models are combined into new potential features. Then, Lasso regression models between potential features and process variables are established. In this way, not only are multiple characteristics in process data considered during the reconstruction, but key potential features (KPFs) can be selected for each process variable. The KPFs for each process variable can form a monitoring subspace to enhance the sensitivity for fault detection. Furthermore, cluster analysis is used to reduce the redundancy of monitoring subspaces based on the similarity of each subspace. Process monitoring can be achieved by fusing the monitoring results of finally determined multiple subspaces and residual space. Case studies on three simulation processes and a real industrial process demonstrate the effectiveness and better performance.

show abstract

Learning uncertainty with artificial neural networks for predictive process monitoring

Cited by 19 publications

References 35 publications

A Survey on Event Prediction Methods from a Systems Perspective: Bringing Together Disparate Research Areas

A Survey on Event Prediction Methods from a Systems Perspective: Bringing Together Disparate Research Areas

Explainability through uncertainty: Trustworthy decision-making with neural networks

A novel monitoring method based on multi-model information extraction and fusion

Contact Info

Product

Resources

About