ENBIS-26 Conference

Session

AI: Machine Learning and Predictive Analytics

Sep 7, 2026, 10:55 AM

Centro Didattico Morgagni

Conveners

AI: Machine Learning and Predictive Analytics

• Nicolas Bousquet (EDF)

AI: Machine Learning and Predictive Analytics

• Francesca Bassi (University of Padova)

AI: Machine Learning and Predictive Analytics

• Riccardo Ceccato (University of Padova)

AI: Machine Learning and Predictive Analytics

• Morten Bormann Nielsen (Danish Technological Institute)

22. Data-Efficient Upscaling and Optimal Control of Fed-Batch Bioprocesses via Hybrid Modelling and Transfer Learning

Luca Riezzo (The University of Manchester)

9/7/26, 10:55 AM

AI: Machine Learning and Predictive Analytics

Optimisation and control of industrial fed-batch bioprocesses remains a complex and resource intensive task. Process development from laboratory to manufacturing scale requires extensive experimental trials to characterise system behaviour and identify optimal conditions, incurring significant costs. While advanced process control (APC) technologies have been widely applied to industry, their...

39. Local Constrained Bayesian Optimization for High-Dimensional Industrial Design

Jingzhe Jing (Academy of Mathematics and Systems Science, Chinese Academy of Sciences)

9/7/26, 11:15 AM

AI: Machine Learning and Predictive Analytics

Bayesian optimization (BO) has become a cornerstone methodology for the data-efficient tuning of expensive black-box systems encountered throughout business and industrial practice, ranging from chemical process design and structural engineering to controller calibration and the configuration of large-scale machine learning pipelines. In most of these applications, the objective must be...

122. Extending Inverse Distance-based Exploration for Active Learning to Streaming: Online Active Learning for Regression

Bernhard Spangl (BOKU University, Vienna)

9/7/26, 11:35 AM

AI: Machine Learning and Predictive Analytics

In statistical and machine learning, efficient data acquisition is pivotal to model performance, particularly when labeled data are costly or time-intensive to obtain. This motivates active learning, in which the learning algorithm selectively queries maximally informative data points to accelerate training and improve predictive efficiency. While many active learning strategies consider query...

28. Belief Propagation for Early Sequential Feature Selection in Manufacturing

Joana Martins (University of Aveiro)

9/9/26, 9:30 AM

AI: Machine Learning and Predictive Analytics

Early sequential feature selection is crucial in manufacturing environments with heterogeneous sensors and tightly coupled process variables. In shop-floor applications, predicting End-of-Line test failures using data collected as early as possible is vital to enable timely corrective actions. However, classical feature selection and Explainable Artificial Intelligence methods (e.g., SHAP)...

27. Decision Reliability in Uplift Modeling: A Stability- and Value-Driven Framework for Customer Retention Policy Selection

Prof. Massimo Pacella (Department of Engineering for Innovation, Università del Salento- Lecce, ITALY)

9/9/26, 9:50 AM

AI: Machine Learning and Predictive Analytics

A stability-aware, value-driven framework for uplift policy selection is presented, applied to a telecommunications churn-retention dataset. The central argument is that reliable deployment of an uplift model requires more than optimizing a causal ranking metric: the targeted customer set must remain consistent across repeated training runs, and the selected policy must be economically sound...

64. Wrapper-Based Variable Selection for Interacting Variables in Manufacturing

Marcus Engsig (Technical University of Denmark)

9/9/26, 10:10 AM

AI: Machine Learning and Predictive Analytics

In manufacturing, identifying variables that influence process outcomes is essential for control and optimization. While wrapper-based variable selection methods, such as Conditional Boruta by Rotari and Kulahci(2025), has been proposed, they remain susceptible to rejecting variables that only influence the outcome through interactions with other variables. Therefore, the purpose of the...

61. A Two-Dimensional View of Classification Difficulty: Local Ambiguity and Global Separability

Dr Yariv N. Marmor (BRAUDE - College of Engineering, Karmiel)

9/9/26, 10:55 AM

AI: Machine Learning and Predictive Analytics

Classification performance is typically assessed empirically, yet its dependence on intrinsic data characteristics is not fully understood. In this study, we examine classification difficulty through two complementary dimensions: local class ambiguity measured in terms of instance hardness and global class separability captured by Silhouette score.
We generated synthetic datasets based on the...

31. Ranking Sets of Variables by Multivariate Association: a Non Parametric Combination Approach

Elena Barzizza (University of Padova)

9/9/26, 11:15 AM

AI: Machine Learning and Predictive Analytics

In many applied contexts, organizations need to evaluate and compare sets of explanatory variables in terms of their association with a Key Performance Indicator (KPI) of interest. This problem frequently arises in industrial and marketing applications, where companies seek to identify which groups of product characteristics or drivers are most strongly related to outcomes such as customer...

98. A two-layer model for opinion spread in hypergraphs as a Markov chain and as the object of machine learning methods

András Zempléni (Eötvös Loránd University, Budapest)

9/9/26, 11:35 AM

AI: Machine Learning and Predictive Analytics

In studies of opinion spread, peer pressure is often modeled through interactions of more than two individuals (higher-order interactions). We introduce a two-layer random hypergraph model, in which households and workplaces form the layers and hyperedges represent individual households and workplaces. Within this structure, individuals may react when their opinion is in the minority within...

115. Semi-Supervised PARAFAC2 Decomposition for Computational Phenotyping Using Electronic Health Records

Mostafa Reisi Gahrooei (University of Florida)

9/9/26, 2:30 PM

AI: Machine Learning and Predictive Analytics

Computational phenotyping uses data mining methods to extract clusters of clinical descriptors, known as phenotypes, from electronic health records (EHR). Tensor factorization methods are very effective in extracting meaningful patterns and have become popular in computational phenotyping. Nevertheless, these techniques mainly focus on regular tensors and are used in a fully unsupervised...

110. Sustainable specialty chemical design through multi-objective latent-variable model inversion

Prof. Pierantonio Facco (University of Padova)

9/9/26, 2:50 PM

AI: Machine Learning and Predictive Analytics

Product formulation in the specialty chemicals industry requires balancing product quality, cost, and environmental impact. This work proposes a data-driven framework for sustainable formulation design based on latent-variable model inversion combined with multi-objective optimization. Partial Least Squares (PLS) models are built to relate raw-material properties and compositions to product...

133. Predictive Maintenance to Reduce the Total Cost of Ownership of Oil and Gas Downhole Tools

Mahmoud Awad (American University of Sharjah)

9/9/26, 3:10 PM

AI: Machine Learning and Predictive Analytics

Downhole oil and gas tools are used to conduct measurement and acquire samples for oil reserves estimation. Current tools are exhibiting failures in the field. We propose the use of predictive maintenance (PdM) to avoid or mitigate the risk of failures and decrease the total cost of ownership of coring tools. Each tool will go through a surface screening test were data is collected and...