Kevin Burke
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Kevin Burke has a total of 79 co-authors. Here are the top co-authors by number of shared publications:
- Joseph D. O'BRien
MACSI, Department of Mathematics and Statistics, University of Limerick, Limerick V94 T9PX, Ireland
4 shared publications - Lingkai Yang
Research Institute of Mine Artificial Intelligence, Chinese Institute of Coal Science, Beijing 100013, China
4 shared publications - Mark Donnelly
School of Computing, Ulster University, Belfast, UK
4 shared publications - Mark E. Burke
Department of Mathematics and Statistics, University of Limerick, Limerick, Ireland
4 shared publications - Sally McClean
School of Computing, Ulster University, Belfast, U.K.
4 shared publications - Gilbert MacKenzie
Centre of Biostatistics, University of Limerick, Limerick, Ireland
3 shared publications
Latest Publications
- Open Access
- 20 February 2026
- Published by Cambridge University Press (CUP) in Mathematics in Industry Repository
Unlocking the objective of energy efficient steel-making by robust scrap melting with the help of advanced algorithms
Electric Arc Furnace (EAF) steelmaking is critical to the European steel industry, and optimising the process is key to achieving highefficiency, low-cost, and high-quality steel production. However, the current method of determining the optimal bucket charge composition for the EAF is complex and time consuming, and may not take into account the availability of scrap in the scrapyard. This report investigates statistical and mathematical models of the EAF process along with Artificial Intelligence (AI) approaches to classifying images of the scrap in a bucket. Ultimately, this work contributes to improved efficiency, reduced costs, and better quality steel. The outcomes of the work will also contribute to the broader conversation around to the fight against climate change and the European steel industry competitiveness by applying highly innovative methods and technologies to the steel sector.
- 20 February 2026
- Published by Cambridge University Press (CUP) in Mathematics in Industry Repository
Open AccessUnlocking the objective of energy efficient steel-making by robust scrap melting with the help of advanced algorithms
Electric Arc Furnace (EAF) steelmaking is critical to the European steel industry, and optimising the process is key to achieving highefficiency, low-cost, and high-quality steel production. However, the current method of determining the optimal bucket charge composition for the EAF is complex and time consuming, and may not take into account the availability of scrap in the scrapyard. This report investigates statistical and mathematical models of the EAF process along with Artificial Intelligence (AI) approaches to classifying images of the scrap in a bucket. Ultimately, this work contributes to improved efficiency, reduced costs, and better quality steel. The outcomes of the work will also contribute to the broader conversation around to the fight against climate change and the European steel industry competitiveness by applying highly innovative methods and technologies to the steel sector.
- Open Access
- 21 January 2026
- Published by SAGE Publications in Social Psychological and Personality Science
- Vol. 17 (7) , 889-900
Attitude (In)congruence in Group Interactions Predicts Social Identification and Favouritism Behaviour
Addressing widespread polarisation requires understanding how attitudes relate to identification and ingroup favouritism. Two studies employ interactive paradigms to examine whether attitude congruence produces behavioural consequences in addition to identification. In Study 1, participants ( N = 375) responded to four novel attitude statements in groups of five and were randomised to either see the responses of the other participants, or to be blind. Ingroup favouritism was measured by token allocation. In Study 2, N = 413 participants in groups of six observed responses to one of three statements supporting an ethnic group before completing collective action measures. Findings illustrated that observing attitudes in small group contexts can foster identification. Participants demonstrated favouritism to those with whom they aligned on three neutral attitudes (Study 1) and showed greater support for the target group when others’ attitudes aligned (Study 2). This illustrates how identification and intergroup dynamics can emerge in online contexts.
- 21 January 2026
- Published by SAGE Publications in Social Psychological and Personality Science
- Vol. 17 (7) , 889-900
Open AccessAttitude (In)congruence in Group Interactions Predicts Social Identification and Favouritism Behaviour
Addressing widespread polarisation requires understanding how attitudes relate to identification and ingroup favouritism. Two studies employ interactive paradigms to examine whether attitude congruence produces behavioural consequences in addition to identification. In Study 1, participants ( N = 375) responded to four novel attitude statements in groups of five and were randomised to either see the responses of the other participants, or to be blind. Ingroup favouritism was measured by token allocation. In Study 2, N = 413 participants in groups of six observed responses to one of three statements supporting an ethnic group before completing collective action measures. Findings illustrated that observing attitudes in small group contexts can foster identification. Participants demonstrated favouritism to those with whom they aligned on three neutral attitudes (Study 1) and showed greater support for the target group when others’ attitudes aligned (Study 2). This illustrates how identification and intergroup dynamics can emerge in online contexts.
- Open Access
- 2 January 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 309
Comparison of generalised additive models and neural networks in applications: A systematic review
- 2 January 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 309
Open AccessComparison of generalised additive models and neural networks in applications: A systematic review
- 2 January 2026
- Published by Springer Nature
- p. 205-225
Distributional Regression Techniques for Wildlife Management
- 2 January 2026
- Published by Springer Nature
- p. 205-225
Distributional Regression Techniques for Wildlife Management
- Open Access
- 21 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 200537-200554
CNN-Based Approaches for Various Types of Tabular Data
Deep learning (DL) includes various architectures, such as deep neural networks (DNN) and convolutional neural networks (CNN). DL is very powerful and flexible for non-tabular (non-structured) data (e.g. image, text). However, in tabular data, standard DNNs often do not outperform traditional machine learning (ML) methods such as tree-based models (e.g. random forest, XGBoost). CNNs carry out dimensionality reduction for non-tabular (especially image) data, but may be useful in tabular data too. In this paper, we present a reformulation of one-dimensional CNN (1D-CNN)-based approaches for various types of tabular data, which provides an end-to-end learning framework. The predictive performance of the proposed method is evaluated by comparing it with existing ML/DL methods using four types of real tabular data, i.e. a binary response data with high dimensional features, over-dispersed count data, high-dimension survival data, and time-series data with substantial variability.
- 21 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 200537-200554
Open AccessCNN-Based Approaches for Various Types of Tabular Data
Deep learning (DL) includes various architectures, such as deep neural networks (DNN) and convolutional neural networks (CNN). DL is very powerful and flexible for non-tabular (non-structured) data (e.g. image, text). However, in tabular data, standard DNNs often do not outperform traditional machine learning (ML) methods such as tree-based models (e.g. random forest, XGBoost). CNNs carry out dimensionality reduction for non-tabular (especially image) data, but may be useful in tabular data too. In this paper, we present a reformulation of one-dimensional CNN (1D-CNN)-based approaches for various types of tabular data, which provides an end-to-end learning framework. The predictive performance of the proposed method is evaluated by comparing it with existing ML/DL methods using four types of real tabular data, i.e. a binary response data with high dimensional features, over-dispersed count data, high-dimension survival data, and time-series data with substantial variability.
- Open Access
- 18 November 2025
- Published by Wiley in Quality and Reliability Engineering International
- Vol. 42 (2) , 598-612
A General Simulation‐Based Optimisation Framework for Multipoint Constant‐Stress Accelerated Life Tests
Accelerated life testing (ALT) is a method of reducing the lifetime of components through exposure to extreme stress. This method of obtaining lifetime information involves the design of a testing experiment, that is, an accelerated test plan. In this work, we adopt a simulation‐based approach to obtaining optimal test plans for constant‐stress accelerated life tests with multiple design points. Within this simulation framework, we can easily assess a variety of test plans by modifying the number of test stresses (and their levels) and evaluating the allocation of test units. We obtain optimal test plans by utilising the differential evolution (DE) optimisation algorithm, where the inputs to the objective function are the test plan parameters, and the output is the RMSE (root mean squared error) of out‐of‐sample (extrapolated) model predictions. When the life‐stress distribution is correctly specified, we show that the optimal number of stress levels is related to the number of model parameters. In terms of test unit allocation, we show that the proportion of test units is inversely related to the stress level. Our general simulation framework provides an alternative approach to theoretical optimisation, and is particularly favourable for large/complex multipoint test plans where analytical optimisation could prove intractable. Our procedure can be applied to a broad range of experimental scenarios and serves as a useful tool to aid practitioners seeking to maximise component lifetime information through accelerated life testing.
- 18 November 2025
- Published by Wiley in Quality and Reliability Engineering International
- Vol. 42 (2) , 598-612
Open AccessA General Simulation‐Based Optimisation Framework for Multipoint Constant‐Stress Accelerated Life Tests
Accelerated life testing (ALT) is a method of reducing the lifetime of components through exposure to extreme stress. This method of obtaining lifetime information involves the design of a testing experiment, that is, an accelerated test plan. In this work, we adopt a simulation‐based approach to obtaining optimal test plans for constant‐stress accelerated life tests with multiple design points. Within this simulation framework, we can easily assess a variety of test plans by modifying the number of test stresses (and their levels) and evaluating the allocation of test units. We obtain optimal test plans by utilising the differential evolution (DE) optimisation algorithm, where the inputs to the objective function are the test plan parameters, and the output is the RMSE (root mean squared error) of out‐of‐sample (extrapolated) model predictions. When the life‐stress distribution is correctly specified, we show that the optimal number of stress levels is related to the number of model parameters. In terms of test unit allocation, we show that the proportion of test units is inversely related to the stress level. Our general simulation framework provides an alternative approach to theoretical optimisation, and is particularly favourable for large/complex multipoint test plans where analytical optimisation could prove intractable. Our procedure can be applied to a broad range of experimental scenarios and serves as a useful tool to aid practitioners seeking to maximise component lifetime information through accelerated life testing.
- Open Access
- 21 July 2025
- Published by Springer Nature in Data Mining and Knowledge Discovery
- Vol. 39 (5) , 1-35
Automating mixture model fitting of task durations for process conformance checking
Process task duration data often exhibit multiple peaks, indicating differences in, for example, customer ages and preferences, resource capabilities or the day/hour of a week. This heterogeneous data, which captures diverse customer patterns, should be represented using different models, resulting in an overall mixture model. This paper introduces gamma mixture models to represent various customer patterns in task duration data, with a focus on automating the fitting process. The approach involves a two-stage procedure: first, divide-and-conquer using peak-, equidistance- and cluster-based techniques to partition data, and automatically fit gamma distributions to each subset. The second stage then improves the fitted mixture model by directly searching the log-likelihood surface. The method is compared with the expectation–maximization (EM) algorithm and an open tool (HyperStar), using both artificially generated datasets and a publicly available hospital billing dataset, demonstrating its effectiveness and time efficiency in modelling heterogeneous process duration data. Furthermore, a case study on process conformance checking is conducted using the hospital billing dataset, highlighting a potential application area for the method in process mining.
- 21 July 2025
- Published by Springer Nature in Data Mining and Knowledge Discovery
- Vol. 39 (5) , 1-35
Open AccessAutomating mixture model fitting of task durations for process conformance checking
Process task duration data often exhibit multiple peaks, indicating differences in, for example, customer ages and preferences, resource capabilities or the day/hour of a week. This heterogeneous data, which captures diverse customer patterns, should be represented using different models, resulting in an overall mixture model. This paper introduces gamma mixture models to represent various customer patterns in task duration data, with a focus on automating the fitting process. The approach involves a two-stage procedure: first, divide-and-conquer using peak-, equidistance- and cluster-based techniques to partition data, and automatically fit gamma distributions to each subset. The second stage then improves the fitted mixture model by directly searching the log-likelihood surface. The method is compared with the expectation–maximization (EM) algorithm and an open tool (HyperStar), using both artificially generated datasets and a publicly available hospital billing dataset, demonstrating its effectiveness and time efficiency in modelling heterogeneous process duration data. Furthermore, a case study on process conformance checking is conducted using the hospital billing dataset, highlighting a potential application area for the method in process mining.
- Open Access
- 21 August 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 18 (8) , 1-24
Detecting Process Duration Drift Using Gamma Mixture Models in a Left-Truncated and Right-Censored Environment
Within the realm of business context, process duration signifies time spent by customers between successive activities. This temporal perspective offers important insight to customer behavior, highlighting potential bottlenecks, and influencing business management decisions. The distribution of these process duration often changes over time due to factors such as seasonality, emerging legislation, changes to supply chains, and customer demand. Referred to as concept drift, these variations pose challenges for robust process modeling, understanding, and refinement. Subsequently, gamma mixture models are widely employed to model durations. These source data can, however, become left-truncated and right-censored within any specific observation window thereby necessitating a (well-known) modification to the likelihood function. The approach reported in this article leveraged this adapted likelihood across a series of observation windows, applying the likelihood ratio test to identify duration changes/concept drift. Due to its flexibility in modelling any duration distribution, the gamma mixture model was used with Nelder–Mead optimized likelihood for the left-truncated and right-censored data. The number of gamma components was determined by the Bayesian information criterion. The proposed framework underwent validation through simulated exponential samples, leading to recommendations for its practical application. Subsequently, we applied the methodology to three real-life event logs exhibiting diverse characteristics. Experimental results showcase the effectiveness of our approach in terms of data fitting, as compared to Kaplan–Meier curves, and in detecting instances of drift. This comprehensive validation underscores the practical utility and reliability of our framework for dynamic business scenarios.
- 21 August 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 18 (8) , 1-24
Open AccessDetecting Process Duration Drift Using Gamma Mixture Models in a Left-Truncated and Right-Censored Environment
Within the realm of business context, process duration signifies time spent by customers between successive activities. This temporal perspective offers important insight to customer behavior, highlighting potential bottlenecks, and influencing business management decisions. The distribution of these process duration often changes over time due to factors such as seasonality, emerging legislation, changes to supply chains, and customer demand. Referred to as concept drift, these variations pose challenges for robust process modeling, understanding, and refinement. Subsequently, gamma mixture models are widely employed to model durations. These source data can, however, become left-truncated and right-censored within any specific observation window thereby necessitating a (well-known) modification to the likelihood function. The approach reported in this article leveraged this adapted likelihood across a series of observation windows, applying the likelihood ratio test to identify duration changes/concept drift. Due to its flexibility in modelling any duration distribution, the gamma mixture model was used with Nelder–Mead optimized likelihood for the left-truncated and right-censored data. The number of gamma components was determined by the Bayesian information criterion. The proposed framework underwent validation through simulated exponential samples, leading to recommendations for its practical application. Subsequently, we applied the methodology to three real-life event logs exhibiting diverse characteristics. Experimental results showcase the effectiveness of our approach in terms of data fitting, as compared to Kaplan–Meier curves, and in detecting instances of drift. This comprehensive validation underscores the practical utility and reliability of our framework for dynamic business scenarios.
- Open Access
- 24 May 2024
- Published by Taylor & Francis in The American Statistician
- Vol. 78 (4) , 437-449
Binomial Confidence Intervals for Rare Events: Importance of Defining Margin of Error Relative to Magnitude of Proportion
- 24 May 2024
- Published by Taylor & Francis in The American Statistician
- Vol. 78 (4) , 437-449
Open AccessBinomial Confidence Intervals for Rare Events: Importance of Defining Margin of Error Relative to Magnitude of Proportion
- Open Access
A Statistical-Modelling Approach to Feedforward Neural Network Model Selection
Feedforward neural networks (FNNs) can be viewed as non-linear regression models, where covariates enter the model through a combination of weighted summations and non-linear functions. Although these models have some similarities to the approaches used within statistical modelling, the majority of neural network research has been conducted outside of the field of statistics. This has resulted in a lack of statistically-based methodology, and, in particular, there has been little emphasis on model parsimony. Determining the input layer structure is analogous to variable selection, while the structure for the hidden layer relates to model complexity. In practice, neural network model selection is often carried out by comparing models using out-of-sample performance. However, in contrast, the construction of an associated likelihood function opens the door to information-criteria-based variable and architecture selection. A novel model selection method, which performs both input- and hidden-node selection, is proposed using the Bayesian information criterion (BIC) for FNNs. The choice of BIC over out-of-sample performance as the model selection objective function leads to an increased probability of recovering the true model, while parsimoniously achieving favourable out-of-sample performance. Simulation studies are used to evaluate and justify the proposed method, and applications on real data are investigated.
Open AccessA Statistical-Modelling Approach to Feedforward Neural Network Model Selection
Feedforward neural networks (FNNs) can be viewed as non-linear regression models, where covariates enter the model through a combination of weighted summations and non-linear functions. Although these models have some similarities to the approaches used within statistical modelling, the majority of neural network research has been conducted outside of the field of statistics. This has resulted in a lack of statistically-based methodology, and, in particular, there has been little emphasis on model parsimony. Determining the input layer structure is analogous to variable selection, while the structure for the hidden layer relates to model complexity. In practice, neural network model selection is often carried out by comparing models using out-of-sample performance. However, in contrast, the construction of an associated likelihood function opens the door to information-criteria-based variable and architecture selection. A novel model selection method, which performs both input- and hidden-node selection, is proposed using the Bayesian information criterion (BIC) for FNNs. The choice of BIC over out-of-sample performance as the model selection objective function leads to an increased probability of recovering the true model, while parsimoniously achieving favourable out-of-sample performance. Simulation studies are used to evaluate and justify the proposed method, and applications on real data are investigated.