Richard John Preen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Richard John Preen has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
Larry Bull
Department of Computer Science and Creative Technologies, University of the West of England, Bristol BS16 1QY, UK
10 shared publications- Larry Bull
University of the West of England, Computer Science Research Centre
9 shared publications - Jim Smith
School of Computing and Creative Technologies, University of the West of England, UK
4 shared publications - Ioannis Ieropoulos
Water & Environmental Engineering Group, School of Engineering, University of Southampton, Bolderwood Campus, SO16 7QF, UK
2 shared publications - Jiseon You
Bristol BioEnergy Centre (BBiC), Bristol Robotics Laboratory, T Block, Frenchay Campus, University of the West of England, Bristol BS16 1QY, UK
2 shared publications - Alba Crespi Boixander
School of Medicine Dept. of Mathematical Sciences https://github.com/AI University of Dundee University of Durham NHS National Services Scotland SDC/AI-SDC
1 shared publication
Latest Publications
- Open Access
- 1 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Privacy
- Vol. 2, 55-66
A Multi-Language Toolkit for the Semi-Automated Checking of Research Outputs
This article presents a free and open source toolkit that supports the semi-automated checking of research outputs (SACRO) for privacy disclosure within secure data environments. SACRO is a framework that applies best-practice principles-based statistical disclosure control (SDC) techniques on-the-fly as researchers conduct their analyses. SACRO is designed to assist human checkers rather than seeking to replace them as with current automated rules-based approaches. The toolkit is composed of a lightweight Python package that sits over well-known analysis tools that produce outputs such as tables, plots, and statistical models. This package adds functionality to (i) automatically identify potentially disclosive outputs against a range of commonly used disclosure tests; (ii) apply optional disclosure mitigation strategies as requested; (iii) report reasons for applying SDC; and (iv) produce simple summary documents trusted research environment staff can use to streamline their workflow and maintain auditable records. This creates an explicit change in the dynamics so that SDC is something done with researchers rather than to them, and enables more efficient communication with checkers. A graphical user interface supports human checkers by displaying the requested output and results of the checks in an immediately accessible format, highlighting identified issues, potential mitigation options, and tracking decisions made. The major analytical programming languages used by researchers (Python, R, and Stata) are supported by providing front-end packages that interface with the core Python back-end. Source code, packages, and documentation are available under MIT license at https://github.com/AI-SDC/ACRO
- 1 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Privacy
- Vol. 2, 55-66
Open AccessA Multi-Language Toolkit for the Semi-Automated Checking of Research Outputs
This article presents a free and open source toolkit that supports the semi-automated checking of research outputs (SACRO) for privacy disclosure within secure data environments. SACRO is a framework that applies best-practice principles-based statistical disclosure control (SDC) techniques on-the-fly as researchers conduct their analyses. SACRO is designed to assist human checkers rather than seeking to replace them as with current automated rules-based approaches. The toolkit is composed of a lightweight Python package that sits over well-known analysis tools that produce outputs such as tables, plots, and statistical models. This package adds functionality to (i) automatically identify potentially disclosive outputs against a range of commonly used disclosure tests; (ii) apply optional disclosure mitigation strategies as requested; (iii) report reasons for applying SDC; and (iv) produce simple summary documents trusted research environment staff can use to streamline their workflow and maintain auditable records. This creates an explicit change in the dynamics so that SDC is something done with researchers rather than to them, and enables more efficient communication with checkers. A graphical user interface supports human checkers by displaying the requested output and results of the checks in an immediately accessible format, highlighting identified issues, potential mitigation options, and tracking decisions made. The major analytical programming languages used by researchers (Python, R, and Stata) are supported by providing front-end packages that interface with the core Python back-end. Source code, packages, and documentation are available under MIT license at https://github.com/AI-SDC/ACRO
- 1 December 2023
- Published by The R Foundation
acro: A Tool for Semi-Automating the Statistical Disclosure Control of Research Outputs
- 1 December 2023
- Published by The R Foundation
acro: A Tool for Semi-Automating the Statistical Disclosure Control of Research Outputs
- Open Access
Safe machine learning model release from Trusted Research Environments: The AI-SDC package
We present AI-SDC, an integrated suite of open source Python tools to facilitate Statistical Disclosure Control (SDC) of Machine Learning (ML) models trained on confidential data prior to public release. AI-SDC combines (i) a SafeModel package that extends commonly used ML models to provide ante-hoc SDC by assessing the vulnerability of disclosure posed by the training regime; and (ii) an Attacks package that provides post-hoc SDC by rigorously assessing the empirical disclosure risk of a model through a variety of simulated attacks after training. The AI-SDC code and documentation are available under an MIT license at https://github.com/AI-SDC/AI-SDC.
Open AccessSafe machine learning model release from Trusted Research Environments: The AI-SDC package
We present AI-SDC, an integrated suite of open source Python tools to facilitate Statistical Disclosure Control (SDC) of Machine Learning (ML) models trained on confidential data prior to public release. AI-SDC combines (i) a SafeModel package that extends commonly used ML models to provide ante-hoc SDC by assessing the vulnerability of disclosure posed by the training regime; and (ii) an Attacks package that provides post-hoc SDC by rigorously assessing the empirical disclosure risk of a model through a variety of simulated attacks after training. The AI-SDC code and documentation are available under an MIT license at https://github.com/AI-SDC/AI-SDC.
- 11 May 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Evolutionary Computation
- Vol. 25 (6) , 1079-1090
Autoencoding With a Classifier System
Autoencoders are data-specific compression algorithms learned automatically from examples. The predominant approach has been to construct single large global models that cover the domain. However, training and evaluating models of increasing size comes at the price of additional time and computational cost. Conditional computation, sparsity, and model pruning techniques can reduce these costs while maintaining performance. Learning classifier systems (LCS) are a framework for adaptively subdividing input spaces into an ensemble of simpler local approximations that together cover the domain. LCS perform conditional computation through the use of a population of individual gating/guarding components, each associated with a local approximation. This article explores the use of an LCS to adaptively decompose the input domain into a collection of small autoencoders where local solutions of different complexity may emerge. In addition to benefits in convergence time and computational cost, it is shown possible to reduce code size as well as the resulting decoder computational cost when compared with the global model equivalent.
- 11 May 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Evolutionary Computation
- Vol. 25 (6) , 1079-1090
Autoencoding With a Classifier System
Autoencoders are data-specific compression algorithms learned automatically from examples. The predominant approach has been to construct single large global models that cover the domain. However, training and evaluating models of increasing size comes at the price of additional time and computational cost. Conditional computation, sparsity, and model pruning techniques can reduce these costs while maintaining performance. Learning classifier systems (LCS) are a framework for adaptively subdividing input spaces into an ensemble of simpler local approximations that together cover the domain. LCS perform conditional computation through the use of a population of individual gating/guarding components, each associated with a local approximation. This article explores the use of an LCS to adaptively decompose the input domain into a collection of small autoencoders where local solutions of different complexity may emerge. In addition to benefits in convergence time and computational cost, it is shown possible to reduce code size as well as the resulting decoder computational cost when compared with the global model equivalent.
- Open Access
Deep Learning with a Classifier System: Initial Results
This article presents the first results from using a learning classifier system capable of performing adaptive computation with deep neural networks. Individual classifiers within the population are composed of two neural networks. The first acts as a gating or guarding component, which enables the conditional computation of an associated deep neural network on a per instance basis. Self-adaptive mutation is applied upon reproduction and prediction networks are refined with stochastic gradient descent during lifetime learning. The use of fully-connected and convolutional layers are evaluated on handwritten digit recognition tasks where evolution adapts (i) the gradient descent learning rate applied to each layer (ii) the number of units within each layer, i.e., the number of fully-connected neurons and the number of convolutional kernel filters (iii) the connectivity of each layer, i.e., whether each weight is active (iv) the weight magnitudes, enabling escape from local optima. The system automatically reduces the number of weights and units while maintaining performance after achieving a maximum prediction error.
Open AccessDeep Learning with a Classifier System: Initial Results
This article presents the first results from using a learning classifier system capable of performing adaptive computation with deep neural networks. Individual classifiers within the population are composed of two neural networks. The first acts as a gating or guarding component, which enables the conditional computation of an associated deep neural network on a per instance basis. Self-adaptive mutation is applied upon reproduction and prediction networks are refined with stochastic gradient descent during lifetime learning. The use of fully-connected and convolutional layers are evaluated on handwritten digit recognition tasks where evolution adapts (i) the gradient descent learning rate applied to each layer (ii) the number of units within each layer, i.e., the number of fully-connected neurons and the number of convolutional kernel filters (iii) the connectivity of each layer, i.e., whether each weight is active (iv) the weight magnitudes, enabling escape from local optima. The system automatically reduces the number of weights and units while maintaining performance after achieving a maximum prediction error.
- 1 August 2019
- Published by Elsevier in BioSystems
- Vol. 182, 1-7
Towards an evolvable cancer treatment simulator
- 1 August 2019
- Published by Elsevier in BioSystems
- Vol. 182, 1-7
Towards an evolvable cancer treatment simulator
- Open Access
- 4 February 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Evolutionary Computation
- Vol. 23 (6) , 962-971
Evolutionary $n$ -Level Hypergraph Partitioning With Adaptive CoarseningHypergraph partitioning is an NP-hard problem that occurs in many computer science applications where it is necessary to reduce large problems into a number of smaller, computationally tractable sub-problems. Current techniques use a multilevel approach wherein an initial partitioning is performed after compressing the hypergraph to a predetermined level. This level is typically chosen to produce very coarse hypergraphs in which heuristic algorithms are fast and effective. This article presents a novel memetic algorithm which remains effective on larger initial hypergraphs. This enables the exploitation of information that can be lost during coarsening and results in improved final solution quality. We use this algorithm to present an empirical analysis of the space of possible initial hypergraphs in terms of its searchability at different levels of coarsening. We find that the best results arise at coarsening levels unique to each hypergraph. Based on this, we introduce an adaptive scheme that stops coarsening when the rate of information loss in a hypergraph becomes non-linear and show that this produces further improvements. The results show that we have identified a valuable role for evolutionary algorithms within the current state-of-the-art hypergraph partitioning framework.
- 4 February 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Evolutionary Computation
- Vol. 23 (6) , 962-971
Open AccessEvolutionary $n$ -Level Hypergraph Partitioning With Adaptive CoarseningHypergraph partitioning is an NP-hard problem that occurs in many computer science applications where it is necessary to reduce large problems into a number of smaller, computationally tractable sub-problems. Current techniques use a multilevel approach wherein an initial partitioning is performed after compressing the hypergraph to a predetermined level. This level is typically chosen to produce very coarse hypergraphs in which heuristic algorithms are fast and effective. This article presents a novel memetic algorithm which remains effective on larger initial hypergraphs. This enables the exploitation of information that can be lost during coarsening and results in improved final solution quality. We use this algorithm to present an empirical analysis of the space of possible initial hypergraphs in terms of its searchability at different levels of coarsening. We find that the best results arise at coarsening levels unique to each hypergraph. Based on this, we introduce an adaptive scheme that stops coarsening when the rate of information loss in a hypergraph becomes non-linear and show that this produces further improvements. The results show that we have identified a valuable role for evolutionary algorithms within the current state-of-the-art hypergraph partitioning framework.
- Open Access
- 7 March 2018
- Published by Springer Nature in Soft Computing
- Vol. 23 (13) , 4673-4683
Design mining microbial fuel cell cascades
- 7 March 2018
- Published by Springer Nature in Soft Computing
- Vol. 23 (13) , 4673-4683
Open AccessDesign mining microbial fuel cell cascades
- Open Access
- 1 May 2017
- Published by MIT Press in Artificial Life
- Vol. 23 (2) , 186-205
On Design Mining: Coevolution and Surrogate Models
Design mining is the use of computational intelligence techniques to iteratively search and model the attribute space of physical objects evaluated directly through rapid prototyping to meet given objectives. It enables the exploitation of novel materials and processes without formal models or complex simulation. In this article, we focus upon the coevolutionary nature of the design process when it is decomposed into concurrent sub-design-threads due to the overall complexity of the task. Using an abstract, tunable model of coevolution, we consider strategies to sample subthread designs for whole-system testing and how best to construct and use surrogate models within the coevolutionary scenario. Drawing on our findings, we then describe the effective design of an array of six heterogeneous vertical-axis wind turbines.
- 1 May 2017
- Published by MIT Press in Artificial Life
- Vol. 23 (2) , 186-205
Open AccessOn Design Mining: Coevolution and Surrogate Models
Design mining is the use of computational intelligence techniques to iteratively search and model the attribute space of physical objects evaluated directly through rapid prototyping to meet given objectives. It enables the exploitation of novel materials and processes without formal models or complex simulation. In this article, we focus upon the coevolutionary nature of the design process when it is decomposed into concurrent sub-design-threads due to the overall complexity of the task. Using an abstract, tunable model of coevolution, we consider strategies to sample subthread designs for whole-system testing and how best to construct and use surrogate models within the coevolutionary scenario. Drawing on our findings, we then describe the effective design of an array of six heterogeneous vertical-axis wind turbines.
- Open Access
- 1 February 2017
- Published by Elsevier in Sustainable Energy Technologies and Assessments
- Vol. 19, 94-101
3D printed components of microbial fuel cells: Towards monolithic microbial fuel cell fabrication using additive layer manufacturing
- 1 February 2017
- Published by Elsevier in Sustainable Energy Technologies and Assessments
- Vol. 19, 94-101
Open Access3D printed components of microbial fuel cells: Towards monolithic microbial fuel cell fabrication using additive layer manufacturing