On Design Mining: Coevolution and Surrogate Models

Preen, Richard J.; Bull, Larry

doi:10.1162/artl_a_00225

Cited by 4 publications

(5 citation statements)

References 57 publications

(79 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[0,20]. We adopt the surrogate-assisted preselection approach (and parameter values) previously used successfully to perform physical test-driven optimisation (Preen and Bull, 2017). As benchmark, a steady-state genetic algorithm (GA) with population size P = 20 is used; tournament size T = 3 for both selection and replacement; uniform crossover is performed with X = 80% probability; and a per allele mutation rate µ = 1/N with a uniform random step size s = [−5, 5]%.…”

Section: Methodsmentioning

confidence: 99%

“…In particular, we explore the attached worker migration bias [0,1]; the unattached worker migration bias [0,1]; worker relative adhesion [0,10]; worker relative repulsion [0,10]; worker motility persistence time (minutes) [0,10]; and the cargo release o 2 threshold (mmHg) [0,20]. We adopt the surrogate-assisted preselection approach (and parameter values) previously used successfully to perform physical test-driven optimisation (Preen and Bull, 2017). As benchmark, a steady-state genetic algorithm (GA) with population size P = 20 is used; tournament size T = 3 for both selection and replacement; uniform crossover is performed with X = 80% probability; and a per allele mutation rate µ = 1/N with a uniform random step size s = [−5, 5]%.…”

Section: Methodsmentioning

confidence: 99%

“…Probabilistic models such as GP are perhaps the most widely used surrogate since they provide a measure of confidence that can be used to efficiently select samples for evaluation (Jin et al, 2018). Preen and Bull (2016) showed that with very small and noisy samples there is little difference between the modelling approaches, with MLPs appearing to be a robust approach capable of capturing the underlying structure of the search space.…”

Section: Introductionmentioning

confidence: 99%

“…It may be necessary to restrict the number of samples for use with a computationally complex model such as GP when there is a large archive set (Jin et al, 2018). Additionally, if there are any significant temporal affects, issues surround how best to select the subset for training (Preen and Bull, 2017).…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Towards an evolvable cancer treatment simulator

2019

Self Cite

View full text Add to dashboard Cite

The use of high-fidelity computational simulations promises to enable high-throughput hypothesis testing and optimisation of cancer therapies. However, increasing realism comes at the cost of increasing computational requirements. This article explores the use of surrogate-assisted evolutionary algorithms to optimise the targeted delivery of a therapeutic compound to cancerous tumour cells with the multicellular simulator, PhysiCell. The use of both Gaussian process models and multi-layer perceptron neural network surrogate models are investigated. We find that evolutionary algorithms are able to effectively explore the parameter space of biophysical properties within the agent-based simulations, minimising the resulting number of cancerous cells after a period of simulated treatment. Both model-assisted algorithms are found to outperform a standard evolutionary algorithm, demonstrating their ability to perform a more effective search within the very small evaluation budget. This represents the first use of efficient evolutionary algorithms within a high-throughput multicellular computing approach to find therapeutic design optima that maximise tumour regression. (Richard J. Preen) 1 PhysiCell source code (BSD license): https://github.com/MathCancer/PhysiCell BioSystems https://doi.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Towards an evolvable cancer treatment simulator

2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…Design Mining (DM) uses Artificial Intelligence techniques to iteratively search the attribute space of a physical object evaluated directly through rapid prototyping, which is generally expensive, and commonly surrogate models are used to reduce the physical system sampling [ 9 ]. DM explores the design space evaluating directly through rapid prototyping in systems in which there are no formal models or the computational models are too expensive and imprecise.…”

Section: Introductionmentioning

confidence: 99%

ASAMS: An Adaptive Sequential Sampling and Automatic Model Selection for Artificial Intelligence Surrogate Modeling

Duchanoy

Calvo

Moreno-Armendáriz

2020

Sensors

View full text Add to dashboard Cite

Surrogate Modeling (SM) is often used to reduce the computational burden of time-consuming system simulations. However, continuous advances in Artificial Intelligence (AI) and the spread of embedded sensors have led to the creation of Digital Twins (DT), Design Mining (DM), and Soft Sensors (SS). These methodologies represent a new challenge for the generation of surrogate models since they require the implementation of elaborated artificial intelligence algorithms and minimize the number of physical experiments measured. To reduce the assessment of a physical system, several existing adaptive sequential sampling methodologies have been developed; however, they are limited in most part to the Kriging models and Kriging-model-based Monte Carlo Simulation. In this paper, we integrate a distinct adaptive sampling methodology to an automated machine learning methodology (AutoML) to help in the process of model selection while minimizing the system evaluation and maximizing the system performance for surrogate models based on artificial intelligence algorithms. In each iteration, this framework uses a grid search algorithm to determine the best candidate models and perform a leave-one-out cross-validation to calculate the performance of each sampled point. A Voronoi diagram is applied to partition the sampling region into some local cells, and the Voronoi vertexes are considered as new candidate points. The performance of the sample points is used to estimate the accuracy of the model for a set of candidate points to select those that will improve more the model’s accuracy. Then, the number of candidate models is reduced. Finally, the performance of the framework is tested using two examples to demonstrate the applicability of the proposed method.

show abstract

Design mining microbial fuel cell cascades

et al. 2018

Self Cite

View full text Add to dashboard Cite

Microbial fuel cells (MFCs) perform wastewater treatment and electricity production through the conversion of organic matter using microorganisms. For practical applications, it has been suggested that greater efficiency can be achieved by arranging multiple MFC units into physical stacks in a cascade with feedstock flowing sequentially between units. In this paper, we investigate the use of computational intelligence to physically explore and optimise (potentially) heterogeneous MFC designs in a cascade, i.e. without simulation. Conductive structures are 3-D printed and inserted into the anodic chamber of each MFC unit, augmenting a carbon fibre veil anode and affecting the hydrodynamics, including the feedstock volume and hydraulic retention time, as well as providing unique habitats for microbial colonisation. We show that it is possible to use design mining to identify new conductive inserts that increase both the cascade power output and power density.

show abstract

On Design Mining: Coevolution and Surrogate Models

Cited by 4 publications

References 57 publications

Towards an evolvable cancer treatment simulator

Towards an evolvable cancer treatment simulator

ASAMS: An Adaptive Sequential Sampling and Automatic Model Selection for Artificial Intelligence Surrogate Modeling

Design mining microbial fuel cell cascades

Contact Info

Product

Resources

About