Algorithms for Triggering General Regression Neural Network

Kowalski, Piotr; Kusy, Maciej

doi:10.1007/978-3-030-74970-5_20

Cited by 1 publication

(1 citation statement)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A hold-out method of selecting the optimal value of σ was proposed in [22]. In [32], a plug-in algorithm and a cross-validation procedure based on traditional mathematical methods, including the theory of kernel density estimators, as well as a nature-inspired optimisation approach known as the particle swarm optimisation method, is described. Article [33] presents an extensive review of the research conducted on the optimisation of ANNs, including GRNNs, through genetic algorithms of artificial intelligence searches.…”

Section: Generalised Regression Neural Network Theorymentioning

confidence: 99%

Intelligent Modelling of the Real Dynamic Viscosity of Rubber Blends Using Parallel Computing

Kopal,

Labaj,

Vršková

et al. 2023

Polymers

View full text Add to dashboard Cite

Modelling the flow properties of rubber blends makes it possible to predict their rheological behaviour during the processing and production of rubber-based products. As the nonlinear nature of such complex processes complicates the creation of exact analytical models, it is appropriate to use artificial intelligence tools in this modelling. The present study was implemented to develop a highly efficient artificial neural network model, optimised using a novel training algorithm with fast parallel computing to predict the results of rheological tests of rubber blends performed under different conditions. A series of 120 real dynamic viscosity–time curves, acquired by a rubber process analyser for styrene–butadiene rubber blends with varying carbon black contents vulcanised at different temperatures, were analysed using a Generalised Regression Neural Network. The model was optimised by limiting the fitting error of the training dataset to a pre-specified value of less than 1%. All repeated calculations were made via parallel computing with multiple computer cores, which significantly reduces the total computation time. An excellent agreement between the predicted and measured generalisation data was found, with an error of less than 4.7%, confirming the high generalisation performance of the newly developed model.

show abstract

Section: Generalised Regression Neural Network Theorymentioning

confidence: 99%