Over 30,000 optimum load patterns are obtained for 21 earthquake excitations recorded on soft soils to investigate the effects of fundamental period of the structure, number of stories, ductility demand, earthquake excitation, damping ratio, damping model, structural post yield behaviour, soil flexibility and structural aspect ratio on the optimum load patterns.
Precise control of the aggregates inner structure (number of crystallites and density) was also achieved and described as a nanostructure map.
Landscape was described by its proportion (cover of spring crops, winter crops, woodland, grassland, set-aside) and its structure (number of fields, number of land use types).
Thirty-two SPSW-WC structures are designed with emphasis on varying the following parameters: height of the structure (number of stories), coupled length and coupling beam properties.
Different learning algorithms with different network configurations are tried and tested in order to minimize the rms errors in terms of the ANN structure, number of layers, and number of neurons in each layer.
The model was proposed to utilize a power equation with six factors, namely shear strength of asphalt mixture, shear stress of pavement structure, number of load repetitions, pavement temperature, vehicle speed and pavement depth.
This paper aims to assess the impact of the traditional cost optimization approach to strategic modelling on overall logistics costs and CO2 emissions by taking into account the supply chain structure (number of depots) and different freight vehicle utilization ratios (90%, 75 % and 60).
The methodology follows the principles already employed by the authors in different applications: the NN models are trained by the Levenberg-Marquardt algorithm using a modified training criterion, and the model structure (number of neurons and input terms) is evolved using a Multi-Objective Genetic Algorithm (MOGA).
A 25 full-factorial experimental design was employed in order to evaluate the effect of ANN's structure (number of hidden units) and training (number of iteration cycles) parameters along with the effect of Raman or FTIR spectra region and data preprocessing (direct orthogonal signal correction – DOSC, second derivative, or no preprocessing) on ANN's fitting performance.
The structure, number-averaged molecular weight (Mn) of the copolymer, and copolymer composition were determined by proton nuclear magnetic resonance (1H NMR) in CDCl3 at 300 Hz (Bruker ACF300, Madison, WI, USA).
The criteria for inclusion of new items in the factor analyses were: comparable answer-structure, number of missing values (combined with the answers 'don't know' and 'not applicable'), importance rating, inter-correlation of the answers of separate questions.
