Search results for "multilayer"
showing 10 items of 141 documents
Comparing ELM Against MLP for Electrical Power Prediction in Buildings
2015
The study of energy efficiency in buildings is an active field of research. Modelling and predicting energy related magnitudes leads to analyse electric power consumption and can achieve economical benefits. In this study, two machine learning techniques are applied to predict active power in buildings. The real data acquired corresponds to time, environmental and electrical data of 30 buildings belonging to the University of Leon (Spain). Firstly, we segmented buildings in terms of their energy consumption using principal component analysis. Afterwards we applied ELM and MLP methods to compare their performance. Models were studied for different variable selections. Our analysis shows that…
Analysis of ventricular fibrillation signals using feature selection methods
2012
Feature selection methods in machine learning models are a powerful tool to knowledge extraction. In this work they are used to analyse the intrinsic modifications of cardiac response during ventricular fibrillation due to physical exercise. The data used are two sets of registers from isolated rabbit hearts: control (G1: without physical training), and trained (G2). Four parameters were extracted (dominant frequency, normalized energy, regularity index and number of occurrences). From them, 18 features were extracted. This work analyses the relevance of each feature to classify the records in G1 and G2 using Logistic Regression, Multilayer Perceptron and Extreme Learning Machine. Three fea…
Khmer character recognition using artificial neural network
2014
Character Recognition has become an interesting and a challenge topic research in the field of pattern recognition in recent decade. It has numerous applications including bank cheques, address sorting and conversion of handwritten or printed character into machine-readable form. Artificial neural network including self-organization map and multilayer perceptron network with the learning ability could offer the solution to character recognition problem. In this paper presents Khmer Character Recognition (KCR) system implemented in Matlab environment using artificial neural networks. The KCR system described the utilization of integrated self-organization map (SOM) network and multilayer per…
Artificial neural networks for predicting dorsal pressures on the foot surface while walking
2012
In this work, artificial neural networks (ANNs) are proposed to predict the dorsal pressure over the foot surface exerted by the shoe upper while walking. A model that is based on the multilayer perceptron (MLP) is used since it can provide a single equation to model the exerted pressure for all the materials used as shoe uppers. Five different models are produced, one model for each one of the four subjects under study and an overall model for the four subjects. The inputs to the neural model include the characteristics of the material and the positions during a whole step of 14 pressure sensors placed on the foot surface. The goal is to find models with good generalization capabilities, (…
Modelling of Adequate Costs of Utilities Services
2016
The paper propose methodology for benchmark modelling of adequate costs of utilities services, which is based on the data analysis of the factual cases (key performance indicators of utilities as the predictors). The proposed methodology was tested by modelling of Latvian water utilities with three tools: (1) a classical version of the multi-layer perceptron with error back-propagation training algorithm was sharpened up with task-specific monotony tests, (2) the fitting of the generalized additive model using the programming language R ensured the opportunity to evaluate the statistical significance and confidence bands of predictors, (3) the sequential iterative nonlinear regression proce…
Variable kinematics models and finite elements for nonlinear analysis of multilayered smart plates
2015
Abstract A variable kinematics approach for moderately large deflection analysis of smart magneto-electro-elastic multilayered plates is presented. The approach is based on the condensation of the electro-magnetic state into the plate kinematics, whose nonlinear strain–displacement relationships are expressed in the von Karman sense. This leads to models resulting in an effective mechanical plate, which takes the multifield coupling effects into account by the plate stiffness, inertia and loading characteristics, consistently defined as combinations of the layers material properties. By a unified approach, both equivalent single layer and layerwise models are developed formulating the assoc…
Multilayered perspectives on language policy in higher education : Finland, Estonia, and Latvia in comparison
2016
This article analyses language policies in higher education (HE) in Finland, Estonia, and Latvia, as well as the European Union (EU). We take a multilayered approach to language policies in order to illuminate the intertwined nature of local, national, and international language policies in HE. We are particularly interested in the construction of national language(s) and the language(s) of internationalisation in our case countries. Finland, Estonia, and Latvia share common features as relatively small non-Anglophone countries in the Baltic region, while simultaneously having somewhat differing political and cultural histories. The results of our discursive analysis indicate that while the…
CADEM: calculate X-ray diffraction of epitaxial multilayers
2017
This article presents a powerful yet simple program, based on the general one-dimensional kinematic X-ray diffraction (XRD) theory, which calculates the XRD patterns of tailor-made multilayers and thus enables quantitative comparison of measured and calculated XRD data. As the multilayers are constructed layer by layer, the final material stack can be entirely arbitrary.
Finite deformation analysis of laminated shell via the discontinuous Galerkin method
2022
In this work, we propose a novel formulation for the large displacements and post-buckling response analysis of laminated composite shell structures. In order to accurately recover the solution in the case of multilayered shells, the covariant components of the displacement field are approximated through the thickness using high-order structural theories. The non-linear two-dimensional total Lagrangian formulation is obtained starting from the Principle of Virtual Displacements for the three-dimensional elasticity assuming a linear constitutive relationship between the second Piola–Kirchhoff stress tensor and the Green-Lagrange strain tensor. The discontinuous Galerkin method is used in com…
Buckling analysis of multilayered structures using high-order theories and the implicit-mesh discontinuous Galerkin method
2022
This work presents a novel formulation for the linear buckling analysis of multilayered shells. The formulation employs high-order Equivalent-Single-Layer (ESL) shell theories based on the through-the-thickness expansion of the covariant components of the displacement field, whilst the corresponding buckling problem is derived using the Euler’s method. The novelty of the formulation regards the solution of the governing equations, which is obtained via implicit-mesh discontinuous Galerkin (DG) schemes. The DG method is a high-order accurate numerical technique based on a discontinuous representation of the solution among the mesh elements and on the use of suitably defined boundary integral…