Search results for "multilayer"
showing 10 items of 141 documents
Crane collision modelling using a neural network approach
2004
Abstract The objective of the present work is to find a Collision Detection algorithm to be used in the Virtual Reality crane simulator (UVSim®), developed by the Robotics Institute of the University of Valencia for the Port of Valencia. The method is applicable to box-shaped objects and is based on the relationship between the colliding object positions and their impact points. The tool chosen to solve the problem is a neural network, the multilayer perceptron, which adapts to the characteristics of the problem, namely, non-linearity, a large amount of data, and no a priori knowledge. The results achieved by the neural network are very satisfactory for the case of box-shaped objects. Furth…
Efficient pruning of multilayer perceptrons using a fuzzy sigmoid activation function
2006
This Letter presents a simple and powerful pruning method for multilayer feed forward neural networks based on the fuzzy sigmoid activation function presented in [E. Soria, J. Martin, G. Camps, A. Serrano, J. Calpe, L. Gomez, A low-complexity fuzzy activation function for artificial neural networks, IEEE Trans. Neural Networks 14(6) (2003) 1576-1579]. Successful performance is obtained in standard function approximation and channel equalization problems. Pruning allows to reduce network complexity considerably, achieving a similar performance to that obtained by unpruned networks.
Classical Training Methods
2006
This chapter reviews classical training methods for multilayer neural networks. These methods are widely used for classification and function modelling tasks. Nevertheless, they show a number of flaws or drawbacks that should be addressed in the development of such systems. They work by searching the minimum of an error function which defines the optimal behaviour of the neural network. Different standard problems are used to show the capabilities of these models; in particular, we have benchmarked the algorithms in a nonlinear classification problem and in three function modelling problems.
Identification of the Parameters of Reduced Vector Preisach Model by Neural Networks
2008
This paper presents a methodology for identifying reduced vector Preisach model parameters by using neural networks. The neural network used is a multiplayer perceptron trained with the Levenberg-Marquadt training algorithm. The network is trained by some hysteresis data, which are generated by using reduced vector Preisach model with preassigned parameters. It is shown how a properly trained network is able to find the parameters needed to best fit a magnetization hysteresis curve.
A method for modeling the battery state of charge in wireless sensor networks
2015
In this paper we propose a method for obtaining an analytic model of the battery State-of-Charge (SoC) in wireless sensor nodes. The objective is to find simple models that can be used to estimate accurately the real battery state and consequently the node lifetime. Running the model in the network nodes, we can provide the motes with the required information to implement applications that can be considered as battery-aware. The proposed methodology reduces the computational complexity of the model avoiding complicated electrochemical simulations and treating the battery as an unknown system with an output that can be predicted using simple mathematical models. At a first stage, during a se…
A beam theory for layered composites subjected to uniformly distributed load
2015
A theory for multilayered composite beams undergoing transverse uniformly distributed loads is presented. The formulation starts by assuming a layer-wise kinematical model characterized by third order approximation of the axial displacements and fourth order approximation of the transverse displacements. By enforcing the point-wise balance equations as well as the interface continuity conditions, the layer-wise kinematical model is rewritten in terms of a set of generalized kinematical variables associated with the beam as a whole. Stress resultants are then obtained in terms of the generalized variables derivatives and of the normal stresses applied to the top and bottom surfaces of the la…
The use of steel angles for the connection of laminated glass beams: Experiments and modelling
2012
Abstract In the present paper the experimental results relative to three-point bending tests on multilayer glass beams and on semi-rigid connections realised with stainless double web angles are presented and discussed. Small and medium size glass beams were tested and load–deflection curves and crack patterns at failure were recorded. The laminated glass specimens, of equal cross-section, were characterised by three different combinations of annealed float and fully thermally tempered glass plies and different interlayers. Steel joints constituted by double web angles to connect two glass beams were tested adopting several geometrical configurations and using stainless steel bolts preloade…
Evaluation of the bending behaviour of laminated glass beams via electronic speckle pattern interferometry
2017
The paper is devoted to the experimental analysis of the kinematical and mechanical behaviour of laminated glass beam structures. In particular, the utilized laminated glass specimens are composed of two glass layers bonded by a polymer layer constituted by Ethylene-vinyl acetate whose thickness has been nominally considered as constant for all the specimens. The experimental behaviour of the analyzed specimens is deduced by applying Electronic Speckle- Pattern Interferometry technique; actually, among optical methods this technique (handled by phase-stepping technique) is very effective to obtain a full-field displacement map and to numerically achieve the longitudinal strain. In particula…
The Application of Machine Learning Algorithms to the Analysis of Electromyographic Patterns From Arthritic Patients
2009
The main aim of our study was to investigate the possibility of applying machine learning techniques to the analysis of electromyographic patterns (EMG) collected from arthritic patients during gait. The EMG recordings were collected from the lower limbs of patients with arthritis and compared with those of healthy subjects (CO) with no musculoskeletal disorder. The study involved subjects suffering from two forms of arthritis, viz, rheumatoid arthritis (RA) and hip osteoarthritis (OA). The analysis of the data was plagued by two problems which frequently render the analysis of this type of data extremely difficult. One was the small number of human subjects that could be included in the in…
Multilayered cultural identity and the perception of the self
2012
This qualitative study examines the reciprocal relationship between a person’s multilayered cultural identity (MCI) and the concept of self (CoS), that is presented purely on a theoretical level and encompasses various theories. Nowadays, in an increasingly globalising world, it is not enough to merely look at a national, ethnic or other type of identity. It is important to realise that there are different layers in an identity that one can view themselves through. The ways an individual perceives themselves through their multicultural background can also be different. This thesis helps identify the ways a person can see themselves. The thesis also attempts to explain the varied nature of o…