In this paper, we propose an artificial neural network (ANN) as a design technique for multilayer circular microstrip antennas based on Levenberg Marquardt training algorithm for modelling, simulation and optimization. Levenberg – Marquart (LM) algorithm has been used to train the MultiLayer Perceptron Neural Networks (MLPNNs). In the design procedure, the feed forward network is defined as a s...

In this paper, the linear (feed-forward) multilayer ICA algorithm is proposed for the blind separation of high-dimensional mixed signals. There are two main phases in each layer. One is the local ICA phase, where the mixed signals are divided into small local modules and a simple ICA is applied to each module. Another is the mapping phase, where the locally-separated signals are arranged as a l...

In this study, artificial neural network was used to predict the microhardness of Al2024-multiwall carbon nanotube(MWCNT) composite prepared by mechanical alloying. Accordingly, the operational condition, i.e., the amount of reinforcement, ball to powder weight ratio, compaction pressure, milling time, time and temperature of sintering as well as vial speed were selected as independent input an...

In this paper, model reference neural network structure is used as a controller for vibration suppression of the Euler–Bernoulli beam under the excitation of moving mass travelling along a vibrating path. The non-dimensional equation of motion the beam acted upon by a moving mass is achieved.  A Dirac-delta function is used to describe the position of the moving mass along the beam and its iner...

Multilayer feed-forward networks, or multilayer perceptrons (MLPs) have one or several " hidden " layers of nodes. This implies that they have two or more layers of weights. The limitations of simple perceptrons do not apply to MLPs. In fact, as we will see later, a network with just one hidden layer can represent any Boolean function (including the XOR which is, as we saw, not linearly separab...

Electroencephalography is a technique for recording the brain’s electrical activity – the electroencephalogram or EEG. It is an important procedure in the diagnosis of several brain disorders, as well being a valuable physiological tool for studies of normal brain function. However, the EEG is often contaminated by numerous artefacts such as eye-blinks, muscle activities, and eye-movements. Thi...

The recent advances in computer technology many recognition task have been automated. OCR, Optical Character Recognition is a scheme of converting the images of typewritten or printed text into a format that is understood by machine. The goal of OCR is to classify the given character data represented by some characteristics, into a predefined finite number of character classes. For the recognit...

Prediction of the scour around a group of pile in the field exposed to oscillatory waves is very important for many offshore structure and coastal engineering projects. Conventional predictive formulas for the geometric properties of scour hole, however, are not able to provide sufficiently accurate results. In this paper the ANNs approach is used to predict the scour depth around pile group us...

We study the possibility to employ neural networks to simulate jet clustering procedures in high energy hadron-hadron collisions. We concentrate our analysis on the Fermilab Tevatron energy and on the k⊥ algorithm. We employ both supervised and unsupervised neural networks. In the first case we consider a multilayer feed-forward network trained by the backpropagation algorithm: our results show...

In this paper, we purpose a diagnostic procedure to identify the optic nerve disease from visual evoked potential (VEP) signals using an Artificial Neural Network (ANN). Multilayer feed forward ANN trained with a Levenberg Marquart backpropagation algorithm was implemented. The correct classification rate was 96.87% for subjects having optic nerve disease and 96.66% for healthy subjects. The en...