Abstract: Artificial Neural Networks (ANN) trained using backpropagation
(BP) algorithm are commonly used for modeling
material behavior associated with non-linear, complex or unknown
interactions among the material constituents. Despite multidisciplinary
applications of back-propagation neural networks
(BPNN), the BP algorithm possesses the inherent drawback of
getting trapped in local minima and slowly converging to a global
optimum. The paper present a hybrid artificial neural networks and
genetic algorithm approach for modeling slump of ready mix
concrete based on its design mix constituents. Genetic algorithms
(GA) global search is employed for evolving the initial weights and
biases for training of neural networks, which are further fine tuned
using the BP algorithm. The study showed that, hybrid ANN-GA
model provided consistent predictions in comparison to commonly
used BPNN model. In comparison to BPNN model, the hybrid ANNGA
model was able to reach the desired performance goal quickly.
Apart from the modeling slump of ready mix concrete, the synaptic
weights of neural networks were harnessed for analyzing the relative
importance of concrete design mix constituents on the slump value.
The sand and water constituents of the concrete design mix were
found to exhibit maximum importance on the concrete slump value.
Abstract: In this paper we present an efficient approach for the prediction of two sunspot-related time series, namely the Yearly Sunspot Number and the IR5 Index, that are commonly used for monitoring solar activity. The method is based on exploiting partially recurrent Elman networks and it can be divided into three main steps: the first one consists in a “de-rectification" of the time series under study in order to obtain a new time series whose appearance, similar to a sum of sinusoids, can be modelled by our neural networks much better than the original dataset. After that, we normalize the derectified data so that they have zero mean and unity standard deviation and, finally, train an Elman network with only one input, a recurrent hidden layer and one output using a back-propagation algorithm with variable learning rate and momentum. The achieved results have shown the efficiency of this approach that, although very simple, can perform better than most of the existing solar activity forecasting methods.
Abstract: The back-propagation algorithm calculates the weight
changes of an artificial neural network, and a two-term algorithm
with a dynamically optimal learning rate and a momentum factor
is commonly used. Recently the addition of an extra term, called a
proportional factor (PF), to the two-term BP algorithm was proposed.
The third term increases the speed of the BP algorithm. However,
the PF term also reduces the convergence of the BP algorithm, and
optimization approaches for evaluating the learning parameters are
required to facilitate the application of the three terms BP algorithm.
This paper considers the optimization of the new back-propagation
algorithm by using derivative information. A family of approaches
exploiting the derivatives with respect to the learning rate, momentum
factor and proportional factor is presented. These autonomously
compute the derivatives in the weight space, by using information
gathered from the forward and backward procedures. The three-term
BP algorithm and the optimization approaches are evaluated using
the benchmark XOR problem.
Abstract: In this paper we present a Feed-Foward Neural
Networks Autoregressive (FFNN-AR) model with genetic algorithms
training optimization in order to predict the gross domestic product
growth of six countries. Specifically we propose a kind of weighted
regression, which can be used for econometric purposes, where the
initial inputs are multiplied by the neural networks final optimum
weights from input-hidden layer of the training process. The
forecasts are compared with those of the ordinary autoregressive
model and we conclude that the proposed regression-s forecasting
results outperform significant those of autoregressive model.
Moreover this technique can be used in Autoregressive-Moving
Average models, with and without exogenous inputs, as also the
training process with genetics algorithms optimization can be
replaced by the error back-propagation algorithm.
Abstract: The objective of this paper is to a design of pattern
classification model based on the back-propagation (BP) algorithm for
decision support system. Standard BP model has done full connection
of each node in the layers from input to output layers. Therefore, it
takes a lot of computing time and iteration computing for good
performance and less accepted error rate when we are doing some
pattern generation or training the network.
However, this model is using exclusive connection in between
hidden layer nodes and output nodes. The advantage of this model is
less number of iteration and better performance compare with standard
back-propagation model. We simulated some cases of classification
data and different setting of network factors (e.g. hidden layer number
and nodes, number of classification and iteration). During our
simulation, we found that most of simulations cases were satisfied by
BP based using exclusive connection network model compared to
standard BP. We expect that this algorithm can be available to
identification of user face, analysis of data, mapping data in between
environment data and information.
Abstract: The ElectroEncephaloGram (EEG) is useful for
clinical diagnosis and biomedical research. EEG signals often
contain strong ElectroOculoGram (EOG) artifacts produced
by eye movements and eye blinks especially in EEG recorded
from frontal channels. These artifacts obscure the underlying
brain activity, making its visual or automated inspection
difficult. The goal of ocular artifact removal is to remove
ocular artifacts from the recorded EEG, leaving the underlying
background signals due to brain activity. In recent times,
Independent Component Analysis (ICA) algorithms have
demonstrated superior potential in obtaining the least
dependent source components. In this paper, the independent
components are obtained by using the JADE algorithm (best
separating algorithm) and are classified into either artifact
component or neural component. Neural Network is used for
the classification of the obtained independent components.
Neural Network requires input features that exactly represent
the true character of the input signals so that the neural
network could classify the signals based on those key
characters that differentiate between various signals. In this
work, Auto Regressive (AR) coefficients are used as the input
features for classification. Two neural network approaches
are used to learn classification rules from EEG data. First, a
Polynomial Neural Network (PNN) trained by GMDH (Group
Method of Data Handling) algorithm is used and secondly,
feed-forward neural network classifier trained by a standard
back-propagation algorithm is used for classification and the
results show that JADE-FNN performs better than JADEPNN.
Abstract: This research paper deals with the implementation of face recognition using neural network (recognition classifier) on low-resolution images. The proposed system contains two parts, preprocessing and face classification. The preprocessing part converts original images into blurry image using average filter and equalizes the histogram of those image (lighting normalization). The bi-cubic interpolation function is applied onto equalized image to get resized image. The resized image is actually low-resolution image providing faster processing for training and testing. The preprocessed image becomes the input to neural network classifier, which uses back-propagation algorithm to recognize the familiar faces. The crux of proposed algorithm is its beauty to use single neural network as classifier, which produces straightforward approach towards face recognition. The single neural network consists of three layers with Log sigmoid, Hyperbolic tangent sigmoid and Linear transfer function respectively. The training function, which is incorporated in our work, is Gradient descent with momentum (adaptive learning rate) back propagation. The proposed algorithm was trained on ORL (Olivetti Research Laboratory) database with 5 training images. The empirical results provide the accuracy of 94.50%, 93.00% and 90.25% for 20, 30 and 40 subjects respectively, with time delay of 0.0934 sec per image.
Abstract: A complex valued neural network is a neural network, which consists of complex valued input and/or weights and/or thresholds and/or activation functions. Complex-valued neural networks have been widening the scope of applications not only in electronics and informatics, but also in social systems. One of the most important applications of the complex valued neural network is in image and vision processing. In Neural networks, radial basis functions are often used for interpolation in multidimensional space. A Radial Basis function is a function, which has built into it a distance criterion with respect to a centre. Radial basis functions have often been applied in the area of neural networks where they may be used as a replacement for the sigmoid hidden layer transfer characteristic in multi-layer perceptron. This paper aims to present exhaustive results of using RBF units in a complex-valued neural network model that uses the back-propagation algorithm (called 'Complex-BP') for learning. Our experiments results demonstrate the effectiveness of a Radial basis function in a complex valued neural network in image recognition over a real valued neural network. We have studied and stated various observations like effect of learning rates, ranges of the initial weights randomly selected, error functions used and number of iterations for the convergence of error on a neural network model with RBF units. Some inherent properties of this complex back propagation algorithm are also studied and discussed.
Abstract: This paper presents a critical study about the
application of Neural Networks to ion-exchange process. Ionexchange
is a complex non-linear process involving many factors
influencing the ions uptake mechanisms from the pregnant solution.
The following step includes the elution. Published data presents
empirical isotherm equations with definite shortcomings resulting in
unreliable predictions. Although Neural Network simulation
technique encounters a number of disadvantages including its “black
box", and a limited ability to explicitly identify possible causal
relationships, it has the advantage to implicitly handle complex
nonlinear relationships between dependent and independent
variables. In the present paper, the Neural Network model based on
the back-propagation algorithm Levenberg-Marquardt was developed
using a three layer approach with a tangent sigmoid transfer function
(tansig) at hidden layer with 11 neurons and linear transfer function
(purelin) at out layer. The above mentioned approach has been used
to test the effectiveness in simulating ion exchange processes. The
modeling results showed that there is an excellent agreement between
the experimental data and the predicted values of copper ions
removed from aqueous solutions.
Abstract: A complex valued neural network is a neural network
which consists of complex valued input and/or weights and/or thresholds
and/or activation functions. Complex-valued neural networks
have been widening the scope of applications not only in electronics
and informatics, but also in social systems. One of the most important
applications of the complex valued neural network is in signal
processing. In Neural networks, generalized mean neuron model
(GMN) is often discussed and studied. The GMN includes a new
aggregation function based on the concept of generalized mean of all
the inputs to the neuron. This paper aims to present exhaustive results
of using Generalized Mean Neuron model in a complex-valued neural
network model that uses the back-propagation algorithm (called
-Complex-BP-) for learning. Our experiments results demonstrate the
effectiveness of a Generalized Mean Neuron Model in a complex
plane for signal processing over a real valued neural network. We
have studied and stated various observations like effect of learning
rates, ranges of the initial weights randomly selected, error functions
used and number of iterations for the convergence of error required on
a Generalized Mean neural network model. Some inherent properties
of this complex back propagation algorithm are also studied and
discussed.
Abstract: The objective of this paper is to design a model of human vital sign prediction for decreasing prediction error by using two states mapping based time series neural network BP (back-propagation) model. Normally, lot of industries has been applying the neural network model by training them in a supervised manner with the error back-propagation algorithm for time series prediction systems. However, it still has a residual error between real value and prediction output. Therefore, we designed two states of neural network model for compensation of residual error which is possible to use in the prevention of sudden death and metabolic syndrome disease such as hypertension disease and obesity. We found that most of simulations cases were satisfied by the two states mapping based time series prediction model compared to normal BP. In particular, small sample size of times series were more accurate than the standard MLP model. We expect that this algorithm can be available to sudden death prevention and monitoring AGENT system in a ubiquitous homecare environment.