Abstract: In this paper a new fast simplification method is
presented. Such method realizes Karnough map with large
number of variables. In order to accelerate the operation of the
proposed method, a new approach for fast detection of group
of ones is presented. Such approach implemented in the
frequency domain. The search operation relies on performing
cross correlation in the frequency domain rather than time one.
It is proved mathematically and practically that the number of
computation steps required for the presented method is less
than that needed by conventional cross correlation. Simulation
results using MATLAB confirm the theoretical computations.
Furthermore, a powerful solution for realization of complex
functions is given. The simplified functions are implemented
by using a new desigen for neural networks. Neural networks
are used because they are fault tolerance and as a result they
can recognize signals even with noise or distortion. This is
very useful for logic functions used in data and computer
communications. Moreover, the implemented functions are
realized with minimum amount of components. This is done
by using modular neural nets (MNNs) that divide the input
space into several homogenous regions. Such approach is
applied to implement XOR function, 16 logic functions on one
bit level, and 2-bit digital multiplier. Compared to previous
non- modular designs, a clear reduction in the order of
computations and hardware requirements is achieved.
Abstract: The main problem for recognition of handwritten Persian digits using Neural Network is to extract an appropriate feature vector from image matrix. In this research an asymmetrical segmentation pattern is proposed to obtain the feature vector. This pattern can be adjusted as an optimum model thanks to its one degree of freedom as a control point. Since any chosen algorithm depends on digit identity, a Neural Network is used to prevail over this dependence. Inputs of this Network are the moment of inertia and the center of gravity which do not depend on digit identity. Recognizing the digit is carried out using another Neural Network. Simulation results indicate the high recognition rate of 97.6% for new introduced pattern in comparison to the previous models for recognition of digits.
Abstract: In this paper, a class of impulsive BAM fuzzy cellular neural networks with distributed delays and reaction-diffusion terms is formulated and investigated. By employing the delay differential inequality and inequality technique developed by Xu et al., some sufficient conditions ensuring the existence, uniqueness and global exponential stability of equilibrium point for impulsive BAM fuzzy cellular neural networks with distributed delays and reaction-diffusion terms are obtained. In particular, the estimate of the exponential convergence rate is also provided, which depends on system parameters, diffusion effect and impulsive disturbed intention. It is believed that these results are significant and useful for the design and applications of BAM fuzzy cellular neural networks. An example is given to show the effectiveness of the results obtained here.
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: In this paper, an approach to reduce the computation steps required by fast neural networksfor the searching process is presented. The principle ofdivide and conquer strategy is applied through imagedecomposition. Each image is divided into small in sizesub-images and then each one is tested separately usinga fast neural network. The operation of fast neuralnetworks based on applying cross correlation in thefrequency domain between the input image and theweights of the hidden neurons. Compared toconventional and fast neural networks, experimentalresults show that a speed up ratio is achieved whenapplying this technique to locate human facesautomatically in cluttered scenes. Furthermore, fasterface detection is obtained by using parallel processingtechniques to test the resulting sub-images at the sametime using the same number of fast neural networks. Incontrast to using only fast neural networks, the speed upratio is increased with the size of the input image whenusing fast neural networks and image decomposition.
Abstract: This paper presents a software quality support tool, a
Java source code evaluator and a code profiler based on
computational intelligence techniques. It is Java prototype software
developed by AI Group [1] from the Research Laboratories at
Universidad de Palermo: an Intelligent Java Analyzer (in Spanish:
Analizador Java Inteligente, AJI). It represents a new approach to
evaluate and identify inaccurate source code usage and transitively,
the software product itself.
The aim of this project is to provide the software development
industry with a new tool to increase software quality by extending
the value of source code metrics through computational intelligence.
Abstract: The stem cells have ability to differentiated
themselves through mitotic cell division and various range of
specialized cell types. Cellular differentiation is a way by which few
specialized cell develops into more specialized.This paper studies the
fundamental problem of computational schema for an artificial neural
network based on chemical, physical and biological variables of
state. By doing this type of study system could be model for a viable
propagation of various economically important stem cells
differentiation. This paper proposes various differentiation outcomes
of artificial neural network into variety of potential specialized cells
on implementing MATLAB version 2009. A feed-forward back
propagation kind of network was created to input vector (five input
elements) with single hidden layer and one output unit in output
layer. The efficiency of neural network was done by the assessment
of results achieved from this study with that of experimental data
input and chosen target data. The propose solution for the efficiency
of artificial neural network assessed by the comparatative analysis of
“Mean Square Error" at zero epochs. There are different variables of
data in order to test the targeted results.
Abstract: This paper proposes the method combining artificial
neural network (ANN) with particle swarm optimization (PSO) to
implement the maximum power point tracking (MPPT) by controlling
the rotor speed of the wind generator. First, the measurements of wind
speed, rotor speed of wind power generator and output power of wind
power generator are applied to train artificial neural network and to
estimate the wind speed. Second, the method mentioned above is
applied to estimate and control the optimal rotor speed of the wind
turbine so as to output the maximum power. Finally, the result reveals
that the control system discussed in this paper extracts the maximum
output power of wind generator within the short duration even in the
conditions of wind speed and load impedance variation.
Abstract: Human activity is a major concern in a wide variety of
applications, such as video surveillance, human computer interface
and face image database management. Detecting and recognizing
faces is a crucial step in these applications. Furthermore, major
advancements and initiatives in security applications in the past years
have propelled face recognition technology into the spotlight. The
performance of existing face recognition systems declines significantly
if the resolution of the face image falls below a certain level.
This is especially critical in surveillance imagery where often, due to
many reasons, only low-resolution video of faces is available. If these
low-resolution images are passed to a face recognition system, the
performance is usually unacceptable. Hence, resolution plays a key
role in face recognition systems. In this paper we introduce a new
low resolution face recognition system based on mixture of expert
neural networks. In order to produce the low resolution input images
we down-sampled the 48 × 48 ORL images to 12 × 12 ones using
the nearest neighbor interpolation method and after that applying
the bicubic interpolation method yields enhanced images which is
given to the Principal Component Analysis feature extractor system.
Comparison with some of the most related methods indicates that
the proposed novel model yields excellent recognition rate in low
resolution face recognition that is the recognition rate of 100% for
the training set and 96.5% for the test set.
Abstract: In this paper, a novel associative memory model will be proposed and applied to memory retrievals based on the conventional continuous time model. The conventional model presents memory capacity is very low and retrieval process easily converges to an equilibrium state which is very different from the stored patterns. Genetic Algorithms is well-known with the capability of global optimal search escaping local optimum on progress to reach a global optimum. Based on the well-known idea of Genetic Algorithms, this work proposes a heuristic rule to make a mutation when the state of the network is trapped in a spurious memory. The proposal heuristic associative memory show the stored capacity does not depend on the number of stored patterns and the retrieval ability is up to ~ 1.
Abstract: Fast forecasting of stock market prices is very important for
strategic planning. In this paper, a new approach for fast forecasting of
stock market prices is presented. Such algorithm uses new high speed
time delay neural networks (HSTDNNs). The operation of these
networks relies on performing cross correlation in the frequency
domain between the input data and the input weights of neural
networks. It is proved mathematically and practically that the number
of computation steps required for the presented HSTDNNs is less
than that needed by traditional time delay neural networks
(TTDNNs). Simulation results using MATLAB confirm the
theoretical computations.
Abstract: Self-Excited Induction Generator (SEIG) builds up voltage while it enters in its magnetic saturation region. Due to non-linear magnetic characteristics, the performance analysis of SEIG involves cumbersome mathematical computations. The dependence of air-gap voltage on saturated magnetizing reactance can only be established at rated frequency by conducting a laboratory test commonly known as synchronous run test. But, there is no laboratory method to determine saturated magnetizing reactance and air-gap voltage of SEIG at varying speed, terminal capacitance and other loading conditions. For overall analysis of SEIG, prior information of magnetizing reactance, generated frequency and air-gap voltage is essentially required. Thus, analytical methods are the only alternative to determine these variables. Non-existence of direct mathematical relationship of these variables for different terminal conditions has forced the researchers to evolve new computational techniques. Artificial Neural Networks (ANNs) are very useful for solution of such complex problems, as they do not require any a priori information about the system. In this paper, an attempt is made to use cascaded neural networks to first determine the generated frequency and magnetizing reactance with varying terminal conditions and then air-gap voltage of SEIG. The results obtained from the ANN model are used to evaluate the overall performance of SEIG and are found to be in good agreement with experimental results. Hence, it is concluded that analysis of SEIG can be carried out effectively using ANNs.
Abstract: The people are differed by their capabilities, skills and mental agilities. The evolution of human from childhood when they are completely dependent up to adultness the time they gradually set the dependency free is too complicated, by considering they have all started from almost one point but some become cleverer and some less. The main control command of a cybernetic hand should be posted by remaining healthy organs of disabled Person. These commands can be from several channels, which their recording and detecting are different and need complicated study. In this research, we suppose that, this stage has been done or in the other words, the command has been already sent and detected. So the main goal is to control a long hand, upper elbow hand missing, by an interest angle define by disabled. It means that, the system input is the position desired by disables and the output is the elbow-joint angle variation. Therefore the goal is a suitable control design based on neural network theory in order to meet the given mapping.
Abstract: This paper discusses the effectiveness of the EEG signal
for human identification using four or less of channels of two different
types of EEG recordings. Studies have shown that the EEG signal
has biometric potential because signal varies from person to person
and impossible to replicate and steal. Data were collected from 10
male subjects while resting with eyes open and eyes closed in 5
separate sessions conducted over a course of two weeks. Features
were extracted using the wavelet packet decomposition and analyzed
to obtain the feature vectors. Subsequently, the neural networks
algorithm was used to classify the feature vectors. Results show that,
whether or not the subjects- eyes were open are insignificant for a 4–
channel biometrics system with a classification rate of 81%. However,
for a 2–channel system, the P4 channel should not be included if data
is acquired with the subjects- eyes open. It was observed that for 2–
channel system using only the C3 and C4 channels, a classification
rate of 71% was achieved.
Abstract: An integrated Artificial Neural Network- Particle Swarm Optimization (PSO) is presented for analyzing global electricity consumption. To aim this purpose, following steps are done: STEP 1: in the first step, PSO is applied in order to determine world-s oil, natural gas, coal and primary energy demand equations based on socio-economic indicators. World-s population, Gross domestic product (GDP), oil trade movement and natural gas trade movement are used as socio-economic indicators in this study. For each socio-economic indicator, a feed-forward back propagation artificial neural network is trained and projected for future time domain. STEP 2: in the second step, global electricity consumption is projected based on the oil, natural gas, coal and primary energy consumption using PSO. global electricity consumption is forecasted up to year 2040.
Abstract: Determination of nano particle size is substantial since
the nano particle size exerts a significant effect on various properties
of nano materials. Accordingly, proposing non-destructive, accurate
and rapid techniques for this aim is of high interest. There are some
conventional techniques to investigate the morphology and grain size
of nano particles such as scanning electron microscopy (SEM),
atomic force microscopy (AFM) and X-ray diffractometry (XRD).
Vibrational spectroscopy is utilized to characterize different
compounds and applied for evaluation of the average particle size
based on relationship between particle size and near infrared spectra
[1,4] , but it has never been applied in quantitative morphological
analysis of nano materials. So far, the potential application of nearinfrared
(NIR) spectroscopy with its ability in rapid analysis of
powdered materials with minimal sample preparation, has been
suggested for particle size determination of powdered
pharmaceuticals. The relationship between particle size and diffuse
reflectance (DR) spectra in near infrared region has been applied to
introduce a method for estimation of particle size. Back propagation
artificial neural network (BP-ANN) as a nonlinear model was applied
to estimate average particle size based on near infrared diffuse
reflectance spectra. Thirty five different nano TiO2 samples with
different particle size were analyzed by DR-FTNIR spectrometry and
the obtained data were processed by BP- ANN.
Abstract: The back propagation algorithm calculates the weight
changes of artificial neural networks, and a common approach is to
use a training algorithm consisting of a learning rate and a
momentum factor. The major drawbacks of above learning algorithm
are the problems of local minima and slow convergence speeds. The
addition of an extra term, called a proportional factor reduces the
convergence of the back propagation algorithm. We have applied the
three term back propagation to multiplicative neural network
learning. The algorithm is tested on XOR and parity problem and
compared with the standard back propagation training algorithm.
Abstract: In this paper we present an efficient system for
independent speaker speech recognition based on neural network
approach. The proposed architecture comprises two phases: a
preprocessing phase which consists in segmental normalization and
features extraction and a classification phase which uses neural
networks based on nonparametric density estimation namely the
general regression neural network (GRNN). The relative
performances of the proposed model are compared to the similar
recognition systems based on the Multilayer Perceptron (MLP), the
Recurrent Neural Network (RNN) and the well known Discrete
Hidden Markov Model (HMM-VQ) that we have achieved also.
Experimental results obtained with Arabic digits have shown that the
use of nonparametric density estimation with an appropriate
smoothing factor (spread) improves the generalization power of the
neural network. The word error rate (WER) is reduced significantly
over the baseline HMM method. GRNN computation is a successful
alternative to the other neural network and DHMM.