Abstract: This paper presents an ESN-based Arabic phoneme
recognition system trained with supervised, forced and combined
supervised/forced supervised learning algorithms. Mel-Frequency
Cepstrum Coefficients (MFCCs) and Linear Predictive Code (LPC)
techniques are used and compared as the input feature extraction
technique. The system is evaluated using 6 speakers from the King
Abdulaziz Arabic Phonetics Database (KAPD) for Saudi Arabia
dialectic and 34 speakers from the Center for Spoken Language
Understanding (CSLU2002) database of speakers with different
dialectics from 12 Arabic countries. Results for the KAPD and
CSLU2002 Arabic databases show phoneme recognition
performances of 72.31% and 38.20% respectively.
Abstract: Neural processors have shown good results for
detecting a certain character in a given input matrix. In this paper, a
new idead to speed up the operation of neural processors for character
detection is presented. Such processors are designed based on cross
correlation in the frequency domain between the input matrix and the
weights of neural networks. This approach is developed to reduce the
computation steps required by these faster neural networks for the
searching process. The principle of divide and conquer strategy is
applied through image decomposition. Each image is divided into
small in size sub-images and then each one is tested separately by
using a single faster neural processor. Furthermore, faster character
detection is obtained by using parallel processing techniques to test the
resulting sub-images at the same time using the same number of faster
neural networks. In contrast to using only faster neural processors, the
speed up ratio is increased with the size of the input image when using
faster neural processors and image decomposition. Moreover, the
problem of local subimage normalization in the frequency domain is
solved. The effect of image normalization on the speed up ratio of
character detection is discussed. Simulation results show that local
subimage normalization through weight normalization is faster than
subimage normalization in the spatial domain. The overall speed up
ratio of the detection process is increased as the normalization of
weights is done off line.
Abstract: One of the main issues in Computer Vision is to extract the movement of one or several points or objects of interest in an image or video sequence to conduct any kind of study or control process. Different techniques to solve this problem have been applied in numerous areas such as surveillance systems, analysis of traffic, motion capture, image compression, navigation systems and others, where the specific characteristics of each scenario determine the approximation to the problem. This paper puts forward a Computer Vision based algorithm to analyze fish trajectories in high turbulence conditions in artificial structures called vertical slot fishways, designed to allow the upstream migration of fish through obstructions in rivers. The suggested algorithm calculates the position of the fish at every instant starting from images recorded with a camera and using neural networks to execute fish detection on images. Different laboratory tests have been carried out in a full scale fishway model and with living fishes, allowing the reconstruction of the fish trajectory and the measurement of velocities and accelerations of the fish. These data can provide useful information to design more effective vertical slot fishways.
Abstract: This paper describes reactive neural control used to
generate phototaxis and obstacle avoidance behavior of walking
machines. It utilizes discrete-time neurodynamics and consists of
two main neural modules: neural preprocessing and modular neural
control. The neural preprocessing network acts as a sensory fusion
unit. It filters sensory noise and shapes sensory data to drive the
corresponding reactive behavior. On the other hand, modular neural
control based on a central pattern generator is applied for locomotion
of walking machines. It coordinates leg movements and can generate
omnidirectional walking. As a result, through a sensorimotor loop this
reactive neural controller enables the machines to explore a dynamic
environment by avoiding obstacles, turn toward a light source, and
then stop near to it.
Abstract: This paper presents a new method to detect high impedance faults in radial distribution systems. Magnitudes of third and fifth harmonic components of voltages and currents are used as a feature vector for fault discrimination. The proposed methodology uses a learning vector quantization (LVQ) neural network as a classifier for identifying high impedance arc-type faults. The network learns from the data obtained from simulation of a simple radial system under different fault and system conditions. Compared to a feed-forward neural network, a properly tuned LVQ network gives quicker response.
Abstract: With the explosive growth of data available on the
Internet, personalization of this information space become a
necessity. At present time with the rapid increasing popularity of the
WWW, Websites are playing a crucial role to convey knowledge and
information to the end users. Discovering hidden and meaningful
information about Web users usage patterns is critical to determine
effective marketing strategies to optimize the Web server usage for
accommodating future growth. The task of mining useful information
becomes more challenging when the Web traffic volume is enormous
and keeps on growing. In this paper, we propose a intelligent model
to discover and analyze useful knowledge from the available Web
log data.
Abstract: The overall objective of this paper is to retrieve soil
surfaces parameters namely, roughness and soil moisture related to
the dielectric constant by inverting the radar backscattered signal
from natural soil surfaces.
Because the classical description of roughness using statistical
parameters like the correlation length doesn't lead to satisfactory
results to predict radar backscattering, we used a multi-scale
roughness description using the wavelet transform and the Mallat
algorithm. In this description, the surface is considered as a
superposition of a finite number of one-dimensional Gaussian
processes each having a spatial scale. A second step in this study
consisted in adapting a direct model simulating radar backscattering
namely the small perturbation model to this multi-scale surface
description. We investigated the impact of this description on radar
backscattering through a sensitivity analysis of backscattering
coefficient to the multi-scale roughness parameters.
To perform the inversion of the small perturbation multi-scale
scattering model (MLS SPM) we used a multi-layer neural network
architecture trained by backpropagation learning rule. The inversion
leads to satisfactory results with a relative uncertainty of 8%.
Abstract: This article presents the development of a neural
network cognitive model for the classification and detection of
different frequency signals. The basic structure of the implemented
neural network was inspired on the perception process that humans
generally make in order to visually distinguish between high and low
frequency signals. It is based on the dynamic neural network concept,
with delays. A special two-layer feedforward neural net structure was
successfully implemented, trained and validated, to achieve
minimum target error. Training confirmed that this neural net
structure descents and converges to a human perception classification
solution, even when far away from the target.
Abstract: Crude oil blending is an important unit operation in
petroleum refining industry. A good model for the blending system is
beneficial for supervision operation, prediction of the export
petroleum quality and realizing model-based optimal control. Since
the blending cannot follow the ideal mixing rule in practice, we
propose a static neural network to approximate the blending
properties. By the dead-zone approach, we propose a new robust
learning algorithm and give theoretical analysis. Real data of crude
oil blending is applied to illustrate the neuro modeling approach.
Abstract: In this paper, based on almost periodic functional hull theory and M-matrix theory, some sufficient conditions are established for the existence and uniqueness of positive almost periodic solution for a class of BAM neural networks with time-varying delays. An example is given to illustrate the main results.
Abstract: In this paper an algorithm based on the adaptive
neuro-fuzzy controller is provided to enhance the tipover stability of
mobile manipulators when they are subjected to predefined
trajectories for the end-effector and the vehicle. The controller
creates proper configurations for the manipulator to prevent the robot
from being overturned. The optimal configuration and thus the most
favorable control are obtained through soft computing approaches
including a combination of genetic algorithm, neural networks, and
fuzzy logic. The proposed algorithm, in this paper, is that a look-up
table is designed by employing the obtained values from the genetic
algorithm in order to minimize the performance index and by using
this data base, rule bases are designed for the ANFIS controller and
will be exerted on the actuators to enhance the tipover stability of the
mobile manipulator. A numerical example is presented to
demonstrate the effectiveness of the proposed algorithm.
Abstract: Gabor-based face representation has achieved enormous success in face recognition. This paper addresses a novel algorithm for face recognition using neural networks trained by Gabor features. The system is commenced on convolving a face image with a series of Gabor filter coefficients at different scales and orientations. Two novel contributions of this paper are: scaling of rms contrast and introduction of fuzzily skewed filter. The neural network employed for face recognition is based on the multilayer perceptron (MLP) architecture with backpropagation algorithm and incorporates the convolution filter response of Gabor jet. The effectiveness of the algorithm has been justified over a face database with images captured at different illumination conditions.
Abstract: Since the presentation of the backpropagation algorithm, a vast variety of improvements of the technique for training a feed forward neural networks have been proposed. This article focuses on two classes of acceleration techniques, one is known as Local Adaptive Techniques that are based on weightspecific only, such as the temporal behavior of the partial derivative of the current weight. The other, known as Dynamic Adaptation Methods, which dynamically adapts the momentum factors, α, and learning rate, η, with respect to the iteration number or gradient. Some of most popular learning algorithms are described. These techniques have been implemented and tested on several problems and measured in terms of gradient and error function evaluation, and percentage of success. Numerical evidence shows that these techniques improve the convergence of the Backpropagation algorithm.
Abstract: The conjugate gradient optimization algorithm is combined with the modified back propagation algorithm to yield a computationally efficient algorithm for training multilayer perceptron (MLP) networks (CGFR/AG). The computational efficiency is enhanced by adaptively modifying initial search direction as described in the following steps: (1) Modification on standard back propagation algorithm by introducing a gain variation term in the activation function, (2) Calculation of the gradient descent of error with respect to the weights and gains values and (3) the determination of a new search direction by using information calculated in step (2). The performance of the proposed method is demonstrated by comparing accuracy and computation time with the conjugate gradient algorithm used in MATLAB neural network toolbox. The results show that the computational efficiency of the proposed method was better than the standard conjugate gradient algorithm.
Abstract: A Novel fuzzy neural network combining with support vector learning mechanism called support-vector-based fuzzy neural networks (SVBFNN) is proposed. The SVBFNN combine the capability of minimizing the empirical risk (training error) and expected risk (testing error) of support vector learning in high dimensional data spaces and the efficient human-like reasoning of FNN.
Abstract: In automotive systems almost all steps concerning the
calibration of several control systems, e.g., low idle governor or
boost pressure governor, are made with the vehicle because the timeto-
production and cost requirements on the projects do not allow for
the vehicle analysis necessary to build reliable models. Here is
presented a procedure using parametric and NN (neural network)
models that enables the generation of vehicle system models based
on normal ECU engine control unit) vehicle measurements. These
models are locally valid and permit pre and follow-up calibrations so
that, only the final calibrations have to be done with the vehicle.
Abstract: In this paper back-propagation artificial neural network
(BPANN )with Levenberg–Marquardt algorithm is employed to
predict the deformation of the upsetting process. To prepare a
training set for BPANN, some finite element simulations were
carried out. The input data for the artificial neural network are a set
of parameters generated randomly (aspect ratio d/h, material
properties, temperature and coefficient of friction). The output data
are the coefficient of polynomial that fitted on barreling curves.
Neural network was trained using barreling curves generated by
finite element simulations of the upsetting and the corresponding
material parameters. This technique was tested for three different
specimens and can be successfully employed to predict the
deformation of the upsetting process
Abstract: In this work, a radial basis function (RBF) neural network is developed for the identification of hyperbolic distributed parameter systems (DPSs). This empirical model is based only on process input-output data and used for the estimation of the controlled variables at specific locations, without the need of online solution of partial differential equations (PDEs). The nonlinear model that is obtained is suitably transformed to a nonlinear state space formulation that also takes into account the model mismatch. A stable robust control law is implemented for the attenuation of external disturbances. The proposed identification and control methodology is applied on a long duct, a common component of thermal systems, for a flow based control of temperature distribution. The closed loop performance is significantly improved in comparison to existing control methodologies.
Abstract: In this paper, by using Mawhin-s continuation theorem of coincidence degree and a method based on delay differential inequality, some sufficient conditions are obtained for the existence and global exponential stability of periodic solutions of cellular neural networks with distributed delays and impulses on time scales. The results of this paper generalized previously known results.
Abstract: Innovation is more important in any companies.
However, it is not easy to measure the innovation performance
correctly. Patent is one of measuring index nowadays. This paper
wants to purpose an approach for valuing patents based on market
reaction to patent infringement litigations. The interesting
phenomenon is found from collection of patent infringement litigation
events. That is if any patent litigation event occurs the stock value will
follow changing. The plaintiffs- stock value raises some percentage.
According to this interesting phenomenon, the relationship between
patent litigation and stock value is tested and verified. And then, the
stock value variation is used to deduce the infringed patents- value.
The purpose of this study is providing another concept model to
evaluate the infringed patents. This study can provide a decision assist
system to help drafting patent litigation strategy and determine the
technology value