Title: Adaptive Control OF Nonlinear Multivariable Dynamical Systems Using MRAN-RBF Neural Networks | ||
Author(s): Tamer A. Al-zohairy | ||
Pages: 1-9 | Paper ID: 110901-7474 IJECS-IJENS | Published: February, 2011 |
Abstract: Most practical systems have multiple inputs
and multiple outputs, and the applicability of neural
networks as practical adaptive identifiers and controllers will
eventually be judged by their success in multivariable
problems. In this paper, we design a model following adaptive
controller for a class of a discrete time multivariable
nonlinear systems. Radial Basis Function (RBF) neural
network with Minimal Resource Allocation Network (MRAN)
training algorithm is used for off-line stable identification. It
implements a stable model following adaptive controller by
utilizing the identification results. Simulation results
demonstrate the proposed controller can drive unknown
MIMO nonlinear systems to follow the desired trajectory
very well.
|
||
Keywords: Adaptive control, MIMO systems, MRAN, RBF neural network, Sequential learning algorithms. | ||
Full Text (.pdf) | 498 KB |
Title: Arabic Discourse Segmentation Based on Rhetorical Methods | ||
Author(s): Iraky Khalifa, Zakareya Al Feki, Abdelfatah Farawila | ||
Pages: 10-15 | Paper ID: 112701-8989 IJECS-IJENS | Published: February, 2011 |
Abstract: The discourse segmentation problem in Arabic language has not been fully addressed. A technique to segment Arabic discourse into complete sentences is presented. The technique is derived from Arabic Rhetorical system by exploiting the main crucial connector "و ", as defined by Arabic linguists almost one thousand years ago. This approach categorizes the six known rhetorical types of "و " into two classes: segment and unsegment, known as, "Fasl" and "Wasl". Segmentation places are decided according to the type of connector "و ". A set of twenty two syntactic and semantic features devised from "Fasl and Wasl" rhetorical methods, are chosen to categorize each type of "و ". The system undergoes the learning and testing stages, using SVM machine learning technique to identify the types of the connector "و ". An Arabic discourse corpus is particularly developed for this experiment. We achieved results with an accuracy of 97.95% of discourse segmentation.
|
||
Keywords: Arabic rhetoric methods "Fasl and Wasl", discourse segmentation, , machine learning, Rhetorical Structure Theory (RST), Support Vector Machine (SVM). | ||
Full Text (.pdf) | 572 KB |
Title: Design and Analysis of Optimized Selection Sort Algorithm | ||
Author(s): Sultanullah Jadoon, Salman Faiz Solehria, Salim ur Rehman, Hamid Jan | ||
Pages: 16-21 | Paper ID: 113201-5454 IJECS-IJENS | Published: February, 2011 |
Abstract: One of the most frequent operation performed on
database is searching. To perform this operation we have
different kinds of searching algorithms, some of which are
Binary Search, Index Sequential Access Method (ISAM), but
these and all other searching algorithms work only on data,
which are previously sorted. An efficient algorithm is required
in order to make the searching algorithm fast and efficient.
This research paper presents a new sorting algorithm named as
“Optimized Selection Sort Algorithm, OSSA”.OSSA is
designed to perform sorting quickly and more effectively as
compared to the existing version of selection sort. The
introduction of OSSA version of selection sort algorithm for
sorting the data stored in database instead of existing selection
sort algorithm will provide an opportunity to the users to save
almost 50% of their operation time with almost 100%
accuracy.
|
||
Keywords: Algorithm, Optimized, OSSA, Sorting. | ||
Full Text (.pdf) | 567 KB |
Title: An Empirical Study on Author Affirmation | ||
Author(s): Mousmi A. Chaurasia, Dr. Sushil Kumar | ||
Pages: 22-26 | Paper ID: 114801-3737 IJECS-IJENS | Published: February, 2011 |
Abstract: Bootlegging and copyright intrusion are major
problems in academic and commercial sectors. Automatic
information processing and retrieval are therefore become an
urgent need. In this paper a novel approach to authorship
affirmation is proposed i.e. initial character n-gram approach
dealing with real-world text (or unrestricted text). However,
with a small experiment, we attempt to affirm the author more
accurately than the previous research has shown. The results
obtained show that the technique of the initial n-gram is very
effective as it reaches the 100% accuracy level in the field of
author identification.
|
||
Keywords: Author identification, Character n-gram, Dis-similarity measure, Natural Language Processing. | ||
Full Text (.pdf) | 261 KB |
Title: The behavior of the dielectric properties of paddy seeds with resonance frequencies | ||
Author(s): Manjur Ahmed, Fareq Malek, Ee Meng Cheng, Ahmad Nasir Che Rosli, Mohammad Shahrazel Razalli, Hasliza A. Rahim, R. Badlishah Ahmad, Rusnida Romli, Mohd Zaizu Ilyas, Muhamad Asmi Romli | ||
Pages: 27-32 | Paper ID: 119501-0808 IJECS-IJENS | Published: February, 2011 |
Abstract: The dielectric properties of two sample paddy seeds D219 and D222 were measured using
microwave perturbation technique in a frequency range 9-12.2GHz of 33 frequency at interval of
100KHz, at a constant temperature (20
o
C), same bulk density and moisture content (nearly same,
10.8% and 11% dry basis). The dielectric constant of D219 sample is higher than D222 before 9.8
GHz then decreases progressively when frequency increases. The loss factor of D219 also decreases
sharply if compared with D222. The deviated values have been ignored as noise. The deviated values
were presented due to the shape of the samples, unequal perturbation which attribute to full height
insertion in cavity and shape perturbation of the cavity. This paper relates to a characterization system
for various categories of paddy seeds to store for post harvesting.
|
||
Keywords: Complex permittivity, Cavity resonant technique, Q-factor, Resonance frequency, unequal perturbation, microwave treatment protocols. | ||
Full Text (.pdf) | 397 KB |
Title: A Hidden Markov Model for identification of exons in DNA of genes Plasmodium falciparum | ||
Author(s): Suhartati Agoes | ||
Pages: 33-36 | Paper ID: 1110101-4949 IJECS-IJENS | Published: February, 2011 |
Abstract: A Hidden Markov Model (HMM) has been developed to identify of exons in DNA of genes
Plasmodium falciparum. Its genome consists of fourteen chromosomes and the most (A+T)-rich genome sequence. The new model using the structure of HMM system based on
structure exons region in coding sequence (CDS). This model separates GT bases into G and
T state in starts of intron and also AG bases in ends of intron region. This HMM was
improved by increasing the state from 20 up to 100 states on the model only on first exon and
intron. The HMM framework used Viterbi algorithm for the training and both algorithm
Viterbi and Baum-Welch for the test. This model has the maximum accuracy around 78% for
identification of exons in DNA of genes Plasmodium falciparum by using 100 states.
|
||
Keywords: Hidden Markov Model –deoxyribonucleic acid – Plasmodium falciparum -coding sequence – correlation coefficient. | ||
Full Text (.pdf) | 216 KB |
Title: Neuro-Fuzzy Approach for solving communication Network Problems | ||
Author(s): Iman Askerbeyli, Fidan Aybike Gedik | ||
Pages: 37-43 | Paper ID: 1110601-3434 IJECS-IJENS | Published: February, 2011 |
Abstract: In this paper, traffic control of the communication systems is examined over the ATM (Asynchronous transfer
mode) networks. Fuzzy mechanism and adaptive neuro fuzzy mechanism are designed to controlling flow rate
on an ATM switch using a specific method of the ABR (Available Bit Rate) service of the ATM technology. Two
models are compared in various cases to evaluate performance in traffic control over the network. Results are
discussed within the framework of today’s technology requirements and problems.
|
||
Keywords: Fuzzy logic, adaptive network fuzzy inference system, traffic control, asynchronous transfer mode. | ||
Full Text (.pdf) | 711 KB |
Title: Phonetic Recognition of Arabic Alphabet letters using Neural Networks | ||
Author(s): Moaz Abdulfattah Ahmad, Rasheed M. El Awady | ||
Pages: 44-49 | Paper ID: 1112501-3434 IJECS-IJENS | Published: February, 2011 |
Abstract: This paper proposes an approach to recognize the
Arabic Alphabet letters spoken by any speaker using
artificial neural networks. This represents a fundamental
step to recognize Arabic speech (continuous words). This
will be useful in converting the spoken words into written
text and using of microphone instead of key board, also
this can help disable people (handicapped) with limited
movement to write any text by voice instead of their hands.
A suggested recognition system is implemented to
recognize Arabic Alphabet letters of independent speakers.
This system is based on analyzing phonetic isolated Arabic
alphabet letters. The main features of the voice signal are
extracted using Principal Component Analysis (PCA)
technique. PCA coefficients corresponding to each
alphabet are used to train multilayer perceptron &
feed-forward back propagation neural networks to produce
recognized binary codes corresponding to each letter.
These binary codes (corresponding to alphabet letters) can
be decoded to be used as displayed letters on monitors, or
printed on paper or used as commands for moving a
controlled mechanism. About 96% detection rate has been
achieved over large dataset.
|
||
Keywords: Arabic letters, Speech processing, Arabic speech recognition, Principal components Analysis (PCA), ANN. | ||
Full Text (.pdf) | 726 KB |
Title: Evaluation of Matrix Multiplication on an MPI Cluster | ||
Author(s): Sherihan Abu ElEnin, Mohamed Abu ElSoud | ||
Pages: 50-57 | Paper ID: 119401-5353 IJECS-IJENS | Published: February, 2011 |
Abstract: An mpi cluster is a group of computers which are loosely connected together to provide fast and reliable services.
Clusters use in many scientific computing, such as the matrix multiplication. Our experiment is based on the master – slave
model in homogenous computers to compute the performance of experiment. We compute the execution time for many
examples to compute the speed up. The developed performance model has been checked and it has been shown that the parallel
model is faster than the serial model and the computation time was reduced.
|
||
Keywords: Matrix multiplication, Cluster of computers, Message Passing Interface, Master/slave algorithm, Performance evaluation. | ||
Full Text (.pdf) | 535 KB |