|
|
|
Submit Paper / Call for Papers
Journal receives papers in continuous flow and we will consider articles
from a wide range of Information Technology disciplines encompassing the most
basic research to the most innovative technologies. Please submit your papers
electronically to our submission system at http://jatit.org/submit_paper.php in
an MSWord, Pdf or compatible format so that they may be evaluated for
publication in the upcoming issue. This journal uses a blinded review process;
please remember to include all your personal identifiable information in the
manuscript before submitting it for review, we will edit the necessary
information at our side. Submissions to JATIT should be full research / review
papers (properly indicated below main title).
|
|
|
|
Journal of Theoretical and Applied Information Technology
April 2014 | Vol. 62 No.1 |
|
Title: |
PERFORMANCE ANALYSIS OF WLAN UNDER VARIABLE NUMBER OF NODES USING THE ADJUSTABLE
PARAMETERS IN EDCA |
|
Author: |
A.ANITHA, J.JAYAKUMARI |
|
Abstract: |
This paper deals with the performance analysis of WLAN under variable number of
nodes using the adjustable parameters such as TXOPLimit, CWmin, CWmax and AIFS
in EDCA. The comparative analysis is done by varying the number of nodes and the
adjustable Access Category (AC) parameters in the EDCA access mechanism. The
throughput and delay parameters of the QoS are measured. The simulation is done
using the Network Simulator NS-2.28 tool in RedHat Linux environment. The
simulation results obtained gave a better performance improvement using the
adjustable altered parameters in EDCA access method than the existing methods.
The high TXOP Limit gave a better performance increase than the other
parameters. |
|
Keywords: |
DCF, EDCA, TXOP Limit, QoS, Access Category |
|
Source: |
Journal of Theoretical and Applied Information Technology
10 April 2014 -- Vol. 62. No. 1 -- 2014 |
|
Full
Text |
|
|
Title: |
IMPROVED FUZZY CLUSTERING METHOD BASED ON INTUITIONISTIC FUZZY PARTICLE SWARM
OPTIMIZATION |
|
Author: |
V.KUMUTHA, S. PALANIAMMAL |
|
Abstract: |
Recent advances in technology has led to huge growth in generating high
dimensional data sets by capturing millions of facts in various fields, time
phases, localities and brands. Microarray data contains gene expression from
thousands of genes (features) from only tens of hundreds of samples. The rich
source of information generated from microarray experiments often consist of
incomplete and/or inconsistent data. Data mining is a powerful technology that
automates the process of discovering hidden patterns. Traditional fuzzy
clustering approaches are available which lacks to process efficiently in case
of incomplete or inconsistent data. It has high influence over the resulting
partitions. In this proposed approach, the degree of membership to indeterminacy
is extended by adopting the concept of generalization of fuzzy logic, which is
known as intuitionistic fuzzy logic. This paper proposes a hybrid approach for
clustering high dimensional data set using FCM and Intuitionistic Fuzzy Particle
Swarm Optimization (IFPSO) to overcome the local convergence problem. To find
similarity among objects and cluster centers intuitionistic based similarity
measure is used. Intuitionistic fuzzy particle swarm optimization optimizes the
working of the Fuzzy c-means algorithm. Experimental results of proposed
approach shows better results when compared with the existing methods. |
|
Keywords: |
Fuzzy Clustering; Intuitionistic Fuzzy; Particle Swarm Optimization; Gene
Expression Data; Yeast Data; Degree Of Membership |
|
Source: |
Journal of Theoretical and Applied Information Technology
10 April 2014 -- Vol. 62. No. 1 -- 2014 |
|
Full
Text |
|
|
Title: |
LOW NOISE LOW POWER TRANSIMPEDANCE AMPLIFIER IN 0.18µM CMOS TECHNOLOGY |
|
Author: |
OHAMMAD ARIF SOBHAN BHUIYAN, KALAIVANI A. TARUMARAJA, MAMUN BIN IBNE REAZ,
FAZIDA HANIM HASHIM, SAWAL HAMID MD. ALI |
|
Abstract: |
Low noise and low Power transimpedance amplifiers (TIA) are essential modules
for optical sensor based systems. But low power and low noise TIAs are still a
challenge for the scientists despite of rapid advances in complementary metal
oxide semiconductor (CMOS) technology. This paper proposes a three-stage nested
miller compensated (NMC) based design of low noise low power transimpedance
amplifier for stable wideband operation. The circuit is designed in the 0.18µm
CMOS technology by using Mentor Graphics environment. The simulation results
show that the proposed TIA can operate at frequency 20 KHz and produces an
output of 1.4265V for ±1.2 V input voltages dissipating only 2.9206 mW power at
27°C temperature. The complete layout of the TIA is only 0.005 µm2.This
shunt-feedback TIA can be a better choice for high-resolution, low-to mid
frequency applications. |
|
Keywords: |
CMOS, low power, Opamp, TIA |
|
Source: |
Journal of Theoretical and Applied Information Technology
10 April 2014 -- Vol. 62. No. 1 -- 2014 |
|
Full
Text |
|
|
Title: |
A SPECIAL MATRIX POWER OPERATION DEVELOPMENT FOR SIMULTANEOUS CALCULATION OF ALL
NETWORK'S SHORTEST PATH |
|
Author: |
HITAPRIYA SUPRAYITNO, INDRASURYA B. MOCHTAR, ACHMAD WICAKSONO |
|
Abstract: |
Network's shortest paths calculation is an important need in transportation
network analysis. The Dijkstra algorithm has long been developed for the
shortest path of a pair of nodes calculation individually. A more practical
method to simultaneously calculate all shortest paths of all pair of nodes of a
network needs to be developed. This paper presents the development of a method
to calculate simultaneously all shortest paths of all pairs of nodes of a
network. This calculation method, called a Min-Plus Algebra, is a modification
of Max-Plus Algebra, having a special Matrix Power Operation, enable and easier
to be executed in spread-sheet software. |
|
Keywords: |
Simultaneous shortest path calculation, Matrix power operation, Min-Plus
Algebra, Max-Plus |
|
Source: |
Journal of Theoretical and Applied Information Technology
10 April 2014 -- Vol. 62. No. 1 -- 2014 |
|
Full
Text |
|
|
Title: |
ADAPTIVE NONLINEAR CONTROL OF THREE-PHASE SHUNT ACTIVE POWER FILTERS: POWER
FACTOR CORRECTION AND DC BUS VOLTAGE REGULATION |
|
Author: |
A. AIT CHIHAB, H. OUADI, F. GIRI |
|
Abstract: |
The problem of controlling three-phase shunt active power filters (SAPF) is
addressed in presence of nonlinear loads supplied with three-phase power grids.
The SAPF-load system is shown to be modeled, in the (α,β) coordinate frame, by a
third-order nonlinear state-space representation. The control objective is
twofold: (i) compensating for the current harmonics and the reactive power
absorbed by the nonlinear load; (ii) regulating the inverter DC capacitor
voltage. To this end, a nonlinear adaptive controller is developed on the basis,
on the average system model, using the backstepping design technique. The
controller is made adaptive for compensating the uncertainty on the unknown SAPF
components and on the switching loss power. The performances of the proposed
adaptive controller are formally analyzed using tools from the Lyapunov
stability and the averaging theory. The theoretical results are confirmed by
numerical simulations. |
|
Keywords: |
Active Power Filters, Current Harmonics, Reactive Power, Backstepping, Lyapunov
Stability, Average Analysis |
|
Source: |
Journal of Theoretical and Applied Information Technology
10 April 2014 -- Vol. 62. No. 1 -- 2014 |
|
Full
Text |
|
|
Title: |
SECURE PATIENT MONITORING SYSTEM |
|
Author: |
R.SUJI PRAMILA, A.SHAJIN NARGUNAM |
|
Abstract: |
Patient monitoring in hospital increases the cost, waiting time and the workload
of doctors. These issues are eliminated by in-home patient monitoring system.
This system is designed with wireless body area networks. Here, a group of body
sensors are fitted on the patient’s body and these sensors monitor and collect
body parameters continuously. In general, the monitoring systems initially
collect and forward the patient’s data to the personal computer (PC) in
patient’s home and send them to the hospital via internet. Here the need for a
PC is eliminated by GPS enabled smart phone. The smart phone also supports long
range outdoor monitoring. Security and privacy are the important issues for
in-home patient monitoring system. Different methods are analyzed to accomplish
security and efficiency of data sharing. The main objectives of the proposed
system are to eliminate the need for a PC and to support the outdoor monitoring
by GPS enabled mobile phone. Security and access control are supported by
cryptographic operations. This work provides better medical treatments, reduces
the health care costs and improves the quality of treatments. |
|
Keywords: |
Body area network, body sensors, data sharing, access control, Global
Positioning System (GPS), CP-ABE, outdoor monitoring. |
|
Source: |
Journal of Theoretical and Applied Information Technology
10 April 2014 -- Vol. 62. No. 1 -- 2014 |
|
Full
Text |
|
|
Title: |
AN EMPIRICAL INVESTIGATION ON THE FACTORS THAT INFLUENCE THE USE OF AUDIENCE
RESPONSE SYSTEM |
|
Author: |
MANTIKAYAN JONATHAN , ABDULLAH LILI , AYU MEDIA , ADAMU ABUBAKAR , ABDULGANI
MONTADZAH |
|
Abstract: |
Majority of the earlier studies regarding the use of audience response systems
have been devoted to higher educational level, with less attention given to
secondary or high school level, and there is a dearth of research done on
secondary education. To address the gap in the research literature, a study
using quantitative survey has been used to explore and document the secondary
students’ result outcomes on using the Audience Response System (ARS) vis-à-vis
the traditional method, and to further explore if utilizing an ARS affects
student performance outcome. In the end, the research examines the impact of ARS
on student active learning, performance outcome and the task-technology fit of
ARS in secondary level education. The major finding from this study shows that
ARS add to a pre-existing active learning in secondary level education as well
as the student’s performance. Above all, the task-technology fit affects the
implementation of this system as regards the learning style of secondary school
level. |
|
Keywords: |
Audience Response System, Active learning, Performances Outcomes Task,
Technology-fit |
|
Source: |
Journal of Theoretical and Applied Information Technology
10 April 2014 -- Vol. 62. No. 1 -- 2014 |
|
Full
Text |
|
|
Title: |
E-LEARNING DEVELOPMENT AS PUBLIC INFRASTRUCTURE OF CLOUD COMPUTING |
|
Author: |
DANNY MANONGGA, WIRANTO HERRY UTOMO, HENDRY |
|
Abstract: |
The purpose of this article is to describe the model we implement to provides
services, such as IaaS, PaaS, and SaaS, for e-learning and collaboration in the
educational environment in Salatiga. Currently, the combination of cloud
technology and e-learning is being explored. Several efforts of using IaaS cloud
technology in education focus on the reservation of the VM for students. This
research used Moodle technology as e-learning applications that is installed on
the Cloud. Moodle is a software package for a training purpose- web and internet
based training commonly known as a Learning Management System (LMS), Course
Management System (CMS), or Virtual Learning Environment (VLE). Moodle is free,
since it is an open source software (under the GNU Public License). Features of
Cloud Computing platform using the OpenStack method quite appropriate for
migration of learning system , so that it is able to form learning environments
fully and efficiently, provide personalized contents, and facilitate the
adaptation to the present model of education. |
|
Keywords: |
Cloud Computing, Public Infrastructure, e-learning, Moodle, OpenStack |
|
Source: |
Journal of Theoretical and Applied Information Technology
10 April 2014 -- Vol. 62. No. 1 -- 2014 |
|
Full
Text |
|
|
Title: |
DESIGN AND ANALYSIS OF ANALYTICAL MODEL OF NOVEL ENERGY CONSTRAINED COOPERATIVE
MAC PROTOCOL FOR AD-HOC NETWORKS |
|
Author: |
ELLAMMAL C, SUDHA SADASIVAM G |
|
Abstract: |
Relay assisted cooperative wireless communication has been shown to have
significant performance gains over the legacy direct transmission scheme for
Ad-hoc network. An efficient cooperative Medium Access Control Scheme (MAC) is
needed to solve the difficulties induced by relaying and cooperative computing.
Another challenging issue is the extension of network lifetime of an Ad-hoc
network with regards to small battery capacity and self sustained operation. So,
designing energy constrained cooperative MAC for improving the network lifetime
is a challenging task. Yet, only less attention has been paid for cooperative
MAC scheme and its potential for lifetime extension. In this paper, we propose a
novel Energy Constrained Cooperative MAC protocol namely ECC-MAC for Ad-hoc
networks with the objective of maximizing the network lifetime and achieving
high throughput. Furthermore, we presents an analytical model for network
lifetime aware cooperative MAC scheme which identify the best possible relay
based on both residual energy and data rate. We show that the proposed model
seeks to optimize the tradeoff between network lifetime and throughput. |
|
Keywords: |
Cooperative Communication, Medium Access Control, Ad-Hoc Network, Throughput,
Network Lifetime. |
|
Source: |
Journal of Theoretical and Applied Information Technology
10 April 2014 -- Vol. 62. No. 1 -- 2014 |
|
Full
Text |
|
|
Title: |
AN EFFICIENT INTRUSION DETECTION USING FAST HIERARCHICAL RELEVANCE VECTOR
MACHINE |
|
Author: |
V. JAIGANESH, Dr. P. SUMATHI |
|
Abstract: |
Internet is a useful source of information in everyone’s daily activity.
Internet becomes a globally used public network. Significance of Intrusion
detection system (IDS) in computer network security is well proven. In order to
protect the organization data, Intrusion Detection System (IDS) offers
protection from external users and internal attackers. Intrusion detection is
the processes of examining the events which happens in a computer system or
network and evaluate them for signs of possible events, which are imminent
threats of violation of computer security policies, standard security practices
and acceptable use policies. In this paper a new algorithm is introduced to find
out the protocol and their attacks are Fast Hierarchical Relevance Vector
Machine (FHRVM). These algorithms are formed by the combination of RVM with LM-AHP.
The main goal of the paper, that successful identification of attacks in reduced
false alarm rate. To demonstrate this by exploiting a probabilistic Bayesian
learning framework, in this paper derive an accurate prediction models which
typically utilize dramatically fewer basis functions than a comparable KSVM and
FHELM. These include the benefits of probabilistic predictions, automatic
estimation of `nuisance' parameters and the facility to utilize arbitrary basis
functions. The experiment is carried out with the help of MATLAB by using KDD
Cup 1999 dataset and the results indicate that the proposed technique can
achieve higher detection rate and very low false 7alarm rate than the regular
KSVM, FHELM algorithms. |
|
Keywords: |
Intrusion Detection System(IDS), Support vector machine (SVM), Extreme Learning
Machine (ELM),Relevance Vector Machine (RVM), Levenberg-Marquardt (LM) |
|
Source: |
Journal of Theoretical and Applied Information Technology
10 April 2014 -- Vol. 62. No. 1 -- 2014 |
|
Full
Text |
|
|
Title: |
ANOMALY BASED INTRUSION DETECTION IN WLAN USING DISCRIMINATION ALGORITHM
COMBINED WITH NAÏVE BAYESIAN CLASSIFIER |
|
Author: |
P.KAVITHA, M.USHA |
|
Abstract: |
The role of Intrusion Detection System (IDS) has been inevitable in the area of
Information and Network security – especially for building a good network
defense infrastructure. Due to the wide popularity of Wireless Networks
tremendous applications are emerging and Wireless Local Area Network (WLAN) has
gained attention by both research and industry communities. The wide spread
deployment of WLAN has also brought new challenges to security and privacy. We
need to distinguish anomalies that change the traffic either abruptly or slowly.
Anomaly based intrusion detection technique is one of the building blocks of
such a foundation. In this paper, the attempt has been made to apply correlation
coefficient based learning approach for detecting anomalies in wireless Local
area network. While a good amount of research has been done for fixed wired
networks, not much research has been done in this area for wireless networks due
to lack of a good dataset. Hence we developed a discrimination algorithm using
correlation coefficient to detect anomalies combined with Naïve Bayesian
classifier in the Wireless traffic and demonstrated the effectiveness using
Kyoto 2006+ datasets. An experiment is carried out in order to evaluate
performance based on accuracy, detection rate and false positive rate of the
classification scheme. Results and analysis shows that the proposed approach has
enhanced the detection rate with minimum false positive rates. |
|
Keywords: |
Intrusion Detection, Anomaly Detection, Correlation Coefficient, Naïve Bayesian
Classifier, Wireless Network. |
|
Source: |
Journal of Theoretical and Applied Information Technology
10 April 2014 -- Vol. 62. No. 1 -- 2014 |
|
Full
Text |
|
|
Title: |
NETWORK TRAFFIC PREDICTION IN 4G NETWORK BASED ON NEURAL NETWORK FOR IMPROVING
QOS |
|
Author: |
K.S SAGAR REDDY, DR S.VARADARAJAN |
|
Abstract: |
Many mechanisms based on bandwidth reservation and handoff mechanism is proposed
in the literature to decrease the connection dropping probability for handoffs
in mobile 4G communications. The handoff events occur at higher rate in
packet-switched fourth generation mobile communication networks than in
traditional cellular systems. Hence, an efficient bandwidth reservation
mechanism for the neighboring cells is critical in the process of handoff during
the connection of multimedia calls. This mechanism avoids the undesired force
termination and waste of limited bandwidth in fourth generation mobile
communication networks, particularly when the mobility of the mobility device is
high. In this paper, a phased solution of priority detection, mobility
scheduling and effective bandwidth estimation have been proposed. The motivation
of the phases is to provide the Quality of Service (QoS) at regular
communication and high mobility condition by considering the physical
parameters. Meanwhile, a neural network based service model is incorporated to
accommodate new metrics used in processing handoffs and task scheduling in
fourth generation networks. This mechanism provides the advantages in terms of
choosing the tasks in a priority based scenario and providing un-interrupted
service at the time of handoffs as well as an effective way of utilizing
bandwidth. |
|
Keywords: |
Neural Network, Iterative Process, Bandwidth Estimation, Weightages, Scheduler |
|
Source: |
Journal of Theoretical and Applied Information Technology
10 April 2014 -- Vol. 62. No. 1 -- 2014 |
|
Full
Text |
|
|
Title: |
DETECTION OF DDOS ATTACKS USING IP TRACEBACK AND NETWORK CODING TECHNIQUE |
|
Author: |
J.SATHYA PRIYA, M.RAMAKRISHNAN , S.P.RAJAGOPALAN |
|
Abstract: |
Distributed denial-of-service attacks can collapse even the well-structured
networks. Nowadays with ever-more-powerful tools in a hacker's armoury, DDoS
attacks are easier to launch. Typical types of DDoS attacks include bandwidth
attacks and application attacks. In a bandwidth attack, network resources or
equipment are exhausted by a bulk volume of packets. In application attack, TCP
or HTTP resources are prevented from processing transactions. We concentrated in
bandwidth attacks by using network coding concept along with the alternate path
selection by using IP trace back one hop concept. Router acts as a intermediate
to transfer packets across networks. Normally DDoS attackers try to paralyze the
router to inject attack. So threshold value should be maintained to identify
normal traffic from abnormal traffic to detect DDoS attacks. This type of
approach will be more efficient for securing sensitive, secure and important
information rather than heavy volume of data sent over router for the commercial
business. |
|
Keywords: |
Ddos Attack, Threshold Value, Network Coding, Alternate Path, Trace Back. |
|
Source: |
Journal of Theoretical and Applied Information Technology
10 April 2014 -- Vol. 62. No. 1 -- 2014 |
|
Full
Text |
|
|
Title: |
MATCHED FILTER BASED SPECTRUM SENSING FOR COGNITIVE RADIO AT LOW SIGNAL TO NOISE
RATIO |
|
Author: |
R. VADIVELU, K. SANKARANARAYANAN, V. VIJAYAKUMARI |
|
Abstract: |
Custom usage of a Cognitive Radio is administrated by the essential utilization
aspect of the radio spectrum the natural resource. Cognitive radio trying to
resourcefully share the radio spectrum along with potential primary users in the
spectrum that must be identified in order to evade causing harmful interference
with other users on the spectrum. The vibrant usage of spectrum belongs to the
white space assessment and how accurately it can be utilized. In this paper we
put forward an open situation of channel estimation at low signal to noise
ratio. A Matched Filter based system is well-thought-out to make the spectrum
sensing resolution based on the observed signal to noise ratio from the
Cognitive Users. With the existing knowledge of the regulated system parameters,
the fusion Centre can make a global sensing decision consistently without any
additional requirements such as channel state information, prior information and
prior prospects about the primary user's signal. Numerical results in terms of
receiver operating characteristics show that the sensing performance of the
proposed Matched filter based system outperforms the performance of the adaptive
Takagi and Sugeno’s fuzzy energy based system model at low Signal to Noise Ratio
and one order Cyclostationary detection based on estimated signal to noise
ratio. |
|
Keywords: |
Cognitive Radio, Spectrum Hole, Signal to Noise Ratio, Matched Filter,
Spectrum Sensing, Channel State Information, Receiver Operating Characteristics |
|
Source: |
Journal of Theoretical and Applied Information Technology
10 April 2014 -- Vol. 62. No. 1 -- 2014 |
|
Full
Text |
|
|
Title: |
PERFORMANCE ENHANCEMENT BY AN ENERGY ADEPT PE-AODV WITH LINK FAILURE PREDICTION |
|
Author: |
M. SAKTHIVEL, Dr. V. PALANISAMY |
|
Abstract: |
Mobile Ad hoc Network (MANET) is a wireless network which has dynamic nature
with infrastructure less without a central administration. In MANETs link
failure occurs due to topological changes of mobile node which causes high data
loss and delay, so the performance is enhanced by predicting the link break in
prior. The most challenging fact in the routing process is affording the energy
proficiency and load balancing with Quality of Service(QoS), Ad-hoc On Demand
Vector protocol (AODV) possess load balancing but to get QoS metrics a new
protocol with Energy Adept AODV is embarked. The protocol is intended to quest
the overloaded, variable nodes by considering the interface queue length
compared with a threshold value. Performance Enhanced Ad-hoc On Demand (PE-AODV)
is used for predicting the link failure prior and forwarding the data packets in
an alternate route which reduces end to end delay and increases Packet Delivery
Ratio (PDR). Finally energy proficient load balancing is obtained by engulfing
packet delivery ratio, end to end delay, load distribution and node energy as
major parameters with a performance enhanced PE-AODV is obtained. |
|
Keywords: |
AODV, LINK BREAK, MANET, PE-AODV, QoS. |
|
Source: |
Journal of Theoretical and Applied Information Technology
10 April 2014 -- Vol. 62. No. 1 -- 2014 |
|
Full
Text |
|
|
Title: |
IMPROVED NEURAL NETWORK TRAINING ALGORITHM FOR CLASSIFICATION OF COMPRESSED AND
UNCOMPRESSED IMAGES |
|
Author: |
L.M. PALANIVELU , P. VIJAYAKUMAR |
|
Abstract: |
For managing data in a smart card’s limited memory, containing medical and
biometric images, images compression is resorted to. For image retrieval, it is
necessary that the classification algorithm be efficient to search and locate
the image in a compressed domain. This study proposes a novel training algorithm
for Multi-Layer Perceptron Neural Network (MLP-NN) to classify compressed
images. MLP-NN is used for image classification. The most common training
algorithm is Error Back Propagation algorithm (EBP) with a very poor convergence
rate. Other second order approaches including Levenberg-Marquardt method and
conjugate gradient method are better to train neural networks. This study
proposes an improved training algorithm based on Levenberg-Marquardt method for
Neural Network. |
|
Keywords: |
Image Classification, Compressed Images, Multi-Layer Perceptron Neural Network (MLP-NN),
Levenberg-Marquardt method. |
|
Source: |
Journal of Theoretical and Applied Information Technology
10 April 2014 -- Vol. 62. No. 1 -- 2014 |
|
Full
Text |
|
|
Title: |
TUMBLING TOTAL HARMONIC DISTORTION IN MULTI INVERTER WITH THE AID OF HYBRID (GA-PSO) |
|
Author: |
V.S.BHARATH, M.GOPINATH |
|
Abstract: |
Multi level inverter is a device used for converting DC voltage to AC voltage.
Multilevel inverters are a source of high power, often used in industrial
applications and can use either sine or modified sine waves. Generally IGBT
switches are used in the inverter to control this switching operation. Instead
of using one converter to convert an AC current into a DC current, a multilevel
inverter uses a series of semiconductor power converters (usually two to three)
thus generating higher voltage. At the output of the multilevel inverter the
sine wave form produces large harmonics. To reduce these harmonics at the output
signal, the corresponding THD of switching angles must be reduced. Generally
genetic algorithm is used for harmonic optimization. But the drawback is the
cost function becomes more difficult to optimize and requires increased number
of iterations. Hence to reduce the number of iteration we proposed a hybrid of
Genetic algorithm and Particle swarm optimization algorithm to optimize the
switching angles. Hence the corresponding THD value is also reduced. The
proposed technique is implemented in the MATLAB/simulink working platform. |
|
Keywords: |
Total Harmonics Distortion (THD), Genetic Algorithm (GA), Particle Swarm
Optimization (PSO) |
|
Source: |
Journal of Theoretical and Applied Information Technology
10 April 2014 -- Vol. 62. No. 1 -- 2014 |
|
Full
Text |
|
|
Title: |
SEMANTIC SCHEMA MATCHING APPROACHES: A REVIEW |
|
Author: |
JAFREEN HOSSAIN, NOR FAZLIDA MOHD SANI, LILLY SURIANI AFFENDEY, ISKANDAR ISHAK,
KHAIRUL AZHAR KASMIRAN |
|
Abstract: |
An extensive review of the existing research work in the field of schema
matching uncovers the significance of semantics in this subject. It is beyond
doubt that both structural and semantics aspect of schema matching have been the
topic of research for many years and there are strong references available for
both. However, an in-depth analysis of all the available approaches suggests
there are further scopes for improvement in the field of semantic schema
matching. Normalization and lexical annotation methods using WordNet have been
proposed in several studies, but the level of matching accuracy in those studies
have not yet reached a point that can encourage full automation of schema
matching in commercial use. This paper lists out several possible future work
based on the existing limitations. |
|
Keywords: |
Database Integration, Schema Matching, Data Heterogeneity, Semantic Schema
Matching, Schema Label Normalization, Stop-Words |
|
Source: |
Journal of Theoretical and Applied Information Technology
10 April 2014 -- Vol. 62. No. 1 -- 2014 |
|
Full
Text |
|
|
Title: |
IMPLEMENTATION OF DATA ENCODING AND DECODING IN ARM BOARDS WITH QOS PARAMETERS |
|
Author: |
S.SUNDAR, R.KUMAR, HARISH M.KITTUR |
|
Abstract: |
Networks must be able to transfer data from one device to another with
acceptable accuracy. For most of the applications, a system must guarantee that
the data received are identical to the data transmitted. Any time data are
transmitted from one node to the next, they can become corrupted in passage.
Many factors can alter one or more bits of a message. Some applications require
a mechanism for detecting and correcting errors and some applications may
require retransmission of error data packets. In this paper, it is proposed to
implement Hamming (7, 4) code for data encoding and decoding in LPC1788ARM
Cortex boards .The proposal is aiming for detecting and correcting the error
without any retransmission of error data. As RISC processor is used, the speed
of execution is high and also QoS (Quality of Service) Parameters are used for
measurement purpose which enable this proposal can be useful for high speed real
time applications. |
|
Keywords: |
Hamming Code (7, 4), LPC1788 ARM Board, UDP and QoS |
|
Source: |
Journal of Theoretical and Applied Information Technology
10 April 2014 -- Vol. 62. No. 1 -- 2014 |
|
Full
Text |
|
|
Title: |
ADAPTATION OF THE HARMONY SEARCH ALGORITHM TO SOLVE THE TRAVELLING SALESMAN
PROBLEM |
|
Author: |
MORAD BOUZIDI, MOHAMMED ESSAID RIFFI |
|
Abstract: |
The travelling salesman problem (TSP) is a discrete combinatorial optimization
problem; it allows us to solve a set of problems in the real world in various
fields. This article presents a new meta-heuristic adaptation to solving this
problem. The numerical results are applied to a set of instances of TSPLIB we
showing us the effectiveness of the adaptation of the harmony search algorithm
band compared to other approaches in terms of quality of the solution, the
search time, and the improvement of the results in terms of the reduction in the
percentage of errors. |
|
Keywords: |
Combinatorial Optimization, Meta-Heuristic, Travelling Salesman Problem, Harmony
Search Algorithm, Local Search. |
|
Source: |
Journal of Theoretical and Applied Information Technology
10 April 2014 -- Vol. 62. No. 1 -- 2014 |
|
Full
Text |
|
|
Title: |
HASHED SYMMETRIC KEY ENCRYPTION BASED VBSR |
|
Author: |
R.RAJAMOHAMED, Dr. V. RAJAMANI |
|
Abstract: |
Security impact on mobile ad hoc network increases more since there is no
architecture and high mobility of nodes along the environment. Security features
include providing authentication and confidentiality. Both these services insist
that the messages should be encrypted and decrypted using some keys either
public key and private key. Before encrypting the information to be secure, the
users in the network should authenticate themselves since there is a central
point to control the users. In this paper, we have taken our VBSR protocol for
the implementation of authentication mechanism. In this work, a hash value is
found then it is checked at receiver for authentication that the message is
generated by the authorized sender and a secure protocol is developed called
Hashed VBSR (HVBSR). The hash value ‘H’ is found using the hash function since
the hash function can be taken as a way to compute the Message Authentication
Code (MAC). Since the high dense of mobile nodes cannot be provide best
security, the mobile nodes must be formed as groups. In order to provide
security, there are pre-requirements like public key infrastructure (PKI), group
key management and key agreement and key agreement so on. Then these keys are
used in the encryption/decryption algorithms such as symmetric key algorithms
and asymmetric key algorithms. |
|
Keywords: |
MANET, Security, Hash function, MAC, VBSR. |
|
Source: |
Journal of Theoretical and Applied Information Technology
10 April 2014 -- Vol. 62. No. 1 -- 2014 |
|
Full
Text |
|
|
Title: |
ASSOCIATION OF DEEP LEARNING ALGORITHM WITH FUZZY LOGIC FOR MULTIDOCUMENT TEXT
SUMMARIZATION |
|
Author: |
G.PADMAPRIYA, Dr.K.DURAISWAMY |
|
Abstract: |
Research in text summarization is predominantly targets on measure of the worth
of sentences for a summary. The proposed work has associated the Deep learning
algorithm with fuzzy logic to improve the efficiency of the generated summary.
The proposed work has two phases, they are training phase and testing phases.
The training phase utilized to extract the benefits of fuzzy logic and deep
learning algorithm for the efficient summary generation. Similar to every
training phase, the proposed training phases is also possessed with well known
data and attributes. Latter to the training phase, the testing phases is
implemented to check the efficiency of the proposed approach. The experimental
evaluation of the proposed work provided the predictable results as, the average
precision obtained is 0.37, the average recall is 0.86 and the average f-measure
is obtained as 0.50%. |
|
Keywords: |
Multi-document Summary, Deep Learning, Fuzzy Logic, Natural Language Processing,
Neural Network. |
|
Source: |
Journal of Theoretical and Applied Information Technology
10 April 2014 -- Vol. 62. No. 1 -- 2014 |
|
Full
Text |
|
|
Title: |
A SURVEY OF UNICAST ROUTING PROTOCOLS BASED-GREEDY FORWARDING STRATEGIES FOR
VEHICULAR AD–HOC NETWORKS IN URBAN SCENARIO |
|
Author: |
MOHAMED SAAD BOBA, SULAIMAN MOHD NOR,SAMI ABBAS NAGAR |
|
Abstract: |
A vehicular ad hoc network (VANET) is a new technology that allows vehicles to
form a self-organized network without reliance on permanent infrastructure. The
characteristics of VANET such as rapid topology changes, high mobility, and
frequent link disconnections makes it difficult to design an efficient routing
protocol for routing data among vehicle to vehicle communication (V2V). Existing
greedy routing protocols for VANET are not efficient to meet every traffic
scenario such as low traffic densities. There are large numbers of surveys that
have studied different greedy routing protocol categories. We select a limited,
but representative number of these surveys to be reviewed in our work. This
survey intends to provide a comprehensive review of these categories of greedy
routing protocols. In this paper we provide a survey of greedy routing protocols
for a vehicular ad-hoc network, and present a timeline of the development of
existing greedy routing protocols. We discuss the advantages and disadvantages
of these routing protocols and define some current issues and possible
directions of future research related to using greedy routing protocols.
Finally, we investigate and compare several greedy algorithms designed for urban
VANET. A qualitative comparison of these approaches can serve as a guideline for
network designers to choose appropriate greedy routing protocols to meet network
application objectives. |
|
Keywords: |
Vehicular Ad Hoc Network V2V Communication, Urban Scenario, Forwarding Strategy,
Greedy Routing Protocol. |
|
Source: |
Journal of Theoretical and Applied Information Technology
10 April 2014 -- Vol. 62. No. 1 -- 2014 |
|
Full
Text |
|
|
Title: |
BIOMEDICAL SIGNALS ANALYSIS BY DWT SIGNAL DENOISING WITH NEURAL NETWORKS |
|
Author: |
GEETA KAUSHIK , DR. H.P.SINHA , DR. LILLIE DEWAN |
|
Abstract: |
The core intention of this work is to investigate the wavelet function that is
optimum in identifying and denoising the various biomedical signals. Using
traditional methods it is difficult to recover the noises present in the
signals. This paper presents a detail analysis of Discrete Wavelet Transform (DWT)
denoising on various wavelet families and biomedical signals such as ECG, EMG
and EEG. We have developed a trained network in order to optimally denoise the
signals by using a back propagation algorithm in the neural network. Initially
noise is added to the original signal, then the signal is decomposed using the
Shift Invariant method. After decomposition, the proposed wavelet based method
is used for noise removal. Then the signal is reconstructed by using wavelet
reconstruction method. The denoised signals will be compressed by a hybrid
wavelet shannon fano coding for reducing its storage size. |
|
Keywords: |
DWT, ECG, EEG, EMG, Neural network, Wavelet frequency thresholding |
|
Source: |
Journal of Theoretical and Applied Information Technology
10 April 2014 -- Vol. 62. No. 1 -- 2014 |
|
Full
Text |
|
|
Title: |
AN RFID BASED SUPPLY CHAIN INVENTORY MANAGEMENT SOLUTION FOR THE PETROLEUM
DEVELOPMENT INDUSTRY: A CASE STUDY FOR SHELL NIGERIA |
|
Author: |
INALEGWU ADOGA, RAUL VALVERDE |
|
Abstract: |
The objective of this paper is to show that an RFID supply chain inventory
management system can be a viable solution to the myriad of challenges
encountered in the operation of the warehouses and stores in the petroleum
development industry. This study involved the analysis of the warehouse and
inventory management system in Shell Petroleum Development Company (SPDC) in
Nigeria with a view of identifying current operational challenges and proffers
solutions to these challenges. A systems architecture of the solution is
presented in the paper and a partial prototype implemented with the purpose to
highlight how modern information technology and communication tools can be used
as a value added tool in the supply chain management of SPDC. |
|
Keywords: |
Inventory Management Systems, Supply Chain Systems, RFID, Petroleum Systems |
|
Source: |
Journal of Theoretical and Applied Information Technology
10 April 2014 -- Vol. 62. No. 1 -- 2014 |
|
Full
Text |
|
|
Title: |
AN ANALYSIS OF PRIVACY RISKS AND DESIGN PRINCIPLES FOR DEVELOPING
COUNTERMEASURES IN PRIVACY PRESERVING SENSITIVE DATA PUBLISHING |
|
Author: |
M. PRAKASH, G. SINGARAVEL |
|
Abstract: |
Government Agencies and many other organizations often need to publish sensitive
data – tables that contain unaggregated information about individuals. Sensitive
data is a valuable source of information for the research and allocation of
public funds, trend analysis and medical research. Publishing data about
individuals without revealing sensitive information about them is a significant
problem. A breach in the security of a sensitive data may expose the private
information of an individual, or the interception of a private communication may
compromise the security of a sensitive data. Private and Sensitive information
is integral to many data repositories. The efficiency of privacy preserving data
mining is crucial to many times–sensitive applications like medical data, voter
registration data, census data, social network data and customer data. Where
information dissemination is quick and easy, both individuals and custodians of
data are getting increasingly cautious about privacy, security and ethical
issues. In this paper privacy risks in publishing sensitive data and the design
principles for developing counter measures are proposed. The main contributions
of this study are four folds. First, domain knowledge about the Privacy and
related issues is described. Secondly the definition of the utility of released
data with reference to social network model is discussed. In the third fold,
knowledge based attacks; vulnerabilities and risk analysis are given. Finally,
the design considerations for developing countermeasures in privacy preserving
sensitive data publishing are presented. |
|
Keywords: |
Data Mining, Data Anonymization, Privacy, Privacy Preservation, Data Publishing,
Data Fusion, Data Security |
|
Source: |
Journal of Theoretical and Applied Information Technology
10 April 2014 -- Vol. 62. No. 1 -- 2014 |
|
Full
Text |
|
|
Title: |
A DYNAMIC QoS MODEL FOR MULTIMEDIA REAL TIME TRANSMISSION IN ENTERPRISE NETWORKS |
|
Author: |
C.G.RAVICHANDRAN , K.MANIVANNAN |
|
Abstract: |
Quality of Service (QoS) is a key factor in many research areas like multimedia
real time systems, Web services, distributed systems, Business networking and
runtime monitoring. QoS is multi-faceted, fuzzy and dynamic. Current researches
focus on implementation level performance assurance, ignoring domain specific or
application level metrics which are also very important to service users. In
multimedia real time transmissions are distributed and it met various hurdles
across the networks. Many real time protocols having difficulties to handle real
time multimedia streaming content through the networks. The proposed system
provides the multimedia streams to the end users in the high quality in terms
reliability, scalability, and uptime with enlarge the communication bandwidth to
transfer the compressed multimedia streams using Switched Ethernet Protocol(SEP)
at the gateway of each network. Video compressors generate highly variable
bit-rate streams that mismatch the constant-bit-rate channels typically provided
by real-time protocols severely reducing the efficiency of network utilization.
This model views on a framework with the bandwidth and the parameters which is
related to the compression. The objective of the model is to provide best
possible Quality of Service to each and every user across the networks that
access the multimedia real time transmission. |
|
Keywords: |
Switched Ethernet (SEP) protocol, Index of Quality (IQ), Quality of Service (QoS),
Non-Functional QoS, Functional QoS. |
|
Source: |
Journal of Theoretical and Applied Information Technology
10 April 2014 -- Vol. 62. No. 1 -- 2014 |
|
Full
Text |
|
|
Title: |
AN ALGORITHM ABOUT PARTNER SELECTION PROBLEM ON CLOUD SERVICE PROVIDER BASED ON
GENETIC |
|
Author: |
KANG YANFANG, NIE GUIHUA |
|
Abstract: |
Aiming at choosing suitable cloud service providers to construct a dynamic
alliance and then satisfying terminal customers more efficiently, to achieve the
optimal allocation of cloud services. This paper uses gray relative
comprehensive evaluation model to determine the optimizing index of cloud
services market. We use the multi-objective optimization model to study partner
selection problem quantificational and explain the model by genetic algorithm.
Selected the provider in the cloud computing market to offer the computing
services, storage services, software services as a research object, extract the
cost, response time, quality of service as a research indicators.
Multi-objective planning was changed into a single objective by weight, the
model is to be solved by genetic algorithm .Though the best fitness value, the
provider find the partners with the interests of the various cloud service
providers. Finally, an example show that the algorithm is rational to solve the
problem about finding the best cloud service provider partners, and it is the
validity of the model and algorithm. |
|
Keywords: |
Cloud Service Provider, Cloud Computing, Partners Selection, Grey Relational
Analysis,Genetic Algorithm, Multi-Objective Optimization |
|
Source: |
Journal of Theoretical and Applied Information Technology
10 April 2014 -- Vol. 62. No. 1 -- 2014 |
|
Full
Text |
|
|
Title: |
A CBR BASED APPROACH FOR WEB SERVICE AUTOMATIC DISCOVERY |
|
Author: |
IBRAHIM EL BITAR, FATIMA-ZAHRA BELOUADHA, OUNSA ROUDIES |
|
Abstract: |
The semantic Web service discovery has been given massive attention within the
last few years. With the increasing number of available Web services (WS) on the
web, looking for a particular service has become very difficult, especially with
the evolution of the clients’ needs, those who have become more and more
demanding. In this context, various approaches of WS Discovery have been
proposed ranging from UDDI syntactic approach to semantic approaches including
the intelligent discovery approaches based on CBR (Case Based Reasoning). In
this paper, we present our approach CBR4WSD (CBR based approach for WS
Discovery) that fits into the category of CBR based approaches for semantic WS
discovery. Our contribution outline includes a set of aspects which aim to
overcome the limitations of existing approaches and to mark the originality of
our CBR4WSD approach. These aspects are mainly related to the rationalization of
the processing, the control and mastery of the operated WS’ volume, the
alignment with standards as well as the improvement of the results quality in
terms of their ability to meet the functional and non- functional clients’
needs. |
|
Keywords: |
WS dynamic discovery, CBR, W3C standards, WS community, client satisfaction. |
|
Source: |
Journal of Theoretical and Applied Information Technology
10 April 2014 -- Vol. 62. No. 1 -- 2014 |
|
Full
Text |
|
|
Title: |
A NOVEL AND ROBUST APPROACH FOR DENOISING OF COMPUTED TOMOGRAPHY IMAGES USING
DUAL TREE COMPLEX WAVELET PACKETS AND EMPIRICAL MODE DECOMPOSITION TOWARDS
OPTIMIZATION |
|
Author: |
A.VELAYUDHAM, R.KANTHAVEL |
|
Abstract: |
Computed tomography (CT) images are usually corrupted by several noises from the
measurement process complicating the automatic feature extraction and analysis
of clinical data. To attain the best possible diagnosis it is very vital that
medical images be clear, sharp, and free of noise and artifacts. While the
techniques for obtaining digital medical images continue to improve, ensuing in
images of higher and higher resolution and quality, noise remains an issue for
many medical images. Removing noise in these medical images remains as one of
the key challenges in the study of medical imaging. A range of literatures have
been developed towards solving the hitch of medical images denoising which is a
significant stage in an automatic diagnosis system. In this research paper, we
propose a new image denoising technique using Dual Tree Complex Wavelet Packets,
Empirical Mode Decomposition and Sobel operator. Here, histon process is used in
order to surmount the smoothing filter type and it will not affect the lower
dimensions. We have taken into consideration two noises, Gaussian and salt &
pepper for proposed technique. The performance of the proposed image denoising
technique is assessed on the five CT images for the parameters, PSNR and SDME.
For performance assessment studies & comparison, our proposed denoising
technique is compared with the existing work in assorted noise levels. From the
obtained outcomes, we can conclude that the proposed denoising technique have
shown better values for the SDME of 67.8798 and PSNR of 24.841 for salt & pepper
noise which is very superior compared to existing methods. |
|
Keywords: |
CT, EMD, Dual Tree Complex Wavelet Packet (DTCWP), PSNR, SDME |
|
Source: |
Journal of Theoretical and Applied Information Technology
10 April 2014 -- Vol. 62. No. 1 -- 2014 |
|
Full
Text |
|
|
Title: |
A NEW REAL CODED GENETIC ALGORITHM CROSSOVER: RAYLEIGH CROSSOVER |
|
Author: |
SIEW MOOI LIM, MD. NASIR SULAIMAN, ABU BAKAR MD. SULTAN, NORWATI MUSTAPHA, BIMO
ARIO TEJO |
|
Abstract: |
This paper presents a comparison in the performance analysis between a newly
developed crossover operator called Rayleigh Crossover (RX) and an existing
crossover operator called Laplace Crossover (LX). Coherent to the previously
defined Scaled Truncated Pareto Mutation (STPM) operator to form two (2)
generational RCGAs called RX-STPM and LX-STPM, both crossovers are utilized. A
set of ten (10) benchmark global optimization test problems is used to
investigate the reliability, efficiency, accuracy and quality of solutions of
both optimization algorithms. Based on computational results, the RX-STPM has
yield a significant better performance as compared to LX-STPM. |
|
Keywords: |
Genetic Algorithms, Mutation Operator, Crossover Operator, Global Optimization |
|
Source: |
Journal of Theoretical and Applied Information Technology
10 April 2014 -- Vol. 62. No. 1 -- 2014 |
|
Full
Text |
|
|
Title: |
DECISION SUPPORT SYSTEM MODEL TO ASSIST MANAGEMENT CONSULTANT IN DETERMINING THE
PHYSICAL INFRASTRUCTURE FUND |
|
Author: |
EVARISTUS DIDIK MADYATMADJA |
|
Abstract: |
Program Nasional Pemberdayaan Masyarakat (PNPM) Mandiri Pedesaan is a learning
and development media for a development agents. Its also becomes a media to
create the development community concept[1]. Program Nasional Pemberdayaan
Masyarakat (PNPM) Mandiri Perdesaan is a real form action to ward off the
poverty in Indonesia. One of the efforts is by giving a physical project fund,
which is expected to increase productivity and efficiency of the community
itself. To obtain the donation, the social groups of communities should
previously submit proposal which are verified by the management of Program
Nasional Pemberdayaan Masyarakat (PNPM) Mandiri Perdesaan. There are many
criteria and proposals that require PNPM management to be able to take into
account the benefits and risks of its decision. To support the PNPM management
decision, it has been designed a system that afford helping PNPM management in
allocating physical project fund. A result of this study shows that decision
support system for fund allocation for physical project will help PNPM
management in making, removing, or editing the existing assessment models. With
an easiness of making a model, PNPM management will be able to understand the
most appropriate model to be applied in physical project, so that the allocation
for physical project fund is really gained by social groups that need it.
|
|
Keywords: |
Decision Support System, Physical, Model, Fund |
|
Source: |
Journal of Theoretical and Applied Information Technology
10 April 2014 -- Vol. 62. No. 1 -- 2014 |
|
Full
Text |
|
|
Title: |
ITERATIVE FUNCTION SYSTEM ALGORITHM BASED A CONFORMAL FRACTAL TRANSFORMATION FOR
BATIK MOTIVE DESIGN |
|
Author: |
RUSMONO YULIANTO, MOCHAMAD HARIADI, MAURIDHI HERY PURNOMO, KUNIO KONDO |
|
Abstract: |
Recently, Indonesia has a traditional painting motive which is widely known as
Batik. Usually, Batik is implemented as a motive for wall, car, clothes and even
airplane. Batik is also as a formal dress code in international meeting. The
Batik motive creation recently produced using traditional tools. Therefore, the
motive rules are creatively design in a traditional fashioned. This research
proposes a new method for creating motive rules to enhance traditional fashioned
Batik motive design. This will lead to more inspirational innovation for batik
motive designer. This research describes a method for creating Batik motive
rules based on fractal (IFS). First, a morphological erosion process is
generated to create template, while repetition and pattern placement are
conducted under Conformal Fractal Transformation based on Iterated Function
System. Iterated Function System also conducts extensive restriction to object
formed. The experimental results have shown that Batik motive produced Conformal
Fractal dimension is 1.83644, whereas the average of error value is 0.0808%. It
shows that our proposed method is closed to excellent, because the value of
error is less than 1%. The experimental results have been also verified by
qualified Batik teachers as respondents coming from different parts of
Indonesia. The verification results show that more than 82% stated that, the
experimental results have been stated as Batik pattern. |
|
Keywords: |
Batik, Iterated Function System, Conformal Transformation, Affine Transformation |
|
Source: |
Journal of Theoretical and Applied Information Technology
10 April 2014 -- Vol. 62. No. 1 -- 2014 |
|
Full
Text |
|
|
Title: |
IMPACT OF MOBILE CONTEXT-AWARE APPLICATIONS ON HUMAN COMPUTER INTERACTION |
|
Author: |
FERESHTEH FALAH CHAMASEMANI, LILLY SURIANI AFFENDEY |
|
Abstract: |
The rapid growth of technological advances and availability of mobile devices
has raised the opportunity to innovate feasible context-aware applications with
the ability to access information anywhere and anytime. Therefore, this paper
intends to review the recent developed mobile context-aware application. The
reviewed articles are selected based on their application domains which cover
the following six categories: smart space, healthcare, advertising, mobile
guide, memory aid and disaster alerting applications. The selected applications
are discussed based on their designed techniques, simulations and areas to show
their impact on human computer interaction. |
|
Keywords: |
Context-Aware, Context-Aware Application, Context-Awareness, Mobile Application,
Human Computer Interaction, |
|
Source: |
Journal of Theoretical and Applied Information Technology
10 April 2014 -- Vol. 62. No. 1 -- 2014 |
|
Full
Text |
|
|
Title: |
A NOVEL MODEL REFERENCE INTELLIGENT ADAPTIVE CONTROL USING NEURAL NETWORK AND
FUZZY LOGIC CONTROLLER |
|
Author: |
Dr.A.MURUGANANDHAM1, Dr. R.PRAKASH, |
|
Abstract: |
In this paper two novel intelligent model reference adaptive controllers are
proposed. In these schemes the intelligent supervisory loop is incorporated into
the conventional model reference adaptive controller framework by utilizing an
online growing neural / fuzzy network structure in parallel with it. In the
conventional MRAC scheme, the controller is designed to realize plant output
converges to reference model output based on the plant which is linear with
disturbance free system. This scheme is for controlling linear plant effectively
with unknown parameters. However, using MRAC to control the linear system with
disturbance and nonlinearities at real time is difficult. In this paper, it is
proposed to incorporate a neural / fuzzy controller in MRAC to overcome the
problem. The control input is given by the sum of the output of conventional
MRAC and the output of neural / fuzzy controller. The effectiveness of the
proposed control schemes is demonstrated by simulations. The proposed schemes
can significantly improve the system’s behavior and force the system to follow
the reference model and minimize the error between the model and plant output |
|
Keywords: |
Model Reference Adaptive Controller (MRAC), Neural Network (NN), Fuzzy Logic
Controller(FLC) |
|
Source: |
Journal of Theoretical and Applied Information Technology
10 April 2014 -- Vol. 62. No. 1 -- 2014 |
|
Full
Text |
|
|
|
