|
|
|
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
August 2019 | Vol. 97
No.16 |
|
Title: |
DETECTION ENVIRONMENT FORMATION METHOD FOR ANOMALY DETECTION SYSTEMS |
|
Author: |
NAZYM ZHUMANGALIYEVA, ANNA KORCHENKO, ALIYA DOSZHANOVA, AIGUL SHAIKHANOVA,
SHANGYTBAYEVA GULMIRA AVKUROVA ZHADYRA |
|
Abstract: |
Due to the intensive development of the digital business, malicious software and
other cyber threats are becoming more common. In order to increase the level of
security there are needed appropriate special countermeasures, which are able to
remain effective when new types of threats occur and which allow to detect cyber
attacks targeting on a set of information system resources in fuzzy conditions.
Different attacking effects on the corresponding resources generate various sets
of anomalies in a heterogeneous parametric environment. There is known a tuple
model of the formation of a set of basic components that allow to identify cyber
attacks. For its effective application a formal implementation of the approach
to the formation of sets of basic detection rules is necessary. For this
purpose, there has been developed a method that focuses on solving problems of
cyber attacks detection in computer systems, which is implemented through three
basic steps: formation of anomaly identifiers subsets; formation of decisive
functions; formation of conditional detection expressions. Using this method, it
is possible to form the necessary set of detection rules, which determine the
level of anomalous state of values in a heterogeneous parametric environment,
characteristic for the impact of a certain type of attack. The use of this
method at the creation intrusion detection systems will expand their
functionality regarding the cyber attacks detection in a weakly formalized fuzzy
environment. |
|
Keywords: |
Detection Rules, Attacks, Cyber Attacks, Anomalies, Intrusion Detection Systems,
Anomaly Detection Systems, Attack Detection Systems |
|
Source: |
Journal of Theoretical and Applied Information Technology
31st August 2019 -- Vol. 97. No. 16 -- 2019 |
|
Full
Text |
|
|
Title: |
CONFORMABLE DECOMPOSITION METHOD FOR TIME-SPACE FRACTIONAL INTERMEDIATE SCALAR
TRANSPORTATION MODEL |
|
Author: |
S.O. EDEKI , G. O. AKINLABI , R. M. JENA , O.P. OGUNDILE , S. CHAKRAVERTY |
|
Abstract: |
This paper considers the analytical solutions of a time-space fractional
intermediate scalar transportation model via the application of Conformable
Decomposition Algorithm. The method is a blend of Adomian Decomposition coupled
with fractional derivative defined in conformable sense; herein referred to as
CADM. Illustrative examples (cases) are considered in order to clarify the
effectiveness of the proposed method, and the solutions are presented in
infinite series form with high level of convergence to the exact form of
solution. |
|
Keywords: |
Advection-Dispersion Model, Adomian Decomposition Method, Fractional Calculus,
Conformable Derivative |
|
Source: |
Journal of Theoretical and Applied Information Technology
31st August 2019 -- Vol. 97. No. 16 -- 2019 |
|
Full
Text |
|
|
Title: |
COMARATIVE STUDY ON METHODS USED IN PREVENTION AND DETECTION AGAINST ADRESS
RESOLUTION PROTOCOL SPOOFING ATTACK |
|
Author: |
TSEHAY ADMASSU ASSEGIE , PRAMOD SEKHARAN NAIR |
|
Abstract: |
Address Resolution Protocol spoofing attack is the most common type of local
area network attacks. This is because the protocol packet does not contain any
authentication information, which indicates the origins of reply packet.
Therefore, all of the devices in Local Area Network are vulnerable to this
attack. A tool like, ARPspoof can be used to generate a forged Address
Resolution Protocol reply packet to perform the attack, even without any
knowledge of the details behind address resolution process. The existence of
such automated tools has created a hole for the attackers to easily attack a
host in a local area network. And although it is underestimated attack, this
attack opens the door for much sophisticated form of attacks, such as
Man-in-Middle attack or even domain name system spoofing and many more
sophisticated forms of attacks. In this paper, we will explore different tools
and methods used in detection and prevention of Address Resolution Protocol
Spoofing attack. The ARPspoof tool will be used to send spoofed Address
Resolution Protocol reply packet to a host in local area network to further
study how a host maintains the address resolution protocol cache table with the
spoofed or a fake media access control, MAC cache table. Finally, we will
compare the tools and methods used in detection and prevention against Address
Resolution Protocol Spoofing attack in terms of their effectiveness in detection
and prevention of the attack and system performance requirements. |
|
Keywords: |
ARP Spoofing, ARP Spoofing Attack, Packet Sniffing, ARP Inspection, Network
Security |
|
Source: |
Journal of Theoretical and Applied Information Technology
31st August 2019 -- Vol. 97. No. 16 -- 2019 |
|
Full
Text |
|
|
Title: |
GLOBAL STABILITY OF SEIR MODEL WITH LYAPUNOV FUNCTION METHOD WITHIN COMPLEX
NETWORK |
|
Author: |
DOUNIA BENTALEB , SAIDA AMINE , ZAKARIA KHATAR |
|
Abstract: |
In this paper we performed a mathematical study of an SEIR epidemic model on
dynamical network. We propose a mathematical SEIR model that consider
Watts-Strogatz type complex network that involve contact among individuals. The
stability conditions are obtained by using the Lyapunov function, and
interpreted using a new threshold noted Ks. In order to show the effect of the
network structure on the disease transmission and its asymptotic behavior. Using
an algorithm programmed in R, a numerical simulation is presented to illustrate
the influence of the small world network properties on the spreading of the
disease in our model. This simulation can be used to determine the statute of
different diseases in a region using data in this region and the corresponding
parameters of the infectious diseases. |
|
Keywords: |
SEIR Epidemic Model, Complex Network, Lyapunov Function, Global Stability,
Infectious Diseases. |
|
Source: |
Journal of Theoretical and Applied Information Technology
31st August 2019 -- Vol. 97. No. 16 -- 2019 |
|
Full
Text |
|
|
Title: |
APPLYING EFFECTIVE KNOWLEDGE MANAGEMENT MATURITY MODEL |
|
Author: |
WANG GUNAWAN, KRISTIAN, MARISA KARSEN |
|
Abstract: |
In todays world, knowledge has become valuable assets in any organization.
Therefore, the use of knowledge should be managed and developed properly to
produce maximum benefits, and to support the organization's objectives. Although
knowledge is considered important, many organizations in Indonesia still face
many difficulties to measure and implement effective knowledge management (KM).
Many corporations have reported major failures in adopting KM system. There are
very few references can be found especially for Indonesian corporations, to
apply an effective KM that provides maximum benefits. So, many companies need KM
framework to implement KM. The article examines the application of knowledge
management system (KMS) in XYZ Co., a large IT service company, that serves
major large corporations in Indonesia with the purpose to provide a reference of
KMS application. The article adopts the successful KMS implementation based on
the maturity level that was developed by Uday Kulkarni, Robert St. Louis, and
Intel Corp. KMS maturity level has advantages in providing systematic thinking
that commonly ignored by the Indonesian corporations. But The KMS maturity model
has been widely applied in major corporations and produced significant results.
This maturity model can be used to measure the level of successful KMS
implementation in corporation.The article combines both KMS maturity model and
10-step KM roadmap developed by Armit Tiwana to maximize the output of KMS. The
outcome of article is an effective KM implementation framework as that can be
used as a reference for large corporation in Indonesia to apply KMS. |
|
Keywords: |
Knowledge Management, Knowledge Management Maturity Level, Knowledge Management
System, KM Maturity Model. |
|
Source: |
Journal of Theoretical and Applied Information Technology
31st August 2019 -- Vol. 97. No. 16 -- 2019 |
|
Full
Text |
|
|
Title: |
COMPARISON OF ECC AND RSA ALGORITHMS IN IOT DEVICES |
|
Author: |
ZEINAB VAHDATI, SHARIFAH MD YASIN, ALI GHASEMPOUR, MOHAMMAD SALEHI |
|
Abstract: |
IoT is the evolution of the internet. Concerning tight communication between the
individual and business, number of IoT nodes are rapidly increasing. Most of the
services in IoT heavily rely on security mechanisms that pose security
imperative for embedded devices in IoT. The failures in IoT can have severe
results; consequently, the research toward security concerns are of extreme
significance in IoT. Preserving the confidentiality and privacy, ensuring the
availability of the services that are proposed by IoT ecosystem, assuring the
safety of the assets in IoT like devices, data, infrastructures, and users, are
the main objectives in IoT security. The significant issue that makes IoT
devices vulnerable is the lack of an appropriate security mechanism to preserve
data. Attackers can exploit these weaknesses to obtain access to valuable data.
Hence, thoughtfully chosen and practically tested encryption algorithm must be
performed to enhance the device efficiency and decrease the risk of sensitive
data exposure. Understanding and comparing algorithms implemented in IoT
devices, regarding performance discussed in this paper. RSA (Rivest Shamir
Adleman) and ECC (Elliptic Curve Cryptography) algorithms have been compared for
identifying the most lightweight, secure, efficient implementation in IoT. Based
on the findings, the ECC algorithm outperforms RSA in a constrained environment
in terms of memory requirements, energy consumption, key sizes, signature
generation time, key generation and execution time, and decryption time while
RSA performs better in verifying the signature and encrypting. |
|
Keywords: |
Elliptic Curve Cryptography, ECC, RSA, Internet of Things (IoT), Security
Services. |
|
Source: |
Journal of Theoretical and Applied Information Technology
31st August 2019 -- Vol. 97. No. 16 -- 2019 |
|
Full
Text |
|
|
Title: |
DATA ANALYSIS BASED ON LATANE THEORY AND ANALYSIS OF EVENTS CHANGING IN SOCIAL
NETWORKS |
|
Author: |
A.Zh. AKHMETOVA, T.V.BATURA, L.L. LA, F.A.MURZIN |
|
Abstract: |
The article describes the main methods and algorithms for analyzing user data
from social networks. Special attention is paid to the method of measuring
informational influence between users in a social network. In the process of
analyzing social networks, it is advisable to consider a number of numerical and
non-numerical characteristics, relations and sets that are naturally associated
with network users and the messages circulating in it. The quantitative
characteristics, relationships, and sets that are computable from data obtained
from social networks, such as numeric single characteristics, non-numeric
characteristics, sets, and numerical characteristics associated with sets, are
presented. Modifications of the theory of dynamic social influence of Latane are
proposed. The formulas describing the amount of social pressure directed at the
individual for different situations have been modified. The method of R/S
analysis, which can be applied to predict the change of events in social
networks, is proposed. This method of time series analysis allows you to
determine whether the time series is random or persistent, that is, having
long-term memory. The article briefly describes the developed software package
that allows to extract information from social networks, to process, analyze and
visualize data. Testing was carried out on the data obtained from the social
network vkontakte. |
|
Keywords: |
Analysis Of Social Networks, The Internet, Vkontakte, Data Analysis, Latane
Theory |
|
Source: |
Journal of Theoretical and Applied Information Technology
31st August 2019 -- Vol. 97. No. 16 -- 2019 |
|
Full
Text |
|
|
Title: |
BALANCING EXPLORATION AND EXPLOITATION IN ACS ALGORITHMS FOR DATA CLUSTERING |
|
Author: |
AYAD MOHAMMED JABBAR, RAFID SAGBAN, KU RUHANA KU-MAHAMUD |
|
Abstract: |
Ant colony optimization (ACO) is a swarm algorithm inspired by different
behaviors of ants. The algorithm minimizes deterministic imperfections by
assuming the clustering problem as an optimization problem. A balanced
exploration and exploitation activity is necessary to produce optimal results.
ACO for clustering (ACOC) is an ant colony system (ACS) algorithm inspired by
the foraging behavior of ants for clustering tasks. The ACOC performs clustering
based on random initial centroids, which are generated iteratively during the
algorithm run. This makes the algorithm deviate from the clustering solution and
performs a biased exploration. This study proposes a modified ACOC called the
population ACOC (P-ACOC) to address this issue. The proposed P-ACOC allows the
ants to process and update their own centroid during the algorithm run, thereby
intensifying the search at the neighborhood before moving to another location.
However, the algorithm quickly produces a premature convergence due to the
exploitation of the same clustering results during centroid update. To resolve
this issue, this study proposes a second modification by adding a restart
strategy that balances between the exploration and exploitation strategy in
P-ACOC. Each time the algorithm begins to converge with the same clustering
solution, the restart strategy is performed to change the behavior of the
algorithm from exploitation to exploration. The performance of the proposed
algorithm is compared with that of several common clustering algorithms using
real-world datasets. The results show that the accuracy of the proposed
algorithm surpasses those of other algorithms. |
|
Keywords: |
Data Clustering, Optimization Clustering, Swarm Clustering, Exploration,
Exploitation. |
|
Source: |
Journal of Theoretical and Applied Information Technology
31st August 2019 -- Vol. 97. No. 16 -- 2019 |
|
Full
Text |
|
|
Title: |
ANALYSIS OF HYBRID METAHEURISTIC TECHNIQUES ON CLASSIFICATION |
|
Author: |
ANJU BALA , PRITI |
|
Abstract: |
This paper discusses different hybrid version of Ant Colony Optimization (ACO),
Particle Swarm Optimization (PSO), Differential Evaluation (DE) and Genetic
Algorithm (GA) and analyzes the performance of different hybrid algorithms in
terms of classification accuracy. The hybridization is done to remove the
limitations of each individual technique by incorporating the advantages of
other techniques resulting in better convergence towards global optima. The
paper covers various hybrid meta-heuristic techniques including ACO-PSO, ACO-GA,
PSO-GA, GA-DE, and ACO-PSO-GA. The analysis has been done on different datasets
downloaded from UCI repository using the parameters classification accuracy,
sensitivity and specificity. The analysis clearly shows the impact of the
hybridization on the classification in terms of accuracy as well as sensitivity
and specificity. |
|
Keywords: |
ACO, PSO, GA, DE, Hybrid, Classification, Meta-heuristic |
|
Source: |
Journal of Theoretical and Applied Information Technology
31st August 2019 -- Vol. 97. No. 16 -- 2019 |
|
Full
Text |
|
|
Title: |
EVALUATION OF THE USE OF E-LEARNING IN AIRLANGGA SAMARINDA STMIK SPB EDUCATION
SYSTEM |
|
Author: |
Achmad Soni, Ahmad Nurul Fajar |
|
Abstract: |
STMIK SPB Airlangga Samarinda is one of the university who applies E-Learning.
In Samarinda there are not many universities who applies E-Learning like SPB
Airlangga. SPB Airlangga is a university who focuses on TI (Teknik Informatika).
E-learning has evolved from just an online course into an advanced technology in
material distribution and course discussions without being bound by permanent
time and place. SPB STMIK Airlangga Samarinda has applied e-learning that is
already used by lecturers and students as the media for online course, included
in them are discussion for lecture courses, tasks arrangement and online tests.
In learing models such as these, lecturers, students and the educational
organization need smarter tools to deal with the problem of ongoing feedback
from the education process. It is to offer a learning environment that can
enhance the learning effectiveness of new learning modes as well as
organizations and efficient institutional resources to gain knowledge on any
topic, So an evaluation how the effect of implementing e-learning in the
learning process in SPB STMIK Airlangga Samarinda using the evaluation through
evaluating system user acceptance is done. The activity of this research is the
evaluation of several variables related to user behavior towards the use of
e-learning in SPB STMIK Airlangga Samarinda where the placing of the variables i
done through TAM approach (Ibrahim, Leng et al. 2018). This research will
measure the following independent variables: (1). Perceived Of Usefulness/POU)
(2). Perceived Ease Of Use/PEOU, (3). Attitude Towards Using, these dependent
variables: (4). Actual Use. The results of this research are expected to provide
useful material for the development of science and research in the scope of
e-learning and everything related to all aspects that influence it. The results
of the evaluation of the use of E-Learning in the STMIK SPB Airlangga Samarinda
Lecture System were obtained from the use of data collection through a
questionnaire method obtained directly from students and lecturers at STMIK SPB
Airlangga Samarinda, and the produced TAM factors assumed to influence the use
of e-learning systems at SPB STMIK Airlangga Samarinda are 1). Perceived Ease Of
Use/PEOU, 2). Perceived Of Usefulness/POU, 3). Attitude Towards Using/ATU, and
4). Actual use/AU |
|
Keywords: |
E-Learning, STMIK, TI, Evaluation |
|
Source: |
Journal of Theoretical and Applied Information Technology
31st August 2019 -- Vol. 97. No. 16 -- 2019 |
|
Full
Text |
|
|
Title: |
UNDERSTANDING CONSUMER BEHAVIOUR TOWARDS UTILIZATION OF ONLINE FOOD DELIVERY
PLATFORMS |
|
Author: |
Dr CHETAN PANSE , Dr SAHILESH RASTOGI , Ms ARPITA SHARMA , NAMGAY DORJI |
|
Abstract: |
The main purposes of this study are to provide a comprehensive relationship
between consumer attitudes toward online food ordering. This study adopted
quantitative research with primary data collected through a questionnaire with
online food delivery platforms and customer based on their knowledge, attitudes,
perspectives, and needs of online food delivery services. In this research
paper, the reserachers examined the growth of food aggregator industry.
Researchers also have examined the business model these companies follow and its
effect on the conventional restaurant business in India.
This study aims at
the behaviour of customers towards online food delivery platforms that are fast
changing the food retailing landscape across India. Hence, the study focuses on
exploring the drivers of consumer behaviour towards online food delivery apps.
The study identifies a research model having seven independent variables and two
dependent variables. The independent variables comprise of, Control,
Credibility, Convenience, Ease of Informativeness, Technology Anxiety, need for
Interaction and Pleasure. The dependent variables comprise of consumer
satisfaction and consumer intentions. Partial Least Squares (PLS) analysis using
Smart PLS software is carried out to test the significance of the model.
The
outcome shows that factors like Convenience, Control, Technology Anxiety & Ease
of Information significantly affect Consumer Satisfaction, which in-tern
significantly affect the Consumer Intentions, while Convenience also
significantly affect the Consumer Intentions. |
|
Keywords: |
Food delivery platform; Credibility; Convenience; Informativeness; Technology
Anxiety; PLS |
|
Source: |
Journal of Theoretical and Applied Information Technology
31st August 2019 -- Vol. 97. No. 16 -- 2019 |
|
Full
Text |
|
|
Title: |
MULTI HYBRIDIZATION OF SWARM INTELLIGENCE METHODS TO SOLVE JOB SHOP SCHEDULING
PROBLEM |
|
Author: |
JEBARI HAKIM, RAHALI EL AZZOUZI SAIDA, SAMADI HASSAN, SIHAM REKIEK |
|
Abstract: |
Scheduling is one of the fundamental and crucial elements in making production
organizations efficient and effective in the usage of resources. It also
concerns the allocation of resources over a period of time to execute a set of
jobs. The purpose of paper is to establish multi hybridization of swarm
intelligence methods HABCPSOGA to solve job shop scheduling problems. The
performance of proposed algorithms are evaluated by applying it to all
well-known benchmark instances and by comparing theirs results with the results
of others methods HABCGA available in the literature. The experiment results
show that the multi hybridization of swarm intelligence methods improve the
effectiveness of the algorithm and they indicate how these proposed methods
influence the resolution of the defined problem. |
|
Keywords: |
Scheduling, Job Shop, Multi Hybridization, Swarm Intelligence, GA. |
|
Source: |
Journal of Theoretical and Applied Information Technology
31st August 2019 -- Vol. 97. No. 16 -- 2019 |
|
Full
Text |
|
|
Title: |
A COGNITIVE ADAPTIVE ARTIFICIAL IMMUNITY ALGORITHM FOR DATABASE INTRUSION
DETECTION SYSTEMS |
|
Author: |
AYMAN MOHAMED MOSTAFA, NACIM YANES, SAAD AWADH ALANAZI |
|
Abstract: |
Applying artificial immune system in database security is a challenging trend to
increase detection rate for internal intrusive users or administrators. Negative
selection algorithm and danger theory are artificial immunity algorithms that
provide promoting solutions for obtaining privacy-preserving data. This paper
develops a mixed innate and adaptive immunity algorithm based on negative
selection algorithm and danger they to detect unknown intrusive users based on
multi-layer pattern matching. A secret sharing mechanism is applied to monitor
database administrators’ transactions in a lowest possible time. The proposed
immunity algorithm is based on a continuous cognitive adaptive methodology for
using detected users as antigens for future faster response to unknown patterns.
The key features of the presented immunity algorithm are its uniqueness for each
detector, multi-layer detection and pattern matching, diversification in
detecting unknown users at all levels of security, self-protection by using
detected users as antigens for future detection process, and finally learning
and memorization for storing previously detected users in antigen table to be
used in pattern detection process. The conducted experimental results of the
developed artificial immunity algorithm are compared to five algorithms and have
achieved a high detection rate, low false positive and low false negative
alarms. |
|
Keywords: |
Database Security, Artificial Immune System, Negative Selection Algorithm,
Danger Theory, and Secret Sharing |
|
Source: |
Journal of Theoretical and Applied Information Technology
31st August 2019 -- Vol. 97. No. 16 -- 2019 |
|
Full
Text |
|
|
Title: |
DEVELOPING A MATHEMATICAL MODEL AND INTELLECTUAL DECISION SUPPORT SYSTEM FOR THE
DISTRIBUTION OF FINANCIAL RESOURCES ALLOCATED FOR THE ELIMINATION OF EMERGENCY
SITUATIONS AND TECHNOGENIC ACCIDENTS ON RAILWAY TRANSPORT |
|
Author: |
AKHMETOV B., LAKHNO V., MALYUKOV V., OMAROV A., ABUOVA К.., ISSAIKIN D., LAKHNO
M. |
|
Abstract: |
The article substantiates the need to use intelligent computer technologies in
order to automate the process of analyzing the selection of a rational strategy
for the distribution of financial and material resources allocated for the
elimination of technogenic situations or emergencies on railway transport. The
authors have proposed a model for developing recommendations to the situation
center for emergency situations elimination and to the liquidators working
directly at the accident place or in the emergency area. The model allows to
create predictive estimates for various options for the distribution of
financial and material resources spent on emergency situations elimination and
its consequences. This model is a component of the intellectual decision support
system in the tasks of choosing the financial component of a emergency
situations elimination strategy and technogenic situations on railway transport.
The model is based on solving an endless antagonistic quality game with
discontinuous gain functions. A distinctive feature of such a game is to
determine the optimal mixed strategies, there was proposed a constructive method
for searching them. This made it possible to develop specific recommendations
for determination the amount of financial and material resources that are
sufficient to eliminate the consequences of emergency situations and technogenic
situations on railway transport in practice. In our opinion, the model is quite
universal. Its application can be extended to the solution of similar problems
associated with the choice of a rational financial and material strategy for
emergency situations elimination in other sectors. |
|
Keywords: |
Decision support system, Emergency situation analysis, Financial and material
strategy, Recommendation generation, Model |
|
Source: |
Journal of Theoretical and Applied Information Technology
31st August 2019 -- Vol. 97. No. 16 -- 2019 |
|
Full
Text |
|
|
Title: |
CENTRAL INTELLIGENT BIOMETRIC AUTHENTICATION BASED ON VOICE RECOGNITION AND
FUZZY LOGIC |
|
Author: |
DR. ALIA KARIM ABDUL-HASSAN, IMAN HASSOON HADI |
|
Abstract: |
Reliable identity management must be built with an accurate user identity
recognition method. This recognition usually is the core of the authentication
method which is the essential part of any identity management system. The
authentication must carefully be designed, especially when it is used among
different service providers. The authentication is a user identity verifying and
protecting mechanism. It consists of three main components, user identity
attributes, the verification method, and the log-in mechanism. The log-in
component has great impact on authentication, when the user needs to be
authenticated to be given access to several service providers. In addition, the
verification of the claimed user attributes, involve the decisive role in the
authentication because it will produce the final decision of the identity
proving process, so it is important to be accurate and intelligent as much as
possible. In this paper, a central intelligent biometric authentication approach
is proposed; this authentication is based on the Mel-frequency Cepstral
coefficients (MFCC) voice attributes, fuzzy classifier, and client-server model
as log-in mechanism. The proposed fuzzy classifier depends on the fuzzy set
inner product and a predefined threshold. This classifier is designed as an
intelligent identity verification method. The experiments show 95.45% accuracy
in offline user authentication using ELSDSR dataset. |
|
Keywords: |
Central Authentication, Voice, Fuzzy Logic, MFCC |
|
Source: |
Journal of Theoretical and Applied Information Technology
31st August 2019 -- Vol. 97. No. 16 -- 2019 |
|
Full
Text |
|
|
Title: |
CONTEXT AWARE IN ADAPTIVE UBIQUITOUS E-LEARNING SYSTEM FOR ADAPTATION
PRESENTATION CONTENT |
|
Author: |
SALMA EL JANATI, ABDELILAH MAACH, DRISS EL GHANAMI |
|
Abstract: |
The Advances in adaptive learning systems (ALS) and the rapid development of
ubiquitous systems (US) mean that e-learning is not limited to certain
parameters. However, the e-learning system (E-LS) must take into account the
context-aware of learners to help them to complete their activity. The
traditional online educational systems suffer from lack of immediate help and
limitations in the presentation of pedagogical content, which yield the learner
unable to receive learning resources that meet his/her needs and reduces the
effectiveness of learning. In this paper, we suggest a new framework to sense
the learner’s context and adapt it automatically to the adequate presentation
content, which meet the learner’s preferences and needs of learners who suffer
from hearing and visual impairments. This framework is based on mixing Dynamic
Adaptive Hypermedia System (DAHS) and Ubiquitous Learning System (ULS). It
proposes a box tools that performs information, transcoding and location in
order to generate a new presentation content based on the context-aware of the
learner. |
|
Keywords: |
Adaptive Learning Systems, Ubiquitous Systems, E-learning, Hypermedia System,
Context-aware, Learner Model, Transcoding, Speech-to-text. |
|
Source: |
Journal of Theoretical and Applied Information Technology
31st August 2019 -- Vol. 97. No. 16 -- 2019 |
|
Full
Text |
|
|
Title: |
METAHEURISTIC APPROACH USING GREY WOLF OPTIMIZER FOR FINDING STRONGLY CONNECTED
COMPONENTS IN DIGRAPHS |
|
Author: |
ALAA AL-SHAIKH, BASEL A. MAHAFZAH, MOHAMMAD ALSHRAIDEH |
|
Abstract: |
Finding strongly connected components (SCCs) in a directed graph (digraph) has
been investigated extensively. Tarjan’s algorithm is the most fundamental method
of finding SCCs in digraphs that uses Depth-First Search (DFS) and it has a
linear time complexity. On the other hand, the Forward-Backward (FW-BW)
algorithm is another well-known method that is based on the divide-and-conquer
approach, yet it is time consuming. In this paper, we introduce a new approach
for finding the SCCs in digraphs in linear time using Grey Wolf Optimizer (GWO),
which is a recent metaheuristic algorithm. Experimental results show that
finding SCCs using GWO outperforms FW-BW in terms of run time. In this context,
GWO achieved 62.27% average run time improvement over FW-BW. Furthermore,
average solution quality (accuracy) from GWO compared to the exact algorithm
FW-BW is 97.57%. |
|
Keywords: |
Grey Wolf Optimizer; Strongly Connected Components; Metaheuristic Algorithms;
Optimization Problem; Forward-Backward Algorithm |
|
Source: |
Journal of Theoretical and Applied Information Technology
31st August 2019 -- Vol. 97. No. 16 -- 2019 |
|
Full
Text |
|
|
Title: |
THE IMPLEMENTATION OF THE OPTIMAL RULE BASES GENERATED BY HYBRID FUZZY C-MEAN
AND PARTICLE SWARM OPTIMIZATION |
|
Author: |
ACHMAD EFENDI, 2SAMINGUN HANDOYO, ARI P.S. PRASOJO, MARJI |
|
Abstract: |
The aims of the paper are to generate fuzzy rule bases that be optimized through
fuzzy c-means (FCM) and particle swarm optmization (PSO), and to develope the
fuzzy inference systems (FIS) that have the system inputs are combination
between the number of linguistic values and the number of assumed lags influence
to the system output. The outputs of FCM including are the cluster centers and
partition matrix. The number of rules in the fuzzy rule bases formed by FCM is
the same as the number of clusters. The cluster centers are used as the center
parameters of the Gaussian membership function (MF), while the elements of
partition matrix are used to determine the optimal spread parameters of
Gaussian's MF through PSO algorithm. The identification of system input
variables is done using plot partial autocorrelation function (PACF). The
formation of a tentative model based on significant PACF values to construct the
input-output pairs matrix which is subsequently grouped by using FCM. The
implementation of FIS uses the exchange rate of USD to IRD dataset that is
obtained four significant PACF values on lags of k = 1, 5, 8, and 10 which are
subsequently used as input variables. Based on the four input variables, systems
with 2 inputs, 3 inputs, and 4 inputs combined with the number of clusters of n
= 3, 5, and 7 formed 21 systems. Based on the values of both MAPE and R2 that is
obtained the result that in training data if the number of input variables and
number of clusters are increased then the system has the better performance, but
in the testing data, the system performance decresed when the number of input
variables and the number of clusters.are increased. The best performing system
is the system with 2 inputs and 5 clusters. |
|
Keywords: |
Exchange rate, Fuzzy C-Means, Generating rule bases, Particle Swarm Optimization |
|
Source: |
Journal of Theoretical and Applied Information Technology
31st August 2019 -- Vol. 97. No. 16 -- 2019 |
|
Full
Text |
|
|
Title: |
GREEN INFORMATION TECHNOLOGY GOVERNMENT REGULATION COMPONENTS: IMPROVING
INDONESIA GREEN INFORMATION TECHNOLOGY |
|
Author: |
HUDIARTO SUKARMAN, NURIL KUSUMAWARDANI SOEPRAPTO PUTRI, CAROLYN HONG GUI QING |
|
Abstract: |
Information and communication technology (ICT) becomes one of the key drivers of
economic growth and competitiveness. In contrary, the increasing of the ICT
usage is not followed by the increasing of the green ICT awareness and behavior.
Our previous research on Private higher education institution practice of green
information technology governance model had resulted some obstruction on the
implementation. One of the most crucial aspect among others is the government
policies and regulations deficiencies. Hence, this study describes as well as
proposes green IT government regulation components which can be regulated by
Indonesia’s government. 6(six) green IT government regulation components (green
knowledge, regulatory design, regulation dimensions, directive cost, awareness
and innovation/technology) were categorized based on literature review. |
|
Keywords: |
Green Computing, Green Information Technology, Green Information Technology
Government, Government Regulation) |
|
Source: |
Journal of Theoretical and Applied Information Technology
31st August 2019 -- Vol. 97. No. 16 -- 2019 |
|
Full
Text |
|
|
|
