|
|
|
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
March 2020 | Vol. 98
No.05 |
|
Title: |
EVALUATING USERS SATISFACTION FACTORS OF THE CUSTOMER RELATIONSHIP MANAGEMENT
SYSTEM: A STUDY OF KHEDMAH SYSTEM AS A SINGLE SERVICE PLATFORM |
|
Author: |
SHAFIQ DARWISH ALABRI , SUZILAWATI KAMARUDIN |
|
Abstract: |
This study investigates the factors that influence user satisfaction of
Khedmah's system in Oman. The Information Systems Success Model (ISSM),
Technology Acceptance Model (TAM), and Theory of Planned Behavior model (TPB)
are integrated to form the theoretical framework for this study. This study
investigates the impact of the individual's computer skills, perceived ease of
use, and perceived usefulness have on the user satisfaction of Khedmah's system.
These constructs were derived from the three models. Data were collected from
the users of Khedmah system through a self-administered questionnaire. The
researchers relied on the judgmental technique to identify the research sample.
Using SPSS v25 and SmartPLS 3, a total of 164 questionnaires were analyzed. The
findings revealed that generally the users are satisfied with the Khedmah’s
performance. The findings also illustrated that the individual's computer
skills, the perceived ease of use, and the perceived usefulness positively and
significantly affect the level of user satisfaction of the system. The findings
of the study would enhance the performance of Khedmah system, which will reflect
positively on the level of user satisfaction. It would enrich the knowledge of
the managers and system developers to further develop the system in order to
achieve high levels of users’ satisfaction. Also, the findings of this study
provide insight for the developers of similar systems in other institutions. The
study findings confirm that combining ISSM, TAM, and TPB models is applicable to
CRM. The findings of the study would enrich the CRM literature. Based on the
researchers’ knowledge, this study is the first of its kind in CRM literature
that combines these three models. |
|
Keywords: |
Information Systems Success Model (ISSM), Technology Acceptance Model (TAM),
Theory of Planned Behavior model (TPB), Customer Relationship Management (CRM),
Khedmahs System |
|
Source: |
Journal of Theoretical and Applied Information Technology
15th March 2020 -- Vol. 98. No. 05 -- 2020 |
|
Full
Text |
|
|
Title: |
ENHANCEMENT OF SINGLE-HANDED BENGALI SIGN LANGUAGE RECOGNITION BASED ON HOG
FEATURES |
|
Author: |
TASNIM TABASSUM, IQBAL MAHMUD, MD. PALASH UDDIN, EMRAN ALI, MASUD IBN AFJAL,
ADIBA MAHJABIN NITU |
|
Abstract: |
Deaf and dumb people usually use sign language as a means of communication. This
language is made up of manual and non-manual physical expressions that help the
people to communicate within themselves and with the normal people. Sign
language recognition deals with recognizing these numerous expressions. In this
paper, a model has been proposed that recognizes different characters of Bengali
sign language. Since the dataset for this work is not readily available, we have
taken the initiative to make the dataset for this purpose. In the dataset, some
pre-processing techniques such as Histogram Equalization, Lightness Smoothing
etc. have been performed to enhance the signs’ image. Then, the skin portion
from the image is segmented using YCbCr color space from which the desired hand
portion is cut out. After that, converting the image into grayscale the proposed
model computes the Histogram of Oriented Gradients (HOG) features for different
signs. The extracted features of the signs’ are used to train the K-Nearest
Neighbors (KNN) classifier model which is used to classify various signs. The
experimental result shows that the proposed model produces 91.1% accuracy, which
is quite satisfactory for real-life setup, in comparison to other investigated
approaches. |
|
Keywords: |
Deaf and Dumb, Bengali Sign Language Recognition, Skin Segmentation, HOG
Features, Bengali Sign Language Dataset |
|
Source: |
Journal of Theoretical and Applied Information Technology
15th March 2020 -- Vol. 98. No. 05 -- 2020 |
|
Full
Text |
|
|
Title: |
AUTOMATED MALARIA DIAGNOSIS USING OBJECT DETECTION RETINA-NET BASED ON THIN
BLOOD SMEAR IMAGE |
|
Author: |
JASMAN PARDEDE, IRMA AMELIA DEWI, REZA FADILAH, YANI TRIYANI |
|
Abstract: |
Malaria diagnosis is decided based on index malaria value which calculated from
the amount of normal and infected erythrocyte on thin blood smear using
microscope by a clinical pathologist. This activity is done manually and wastes
a lot of time. Object detection using Convolutional Neural Network (CNN) is one
of approach for solving this problem. However, the traditional object detection
using CNN shows inadequate classification performance in labelling classes
object. This paper is focused on the implementation of RetinaNet object
detection approach to diagnose malaria. First, ResNet101 and ResNet50 used as
RetinaNet backend network architecture for detecting both normal and infected
erythrocytes on thin blood smear image with 1000x microscope zoom. Next, count
every label of detected-object and calculate malaria-index value. Finally, after
malaria-index value obtained, malaria diagnosis is defined. The algorithm
performance with ResNet101 backend shows average precision (AP) 0,94, average
recall 0,74, and average accuracy 0,73. Then the usage of ResNet50 backend in
RetinaNet algorithm show average precision (AP) 0,90, average recall 0,78 and
average accuracy 0,71. |
|
Keywords: |
Convolutional Neural Network, Object Detection, Deep Learning, Malaria
Detection, Thin Blood Smear Image |
|
Source: |
Journal of Theoretical and Applied Information Technology
15th March 2020 -- Vol. 98. No. 05 -- 2020 |
|
Full
Text |
|
|
Title: |
CLASSIFICATION OF FACIAL SKIN TYPE USING DISCRETE WAVELET TRANSFORM, CONTRAST,
LOCAL BINARY PATTERN AND SUPPORT VECTOR MACHINE |
|
Author: |
INDRIYANI , I MADE SUDARMA |
|
Abstract: |
There are two effects cosmetics on the skin, namely positive and negative
effects. The use of cosmetics in accordance with the skin type will have a
positive impact on the skin while the use of cosmetics that do not fit the skin
type will negatively affect the skin. Each person's skin type is not the same,
therefore it is important to know the type of skin before deciding to buy
suitable cosmetics. This research will build an intelligent system that can
classify facial skin types by utilizing the concept of data mining. This
research uses Discrete Wavelet Transform (DWT), contrast, and Local Binary
Pattern (LBP) for extracting the features contained in the face image and use
Support Vector Machine (SVM) as the classifier to determine the facial skin
type. Based on the experimental results, it is proven that the proposed method
able to properly classify facial skin types. The proposed method gives the
average classification accuracy of 91.66% with the average running time of
31.571 seconds. |
|
Keywords: |
Classification, Facial Skin Type, Discrete Wavelet Transform, Local Binary
Pattern, Support Vector Machine |
|
Source: |
Journal of Theoretical and Applied Information Technology
15th March 2020 -- Vol. 98. No. 05 -- 2020 |
|
Full
Text |
|
|
Title: |
SOLVING PORTFOLIO SELECTION PROBLEM USING PARTICLE SWARM OPTIMIZATION WITH
CARDINALITY AND BOUNDING CONSTRAINTS |
|
Author: |
THERESA N. ABIODUN, AYODELE A. ADEBIYI, MARION O. ADEBIYI |
|
Abstract: |
The portfolio selection of assets for an investment by investors has remain a
challenge in building appropriate portfolio of assets when investing hard earned
money into different assets in order to maximize returns and minimize associated
risk. Different models have been used to resolve the portfolio selection problem
but with some limitations due to the complexity and instantaneity of the
portfolio optimization model, however, particle swarm optimization (PSO)
algorithm is a good alternative to meet the challenge.
This study applied
cardinality and bounding constraints to portfolio selection model using a
meta-heuristic technique of particle swarm optimization. The implementation of
the developed model was done with python programming language. The results of
this study were compared with that of the genetic algorithms technique as found
in extant literature. The results obtained with the model developed shows that
particle swarm optimization approach gives a better result than genetic
algorithm in solving portfolio selection problem. |
|
Keywords: |
Portfolio, Genetic Algorithm, Particle Swarm Optimization, Cardinality and
Bounding Constraints. |
|
Source: |
Journal of Theoretical and Applied Information Technology
15th March 2020 -- Vol. 98. No. 05 -- 2020 |
|
Full
Text |
|
|
Title: |
THE IMPACT OF INNER-PARAMETERS B-MAC PROTOCOL BY TAGUCHI METHOD FOR WSN |
|
Author: |
ALAA KAMAL YOUSIF, M.N.MOHD WARIP, MOHAMED ELSHAIKH |
|
Abstract: |
The MAC protocols play an important role in the performance of wireless sensor
network (WSN). MAC protocols are controlled with set of parameters from being
dragged to undesired situation such as reduce the power consumption, listening
idle, and overhead. This inner- parameters have direct impact on the efficiency
of a MAC protocols and overall network performances. The impacts of theses
parameters on reduce the power consumption are less considered. In the
literature, a lot of studies concentrates on introducing a new protocols to
reduce the power consumption for WSN. This paper aims to analysis the inner-
parameters of MAC protocols for WSN power consumption by using Taguchi Delta
Analysis (TDA). Moreover, the measure of inner - parameters is very important to
find the optimal values to reduce the power consumption. This paper utilized
Taguchi method to analysis the impact of B-MAC protocol parameters in WSN
scenarios by exploits Taguchi delta analysis. Further, four inner - parameters
are investigated in a simulation platform. Moreover, simulation experiments are
carried out by OMNET++5 to prove the work in this paper. The obtained results
show that inner- parameters B-MAC inner- protocol reduce the power consumption
of WSN for two different scenarios. |
|
Keywords: |
B-MAC, Taguchi Delta analysis (TDA), Power consumption, Taguchi method, WSN |
|
Source: |
Journal of Theoretical and Applied Information Technology
15th March 2020 -- Vol. 98. No. 05 -- 2020 |
|
Full
Text |
|
|
Title: |
FACE RECOGNITION FOR ONLINE USERS AUTHENTICATION |
|
Author: |
FIRAS AJJOUR, DR. MHD BASSAM KURDY |
|
Abstract: |
In the last decade, advancement in Artificial Intelligence attracted a lot of
experts that lead to massive growth and advancement in all human life aspects.
Therefore, one of the key fields to point at, which attracted a lot of attention
and development lately, is Face Recognition.
In recent years, Face
Recognition tends to be one of the most widely used technologies in many
different domains and workspaces, such as emotional recognition, security,
health sector, marketing, and retail, etc.
this approach will consist of an
online system with real-time functionality (close to real-time), that will be
responsible for the declaration of users to be recognized later. Based on the
recognition results, the system will then grant the users the needed
authentication.
In this research, various different challenges related to the
development and the use of Face Recognition, including the variations in light
conditions, camera resolution, processing power, facial changes over time,
number of users to be recognized, etc...
During this work, “Viola and Jonesâ€
and “MTCNN†were used for face detection, and “FaceNet†was applied for facial
features extraction. Also, similarity neural network (Similarity Net) has been
created to regress similarity percent between user’s features’ vectors, beside
it has been trained on user’s features by exploiting the Euclidian distance
between embeddings.
This approach was tested on a group of datasets -
personal, Kaggle and LFW dataset. The tests returned 100% successful
recognitions on personal and Kaggle dataset, and 99.5% on LFW dataset. |
|
Keywords: |
Face Detection, Face Recognition, Facenet, MTCNN (Multi-Task Cascaded
Convolutional Neural Networks for Face Detection), Embeddings, Feature Vectors,
Kaggle (Website for AI Contests), LFW (Labelled Faces in The Wild), CNN
(Convolutional Neural Network), CLAHE (Contrast Limited Adaptive Histogram),
Histogram Equalization, Face Authentication. |
|
Source: |
Journal of Theoretical and Applied Information Technology
15th March 2020 -- Vol. 98. No. 05 -- 2020 |
|
Full
Text |
|
|
Title: |
FAST OBJECT DETECTION FRAMEWORK BASED ON MOBILENETV2 ARCHITECTURE AND ENHANCED
FEATURE PYRAMID |
|
Author: |
HOANH NGUYEN |
|
Abstract: |
Recently, many object detectors based on deep convolutional neural networks such
as Faster R-CNN, SSD, RetinaNet, and so on have been proposed and showed
significant improvements over traditional object detectors. However, these deep
learning-based object detectors usually focus on detection accuracy. This paper
proposes a one-stage deep learning-based object detection framework to improve
the inference speed and achieve real-time object detection in outdoor scene
images without compromising on accuracy. To improve the inference speed, this
paper adopts MobileNet v2 architecture at first to generate the base convolution
feature maps. MobileNet v2 achieved comparable performance compared with other
state-of-the-art networks while being simpler and faster. To improve the
detection accuracy, an enhanced feature pyramid generation module is used to
construct rich and multi-scale feature maps from a single resolution input
image. Each feature level is a high-level semantic feature map and can be used
for detecting objects at a different scale. Finally, a detection network which
includes a classification subnet to predict the probability of object presence
and a box regression subnet to regress the offset from each anchor box to a
nearby ground-truth object is attached to each feature level in the enhanced
feature pyramid to locate objects at different scales. In addition, focal loss
function is used in the classification branch of the detection network to
dedicate the class imbalance problems for the one-stage object detector.
Experimental results on public datasets show that the proposed approach achieves
nearly as performance as other state-of-the-art approaches, while the inference
speed is significant improved. |
|
Keywords: |
Deep Learning, Object Detection, Convolutional Neural Networks, MobileNets,
Feature Pyramid |
|
Source: |
Journal of Theoretical and Applied Information Technology
15th March 2020 -- Vol. 98. No. 05 -- 2020 |
|
Full
Text |
|
|
Title: |
AN EFFICIENT INTRUSION DETECTION APPROACH USING LIGHT GRADIENT BOOSTING |
|
Author: |
HAYEL KHAFAJEH |
|
Abstract: |
Nowadays, network security has been received more attention from researchers.
Intrusion detection systems (IDSs) serves as an essential element of network
security. In order to increase the network’s security, machine-learning
algorithms may be utilized for the detection and prevention of the attacks that
launched against the network. The researcher of this study used LightGBM’s
algorithm for training a model in order to detect several types of network
attacks. The proposed approach was compared with classical machine learning in
terms of performance on the same dataset. The experimental results show that the
proposed approach achieves a detection rate of 97.4% with a false-positive rate
of 0.9%. |
|
Keywords: |
Network security, IDS, Machine learning, LGBM. |
|
Source: |
Journal of Theoretical and Applied Information Technology
15th March 2020 -- Vol. 98. No. 05 -- 2020 |
|
Full
Text |
|
|
Title: |
INFORMATION RISK BEFORE AND AFTER XBRL (EXTENSIBLE BUSINESS REPORTING LANGUAGE)
IMPLEMENTATION: A STUDY ON LQ45 INDEX OF INDONESIAN STOCK EXCHANGE |
|
Author: |
ADHITYA AGRI PUTRA, NANDA FITO MELA |
|
Abstract: |
This research is aimed to examine effect of XBRL implementation by LQ45
companies on information risk. Research samples are 108 companies listed in LQ45
index of Indonesian Stock Exchange 2013-2016. Information research is measured
by event return volatility, information efficiency, change of standard deviation
of daily return, and bid-ask spread. Data analysis uses common-effect regression
for event return volatility, change of standard deviation of daily return, and
bid-ask spread; and random-effect regression for information efficiency. The
result shows that XBRL implementation by LQ 45 companies has negative effect on
information risk. It indicates that XBRL implementation reduce information risk
by decreasing of return volatility, standard deviation of stock return, change
of standard deviation of daily stock return, and bid-ask spread. XBRL
implementation is useful for improvement of information accuracy, reducing of
information asymmetry, reducing of error, and allows investor to make stock
investment decision rapidly, accurately, and low cost. |
|
Keywords: |
Information Risk, XBRL Implementation, LQ45 Index, Indonesian Stock Exchange,
XBRL based Financial Reporting |
|
Source: |
Journal of Theoretical and Applied Information Technology
15th March 2020 -- Vol. 98. No. 05 -- 2020 |
|
Full
Text |
|
|
Title: |
COMPUTATIONAL ANALYSIS OF DNA SEQUENCES BASED UPON AN INNOVATIVE MATHEMATICAL
HYBRIDIZATION MECHANISM OF PROBABILISTIC CELLULAR AUTOMATA AND PARTICLE SWARM
OPTIMIZATION |
|
Author: |
WESAM M. ELSAYED , MOHAMMED ELMOGY , B.S. EL-DESOUKY |
|
Abstract: |
The deoxyribonucleic acid (DNA) sequence reconstruction problem is a very
complex issue of computational biology. In this paper, we introduce a modified
procedure for the reconstruction process based on probabilistic cellular
automata (PCA) integrated with a particle swarm optimization (PSO) algorithm.
PSO is utilized to detect the optimal and adequate transition rules of cellular
automata (CA) for the reconstruction process. This integration makes our
algorithm more efficient. The evolution of organisms occurs due to mutations of
DNA sequences. As a result, we attempt to model the evolutions of DNA sequences
using our proposed system. In Particular, we determine the impact of neighboring
DNA base pairs on the mutation process. We used CA rules for analysis and
prediction of the DNA sequence. Our innovative model leans on the hypothesis
that mutations are probabilistic events. As a result, their evolution can be
simulated as a PCA model, and this enables us to discover the effects of some
neighborhood base-pairs on a DNA segment evolution. The main target of this
paper is to analyze various DNA sequences and try to predict the changes that
occur in DNA sequences during evolution (mutations). We use a similarity score
as our measure of fitness to detect symmetry relations, which in turn makes our
method appropriate for comparison of numerous extremely long sequences.
Phylogenetic trees are exhibited in order to view our investigated samples.
Unlike using Markov chains, our proposed technique does not reveal biases in
mutation rates that depend on the neighboring bases, which indicates the effect
of neighbors on mutations. Incorporating probabilistic components in our
proposed technique helps to produce a tool capable of foretelling the likelihood
of specific mutations. |
|
Keywords: |
DNA Sequence Reconstruction, Computational Biology, Mutation Rates,
Probabilistic Cellular Automata (PCA), Particle Swarm Optimization (PSO). |
|
Source: |
Journal of Theoretical and Applied Information Technology
15th March 2020 -- Vol. 98. No. 05 -- 2020 |
|
Full
Text |
|
|
Title: |
AN IMPROVEMENT OF SIMILARITY IN CASE BASED REASONING USING
SUBJECTIVE-GENERALIZED WEIGHT FOR TRADITIONAL INDONESIAN CUISINE |
|
Author: |
SETYAWAN WIBISONO, WIWIEN HADIKURNIAWATI, HERNY FEBRUARIYANTI, MARDI SISWO UTOMO |
|
Abstract: |
In this study, a system for providing recommendations from a traditional
Indonesian food recipe consultation using the CBR (Case Based Reasoning) method
was designed. A recommendation is given based on the similarity of the input in
the form of ingredients for cooking compared to the ingredients for cooking from
a recipe that has been stored in the database. Increasing the accuracy of the
similarity value is the goal to be achieved in this study. This method used is
intented to give the weight to each food-forming material, then the Dice
algorithm is used to calculate the value of similarity. Weighting is determined
subjectively but takes into account the principle of appropriateness in general.
Test the validity of the weight value using the weighting principles in the AHP
(Analytical Hierarchy Process). This makes the value of the similarity of a
recipe suggestion more accurate because it considers proportional weighting of
the ingredients forming the recipe. |
|
Keywords: |
consultation similarity value, CBR, weighting, Dice algorithm, AHP |
|
Source: |
Journal of Theoretical and Applied Information Technology
15th March 2020 -- Vol. 98. No. 05 -- 2020 |
|
Full
Text |
|
|
Title: |
METHODS AND ALGORITHMS OF ANALYZING SYLLABUSES FOR EDUCATIONAL PROGRAMS FORMING
INTELLECTUAL SYSTEM |
|
Author: |
D. KAIBASSOVA, L. LA, A. SMAGULOVA, L. LISITSYNA, A. SHIKOV, M. NURTAY |
|
Abstract: |
This article reviews using methods of intellectual data analysis for educational
program formation in the context of determining the sequence of studying
disciplines in the direction by consideration. The model of the forming
educational programs that satisfy given competencies is described on the basis
of text documents processing through their vector representations. Proposed
model performs clustering of text documents taking into weights coefficient of
individual words in the corpus. The article succinctly describes the developed
software application that allows extract information from text documents,
process, analyze, and visualize data. Testing was carried out according to data
obtained from 350 syllabuses of disciplines for conformity with 120 competencies
in the areas of IT-specialists training. This research solves the issues of
intellectual support for the educational programs disciplines of higher
education with a view to diminish the complexity of developing new educational
programs and improve the quality of academic content. |
|
Keywords: |
Educational Program, Information Extraction, Vectorization, Text Mining, Cosine
Similarity, Hierarchical Clustering. |
|
Source: |
Journal of Theoretical and Applied Information Technology
15th March 2020 -- Vol. 98. No. 05 -- 2020 |
|
Full
Text |
|
|
Title: |
A FAST PYRAMID NETWORK FOR ACCURATE LOCALIZATION OF CAR IN AERIAL IMAGES |
|
Author: |
HOANH NGUYEN |
|
Abstract: |
Although deep learning-based object detectors have achieved great success in
general object detection in recent years, detecting of objects like car in
aerial images is still a challenge. The main difficulty of car detection in
aerial images comes from the relatively small size with multiple orientations of
car in images. In addition, due to the high resolution of aerial images, the
inference time of current approaches is still high. To solve these problems,
this paper proposes an enhanced framework for fast and efficient car detection
in aerial images. In the proposed approach, ResNet-34 architecture is adopted to
create the base convolution layers. Compared with ResNet-50 and ResNet-101,
ResNet-34 achieves comparable performance while being faster and simple. Then,
an enhanced feature map generation module is designed to generate enhanced
feature maps from input feature maps. To speed up the detection process, the
detection network based on region proposal network is used to exactly locate
cars in original aerial images. The detection network included region proposal
networks is applied at different enhanced feature maps with different scales to
detect multi-scale car in input image. Experimental results on public dataset
show that the proposed approach achieves comparable performance compared with
other state-of-the-art approaches. |
|
Keywords: |
Car Detection, Convolutional Neural Network, Intelligent Transportation System,
Object Detection, Pyramid Network |
|
Source: |
Journal of Theoretical and Applied Information Technology
15th March 2020 -- Vol. 98. No. 05 -- 2020 |
|
Full
Text |
|
|
|
