|
|
|
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
June 2021 | Vol. 99
No.11 |
|
Title: |
THE ANTECENDENTS OF PURCHASING DECISION OF COSMETIC PRODUCTS OF LIZZIE
PARRA BEAUTY IN SOCIAL MEDIA |
|
Author: |
NURHAYATI WIDIANINGRUM, LA MANI |
|
Abstract: |
This study aims to examine the effect of social media use, brand image, and
sales promotion on purchasing decisions for cosmetic products by Lizzie Parra
Beauty. This study uses a quantitative method with an analytic survey approach.
The data collection technique was carried out by distributing questionnaires
online to 100 followers of the Instagram By Lizzie Parra Beauty account. The
sampling technique was purposive sampling, in which Instagram followers who
actively gave responses in the form of likes and comments. Data analysis used
multiple linear regression on all research variables. The results showed that
the use of social media and sales promotion had a significant influence on
purchasing decisions. Meanwhile, brand image partially does not have a
significant effect on purchasing decisions for cosmetic products by Lizzie Parra
Beauty. But overall, both social media, brand image, and sales promotion
simultaneously influence the purchasing decision of By Lizzie Parra Beauty
cosmetic products. Thus, to increase cosmetic purchasing decisions, a company
can use social media, build a brand image, and increase sales promotions. |
|
Keywords: |
Social Media, Brand Image, Sales Promotion, Purchasing Decision, Marketing |
|
Source: |
Journal of Theoretical and Applied Information Technology
15th June 2021 -- Vol. 99. No. 11 -- 2021 |
|
Full
Text |
|
|
Title: |
DETECTION OF COVID-19 FROM CHEST CT IMAGES USING SELECTED FOURIER TRANSFORM
FEATURES |
|
Author: |
FARID ALI MOUSA, TAHA M. MOHAMED |
|
Abstract: |
In this paper, a novel method is proposed for COVID-19 detection from chest
images. The proposed method uses some important features from both spatial and
the Fourier transform of the input images. The binary particle swarm
optimization is used to select the most relevant features. Two common
classifiers are used for testing; support vector machine and k-nearest neighbor.
Results show that the k-nearest neighbor outperforms support vector machine. The
accuracy of the proposed method outperforms other algorithms in the literature.
The accuracy of the proposed method approximately equals 91% when using the
proposed features combined with the binary particle swarm optimization (BPSO).
The sensitivity exceeds 89%, and also outperforms that proposed in previous
work. Specificity is also maintained. These important findings may represent
physicians' importance in decreasing diagnosis time and cost using automated
systems. These systems may be useful for physicians in case of resource
limitation. |
|
Keywords: |
COVID-19, non-COVID, Classification, FT, Feature Selection, and BPSO. |
|
Source: |
Journal of Theoretical and Applied Information Technology
15th June 2021 -- Vol. 99. No. 11 -- 2021 |
|
Full
Text |
|
|
Title: |
CLASSIFICATION AND FEATURES SELECTION METHOD FOR OBESITY LEVEL PREDICTION |
|
Author: |
D.MOLINA, A. DE-LA-HOZ, F. MENDOZA |
|
Abstract: |
Obesity has become one of the world’s largest health issues, rich and poor
countries, without exception, have each year larger populations with this
condition. Obesity and overweight are defined as abnormal or excessive fat
accumulation that may impair health according to the World Health Organization
(WHO) and has nearly tripled since 1975. Data Mining and their techniques have
become a strong scientific field to analyze huge data sources and to provide new
information about patterns and behaviors from the population. This study uses
data mining techniques to build a model for obesity prediction, using a dataset
based on a survey for college students in several countries. After cleaning and
transformation of the data, a set of classification methods was implemented
(Logistic Model Tree - LMT, RandomForest - RF, Multi-Layer Perceptron - MLP and
Support Vector Machines - SVM), and the feature selection methods InfoGain,
GainRatio, Chi-Square and Relief, finally, crossed validation was performed for
the training and testing processes. The data showed than LMT had the best
performance in precision, obtaining 96.65%, compared to RandomForest (95.62%),
MLP (94.41%) and SMO (83.89%), so this study shows that LMT it can be used with
confidence to analyze obesity and similar data. |
|
Keywords: |
Data mining, Dataset, Obesity, Decision Trees, Support Vector Machines |
|
Source: |
Journal of Theoretical and Applied Information Technology
15th June 2021 -- Vol. 99. No. 11 -- 2021 |
|
Full
Text |
|
|
Title: |
A TECHNIQUE FOR ANALYZING NEURAL NETWORKS IN TERMS OF TERNARY LOGIC |
|
Author: |
IBRAGIM E SULEIMENOV, AKHAT S BAKIROV, DINARA K MATRASSULOVA |
|
Abstract: |
There is an extensive class of neural networks, the functioning of which can be
described in terms of binary logic: a set of logical variables describing the
state of the inputs is associated with a set of logical variables characterizing
the state of the outputs. Such networks can be described in terms of logical
functions, in particular, through the Zhegalkin polynomial. This imposes
significant restrictions on the variability of the neuron weights. This fact is
of significant interest from the point of view of overcoming the thesis about
the logical opacity of neural networks, which is associated with the most common
approaches to training neural networks, which are actually the results of
computer experiments. Therefore, it can be considered that neuroscience is
predominantly an empirical science, with the only difference that its
foundations are not laboratory, but computer experiments. An important step
towards overcoming the thesis about the logical opacity of neural networks is to
establish restrictions on the variability of the weight coefficients, i.e. proof
of the fact that in reality neurons can perform only a limited set of operations
that can be reduced to logical ones. At the same time, there is no reason to
assert that artificial neural networks must necessarily be built on the basis of
the apparatus of binary logic. This paper shows that appliance of ternary logic
in combination with a geometric interpretation of the operation of neural
networks allows us to reveal the existence of more than strict restrictions on
the variability of the weight coefficients of a neural network. An exhaustive
description of a neuron with four inputs, which shows how the proposed approach
can be extended to the analysis of neurons with an arbitrary number of inputs. |
|
Keywords: |
Artificial Intelligence, Artificial Neural Networks, Ternary Logic |
|
Source: |
Journal of Theoretical and Applied Information Technology
15th June 2021 -- Vol. 99. No. 11 -- 2021 |
|
Full
Text |
|
|
Title: |
FACTORS AND CHALLENGES THAT INFLUENCE HIGHER EDUCATION STUDENTS’ ACCEPTANCE OF
E-LEARNING SYSTEM AFTER CORONAVIRUS PANDEMIC |
|
Author: |
RASHA HASSAN |
|
Abstract: |
As the coronavirus pandemic continues to spread, and the world is now in a state
of emergency, universities around the world are reacting with different and
alternative ways of learning such as e-learning systems applications to slow the
spread of this disease. However, the successful implementation of e-learning in
higher education will be based on users’ acceptance of this technology and on
understanding the main challenges that face the current e-learning systems.
Thus, the purpose of this paper is to study the factors that influence
university students’ intentions to accept e-learning after coronavirus pandemic
where the e-learning became an obligatory system and to investigate the critical
challenges of it. Based on the unified theory of acceptance and use of
technology (UTAUT) this study proposes a model to identify the factors that
influence the acceptance of web-based learning platform, Moodle in Faculty of
Economics and Political Sciences, after coronavirus pandemic. Partial Least
Square-Structural Equation Modelling (PLS-SEM) was used to analyze the data
collected from 346 students' participants. The results indicated that behavioral
intention and facilitating conditions have direct impacts on use behavior while
performance expectancy, effort expectancy, social influence, price value,
facilitating conditions and motivation to use were all significant factors that
affect behavioral intention to use e-learning. In addition, the results
indicated that there are many main challenges that obstruct the usage of
e-learning system not related only to the technological challenges, but also
culture challenges which must be taken under consideration. Overall, the
respondents expressed unfavorable opinion concerning e-learning acceptance
during the lockdown situation and its impacts on students’ academic performance,
they accept using the technology but as a complementary part in the education
process, not as the alternative of the face to face educational process. It is
believed that the findings will be useful for understanding challenges better
and to help the universities policy makers, designers and developers to make
superior decisions based on them as soon as possible. |
|
Keywords: |
E-Learning, Unified Theory Of Acceptance And Use Of Technology (UTAUT),
Behavioral Intention, Challenges Of E-Learning, Coronavirus Pandemic |
|
Source: |
Journal of Theoretical and Applied Information Technology
15th June 2021 -- Vol. 99. No. 11 -- 2021 |
|
Full
Text |
|
|
Title: |
DETECTION OF SEMANTIC OBSESSIVE TEXT IN MULTIMEDIA USING MACHINE AND DEEP
LEARNING TECHNIQUES AND ALGORITHMS |
|
Author: |
AADIL GANI GANIE, DR SAMAD DADVANDIPOUR, MOHD AAQIB LONE |
|
Abstract: |
Word boycott has been seen frequently trending in India on various social media
platforms. We studied the obsession of Indians with the word boycott; to show
the protest or dissent against any government policy, Netflix series, political
or religious commentary, and on various other matters, people in India prefer to
trend word "Boycott" on multiple mediums. We studied how ingrained the word
"Boycott" is in Indians in our research and how it affects daily life,
unemployment, and the economy. The data was collected using Youtube API with the
next page token to get all the search results. We preprocessed the raw data
using different preprocessing methods, which are discussed in the paper. To
check our data's consistency, we fed the data into various machine learning
algorithms and calculated multiple parameters like accuracy, recall, f1-score.
Random forest showed the best accuracy of 90 percent, followed by SVM and Knn
algorithms with 88 percent each. We used word cloud to get the most dominant
used words, Textblob, for sentiment analysis, which showed the mean Polarity of
0.07777707038498406 and mean subjectivity 0.2588880457405638. We calculated
perplexity and coherence score using the LDA model with results
-12.569424703238145 and 0.43619951201483725, respectively. This research has
observed that the word boycott is a favorite to the Indians who are often using
it to show opposition or support related day-to-day matters. |
|
Keywords: |
Sentiment analysis, NLP, Machine learning, Deep learning, Topic modeling |
|
Source: |
Journal of Theoretical and Applied Information Technology
15th June 2021 -- Vol. 99. No. 11 -- 2021 |
|
Full
Text |
|
|
Title: |
INTELLIGENT SYSTEM FOR THE AUTOMATIC DETECTION AND CONTROL OF ACCIDENTS ON THE
ROAD IN REAL TIME |
|
Author: |
KHAMLICH FATHALLAH, KHAMLICH SALAHEDDINE, EL JOURMI MOHAMMED, BENRABH MOHAMED |
|
Abstract: |
Accidents remain a serious public health problem nationally and globally. Our
contribution is part of the development of an on-board system to identify
accident sites in real time and provide assistance to people who have been
exposed to a vehicle accident. This work is interested in the design and
realization of a management and control system of road accidents based on IOT
(Internet of Things) in the form of an on-board WEB server more efficient in
terms of calculation created physically by an FPGA card (Field Programmable Gate
Array) and an intelligent system installed in each vehicle based on Raspberry Pi
allowing the following detection of sensors and alerting the server by SMS of
accidents in real time. The latter transmits a request to the nearest ambulance
or service concerned at that location in order to minimize the time required for
the process of moving the ambulance (or the firefighter). It automatically and
intelligently controls the traffic signal to facilitate the process of moving
the ambulance and getting the ambulance to its destination in a short period of
time. |
|
Keywords: |
Smart Car, Raspberry Pi, FPGA, Embedded System, Internet Of Things, Connected
Systems, Embedded Web Server, NIOSII, GPS |
|
Source: |
Journal of Theoretical and Applied Information Technology
15th June 2021 -- Vol. 99. No. 11 -- 2021 |
|
Full
Text |
|
|
Title: |
ASSESSING THE SUCCESS OF KOMINFO MAIL HANDLING SYSTEM BASED ON EMPLOYEE
PERSPECTIVE |
|
Author: |
ANAK AGUNG ISTRI KRISNA GANGGA DEWI, AHMAD NURUL FAJAR |
|
Abstract: |
The Ministry of Communication and Informatics (KOMINFO) is an institution that
plays an important role in assisting the Indonesian government in carrying out
government affairs in the field of communication and informatics. SiMAYA is a
cloud-based e-government system that is used as a daily operational system to
support the mail handling process in order to facilitate the process of sending,
receiving and disposition of letters. In practice, the SiMAYA system is expected
to improve the correspondence process to be more effective and efficient. At
present, the SiMAYA system is experiencing several problems, such as an error
system and unable to carry out a disposition, which it’s hinders the operational
activities. For this reason, it is necessary to evaluate the SiMAYA system, so
that employees do not experience difficulties in its use. The main objective of
this research is to analyze how successful the implementation of the SiMAYA
system in the Ministry of Communication and Informatics from the perspective of
employees. Structural equation modeling-Partial Least Squares (SEM-PLS)
technique are applied. Data were collected using a questionnaire from 140
employees. The questionnaires were distributed via google form and paper.
Empirically, this study evaluates a model to measure the success of the SiMAYA
system which refers to the updated Delone and Mclean IS Success Model theory
with an extended variable performance expectancy from UTAUT. Seven out of ten
were hypothesized to be successful and significantly supported and the other
three variables were found to be rejected. These results can provide new
insights for government agencies in making improvements to information systems
used in the future. |
|
Keywords: |
Delone and Mclean, E-government, Information Systems |
|
Source: |
Journal of Theoretical and Applied Information Technology
15th June 2021 -- Vol. 99. No. 11 -- 2021 |
|
Full
Text |
|
|
Title: |
BENCHMARKING MICROSERVICES ARCHITECTURE IN IMPROVING USER EXPERIENCE |
|
Author: |
HERALDO YUSRON P, NAUFAL RIZQULLAH P H, BENFANO SOEWITO |
|
Abstract: |
Technology is an important thing that must be considered, technology continues
to be developed in order to help people to work more efficiently. In every
company, one of their main goals is to achieve maximum efficiency, with
efficient work, it could reduce the cost necessary and increase the productivity
of its business process without sacrificing the quality of their byproduct. One
of them came from the terms of communication between employees. How many
companies use web applications as a medium to communicate, but the current
adopted architecture is mostly still monolithic. A commonly known monolithic
architecture has some limitations, especially when applications tend to be more
complex such as slow access speeds because programs are running simultaneously
in one mass architecture system, small changes to the system require an entire
monolithic to be rebuilt, and limited scalability can occur. Therefore, it is
proposed to use microservices for internal web applications. Microservice has
recently gained popularity among developers since 2014. Because many companies
that have implemented this technology can maximize their profits and get a
better user experience due to better access speed capabilities. Therefore, in
this study, we try to fix the problem and implement a microservice architecture
in the hope of providing a better user experience and increasing productivity
for their employees. Thus, we need to compare both architectures using
comparable benchmarks and try to prove that microservices can lead to better
performance and user experience. |
|
Keywords: |
Benchmark, Microservices, Software Architecture, Monolithic, DDD |
|
Source: |
Journal of Theoretical and Applied Information Technology
15th June 2021 -- Vol. 99. No. 11 -- 2021 |
|
Full
Text |
|
|
Title: |
ANALYSIS OF FACTORS AFFECTING SATISFACTION AND LOYALTY OF DIGITAL LOAN CUSTOMER
AT PT BANK XYZ |
|
Author: |
JAROT S. SUROSO , YOSEP WAHJUDI |
|
Abstract: |
Digital loan is one of the data processing methods, be it processing loan
documents and information online via the internet, wireless, and other
telecommunication systems without credit customers having to come to bank
branches to make the desired credit application. PT BANK XYZ is a company
engaged in banking in Indonesia. As a growing banking company with more than 400
branches throughout Indonesia and one of PT Bank XYZ's missions is to expand the
office network for market penetration and financing in consumer centers, SME and
corporate scale business sectors as well as increasing the level of competition
among Indonesian banking companies, PT Bank XYZ developed digital loan
technology in 2017 specifically for distribution of micro credit products.
Customer satisfaction and loyalty are very important aspects for banks to win
the competition in the digital market and retain existing customers in this
technological era. The problem is, it is not high enough to meet the criteria
for the best digital loan services to provide satisfaction to customers who
apply for loans through digital loan applications. The purpose of this study was
to determine the influence of factors, namely Perceived Ease of Use, Perceived
Usefulness, Perceived Risk, Perceived Service Quality, Perceived Functional
Quality, Perceived Customer Experience, Brand Image and Digital Innovation on
customer satisfaction and loyalty on digital loans. at PT. XYZ Bank. In this
study, to analyze the factors that affect customer satisfaction and loyalty of
digital loans at PT Bank XYZ, the researcher used a modified model of the
Technology Acceptance Model (TAM). This type of research is quantitative
research. 100 questionnaires were successfully collected from customers using
the Digital Loan Application at PT Bank XYZ. The author analyzes the data
collected using Partial Least Squares (PLS-SEM). PLS was chosen as the
methodology for this study. The expected results of this research are factors,
namely Perceived Ease of Use, Perceived Usefulness, Perceived Risk, Perceived
Service Quality, Perceived Functional Quality, Perceived Customer Experience,
Brand Image and Digital Innovation whether it affects customer satisfaction and
loyalty and how much influence to satisfaction. towards customer loyalty in
applying for digital loans at PT Bank XYZ. This research is expected to help PT
Bank XYZ to improve and innovate services in the field of digital loans and make
better service improvements so that customer satisfaction and loyalty can always
increase. |
|
Keywords: |
Banking Industry, Brand Image, Digital Loan, Digital Innovation, Perceived Ease
of Use, Perceived Customer Experience, Perceived Functional Quality, Perceived
Risk, Perceived Service Quality, Perceived Usefulness, Satisfaction, Loyalty,
Technology Acceptance Model (TAM) |
|
Source: |
Journal of Theoretical and Applied Information Technology
15th June 2021 -- Vol. 99. No. 11 -- 2021 |
|
Full
Text |
|
|
Title: |
ANALYZING THE CONTINUOUS USE INTENTION OF ONLINE CONSUMER ON LEADING ONLINE
SHOPPING PLATFORM |
|
Author: |
FATHY RADHIA , VIANY UTAMI TJHIN |
|
Abstract: |
E-commerce in Indonesia is growing very fast. It is supported by the increasing
number of internet users in Indonesia and the value of e-commerce transactions.
Based on the number of e-commerce companies, Shopee has excellent potential to
be utilized by the public to market and sell products. The problem is that the
number of visitors to the Shopee application has decreased even though Shopee is
still in the first rank of other e-commerce sites. The research referred to the
modified UTAUT2 with trust and continuous use intention as a novelty. This study
aims to: 1) identify and analyze the factors that influence the continuous use
intention of Shopee application in making product purchases; 2) determine and
analyze whether age and gender variables moderate the relationship between these
factors to continuous use intention. The research focuses on the process of
purchasing a product in the Shopee application and active users of the Shopee
application who have previously purchased products as research respondents. The
research data were obtained through an online questionnaire. The data processing
process is carried out using the Structural Equation Model (SEM) technique with
the PLS approach, and there are measurement models and structural models. The
conclusions from the results of this study are: 1) Facilitating conditions have
a significant effect on continuous use intention; 2) Habit has a significant
effect on continuous use intention; 3) Gender has a significant moderating
effect which affects social influence on continuous use intention; 4) Age has a
significant moderating effect that affects facilitating conditions towards
continuous use intention. |
|
Keywords: |
E-Commerce, Modified UTAUT2, Continuous Use Intention, Online Shopping |
|
Source: |
Journal of Theoretical and Applied Information Technology
15th June 2021 -- Vol. 99. No. 11 -- 2021 |
|
Full
Text |
|
|
Title: |
COVID-19 AGE: CHALLENGES IN CYBERSECURITY AND POSSIBLE SOLUTION DOMAINS |
|
Author: |
ZAINA ALSAED , MAHMOUD JAZZAR |
|
Abstract: |
Threats to cybersecurity and cyberattacks respect no boundaries. Cybercriminals
always try to exploit any crisis to facilitate their attacks, and of course, the
COVID-19 pandemic is not an exception. From the very first beginning of the
COVID-19 virus outbreak in March 2020, it has become very effective tool to
commit cybercrimes as it has not only triggered huge upheavals in health,
education, and the economy but has also led to broad implications on
communication and information technology as well. In line with the increasing
number and scope of cyberattacks, the growing concern caused by the pandemic has
increased the possibility of successful cyberattacks. The significance of this
paper is to highlight and review some types of cyberattacks associated with the
COVID-19 presence. In addition, the paper recommends some guidelines and
countermeasures for the micro-level of families, individuals and for business
enterprise to implement potential means of risk management plans to actively
mitigate and control the consequences of such malicious attacks. |
|
Keywords: |
COVID-19, Cybersecurity, Cybercrime, Cyberattacks, Risk Management |
|
Source: |
Journal of Theoretical and Applied Information Technology
15th June 2021 -- Vol. 99. No. 11 -- 2021 |
|
Full
Text |
|
|
Title: |
IMPROVING SEMANTIC PROPERTIES RELATIONSHIPS EXTRACTION IN ONTOLOGY EVOLUTION |
|
Author: |
ABDULELAH A. ALGOSAIBI |
|
Abstract: |
The ontology allows enriching the structure meaning for RDF data. It is
necessary to explicitly impose formal interpretation that leads to a unified
understanding of the meaning of these data. Exploring non-taxonomic
relationships helps in building a mature ontology. The existing studies show
some challenges to extract the semantic properties relationship from the
ontologies. The study intends to develop a novel technique for semantic
properties relationship extraction. It deliberates observing link intersections
within domain individuals. That is, a parallel process is proposed to scale the
performance of generating context-aware domain-independent routine. The proposed
model follows a bottom-up approach to nominate non-taxonomic relationships using
Natural Language Processing (NLP) and heuristics through three major phases,
semantic-based bulk processing, relationship mining, and relationship evolution.
The evaluation metrics include accuracy, precision, recall, and F-measure are
employed for evaluating the proposed approach's efficiency, which shows
promising outcomes. The outcome of the study suggests that NLP based heuristics
assist the relationship extraction process. Moreover, this work discusses some
recommendations for future research directions. |
|
Keywords: |
Ontology, Natural Language Processing, Non- Taxonomic Relationship, Relationship
Mining, Web Semantics |
|
Source: |
Journal of Theoretical and Applied Information Technology
15th June 2021 -- Vol. 99. No. 11 -- 2021 |
|
Full
Text |
|
|
Title: |
AUTISM SPECTRUM DISORDER PREDICTION USING ROBUST KALMAN FILTERING BASED NEURAL
NETWORK |
|
Author: |
BINDU GEORGE, Dr. E. CHANDRA BLESSIE |
|
Abstract: |
Autism Spectrum Disorder (ASD) is a specific category of neurological disorder.
A person affected by ASD faces lifelong effect in making communication and
interaction with other common people. In individual’s life, autism can be
detected at any stage and it is also called behavioral disease. Symptoms of
autism appear in the first three years of childhood and it continues its growth
even if they reach adolescence and adulthood. Earlier prediction of ASD provides
a way for recovery from ASD. Machine learning algorithms have been widely
applied in various fields for better results. In this paper, Robust kalman
filtering based neural network (RKFNN) is proposed to predict the ASD more
accurately. In RKFNN has been modified to meet the prediction of ASD and it is
integrated with neural network for better results. Results with better
classification accuracy show the effectiveness of RKFNN towards the prediction
of ASD. |
|
Keywords: |
Autism ,ASD, Classification, Kalman, Neural Network |
|
Source: |
Journal of Theoretical and Applied Information Technology
15th June 2021 -- Vol. 99. No. 11 -- 2021 |
|
Full
Text |
|
|
Title: |
UNSUPERVISED LEARNING AS A DATA SHARING MODEL IN THE FP-GROWTH ALGORITHM IN
DETERMINING THE BEST TRANSACTION DATA PATTERN |
|
Author: |
MUSTAKIM, ULYA KHAIRUNNISA, ALEX WENDA, AHMAD ILHAM, FOLKES E. LAUMAL, ACHMAD
DAENGS GS, DARMA SETIAWAN PUTRA, IDA BAGUS ARY INDRA ISWARA, SRI RAHMAWATI
FITRIATIEN, ROBBI RAHIM |
|
Abstract: |
Market Basket Analysis is an analysis related to consumers and products in
marketing. One of the successes of a company in the retail sector depends on
promotion and shopping cart analysis. The data patterns generated from an
association-based analysis are mostly applied by companies, one of which is the
use of data mining technology. FP-Growth has been known as a reliable algorithm
in terms of association, but some obstacles in its implementation in the field
are often not finding a rule if using a diverse dataset. Unsupervised Learning
or what is often known as grouping techniques such as K-Means, K-Medoid, and
Fuzzy C-Means (FCM) can divide optimal data based on euclidean distances so that
it finds better data patterns than without data sharing, especially in the case
of FP-Growth. Comparisons are made by experimenting with the number of clusters
2 to 7, each of which is applied to the clustering algorithm. The results of
these experiments, K-Medoid is the algorithm with the best validity value
compared to other algorithms. Besides, the use of unsupervised learning
techniques combined with FP-Growth can generate rules for each algorithm
compared to simply applying FP-Growth. |
|
Keywords: |
K-Means, K-Medoids, FCM, FP-Growth, Data Sharing, Silhouette Index, Cluster
Validity. |
|
Source: |
Journal of Theoretical and Applied Information Technology
15th June 2021 -- Vol. 99. No. 11 -- 2021 |
|
Full
Text |
|
|
Title: |
THE ROLE OF MANUAL SKETCH UPLOADS ON INSTAGRAM TO UNDERSTANDING PLACE
IDENTITIES: A SYSTEMATIC LITERATURE REVIEW |
|
Author: |
AUGUSTINUS MADYANA PUTRA , GAGOEK HARDIMAN , AGUNG BUDI SARDJONO , GERALDO FREDO
EMOR , EVARISTUS DIDIK MADYATMADJA |
|
Abstract: |
Today, Instagram becomes an option for many people to share their experiences.
They uploaded photos and sketches that were related to their experiences. Their
sketches are usually captured the uniqueness of a place, which differentiates
one place from another. This unique character is a place identity. On the other
hand, the rapid development of functional demands can affect the sustainability
of place identities. This paper attempted to bridge these problems and
potentials through literature reviews. The review results showed that sketches
are a very sharp tool in revealing the place identity. Meanwhile, the
advancement in information technology through social networking sites (SNS)
makes these messages easily and quickly known and evaluated by many parties. The
knowledge obtained can be input for many interested parties to manage and well
preserve place identities. |
|
Keywords: |
Social Networking Sites, Instagram, On The Spot Sketch, Place Identities |
|
Source: |
Journal of Theoretical and Applied Information Technology
15th June 2021 -- Vol. 99. No. 11 -- 2021 |
|
Full
Text |
|
|
Title: |
THE OPTIMAL CUSTER BASED ON COMBINATORIAL OPTIMIZATION APPROACH FOR DATA
DETERMINATION ALGORITHM IN CLUSTER |
|
Author: |
DENY JOLLYTA, SYAHRIL EFENDI, MUHAMMAD ZARLIS, HERMAN MAWENGKANG |
|
Abstract: |
Clustering still leaves problems in selecting optimal clusters in order to
obtain a right and correct classification analysis. Right in the sense of the
number of clusters, while correct in terms of the information generated by a
group of cluster members that is optimally grouped. Determining the optimal
number of clusters is a difficult problem in non-polynomials. A number of
existing approaches generally still rely on the number of K tests tested. This
study aims to produce a new approach that can determine and place data in
clusters optimally in a combinatorial form. This can be done by considering that
the problem of selecting cluster placement has a combinatorial optimization
structure pattern. However, the resulting combinatorial optimization model is
quadratic. Therefore, in order to make the combinatorial clustering problem
easier to solve, linearization of the cluster data was carried out so that a
combinatorial optimization approach was produced with the algorithm. Several
illustrations have been put forward to demonstrate the validity of the method.
The combinatorial optimization approach as proposed in this research produces
novelty on cluster data analysis techniques. |
|
Keywords: |
Clustering, Information, Combinatorial Optimization, Linearization, Cluster Data |
|
Source: |
Journal of Theoretical and Applied Information Technology
15th June 2021 -- Vol. 99. No. 11 -- 2021 |
|
Full
Text |
|
|
Title: |
INNOVATION OF THE PHOTOVOLTAIC SYSTEM, GENERAL AND MAXIMUM POWER POINT TRACKING
DEVICE FOR SMART CITIES |
|
Author: |
S.ENNIMA, S.BOUREKKADI, O.EL IMRANI, M.KASSOU, S.SOUABY, M.EZZAKI , A.EL GHARAD |
|
Abstract: |
Photovoltaic solar energy becomes more and more a solution that promises to
replace fossil fuels, thanks to these benefits that we can mention abundance,
the absence of pollution and availability of more or less important amounts at
all. Points on the earth's globe. It is also a reliable energy (no moving
mechanical parts), flexible (adaptable size of the facilities) and which can be
produced as close as possible from the consumption site. Photovoltaic solar
systems have power generation directly depending on weather conditions
(temperature, irradiation). Thus, sizing and optimum use of the energy produced
by these generators requires the use of appropriate control methods. Recovery
efficiency photovoltaic system requires the recovery of maximum power PV
generator to establish proper control to receive maximum power in these
generators. The objective of this article is to study the performance of a
photovoltaic installation injected into the grid, to meet the energy needs of a
building, to then make athe implementation of two algorithms which are the MPPT
P&O algorithm and the algorithm Incremental conductance. |
|
Keywords: |
Photovoltaic solar, performance, energy needs, MPPT |
|
Source: |
Journal of Theoretical and Applied Information Technology
15th June 2021 -- Vol. 99. No. 11 -- 2021 |
|
Full
Text |
|
|
Title: |
A HYBRID APPROACH FOR WEB SEARCH RESULT CLUSTERING BASED ON GENETIC ALGORITHM
WITH K-MEANS |
|
Author: |
BOURAIR AL-ATTAR, AHMED J. ALLAMI, ALI THOULFIKAR A. IMEER, , YUSOR FADHIL
ALASADI, NORITA MD., NORWAWI, HAWRAA M. KADHIM |
|
Abstract: |
Nowadays, search engines tend to use the latest technologies in enhancing the
personalization of web searches, which leads to a better understanding of user
needs. One of these technologies is web search results clustering which returns
meaningful labeled clusters from a set of Web snippets retrieved from any Web
search engine for a given user’s query. Search result clustering aims to improve
searching for information from the potentially huge amount of search results.
These search results consist of URLs, titles, and snippets (descriptions or
summaries) of web pages. Dealing with search results is considered as treating
large-scale data, which indeed has a significant impact on effectiveness and
efficiency. However, unlike traditional text mining, queries and snippets tend
to be shorter which leads to more ambiguity. K-means tend to converge to local
optima and depend on the initial value of cluster centers. In the past, many
heuristic algorithms have been introduced to overcome this local optima problem.
Nevertheless, these algorithms suffer several shortcomings. In this paper, we
present an efficient hybrid web search results clustering algorithm referred to
as G-K-M, whereby, we combine K-means with a modified genetic algorithm. The AOL
standard dataset is used for evaluating web data log clustering. ODP-239 and
MORESQUE are used as the main gold standards for the evaluation of search
results clustering algorithms. The experimental results show that the proposed
approach demonstrates its significant advantages over traditional clustering.
Besides, results show that proposed methods are promising approaches that can
make search results more understandable to the users and yield promising
benefits in terms of personalization. |
|
Keywords: |
Personalized Search Engine, Search Results Clustering, G-K-M Clustering
Algorithm, K-Means |
|
Source: |
Journal of Theoretical and Applied Information Technology
15th June 2021 -- Vol. 99. No. 11 -- 2021 |
|
Full
Text |
|
|
Title: |
APACHE HADOOP PERFORMANCE EVALUATION WITH RESOURCES MONITORING TOOLS, AND
PARAMETERS OPTIMIZATION: IOT EMERGING DEMAND |
|
Author: |
MO TAZ AL-HAMI , MAJDI MAABREH , SALAH TAAMNEH , AAKASH PRADEEP , HANI BANI
SALAMEH |
|
Abstract: |
Recently, IoT has revealed a key value in the smart cities. Our living
comfortability level has been improved. Such technology requires extensive data
processing especially when it is a real time driven data. Apache Hadoop
framework is a necessary and efficient model that can be incorporated with the
IoT technology. Hadoop, the open-source framework, is typically used for
off-line batch processing on large-scale clusters. It has a wide range of
applications in the big data industry due to its capability in processing
massive data in distributed and parallel environments. However, several aspects
should be carefully evaluated before deploying Hadoop-based solutions. The
authors thoroughly investigate the Apache Hadoop framework with the focus on
factors that directly affect its performance. The work discusses and evaluates
two crucial dimensions of Hadoop systems; monitoring tools and their impact on
the performance of the Apache Hadoop based clusters, and the most influential
parameters and the optimization techniques of Apache Hadoop based systems.
Results showed that monitoring tools play a major role in Hadoop-based solutions
planning and maintenance. According to the used experimental settings, the Cacti
monitoring tool consumes around 45% of the memory usage, however memory usage in
Ganglia is more efficient than Cacti tool (i.e., on average around 2.5%). For
CPU utilization, both monitoring tools are efficient and the monitoring tool
usage amount is almost negligible. The results also showed that there is a
shortlist of critical parameters that significantly affect the overall
performance. Based on the results, the authors conclude the paper by future
directions and possible improvements that need further explorations and
experiments. |
|
Keywords: |
Big Data, Iot, Distributed System, High Performance Computing, Artificial
Intelligence, Smart Sensors. |
|
Source: |
Journal of Theoretical and Applied Information Technology
15th June 2021 -- Vol. 99. No. 11 -- 2021 |
|
Full
Text |
|
|
Title: |
THE DETECTION AND COUNTING OF OBJECT BOTTLES IN THE BOXS BASED ON IMAGE
PROCESSING USING WATERSHED ALGORITHM |
|
Author: |
CHAERUR ROZIKIN, MOHAMAD IQBAL SURIANSYAH, ARIES SUHARSO, KUSNADI,
MUHAMMAD FAJAR ESTU NUGROHO, NURLANA SANJAYA |
|
Abstract: |
Quality control using image processing and machine vision offers faster
performance and high accuracy, with minimum human contact. A significant
application refers to bottle counting in a box-based pattern to deliver
appropriate quantity, according to customers' demand. The precise arrangement
with very close proximity to each other poses a significant challenge. As a
result, missed detection tends to occur during segmentation due to
interconnected boundaries and contacts. The watershed algorithm provides a
possible solution with the capacity to segregate touching and overlap. A
particular approach to bottle detection and counting used in this research. The
results showed the average detection accuracy for 9-12 bottles at 99.5726%.
However, with mean values for memory usage on every detection of 0.6 MiB and
time interval on every 3 boxes detection within 0.21 secs, the use of the
watershed algorithm was strongly believed as a suitable alternative. |
|
Keywords: |
Watershed Algorithm, Object Counting, Image Segmentation |
|
Source: |
Journal of Theoretical and Applied Information Technology
15th June 2021 -- Vol. 99. No. 11 -- 2021 |
|
Full
Text |
|
|
Title: |
DEVELOPING AUGMENTED REALITY APPLICATION ON KOMODO DRAGON FOR ELEMENTARY SCHOOL
CHILDREN DURING THE NEW NORMAL OF COVID-19 PANDEMIC |
|
Author: |
MEIKE PAAT, HADI SUTOPO, NURLIANI SIREGAR |
|
Abstract: |
The COVID-19 pandemic has brought much challenge and disruption to the lives of
students in elementary through high schools, their families, and their
communities. Most students cannot attend schools due to the increased spread of
COVID-19, and they learn online from home. This paper aims to develop an
augmented reality learning model that delivers information on Komodo dragons
that can be accessed using smartphones. The developing augmented reality
application uses the Augmented Reality Development Method. It can be that the
augmented reality learning model would be easier, more fun, and interesting for
students in conducting online learning the New Normal of COVID-19 Pandemic. The
research findings show that the learning model is useful to help teachers since
it can be used for independent learning and motivates children to learn in
COVID-19 pandemic. |
|
Keywords: |
Instruction; Augmented reality; learning; Mobile device; COVID-19 |
|
Source: |
Journal of Theoretical and Applied Information Technology
15th June 2021 -- Vol. 99. No. 11 -- 2021 |
|
Full
Text |
|
|
Title: |
FACTORIZATION OF SMALL RPRIME RSA MODULUS USING FERMAT’S DIFFERENCE OF SQUARES
AND KRAITCHIK’S ALGORITHMS IN PYTHON |
|
Author: |
MAYA SILVI LYDIA, MOHAMMAD ANDRI BUDIMAN, DIAN RACHMAWATI |
|
Abstract: |
The RPrime RSA is one among many public key algorithms that relies its security
on the hardness of finding prime factors of a very large integer. While its
predecessor, the RSA, utilizes two large prime numbers to formulate its modulus,
the RPrime RSA can utilize two or more prime numbers. Therefore, the RPrime RSA
is intuitively taken into account to be securer the than the RSA. The modulus of
the RPrime RSA, n, is the public key whose size determines the security of the
entire cryptosystem: the larger the modulus, the securer the cryptosystem. In
this study, we shall show the way to factorize small modulus of the RPrime RSA
using two factorization algorithms, which are the Fermat’s difference of squares
algorithm and the Kraitchik’s algorithm. The programming of the factorization is
completed using Python programming language. Our study shows that both of
Fermat’s difference of squares and Kraitchik’s algorithms can be used
effectively as methods to factorize small modulus of RPrime RSA. The time both
algorithms take to factorize is mostly directly proportional to the size of n.
However, Fermat’s difference of squares is much faster than Kraitchik’s
algorithm: while factoring six digits to eleven digits of n, Fermat’s is about
24 to 550 times faster than Kraitchik. |
|
Keywords: |
Cryptography, Public Key Cryptosystem, Cryptanalysis, Rprime RSA, Difference of
Squares, Kraitchik |
|
Source: |
Journal of Theoretical and Applied Information Technology
15th June 2021 -- Vol. 99. No. 11 -- 2021 |
|
Full
Text |
|
|
|
