|
|
|
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
October 2019 | Vol. 97
No.20 |
|
Title: |
A SYSTEMATIC REVIEW OF MOBILE-BASED ASSESSMENT ACCEPTANCE STUDIES FROM 2009 TO
2019 |
|
Author: |
ALI MAMDOUH ALROFOUH, MUHAMMAD MODI LAKULU, MOHAMMED AMIN ALMAIAH |
|
Abstract: |
Despite many studies being conducted on mobile learning acceptance, few
investigate mobile-based assessment acceptance. The objectives of this study
are: (1) to provide valuable insights into current research on mobile-based
assessment literature and (2) to identify the main gaps in the mobile-based
assessment acceptance literature. Therefore, the present study systematically
reviews 45 previous studies and eight articles related to mobile-based
assessment acceptance to provide a comprehensive analysis of the articles
published from 2009 to 2019. Findings indicate that majority of mobile-based
assessment studies focused on evaluating the effectiveness and performance of
mobile-based assessment system and conducted at the secondary school level. In
addition, this study identified several gaps. Further research is needed to
study the acceptance problem of a mobile-based assessment system. More
investigation is required to predict which external factors that can enhance the
acceptance and use of mobile-based assessment among students. The findings of
this review study provide a valuable reference for researchers about the current
trend of mobile-based assessment research as well as the research gaps that
should be covered in future studies. |
|
Keywords: |
Mobile-Based Assessment; Acceptance studies; Systematic Review |
|
Source: |
Journal of Theoretical and Applied Information Technology
31st October 2019 -- Vol. 97. No. 20 -- 2019 |
|
Full
Text |
|
|
Title: |
EFFICIENT APPROACH FOR VEHICLE COUNTING BASED ON DEEP CONVOLUTIONAL NEURAL
NETWORKS |
|
Author: |
HOANH NGUYEN |
|
Abstract: |
Vehicle counting plays an important role in intelligent transport systems. A
vehicle counting system should be fast to be implemented in real-time
circumstances. Recent methods for vehicle counting usually include two stages,
vehicle detection and vehicle tracking. Vehicle tracking stage requires more
computational cost, which makes the system less efficient. In this paper, a new
approach for vehicle counting based on deep convolutional neural networks (CNN)
is proposed. First, an improved single shot multibox detector (SSD) is proposed
for fast vehicle detection. The base network and detection network in the
original SSD are replaced and modified to reduce the computational cost. To
eliminate vehicle tracking step, a region of interest (ROI) is set in each image
frame. The number of vehicles is increased when a vehicle is passing the ROI.
Furthermore, an improved algorithm for counting exactly the number of vehicles
is introduced. Experimental results on public datasets show that the proposed
method is the fastest system for counting vehicle among current systems and
achieves comparable accuracy compared with state-of-the-art methods. |
|
Keywords: |
Vehicle Counting, Convolutional Neural Networks, Intelligent Transportation
Systems, Object Detection, Deep Learning |
|
Source: |
Journal of Theoretical and Applied Information Technology
31st October 2019 -- Vol. 97. No. 20 -- 2019 |
|
Full
Text |
|
|
Title: |
REVIEW ON AVOIDING SYBIL ATTACK IN VANET WHILE OPERATING IN AN URBAN ENVIRONMENT |
|
Author: |
NITHA C VELAYUDHAN , A.ANITHA , MUKESH MADANAN , VINCE PAUL |
|
Abstract: |
VANET security became a significant and active area within the research
community. Despite the different attacks on certain nodes of the VANET which
have been revealed, numerous attacks for instance Jamming, Sybil, and also
passive eavesdropping can debase the VANET performance. Consequently, it is
vital to have some precautionary mechanism in opposition to these attacks. In
Sybil Attack (SA), the attacker produces multiple identities that might belong
to other vehicles or dummy identities and send messages to legal nodes. These
sham identities are generated by the assailant to get the trust of the legal
node. In VANETs (Vehicular Ad Hoc Networks), the vehicular needs smart road
maintenance, smart signaling, along with other services. The new security
problem arises because of the actuality that there is chance for the
semi-trusted Road Side Units (RSUs) to be compromised. This Review Paper
highlighted the latest studies regarding the avoidance of the SA in VANET like
detecting SA on urban Vehicular Networks (VN), attacks in VANET, security
challenges on VANET and robust technique for SA detection. Also, details of SA
and VANETs are examined. The mechanisms are assessed centered on the positive
rate, non-trustworthy rate, and false negative rate. |
|
Keywords: |
Vehicular Ad-Hoc Network, Instance Jamming, Sybil Attack, Passive Eavesdropping,
Road Side Units. |
|
Source: |
Journal of Theoretical and Applied Information Technology
31st October 2019 -- Vol. 97. No. 20 -- 2019 |
|
Full
Text |
|
|
Title: |
IMPLEMENTATION OF LINK POLICY CONSULTING IN-DEPTH SEARCHING SYSTEM FOR LINKED
OPEN DATA CLOUD |
|
Author: |
YONGLAK SOHN |
|
Abstract: |
For Linked Open Data (LOD) cloud, an implementation of semantic web, this
research suggested the effectiveness of link policies in order to evaluate
sameness of entities in different LODs. Operating the link policies reduced
heavy burdens of explicitly specifying sameAs links between the entities. It
overcame the problem of omitting entities which must have been searched properly
from LOD cloud. Knowledge expansion is LOD cloud’s major goal. Until now, it has
been realized by the sameAs links. The links have been specified explicitly and
appended to LODs periodically. At the time of searching, therefore, considerable
number of entities had been excluded from being searched. In addition, the
burden of specifying sameAs links resulted in severe paucity of linkages in LOD
cloud and knowledge expansion has been limited consequently. To overcome the
limitations, this research suggested LODs to prepare their own link policies.
For the policy establishment, this paper devised vocabularies set. Instead of
following the sameAs links which have been specified explicitly and appended to
LODs, searching process consults link policies of source and target LODs and
evaluates the sameness between source and target entities. As the link policies
substitute the sameAs links, burdens of specifying and maintaining the sameAs
links have been reduced. By consulting the policies at the time of searching,
moreover, any changes in LOD cloud will not be omitted from the searching
results. In order to verify the effectiveness of link policies, this research
implemented In-Depth Searching (IDS) system. For a given searching request, IDS
progresses in depth by consulting the link policies and by accessing LODs.
Analysis on the effectiveness has been performed from the standpoint of recall
ratio and precision ratio. |
|
Keywords: |
Linked Open Data Cloud, SameAs Link, Link Policy, Ontology, Semantic Web |
|
Source: |
Journal of Theoretical and Applied Information Technology
31st October 2019 -- Vol. 97. No. 20 -- 2019 |
|
Full
Text |
|
|
Title: |
A SEMANTIC QUESTION CLASSIFICATION FOR QUESTION ANSWERING SYSTEM USING LINKED
OPEN DATA APPROACH |
|
Author: |
KITTIPHONG SENGLOILUEAN, NGAMNIJ ARCH-INT, SOMJIT ARCH-INT |
|
Abstract: |
Semantic question answering (SQA) was the research study regarding the natural
language processing. The purposes of this study were 1) to encourage the users
to query via the computer with the semantic natural language, and 2) to obtain
the concise, accurate, and relevant to the users’ needs. Recently, it was found
that the research studies have encountered the problems with semantic
communication, flexibility, and accuracy of processes, especially the process of
question classification. It was considered the vital process of developing the
semantic question answering system. Thus, this paper attempted to propose a
semantic question classification for the question answering system using the
linked open data approach. It proposed the problem-solving technique for
question classification through semantic grammar rules derived from the
questions based on principles of English grammar. Moreover, the linked open
data, WordNet and DBpedia were implemented to solve the problems of words
similarity and question classification through the question classification
taxonomy consisting of six main classes and fifty subclasses as standards for
question classification. Besides this, the dataset from the question sets of
TREC with one thousand questions were also implemented. The evaluation indicated
a high accuracy of question classification with the total scores of precision,
recall, and F-measure, at 92.82%, 95.16%, and 93.97%, respectively. |
|
Keywords: |
Semantic Question Answering, Natural Language Processing, Question
Classification, Linked Open Data, Semantic Web |
|
Source: |
Journal of Theoretical and Applied Information Technology
31st October 2019 -- Vol. 97. No. 20 -- 2019 |
|
Full
Text |
|
|
Title: |
INFORMATION MANAGEMENT USING INTELLIGENCE MEDIA MANAGEMENT (IMM) DIGITAL MEDIA
ANALYSTS IN MANAGING THE REPUTATION OF THE INDONESIAN NATIONAL POLICE |
|
Author: |
BOY RAFLI AMAR1, DEDDY MULYANA, ATWAR BAJARI, EDWIN RIZAL |
|
Abstract: |
The purpose of this study is to examine the information management using
intelligence media management (IMM) digital media analysts in managing the
reputation of the Indonesian National Police. The research method used in this
research is a case study method. The case study method can be used to
comprehensively explain an organization, and the program developed by the
Indonesian National Police Institution. Data collection was obtained through
in-depth interviews with informants who met the research criteria and
participatory observation. Research supports data obtained through the study of
literature from previous studies, documents, and relevant books. The results
revealed that Media management is needed by the Indonesian National Police as a
fact-finding function to obtain a picture of public opinion towards the
Indonesian National Police institution. The data is processed and analyzed and
then compiled into the Indonesian National Police strategic plan. The form of
media management integration in the public relations strategy is manifested in
collaboration with mainstream media, social media optimization, suppressing
negative news, the use of the IMM application, Police Success Dissemination,
rapid response to negative sentiments and managing trending topics. The strategy
is able to reverse the public perception of the performance of the Indonesian
National Police, where the Indonesian National Police Institution is on a
positive trend, the image of the Indonesian National Police continues to
increase every year. |
|
Keywords: |
Media Management; PR; The Indonesian National Police; Strategy; Image |
|
Source: |
Journal of Theoretical and Applied Information Technology
31st October 2019 -- Vol. 97. No. 20 -- 2019 |
|
Full
Text |
|
|
Title: |
DESIGNING PRODUCTION SYSTEM USING SERVICE ORIENTED ARCHITECTURE (SOA) CASE STUDY
IN AUTOMOTIVE MANUFACTURING |
|
Author: |
RIFKY AJI NUGROHO, AHMAD NURUL FAJAR |
|
Abstract: |
Management system development in a manufacturing company is very complex, this
is because the business conditions in the company is very flexible, so it
requires the concept of developing a flexible and reusable system. The concept
of enterprise architecture is now entering a level that can be considered very
tough to apply to manufacturing companies that business looks very volatile. In
addition to highly competitive business issues, another problem is the very high
investment infrastructure that requires an infrastructure service that expenses
the cost in accordance with its use. The concept of enterprise architecture
using SOA is a method that can accommodate the development of existing systems
in manufacturing companies based on service oriented. Then, viewed from the side
of the production system concept, generally the automotive company uses the TPS
concept, namely the Toyota Production system, this concept in general is to
develop products based on continuous improvement, so that the production process
will continue to evolve to adjust customer needs. to support sustainable
improvement, the concept of developing a flexible and effective system is
needed. This SOA architecture can be used to support such production system
concepts, so companies can continue to develop the production process without
being hindered by the development of a complex system |
|
Keywords: |
Enterprise Architecture, Manufacture Production System, Service Oriented
Architecture. |
|
Source: |
Journal of Theoretical and Applied Information Technology
31st October 2019 -- Vol. 97. No. 20 -- 2019 |
|
Full
Text |
|
|
Title: |
MODELLING AND SIMULATION: AN INJECTION MODEL APPROACH TO CONTROLLING DYNAMIC
STABILITY BASED ON UNIFIED POWER FLOW CONTROLLER |
|
Author: |
RAHMANIAR, AGUS JUNAIDI, GANEFRI, ABD. HAMID K, NIZWARDI JALINUS, JALIUS JAMA |
|
Abstract: |
This study aims to determine the effect of UPFC as a Flexible AC Transmission
System (FACTS) tool to improve dynamic stability. FACTS is a power electronic
device used for various controls on power transmission systems. Power Flow
Control, Oscillation Control System can be done by FACTS device. FACTS devices
using the Unified Power Flow Controller (UPFC) are modelled to see the
performance of dynamic oscillations through software-assisted simulations.
Dynamic oscillation occurs due to a temporary disturbance or Short Circuit,
causing instability. UPFC devices which are installed on the transmission line.
Effect of UPFC to damp oscillation of power system with a model. The injection
model is modelled by the active and reactive power supply equation of the
injected UPFC to the transmission line. A dynamic oscillation repair is
performed by regulating the shunt bus voltage of the reference value and which
maintains the dc link on the capacitor voltage. Voltage, The magnitude in the
shunt bus, depends on the injected reactive power, where the dc is connected to
the capacitor on the UPFC device. The injection model is applied to the
simulated effect of UPFC device, showing the simulated effect of UPFC mounting
can improve the oscillation caused by disturbances in the power system. Speed
Change Oscillations for the generator 1 dan Generator 2, the system without UPFC
oscillates for Generator 1, with Over-shoot 6.5x10-1 while using UPFC Over-shoot
of 4x10-4. UPFC can reduce the speed change in Generator 1 in about 7.5 seconds;
the system returns the equilibrium position (Steady-State). |
|
Keywords: |
Injection Model, Simulation, FACTS, UPFC |
|
Source: |
Journal of Theoretical and Applied Information Technology
31st October 2019 -- Vol. 97. No. 20 -- 2019 |
|
Full
Text |
|
|
Title: |
ANALYSIS OF SALES FORCE AUTOMATION SYSTEM IMPLEMENTATION WITH THE DELONE AND
MCLEAN MODEL |
|
Author: |
TEGUH WIBOWO, AHMAD NURUL FAJAR |
|
Abstract: |
Optimis is a sales force automation information technology to carry out the
sales process used by employees at PT XYZ. But in reality there are still
problems and obstacles in the application of these technologies. This is due to
the lack of utilization of the Optimis system so that it influences the quality
of the data and reports on the sales process contained in the Optimis sales
force automation system. To find out the extent of the success of the system
implementation of the Optimis sales force automation, an analysis of the
implementation of the system was carried out Optimis sales force automation with
the framework of Delon and Mclean and using the PLS-SEM (Partial Least Square)
analysis method. The results of hypothesis testing that have been carried out
that the variables used are information quality and service quality have a
positive effect on system usage, information quality and service quality have a
positive effect on user satisfaction and information quality, system usage and
user satisfaction have a positive effect on net benefits. And from the
statistical tests performed, the level of influence is higher in student
acceptance of the system Optimis sales force automation is the quality of
service to the use of the system Optimis sales force automation with a value of
3,643. While the level of influence that is lower in acceptance is the quality
of the system towards user satisfaction with a value of 0.151. |
|
Keywords: |
SFA, Delon and Mclean, SEM, PLS-SEM, Information System Success Model |
|
Source: |
Journal of Theoretical and Applied Information Technology
31st October 2019 -- Vol. 97. No. 20 -- 2019 |
|
Full
Text |
|
|
Title: |
AN ANTICIPATORY ACTION: PORNOGRAPHIC EXPOSURE VIA INTERNET AND THE ATTITUDES OF
THE STUDENT WITH VISUAL IMPAIRMENT TOWARD SEXUALITY |
|
Author: |
HANNY HAFIAR, SYAUQY LUKMAN, FAJAR SYUDERAJAT, FX. ARI AGUNG PRASTOWO |
|
Abstract: |
The presence of assistive technology to facilitate people with visual impairment
in reading texts digitally, has other impacts that were previously not
anticipated. Some negative digital content, includes pornography, can be easily
accessed and have impact on attitudes regarding sexuality. The purpose of this
study was to determine the effect of exposure to pornography on students with
visual impairment regarding sexuality, in the cultural context adopted by most
Indonesian people, sexuality has certain limitations that must be maintained in
accordance with social values. The findings are the initial stage for mapping
efforts that can be taken by school institutions to expect the negative effects
of pornography among students. The method used is a quantitative, using simple
linear regression test, while the samples taken are 41 students. Along with data
got from interviews and observations to map out the anticipation effort. The
results showed that there was an influence from pornographic exposure on
students with visual impairment regarding sexuality so there was a shift in the
values adopted by some of them regarding sexuality, compared to the previous
generation who were not familiar with pornographic content obtained from the
internet. The anticipated actions include filtering, socializing the negative
effects of pornography, teacher supervision, coordination between schools with
parents, reminding each other among peers, strengthening religious value,
consultation and addition activities that students can follow. |
|
Keywords: |
Pornography, Sexuality, Students, Adolescents, Visual Impairment. |
|
Source: |
Journal of Theoretical and Applied Information Technology
31st October 2019 -- Vol. 97. No. 20 -- 2019 |
|
Full
Text |
|
|
Title: |
FACTORS AFFECTING INTENTION TO USE “SAKUKU” E-MONEY OF GENERATION Y IN INDONESIA |
|
Author: |
JERRY MARCELLINUS LOGAHAN, MAULANA VILIANO, BACHTIAR H. SIMAMORA |
|
Abstract: |
To succeed in the retail banking business, the bank must continue to innovate
and apply the latest technologies into their business to meet the various needs
of customers. Generation Y (Gen Y) is a very potential market segments,
especially with the latest technology that are already phenomenal, so-called
e-money or electronic money with a smartphone device. This study was conducted
to evaluate the factors that affect on intention to use Sakuku e-money of Gen Y.
Based on the Technology Acceptance Model, and previous research journals, we
propose a model research with five direct and indirect factors that affect on
intention to use Sakuku e-money of generation Y. This research was conducted in
Indonesian territory involving 100 respondents aged 16 s / d 35 years, have a
smartphone and non Sakuku users. The data collection is done by distributing a
questionnaire containing 26 questions with Likert scale of 1 - 5. The data was
analyzed by SEM-based PLS. After analyzing the data collected from our survey,
we showed five significant factors, and two of them have the most powerful
affect to increase intention to use Sakuku e-money of the Y generation in
Indonesia. According to these findings, we propose some strategy on how the bank
to increase the number of Sakuku e-money users of the Gen Y in Indonesia. |
|
Keywords: |
Perceived Usefulness, Perceived Ease Of Use, Attitude Towards Behavior,
Intention To Use. |
|
Source: |
Journal of Theoretical and Applied Information Technology
31st October 2019 -- Vol. 97. No. 20 -- 2019 |
|
Full
Text |
|
|
Title: |
DESIGNING ENTERPRISE ARCHITECTURE USING TOGAF FRAMEWORK IN METEOROLOGICAL,
CLIMATOLOGICAL, AND GEOPHYSICAL AGENCY |
|
Author: |
FERGYANTO E. GUNAWAN, JOHANES FERNANDES ANDRY, HENDY TANNADY, ROURENTSIA
MEYLOVSKY |
|
Abstract: |
The Deputy of Instrumentation, Callibration, Engineering and Communication
Network (IKRJK) in Meteorological, Climatological, and Geophysical Agency (BMKG)
does not have an adequate integrated information system with other deputies to
support its activities. The purpose of this research is to produce enterprise
architecture design, especially in business architecture. The results of this
research, namely a proposed enterprise architecture model using a TOGAF ADM
framework whereas this model adapted with the requirement of business process of
Deputy IKRJK in BMKG for the development of Information System (IS) or
Information Technology (IT). |
|
Keywords: |
Enterprise Architecture, TOGAF, BMKG, Information System, Information
Technology, Business Architecture |
|
Source: |
Journal of Theoretical and Applied Information Technology
31st October 2019 -- Vol. 97. No. 20 -- 2019 |
|
Full
Text |
|
|
Title: |
DESIGNING MULTIPLE CLASSIFIER COMBINATIONS: A SURVEY |
|
Author: |
ABDULLAH HUSIN, KU RUHANA KU-MAHAMUD |
|
Abstract: |
Classification accuracy can be improved through multiple classifier approach. It
has been proven that multiple classifier combinations can successfully obtain
better classification accuracy than using a single classifier. There are two
main problems in designing a multiple classifier combination which are
determining the classifier ensemble and combiner construction. This paper
reviews approaches in constructing the classifier ensemble and combiner. For
each approach, methods have been reviewed and their advantages and disadvantages
have been highlighted. A random strategy and majority voting are the most
commonly used to construct the ensemble and combiner, respectively. The results
presented in this review are expected to be a roadmap in designing multiple
classifier combinations. |
|
Keywords: |
Multiple Classifier Combination, Classifier Ensemble Construction, Combiner
Construction |
|
Source: |
Journal of Theoretical and Applied Information Technology
31st October 2019 -- Vol. 97. No. 20 -- 2019 |
|
Full
Text |
|
|
Title: |
WHAT IS THE MOST INFLUENTIAL FACTOR ON DECISIONS USING YOUTUBE AS A TOOL TO
SUPPORT BUY OR SELL MEANS? (CASE STUDY SURABAYA CITY AND SURROUNDING AREA) |
|
Author: |
RINABI TANAMAL |
|
Abstract: |
In the era of communication technology which is getting faster and more eager to
adapt, this change the pattern of human life. The increasing use of smart phones
has also changed the way human seek information. YouTube is one of the social
medias that is now widely used in parts of the world from children to adults. To
find information on items that you want to buy, now people trust reviews from
some active YouTube users. According to SocialMediaWeek, 74% of shoppers make
buying decisions based on social media. The shoppers tend to believe what the
Social Influencer has to say.
Knowing the transition of people's lifestyle
that previously if you want to buy goods do not know the quality of these items,
can now get information from YouTube from several people who review the items
you want to buy. The seller can also promote goods or services that will be sold
through YouTube. Thus, through this research the researcher wants to obtain the
research data by using the TAM method with additional external variables such as
customer satisfaction, computer self-efficacy and trust. This research was
conducted to Surabaya People and surround area. In this study The Customer
Satisfaction contribute the Highest factor in the desire to use YouTube as a
means of selling / buying. |
|
Keywords: |
YouTube, TAM, Trust, Perceived Usefulness, Consumer Satisfaction, PEOU |
|
Source: |
Journal of Theoretical and Applied Information Technology
31st October 2019 -- Vol. 97. No. 20 -- 2019 |
|
Full
Text |
|
|
Title: |
MALDROID: ATTRIBUTE SELECTION ANALYSIS FOR MALWARE CLASSIFICATION |
|
Author: |
RAHIWAN NAZAR ROMLI, MOHAMAD FADLI ZOLKIPLI, MOHD ZAMRI OSMAN |
|
Abstract: |
Android is the most dominant operating system in the mobile market and the
number of Android users is increasing year by year. Malware authors use android
market as a hub for malicious apps and spread malware to users with the
intention to threaten privacy; and this has remained undetected due to the
weakness in signature-based detection. A major problem with malware detection is
the existence of numerous features in malware code and the need to look at the
relevant features in malware analysis. As a result, applying any security
solution in malware analysis is considered inefficient because mobile devices
have limited resources in terms of its memory, processor and storage. Hence, the
objective of this paper is to find the most effective and efficient attribute
selection and classification algorithm in malware detection. Moreover, in order
to get the best combination between attribute selection and classification
algorithm, eight attributes selection and seven categories machine learning
algorithm are applied in this study. The experiment evaluated 8000 real data
samples and the result showed that InfoGainEval and KNN algorithm are the most
selected in attribute selection and classification process. |
|
Keywords: |
Android, Malware, Malware Analysis, Machine Learning Algorithm, Info Gain
Evaluation |
|
Source: |
Journal of Theoretical and Applied Information Technology
31st October 2019 -- Vol. 97. No. 20 -- 2019 |
|
Full
Text |
|
|
Title: |
USING FUZZY LOGIC TO ENHANCE THE CLASSIFICATION AND DIAGNOSING OF HYPERTENSION |
|
Author: |
SHIRAZ H.E., NORMA ALIAS |
|
Abstract: |
High blood pressure, which has a widespread in today's world, is a disease that
can cause serious damage to the cardiovascular system. To illustrate, in 1975,
594 million people were diagnosed with hypertension. However, the number has
doubled over the last 40 years to become over 1.1 billion in 2015. Moreover, a
significant number of patients do not even know they have hypertension due to
the inadequate awareness of hypertension symptoms. Because of the difficulty
with distinguishing the symptoms of hypertension, fuzzy logic can be utilized as
an efficient diagnostic tool. Several research papers have suggested various
diagnostic algorithms based on fuzzy logic. Hence, the contribution of this
research is to investigate the most recent researches conducted on fuzzy logic
for diagnosing hypertension. This will help to enhance the classification,
diagnosing method and to overcome the limitations of existing approaches. |
|
Keywords: |
Fuzzy logic, classification method, diagnosing method, Hypertension, Blood
Pressure. |
|
Source: |
Journal of Theoretical and Applied Information Technology
31st October 2019 -- Vol. 97. No. 20 -- 2019 |
|
Full
Text |
|
|
Title: |
THE USE OF PARTICLE SWARM OPTIMIZATION TO OBTAIN N-GRAM OPTIMUM VALUE FOR MOVIE
GENRE CLASSIFICATION |
|
Author: |
EDI NOERSASONGKO , D. SALVANA ERVAN1, H. AGUS SANTOSO , CATUR SUPRIYATO , FARIKH
AL ZAMI , M.A. SOELEMAN |
|
Abstract: |
Document Classification that until now still be done by experts / human in the
field related to the document. In recent years researchers included in this
study proposed a variety of methods to solve the problem of document
classification automatically. In this research, we used classification of movie
genre based on synopsis as research object. Previous research proposed a model
with a statistical approach with the Naive Bayes algorithm that proved to get
the best results compared to other classification algorithms. Several studies
have proposed adding a selection of N-gram features to pre-processing. The
resulting classification becomes better than before. However, there is a
weakness of N-gram between is the value of n which is determined still randomly
or by trial and error. With these weaknesses, in this study proposes to optimize
the N-gram model to obtain optimum n values using the Particle Swarm
Optimization algorithm. Acquisition of an optimal N-gram n value will improve
document performance and classification results with Naive Bayes. Based on the
proposed model can then be used as a document classification model with
different objects |
|
Keywords: |
Document Classification, N-gram, Particle Swarm Optimization, Naive Bayes |
|
Source: |
Journal of Theoretical and Applied Information Technology
31st October 2019 -- Vol. 97. No. 20 -- 2019 |
|
Full
Text |
|
|
Title: |
AN ENHANCED EVOLUTIONARY ALGORITHM WITH LOCAL HEURISTIC APPROACH FOR DETECTING
COMMUNITY IN COMPLEX NETWORKS |
|
Author: |
DHUHA ABDULHADI ABDULJABBAR, SITI ZAITON MOHD HASHIM, ROSELINA SALLEHUDDIN |
|
Abstract: |
These days, the properties of numerous systems in biology, engineering and
sociology paradigms can be captured and analysed as networks of connected
communities. The increasing emergence of these networked systems has fuelled the
desire to study and analyse them into several sub-networks called communities.
Community detection in a complex network is an ill-defined problem. Evolutionary
Algorithms (EAs) have shown promising performance in community detection, but
it's difficult to identify natural divisions included in such complex networks
accurately and effectively without designing a problem-specific operator that
exploits domain knowledge and guides the search process. Moreover, most of the
contemporary studies only employ EA-based models to detect communities, which
may not be adequate to represent the real community structure of networks due to
the limitation in their topological properties. Thus, to enhance the predictive
power of the state-of-the-art EA-based models, the main contribution of this
research work is to put forward a framework that integrates evolutionary
algorithm (EA) with a local heuristic approach. In the experiments, we select
and optimise four well-known community detection models within the evolutionary
algorithm framework, i.e. expansion model, scaled cost function model,
conductance model, and internal density model. Then, the proposed heuristic
approach is employed to locally aid along with the optimisation model, in which
the nodes having dense intra-connections with nodes of other communities are
moved to neighbouring communities. In the experiments, the performance of the
optimisation models has been examined on both synthetic and real-world networks
that are publicly available. The results show that the put forward local
heuristic approach has a positive effect that significantly enhanced the
existing optimisation models’ detection ability. |
|
Keywords: |
Community Detection, Complex Network, Evolutionary Algorithm, Optimisation
Model, Local heuristic Approach |
|
Source: |
Journal of Theoretical and Applied Information Technology
31st October 2019 -- Vol. 97. No. 20 -- 2019 |
|
Full
Text |
|
|
Title: |
COMPUTER SIMULATION IN THE MATHCAD PACKAGE OF PLASTIC DEFORMATION OF THE
DEPOSITED LAYER ON THE FLAT SURFACE OF THE PART |
|
Author: |
BULEKBAEVA G., KIKVIDZE O.G., LAKHNO V., 4BRZHANOV R., TABYLOV A. 5SMIRNOV S. |
|
Abstract: |
The one-dimensional problem of plastic deformation of the deposited layer on a
flat surface was studied when a cylindrical roller was rolled in, including the
Coulomb friction law on the contact surface. The equation of state of the
material is selected on the basis of the theory of creep (hardening theory). An
application program was developed in the mathematical editor Mathcad for the
numerical analysis of a non-linear one-dimensional problem. In the course of
computer simulation and subsequent experimental checks, it has been established
that the stress-strain state in the deformation zone significantly depends on
magnitude and on the friction coefficient on the surface of contact of the
material with the roller. According to the results of computer simulation and
field experiments, a method for calculating the deposited layer was proposed.
The given technique can be used to determine the parameters of the technological
process during the restoration of flat surfaces. The article demonstrates with a
specific example that, since every year the interest of various enterprises in
the mathematical modeling of technological processes of metal processing grows
much faster than various databases of material properties are filled in
specialized packages such as JMatPro, Forge, Finel, Abaqus, LS Dyna, Deform
required for calculations and obtaining adequate results, modeling the
properties of materials in such common programs as, for example, MathCad, can be
an excellent solution for enterprises that do not have the opportunity to engage
in expensive experimental research. It is shown that the solutions proposed in
the article for the MathCad package that implement the mathematical model of
plastic deformation of the deposited layer allows studying the processes of
plastic deformation for a user who does not have programming experience and work
with numerical methods for solving systems of ordinary differential equations. |
|
Keywords: |
Plastic Deformation, Computer Simulation, Non-Stationary Thermal Conductivity |
|
Source: |
Journal of Theoretical and Applied Information Technology
31st October 2019 -- Vol. 97. No. 20 -- 2019 |
|
Full
Text |
|
|
Title: |
DEVELOPMENT OF AN ANDROID APP FOR TEXT DETECTION |
|
Author: |
MUHAMMAD AHMED ZAKI, SAMMER ZAI, MUHAMMAD AHSAN, UROOBA ZAKI |
|
Abstract: |
The field of text recognition is an important area as it finds various useful
applications in computer vision such as document analysis, image search, robot
navigation etc. Even though, a bunch of research has been carried out in this
area but still there is a room for the improvement as none of the presented
methods are error-free due to the challenges that may include the font of the
characters, multi-oriented text, and the quality of pictures that contain text.
Text detection is an important step towards the various content-based image
retrieval techniques (CBIR). This study aim is to provide a flexible method to
extract texts from challenging images and show them line-by-line by employing
basic image processing techniques. The proposed system is an image processing
and data retrieval system for English text. The system tends to build up an
application that can recognize the English content present in an image captured
by using a smart phone and then display the recognized text into editable format
on the mobile screen. In order to show the effectiveness of the proposed
technique extensive experiments have been performed on smart phone and the
results are compared with various top-ranked commercial mobile apps. |
|
Keywords: |
CBIR , OCR, Android App Development, image processing, Tesseract, Artificial
Intelligence. |
|
Source: |
Journal of Theoretical and Applied Information Technology
31st October 2019 -- Vol. 97. No. 20 -- 2019 |
|
Full
Text |
|
|
|
