|
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
September 2020 | Vol. 98
No.17 |
Title: |
ENSEMBLE ADABOOST IN CLASSIFICATION AND REGRESSION TREES TO OVERCOME CLASS
IMBALANCE IN CREDIT STATUS OF BANK CUSTOMERS |
Author: |
ACHMAD EFENDI, RAHMA FITRIANI, HAFIZH IMAN NAUFAL, BAYU RAHAYUDI |
Abstract: |
The Classification and Regression Trees (CART) is a popular classification
method. Generally, at a bank, debtors who have delinquent loans (Non-performed
Loan/NPL) have a small proportion compared to debtors who have smooth loan
(Performed Loan/PL). Standard classification methods CART is not suitable for
handling such cases as it is sensitive to classes with a high degree. Hence,
additional methods are needed in order to improve classification accuracy in the
case of class imbalance. This study aims at determining the results of the
classification using the CART and Adaptive Boosting (Adaboost) CART methods on
bank loan or credit collectability data where there is class imbalance. The data
used for analysis are secondary data in the form of bank debtor credit
collectability data with 9 predictor variables and one response variable.
Simulations are also conducted to find out the consistency of the results of
analysis and general performance of Adaboost CART. The results of this study
indicate the accuracy of the classification on the Adaboost CART method can be
increased compared to the CART method. This implies that Adaboost can add
weights to classifiers which have small misclassifications and can reduce
weights on the correctly classified objects. This research can be taken into
consideration in choosing the right classification analysis in the case of data
with class imbalance. Simulation results confirm that the classification
accuracy of Adaboost CART is relatively large, 84.1%. |
Keywords: |
Adaboost, Classification and Regression Tree (CART), Class Imbalance, Credit,
Bank |
Source: |
Journal of Theoretical and Applied Information Technology
15th September 2020 -- Vol. 98. No. 17 -- 2020 |
Full
Text |
|
Title: |
A KEY POINT ALGORITHM IMPROVING INDOOR POSITIONING ACCURACY BASED ON BEACONS |
Author: |
QIANFENG LIN, JOOYOUNG SON |
Abstract: |
The indoor positioning technology in this paper identifies real-time positions
of the crew in ships. It can be used to get the regional personnel distribution
and find timely locations of accidents. Therefore, the accuracy is very
important when estimating positions in ships. This research considers the
nearest reference point and beacon in ships as key points for improving the
accuracy. We look for three key points to predict a user position. Firstly, KNN
algorithm is used to get the first point P1. Secondly, the nearest reference
point to the nearest beacon is the second point P2. Finally, the weighted
centroid point of nearest beacons is the third point P3. The centroid position
of these three key points is the predicted user position. Experimental results
show the accuracy has been improved by at most 54%. |
Keywords: |
Indoor Positioning, Key Point, Reference Point, In-ship Position, Crew Safety |
Source: |
Journal of Theoretical and Applied Information Technology
15th September 2020 -- Vol. 98. No. 17 -- 2020 |
Full
Text |
|
Title: |
SMART-ETL-MR: NOVEL ETL FRAMEWORK FOR BUILDING DATA WAREHOUSE FROM BIG DATA
SOURCE USING MAPREDUCE |
Author: |
ABDELJALIL BOUMLIK, NASSIMA SOUSSI, MOHAMED BAHAJ |
Abstract: |
The concept of Big Data created to face the massive explosion of data produced
from web 2.0, smart devices, sensors, social networks platforms like Facebook,
Twitter, Instagram, LinkedIn, has increased continuously. However, new
challenges and opportunities appear due to the growth of data. Nevertheless,
several prominent organizations and companies have realized that data is
valuable and offers competitive advantages, great benefits, and relevant
knowledge when it gets converted to actionable information they can use.
However, collecting these massive data is not enough, as we should be able to
integrate and analyze these data pulled from different heterogeneous sources
after loading them to improve analysis goals. This research article's primary
objective is to adapt the ETL (extraction transformation-loading) processes with
the potential of Big Data technologies in order to deal with these new
challenges from data warehousing perspective and knowledge discovery that
directly impacts business decision-making systems. In this article, a new
approach based called SMART-ETL-MR presented on the Map-Reduce paradigm to
expedite data handling and to build a well-organized data warehouse.
Experimental results prove that the ETL operation performs successfully with
optimal algorithms. |
Keywords: |
Big Data, ETL, HBase, Map Reduce, Data Warehouse, Facebook |
Source: |
Journal of Theoretical and Applied Information Technology
15th September 2020 -- Vol. 98. No. 17 -- 2020 |
Full
Text |
|
Title: |
GENETIC ALGORITHM APPROACH FOR AUTOMATED GENERATION OF NEURAL NETWORKS
ARCHITECTURE FOR ROBUST DIGIT RECOGNITION |
Author: |
RULLY SOELAIMAN, YOLANDA HERTITA PRATAMA, M.M. IRFAN SUBAKTI, YUDHI PURWANANTO |
Abstract: |
Digit recognition is a special part of research in Optical Character
Recognition. It is a common technique to recognize the numeric characters from
printed images. A solution’s design for the digit recognition problem on a case
study of SPOJ Hard Image Recognition (HIR) has been proposed in this paper. The
case study’s problem has challenging constraints such as runtime limit and
source code limit and it has many noisy images. An artificial neural network has
been implemented to solve this problem in consideration of its simplicity yet
powerful enough algorithm. The selection of best ANN architecture is commonly
achieved through trial and error process, which is a very time-consuming
process. This paper also provides the use of a Genetic Algorithm to determine
the architecture of ANN automatically. The creation of the dataset also has an
important role to improve the accuracy. The proposed architecture development
successfully passed the challenging constraints and achieved a high score of 108
at SPOJ HIR. The score obtained by using GA is higher than our predetermined ANN
architecture. |
Keywords: |
Artificial Neural Network, Digit Recognition, Genetic Algorithm, Optimization,
Pattern Classification |
Source: |
Journal of Theoretical and Applied Information Technology
15th September 2020 -- Vol. 98. No. 17 -- 2020 |
Full
Text |
|
Title: |
MODALITY CONFLICT DETECTION MODEL WITH AUTHORIZATION PROPAGATION IN POLICY
EVALUATION |
Author: |
TEO POH KUANG , HAMIDAH IBRAHIM , FATIMAH SIDI , AND NUR IZURA UDZIR |
Abstract: |
Modality conflict is one of the main issues in policy evaluation. Existing
modality conflict detection approaches do not consider complex condition
attributes such as spatial and temporal constraints. In this paper, a modality
conflict detection model is proposed to identify the applicable policies during
policy evaluation, which supports an authorization propagation rule to
investigate the class-subclass relationships of a subject, resource, action, and
location of a request and a policy. We have evaluated the effectiveness of our
proposed modality conflict detection model on real XACML policies for
university, conference management, and health-care domain. Overall, our solution
achieved higher percentage of P, R, and F in retrieving the applicable policies
and in detecting modality conflict as compared to the previous work. |
Keywords: |
Modality Conflict, Authorization Propagation, Policy Evaluation, Spatial and
Temporal Constraints, Distributed Environment |
Source: |
Journal of Theoretical and Applied Information Technology
15th September 2020 -- Vol. 98. No. 17 -- 2020 |
Full
Text |
|
Title: |
INNOVATIVE ARCHITECTURE BASED ON BIG DATA AND GENETIC ALGORITHM FOR TRANSPORT
LOGISTICS OPTIMIZATION |
Author: |
Z. MOUAMMINE, A. AMMOUMOU , B. NSIRI , S. BOUREKKADI |
Abstract: |
Many studies were carried out in the smart city field to improve the integration
or to optimize the intelligent transport systems (ITS) in business. Yet, there
were very few researches studying how ITS can still work outside of the context
of a smart city. Taking this issue into consideration, this study was carried
out to suggest a new system allowing shipping companies to keep working with
their ITS even outside of the context of Smart city based on Genetic algorithm,
Big Data, and multi-agent architecture. This is possible through implementing a
transport information system, which will provide and exchange data about the
optimum path to follow with vehicles (traveling vehicle problem) on the road.
Theoretically speaking, this proposed system accelerates the processing time and
enhances the quality of the obtained result with the Genetic algorithm to solve
Salesman problem. |
Keywords: |
Distribution Logistics, Intelligent Transport Systems, Traveling Salesman
Problem, Genetic Algorithm, Big Data, Smart City. |
Source: |
Journal of Theoretical and Applied Information Technology
15th September 2020 -- Vol. 98. No. 17 -- 2020 |
Full
Text |
|
Title: |
IMPROVING RECOMMENDATION ACCURACY AND DIVERSITY USING NETWORK EMBEDDING METHOD |
Author: |
NADIA BUFARDI, HAYTAM HMAMI, ABDELHADI FENNAN, ABDELOUAHID LYHYAOUI |
Abstract: |
In recent years, diversity in recommender systems have become increasingly an
essential dimension for evaluating the effectiveness of recommendations.
However, many existing recommendation techniques are challenged by information
overload with the widespread use of recommender systems in many real-world
applications. In this paper, we propose a new diversified recommendation
approach, namely DRN2V, based on rich constructed graphs and Network Embedding
technology. Specifically, we construct a knowledge graph of two sub-graphs, the
User-Item subgraph that represents the interactions between users and items and
the Item-Category subgraph which uses the item categorization to enrich the
network structure. Afterwards, we use Node2vec algorithm to capture the complex
latent relationships between users and items from the constructed knowledge
graph. Moreover, to propose personalized and relevant predictions for each user,
a new formula was proposed based on category coverage and users' preferences for
categories. The experimental results demonstrate the significant outperforms of
our approach over several embedding-based methods and recommendation algorithms
including both traditional and diversity-oriented algorithms) regarding accuracy
and diversity. |
Keywords: |
Recommender system, Accuracy, Diversity, Network embedding, Node2vec |
Source: |
Journal of Theoretical and Applied Information Technology
15th September 2020 -- Vol. 98. No. 17 -- 2020 |
Full
Text |
|
Title: |
ADAPTIVE LEARNING SCHEME FOR THE VIRTUALIZATION OF A ROTARY SERVO BASE UNIT |
Author: |
HOLMAN MONTIEL A., FREDY H. MARTÃNEZ S., EDWAR JACINTO G. |
Abstract: |
A system is a structure composed of mechanical, electrical or electromechanical
parts that interact with each other to fulfill an objective. At an industrial
level they are known as manufacturing processes and at an academic level these
processes are emulated by implementing mechanisms such as: designing scale
prototypes, building test and trial laboratories or developing specialized
simulators. However, the efforts made by the authors to build scale or simulated
prototypes that are an ideal copy of the real process are not perfect. On the
one hand, some real physical implementations reduce the margin of error by
improving the quality of the prototype materials, but as the quality of the
materials increases, so does their cost, which reduces accessibility to the
population. On the other hand, the simulators do not perfectly emulate
characteristics of the environment, such as humidity, temperature, vibrations,
among others, which reduces its reliability in the presentation of the results
obtained. Therefore, this article proposes a strategy to virtualize a QUANSER
SRV-02 rotary servo base unit, which from experimental data reconstructs a
mathematical model using a Genetic Algorithm (GA), which minimizes the margin of
error between experimental and practical data. This tool will allow virtual
practices (simulation) with results very close to the behavior of the real
plant. |
Keywords: |
Genetic Algorithm; ARIMA Models; Servomechanisms; Virtualization; Prototypes. |
Source: |
Journal of Theoretical and Applied Information Technology
15th September 2020 -- Vol. 98. No. 17 -- 2020 |
Full
Text |
|
Title: |
AN EFFICIENT SELF-MAPPING ALGORITHM FOR HEXAGON-BASED GRIDDING IN AD HOC
NETWORKS |
Author: |
MOHAMMAD M. QABAJEH, LIANA K. QABAJEH |
Abstract: |
Mobile Ad hoc NETwork (MANET) is a multi-hop autonomous network formed
exclusively among a collection of mobile nodes without any centralized
infrastructure. MANETs are generally unstable; the alternative for this
non-infrastructure topology is to construct a virtual infrastructure. Using
virtual clustering helps in creating an infrastructure for MANET to simplify
routing and network management. Network terrain may be portioned into numerous
shapes to support scalable routing. Hexagon-based gridding outperforms other
gridding shapes; due to its geometric features. However, cell coordinate
assignment and mapping node physical location into grid map is an important
aspect. In this paper, we introduce a self-mapping algorithm to enable each
mobile node to be aware of the precise cell it belongs to during the network
lifetime without the need to communicate with other nodes. This algorithm is a
core part of the position-based unicast and multicast routing protocols that
rely on virtual hexagon infrastructure. Our algorithm has been developed to
simplify routing discovery in large-scale MANETs and to ensure that the overhead
is as low as possible. |
Keywords: |
MANETs, Position-based, Routing, GPS, Self-mapping, Multicast Routing,
Unicast Routing |
Source: |
Journal of Theoretical and Applied Information Technology
15th September 2020 -- Vol. 98. No. 17 -- 2020 |
Full
Text |
|
Title: |
BLOCKCHAIN-ENABLED SMART UNIVERSITY: A FRAMEWORK |
Author: |
RANIA A. ABOUGALALA, MOHAMED A. AMASHA, MARWA F. AREED, SALEM ALKHALAF, DALIA
KHAIRY |
Abstract: |
Digitizing has become a necessity for universities to develop and improve their
services to facilitate access for beneficiaries. Utilizing new technologies
helps universities be more effective, efficient, flexible, and comfortable.
Smart university, a concept that represents higher education in the digital age,
has increased these considerations greatly, and blockchain is one of the fastest
emerging technologies in this era. This paper discusses the definitions of
blockchain and smart university and it also presents a conceptual framework to
illustrate how smart universities can use blockchain technology to support and
ensure a better understanding of the involvement their students with the
university. Furthermore, it presents two case studies using the formative
assessment to show the impact on the quality of education and the assessment of
academic supervision on scientific theses. A seven-tier framework of formative
assessment in smart universities will be used to improve the quality of
education. |
Keywords: |
Smart University, Blockchain, Distributed Database, Smart University ,
Digitizing |
Source: |
Journal of Theoretical and Applied Information Technology
15th September 2020 -- Vol. 98. No. 17 -- 2020 |
Full
Text |
|
Title: |
DEVELOPMENT OF ADAPTIVE LOAD REGULATOR FOR SHEARER ELECTRIC DRIVE, PROVIDING
MAXIMUM RESPONSE TIME OF CONTROL SYSTEM |
Author: |
SHPREKHER D.M., BABOKIN G.I., ZELENKOV A.V. |
Abstract: |
Using the Matlab/Simulink software package a mathematical model of the
electromechanical system of a shearer with an built-in moving system has
developed. It takes into account all the main factors that determine its
operating modes: electro-magnetic transients in drive motors for cutting and
moving; dynamic forces in transmissions; the distribution of the cutting force
between the cutting drive and drive for moving, the nature of the change in the
moment of resistance forces during operation by changing the strength of the
coal. The shearer control system contains a load regulator with a PI-controller.
However, it was found that, despite the simplicity of the configuration and
physical implementation, as well as the relatively high reliability, this class
of control devices may not provide optimal operation of the control system in
all modes due to the non-linearity of the control object and the random nature
of the coal force changes as the shearer moves in the coal face. To overcome
these shortcomings, the possibility of a neural-network implementation of
correction of the PI-controller coefficients is considered. The possibility of
the correction of the PI-controller coefficients controlling the speed of the
shearer movement, with a random nature of the coal strength changing, is
proposed and experimentally proved. It is shown that the use of the
PI-controller with the corrector in the form of the neural network in the
control system will increase performance of the load regulator by an average of
1.5–3 times in comparison with the classical regulator. All this will allow to
avoid critical overloads, and hence the possible breakdown of the mechanical
parts in the transmission of the shearer in case of a sudden collision of the
executive body of the shearer with a solid inclusion. |
Keywords: |
Shearer, cutting drive, coal strength, neural network, PI-controller |
Source: |
Journal of Theoretical and Applied Information Technology
15th September 2020 -- Vol. 98. No. 17 -- 2020 |
Full
Text |
|
Title: |
SOME APPROACHES TO ASSESSING THE QUALITY OF MASKING NOISE INTERFERENCE OF
SPATIAL NOISE GENERATORS |
Author: |
NURZHIGIT SMAILOV, ASKHAT BATYRGALIYEV, NURGUL SEILOVA, AINUR KUTTYBAEVA, AIDOS
IBRAYEV |
Abstract: |
The article discusses the characteristics of spatial electromagnetic noise
generators and the formation of a broadband noise signal. It also describes a
number of known methods and methods for assessing the quality of masking noise
interference and their differences. Different approaches to measuring masking
noise when evaluating its quality are proposed. The first method is based on the
measurement of the instantaneous values of the amplitudes of the noise signal
and the calculation of the entropy coefficient based on this method. The
second method involves searching for correlation of masking noise signals of
noise generators in different frequency subbands. The third approach is to use
statistical and (or) graphical methods (tests) for randomness. The completeness
and objectivity of assessing the quality of masking noise interference from
spatial noise generators will be achieved by combining all the methods. |
Keywords: |
noise generators, masking noise, TEMPEST, noise quality rating, electromagnetic
radiation |
Source: |
Journal of Theoretical and Applied Information Technology
15th September 2020 -- Vol. 98. No. 17 -- 2020 |
Full
Text |
|
Title: |
AUTHORSHIP AUTHENTICATION OF POLITICAL ARABIC ARTICLES BASED ON MODIFIED TF-IGF
ALGORITHM |
Author: |
HEBA M . KHALIL, AHMED TAHA, TAREK . EL-SHISTAWY |
Abstract: |
Recently, authorship forensic analysis for political articles has become very
important. It is the process in which a linguist attempts to identify the author
of an anonymous text based on the vocabulary used and the linguistic style of
the writer. The most existing studies of authorship forensic analysis focus on
the English language, while researches concerning the Arabic language is rare.
In this research, we present a new methodology that enhances authorship forensic
analysis focusing on the Arabic language. The basic idea is to extract the
unique vocabulary terms identifying the author (or a political group) and used
for recognition of unknown authors. In the current work, a Term Frequency-
Inverse Group Frequency (TF-IGF) is proposed, which is a modification of the
traditional TF-IDF method. Our approach is tested with large political dataset
and determine the performance of Authorship forensic analysis method based on
vocabulary words.The experimental results show that the average accuracy for
recognizing groups has increased from 89.33 % when using TF-IDF, to 92% with the
proposed TF-IGF. Further improvement is achieved when representing the
vocabulary terms in its Arabic lemma form, rather than its root form. The
results show that the accuracy is improved from 89.33 % to 92%. |
Keywords: |
Authorship Forensic Analysis, TFIDF, Term Weighting, Linguistic Style. |
Source: |
Journal of Theoretical and Applied Information Technology
15th September 2020 -- Vol. 98. No. 17 -- 2020 |
Full
Text |
|
Title: |
THE INFLUENCE OF TRUST, PERCEIVED USEFULNESS, AND PERCEIVED EASE UPON CUSTOMERS’
ATTITUDE AND INTENTION TOWARD THE USE OF MOBILE BANKING IN JAKARTA |
Author: |
MOHAMAD SAPARUDIN , AGUS RAHAYU , RATIH HURRIYATI , MOKH. ADIB SULTAN |
Abstract: |
The rapid development of information technology has encouraged the banking
industry to innovate in serving its customers. One of the most phenomenal
technology service facilities is m-banking. This could be seen from the use of
mobile banking is steeply increasing in recent years since almost every bank
offers mobile banking services. In response to this fact, this study aims at
examining the influence of trust, perceived benefits and perceived ease upon
attitudes and intention of customers to use mobile banking. This study used
technological acceptance model (TAM) with trust. The collection of data was
conducted through a survey-based empirical study of 150 of respondents using
convenience sampling. The result of study shows that attitude highly influences
the intention to use mobile banking and attitude, as mediation, is influenced by
perceived benefits, ease and trust. |
Keywords: |
Trust, Perceived Usefulness, Perceived Ease, Attitude, Intention. |
Source: |
Journal of Theoretical and Applied Information Technology
15th September 2020 -- Vol. 98. No. 17 -- 2020 |
Full
Text |
|
Title: |
VIRTUAL LEARNING ENVIRONMENT AND LEARNING STYLES |
Author: |
HHANI HOSNI, MOHAMED EL-DOSUKY , MOHAMED EISA |
Abstract: |
Virtual Learning Environments are computer based Learning environment that offer
online learning opportunities to learn. The paper overviews VLEs before
proposing a new VLE, that is capable of determining the learning styles of
students (visual, tactile, auditory). This helps the system in recommending
study materials to each student. |
Keywords: |
Virtual learning environment (VLE), Learning styles (LS), Learning management
systems (LMS) |
Source: |
Journal of Theoretical and Applied Information Technology
15th September 2020 -- Vol. 98. No. 17 -- 2020 |
Full
Text |
|
Title: |
THE EFFECT OF COGNITIVE FACTORS IN DETERMINING STUDENT’S SUCCESS IN COMPUTER
PROGRAMMING |
Author: |
MURIMO BETHEL MUTANGA |
Abstract: |
There is a growing reliance on technology as the core driver of the 4th
industrial revolution. This trend not only delineates Information Technology
(IT) as a key topic of global discussion but also makes programming the most
rapidly growing skills required by employers. Also, on the academic front, it
challenges the capability of current curricula to produce competent IT graduates
armed with the right skill-set to meet the surging demand for IT professionals.
Moreover, addressing this challenge goes beyond designing a university
curriculum for fields that offer IT courses with a computer programming
component because unlike other subjects, students often have little to no
experience with computer programming before arriving at the university.
Consequently, teaching and learning computer programming becomes more
challenging than other subjects, and aside from the direct result in poor
students’ academic performance, fewer students also master the skill. Generally,
the debate on improving student’s academic performance has inspired a myriad of
investigations into factors with correlative impact. However, while literature
significantly links student’s academic performance to the impact of cognatic
factors, there is still a need to investigate the impact of cognition on
subjects. Such investigation has the potential to contribute toward enhancing
curriculum development and inform approaches to teaching and learning.
Therefore, in this paper, we investigated the effect of cognitive factors on
students’ performance in introductory programming. Using a case study of
undergraduate students at a South African University of Technology, our findings
show that enhancing cognitive abilities leads to greater performance in
introductory programming. More so, personal motivation was found to be the core
driving force behind developing and enhancing cognitive ability. |
Keywords: |
Cognitive factors, Cognitive performance, Programming, Curriculum, Learning |
Source: |
Journal of Theoretical and Applied Information Technology
15th September 2020 -- Vol. 98. No. 17 -- 2020 |
Full
Text |
|
Title: |
A SYSTEMATIC MAPPING STUDY ON SOFTWARE EFFORT ESTIMATION |
Author: |
AHLAM ALHADDAD , IBRAHIm Al-BALTAH , ABEDALLAH ABUALKISHIK , MAJDI ABDELLATIEF ,
ABDULMONEM ALI AL KHARUSI |
Abstract: |
Context: software effort estimation has been considered as one of the key
drivers in software development success. A comprehensive understanding of
state-of-the-art of software effort estimation techniques is very important.
Objective: the aim of this study is to identify and characterize the existing
software effort estimation techniques and to points insights of this research
field. Method: a systematic mapping study on 136 primary studies was
conducted to answer six research questions. Results: the study revealed that
most of the existing work have used MMRE, MRE, and PRED for measuring the
accuracy of effort estimation, where NASA93 and COCOM81 were the most used
dataset. Furthermore, most of the reviewed studies attempted to use machine
learning methods, whereas other studies proposed hybrid models. With respect to
size metrics, most of the reviewed studies used line of code ( KLOC/ LOC/SLOC).
Conclusion: new research should be carried out and oriented towards studying the
relationship between the various factors that increase or decrease software
effort such as, project type, team member’s expertise, required software
reliability, and software complexity, which can be very useful to enhance effort
estimation techniques. |
Keywords: |
Software Effort Estimation, cost estimation, Systematic mapping study. |
Source: |
Journal of Theoretical and Applied Information Technology
15th September 2020 -- Vol. 98. No. 17 -- 2020 |
Full
Text |
|
Title: |
A COMPARISON STUDY OF DOCUMENT CLUSTERING USING DOC2VEC VERSUS TFIDF COMBINED
WITH LSA FOR SMALL CORPORA |
Author: |
AMALIA AMALIA, OPIM SALIM SITOMPUL, ERNA BUDHIARTI NABABAN, TEDDY MANTORO |
Abstract: |
The selection of a suitable word vector representation is one of the essential
parameters in document clustering because it affects the performance of
clustering. The excellent word vector representation will generate a good
clustering result, even only using the simple clustering algorithm like K-Means.
Doc2Vec, as one of word vector representations, has been extensively studied in
large text datasets and proven outperforms the performance of traditional word
vector representation in document categorization. However, only a few studies
analyze word vector representations of small corpora. As appropriate, learning
observation in a small corpus is also crucial because, in some cases, a large
corpus was not always available, particularly in some low-resources languages
like Bahasa Indonesia. Moreover, the clustering of the small datasets also plays
essential roles in pattern recognition and can be an initial step to implement
the analysis result in a more significant corpus. This study is an experimental
study that aims to explore more in-depth exploration to compare document
clustering using Doc2Vec versus TFIDF-LSA for small corpora in Bahasa Indonesia.
In this study, the quality of word vector representation is measure by the
cluster performance using intrinsic and extrinsic measurements. The study also
considers measuring word representation based on time and memory consumption.
This study also concerns with getting an optimal word vector representation by
tuned appropriate hyper-parameter. The word vector representations were tested
to various sizes of the small corpora using the K-Means algorithm. The result of
this study, a TFIDF-LSA gets a better cluster performance; meanwhile, the
Doc2Vec model gets a better time and memory usage efficiency. |
Keywords: |
Clustering, Word Vector Representation, Word Embedding, Clustering Comparison,
Small Corpora |
Source: |
Journal of Theoretical and Applied Information Technology
15th September 2020 -- Vol. 98. No. 17 -- 2020 |
Full
Text |
|
Title: |
COMPARATIVE ANALYSIS OF DEPTH-FIRST SEARCH ALGORITHM AND GREEDY ALGORITHM AT
NEAREST ATM SEARCH IN PADANG SIDEMPUAN CITY |
Author: |
DIAN RACHMAWATI , SYAHRIL EFENDI , ADI SYAHPUTRA SITUMORANG |
Abstract: |
The Automated Teller Machine (ATM) is needed when users need immediate banking
transactions. But sometimes ATM has some problems such as ATMs are being broken,
money deposited in ATM depleted, the number of people who queued at ATM, etc. At
that time, people needed an alternative ATM located nearby. To make the process
of ATM search easier, than it takes a system that serves to find the nearest ATM
from the ATM location that the user is visiting. Padang Sidempuan City has many
ATMs in various places. This research will make the nearest ATM search system in
Padang Sidempuan city. In this system, there is a menu to search by selecting
the starting point and ATM of the bank that you want to go and will produce the
nearest ATM and the line from the starting point to the ATM. To support the
closest ATM search in this system, the deep first search algorithm and the
greedy algorithm applied to this system. Then, the performance of both
algorithms will be compared based on process time and distance. After
implementation and comparison, it is known that the complexity of the
depth-first search algorithm is the same as the complexity of the algorithm
greedy, (N2). Attesting with a sample of 10 starting points and 1 ATM
destination, the depth-first search algorithm has an average running time of
239.9675 milliseconds, and the average distance is 3033.555 meters, while a
greedy algorithm has an average running time of 274.8501 milliseconds and the
average distance is 2035.2568 meters. So it concludes that the depth-first
search algorithm is more efficient in running time than the greedy algorithm.
But in generating shorter distances, the greedy algorithm is better than the
depth-first search algorithm. |
Keywords: |
Depth First Search, Greedy, ATM, Shortest Path, Algorithm |
Source: |
Journal of Theoretical and Applied Information Technology
15th September 2020 -- Vol. 98. No. 17 -- 2020 |
Full
Text |
|
Title: |
DIMENSIONS OF PROTECTION BEHAVIORS: A SYSTEMATIC LITERATURE REVIEW |
Author: |
IBRAHIM MOHAMMED AL-HARTHY , FIZA ABDUL RAHIM , NOR'ASHIKIN ALI , AMANDO P.
SINGUN JR |
Abstract: |
The term Bring Your Own Device (BYOD) has generated many hopes and fears among
many users in this field related to behaviors of information protection. Threats
of BYOD include illegal access to policy changes and information, disclosure of
confidential details to the public, leakage of organization data and privacy,
access control, abuse, and lost of devices. This study examines the existing
studies on various dimensions in conceptualizing the behaviors of information
protection. Using a systematic method, we analyzed four major databases,
including IEEE, Science Direct, SpringerLink, and Taylor & Francis, from which
57 articles were selected from the year 2010 to 2019. In this study, ten (10)
dimensions are discussed: protection behaviors and its Perceived Severity,
Perceived Vulnerability, Self-Efficacy, Response Efficacy, Response Cost,
Subjective Norm, Attitude, Security Self-Efficacy, Information Security
Awareness and Perceived Behavioral Control. |
Keywords: |
Bring Your Own Device, BYOD, Protection Behaviors, Systematic Literature Review |
Source: |
Journal of Theoretical and Applied Information Technology
15th September 2020 -- Vol. 98. No. 17 -- 2020 |
Full
Text |
|
|
|