Data Science: Journal of Computing and Applied Informatics 2019-08-03T01:11:12+07:00 Erna Budhiarti Nababan Open Journal Systems <p align="justify"><span class="" lang="en"><span class="">Data Science: Journal of Computing and Applied Informatics (JoCAI) is a peer-reviewed biannual journal (January and July) published by TALENTA Publisher and organized by Faculty of Computer Science and Information Technology, Universitas Sumatera Utara (USU) as an open access journal. It welcomes full research articles in the field of Computing and Applied Informatics related to Data Science from the following subject area: Analytics, Artificial Intelligence, Bioinformatics, Big Data, Computational Linguistics, Cryptography, Data Mining, Data Warehouse, E-Commerce, E-Government, E-Health, Internet of Things, Information Theory, Information Security, Machine Learning, Multimedia &amp; Image Processing, Software Engineering, Socio Informatics, and Wireless &amp; Mobile Computing. <br></span></span><span class="" lang="en"><span class="">Each publication contains 5 (five) research articles which will be published online. These articles are indexed by&nbsp;<a href="">Indonesian Publication Index (Garuda Portal)</a>, <a href=";repository_id=6638">One Search Perpustakaan Nasional</a>,&nbsp;<a href=";hl=id">Google Scholar</a>, <a href="">PKP Indexing</a>, <a href=";refid=dclink">BASE (Bielefeld Academic Search Engine)</a>,&nbsp;<a href="">CiteFactor (Academic Scientific Journal)</a>, <a href="">Scientific Indexing Services (SIS)</a> and <a href="">Directory of Research Journal Indexing (DRJI)</a>.&nbsp;</span></span><span class="" lang="en"><span class=""><span id="result_box" class="" lang="en">JoCAI strives to be a means of periodic, accredited, national scientific publications or reputable international publications through printed and online publications.<br></span></span></span><span class="" lang="en"><span class="">ISSN (Print) &nbsp;&nbsp;&nbsp; : 2580-6769<br></span></span><span class="" lang="en"><span class="">ISSN (Online)&nbsp;&nbsp;&nbsp;&nbsp; : 2580-829X</span></span><br>This work is licensed under a <a href="" rel="license">Creative Commons Attribution-NoDerivatives 4.0 International License</a>.</p> Samawa Part of Speech Tagging using Brill Tagger 2019-08-03T00:55:47+07:00 Trienani Hariyanti Saori Aida Hiroyuki Kameda <p>There exist 7,097 living languages in the world cited by Ethnologue. Most of them, however, do not exist on the Internet as the objects of research. It indicates the gap in language resources. One of them is Samawa language which has over 500,000 native speakers and is identified as endangered language by UNESCO. What we known about Samawa so far is a lack of information, tools, and resources to maintain its sustainability. This paper aims to contribute to NLP, a growing field of research, by exploring Samawa part of speech tagging problem using rule-based approach, i.e. Brill tagger. It has been trained on very limited data of Samawa corpus, which is 24,627 tokens including punctuation marks with 24 tags of our original tagset. K-fold cross-validation (k = 5 and k = 10) was applied to compare Brill’s performance with Unigram, HMM, and TnT. Brill tagger with the combination of default tagger, Unigram, Bigram and Trigram as baseline tagger achieve higher accuracy over 95% than others. It suggests that the Brill tagger can be used to extend Samawa corpus automatically.</p> 2019-07-31T00:00:00+07:00 Copyright (c) 2019 Trienani Hariyanti, Saori Aida, Hiroyuki Kameda Message /Data Security Using Multi-bit LSB and Modified Vernam Cipher 2019-08-03T00:58:13+07:00 Goklas Tomu Simbolon Opim Salim Sitompul Erna Budhiarti Nababan <p>Information security is one of the most important aspects in today's information technology advancement era. There are many methods that can be used to secure important information from those who commit crimes. LSB is a steganographic algorithm that is often used to store data in the last bit. Vernam is one of the most popular methods used to encrypt messages easily and quickly. But some possibilities can make LSB and Vernam less safe to use in the long run. The combination of steganography with cryptography enables storage to be better. Vernam's algorithm can be modified so that its power is better. Modifications are made to the bits of each character, the rotation by a certain amount can randomize the plaintext content before Vernam encryption is performed. Modifications to the LSB can be performed on some multi-bit models. Bit on LSB can be inserted data as much as 1, 2, 3 or 4-bit information. Image results will be tested which one is better and has the highest perfection among the multi-bits.</p> 2019-07-29T00:00:00+07:00 Copyright (c) 2019 Goklas Tomu Simbolon Usability Engineering and Evaluation of Usability In District Tourism And Culture Information Systems 2019-08-03T01:02:22+07:00 Wasis Haryono <p>So far, the potential of natural resources has not been fully managed by the government or the community. For that we need a mature tourist object planning either by visitors or by developers. Communities need information provided on a mobile basis that can be accessed anywhere. This information is inseparable from the role of technology that supports so that applications can be used by tourists who want to visit either in the form of an address or location. Applications that are worthy of use are applications that have been tested usefulness or called usability. To test a system requires a questionnaire which one of them is SUMI (Software Usability Measurement Inventory). This study uses a method adopted from usability engineering lifecycle. The results of this study in the form of assessment with several criteria, so the application is feasible to use.</p> 2019-07-29T00:00:00+07:00 Copyright (c) 2019 Wasis Haryono Randomness of Poisson Distributed Random Number in the Queue System 2019-08-03T01:06:52+07:00 Ernestasia Esther Nababan Asima Manurung <p>In the queuing system, inter arrival variable and service time variable are probabilistic and its pattern follow a Poisson distribution. Simulations experiment for performance measurement of a queuing system required random data. In practice, random data is built using an application program. Pseudorandom data generated from application programs often have different patterns of randomness, although in each experiment simulated the same data distribution. Level of randomness may cause the results of simulation experiments experienced statistically significant deviations, especially on problems with stochastic variables. Statistical deviation can cause errors in interpreting the results of simulation experiments, especially in the assessment of the performance of the queuing system. It is required to evaluate whether the level of randomness of pseudorandom data effect on simulation results of performance measurement of a system. Simulation experiments on a simple queuing system (M / M / 1) was carried out by using a pseudorandom number generator. Application program used to generate pseudorandom numbers is Fortran90. The experimental results show that the greater the amount of pseudorandom data, the greater the statistical deviations occur, and the smaller the degree of randomness of data. This affects the results of the simulation system in which there is a probabilistic variable that require random data to conduct simulation</p> 2019-07-31T00:00:00+07:00 Copyright (c) 2019 Esther Nababan, Ernestasia, Asima Manurung Evaluation of a Proposed Road in a Campus Network based on Ideal Flow 2019-08-03T01:11:12+07:00 Kardi Teknomo <p>A proposed road project inside a campus that will have to down trees from its mini forest have attracted different public opinion among the faculty and students. In this paper, we would like to justify our view objectively based on transportation engineering point of view. The Ideal Flow Network (IFN) method was used to do the analysis because its source code is publicly available for clarification. The network data is based on previous study of Ateneo Traffic Group report. Two scenarios were set: based scenario that represents the current road network, and two proposed scenario that represents the current road network with additional proposed road in two ways and one way respectively. Analysis of the results show that the total network travel time of the proposed scenario are increased by 4.69% and 2.32% respectively for two ways and one-way scenarios. The network speed will be slightly improved by 0.03% in when the proposed road project is added in two ways. Thus, we failed to justify that the proposed network has better network performance.</p> 2019-07-31T00:00:00+07:00 Copyright (c) 2019 Kardi Teknomo