https://talenta.usu.ac.id/index.php/JoCAI/issue/feed Data Science: Journal of Computing and Applied Informatics 2018-11-05T23:27:11+07:00 Dr. Erna Budhiarti Nababan, M.I.T. jocai@journal.usu.ac.id Open Journal Systems <p style="text-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.</span></span></p> <p style="text-align: justify;">ISSN (Print) &nbsp;&nbsp;&nbsp; : 2580-6769<br>ISSN (Online)&nbsp;&nbsp;&nbsp;&nbsp; : 2580-829X</p> https://talenta.usu.ac.id/index.php/JoCAI/article/view/324 Enhancing Performance of Parallel Self-Organizing Map on Large Dataset with Dynamic Parallel and Hyper-Q 2018-11-05T23:25:22+07:00 Alexander F.K. Sibero alexander@gmail.com Opim Salim Sitompul opim@usu.ac.id Mahyuddin K.M. Nasution mahyuddin@usu.ac.id <p>Self-Organizing Map (SOM) is an unsupervised artificial neural network algorithm. Even though this algorithm is known to be an appealing clustering method,<br>many efforts to improve its performance are still pursued in various research works. In order to gain faster computation time, for instance, running SOM in parallel had been focused in many previous research works. Utilization of the Graphics Processing Unit (GPU) as a parallel calculation engine is also continuously improved. However, total computation time in parallel SOM is still not optimal on processing large dataset. In this research, we propose a combination of Dynamic Parallel and Hyper-Q to further improve the performance of parallel SOM in terms of faster computing time. Dynamic Parallel and Hyper-Q are utilized on the process of calculating distance and searching best-matching unit (BMU), while updating weight and its neighbors are performed using Hyper-Q only. Result of this study indicates an increase in SOM parallel performance up to two times faster compared to those without using Dynamic Parallel and Hyper-Q.</p> 2018-08-03T01:02:51+07:00 ##submission.copyrightStatement## https://talenta.usu.ac.id/index.php/JoCAI/article/view/325 A Two Microphone-Based Approach for Detecting and Identifying Speech Sounds in Hearing Support System 2018-09-07T11:30:33+07:00 Andre Sitompul andre.sitompul.15@shizuoka.ac.jp Masafumi Nishimura masafumi@shizuoka.ac.jp <p>For people with hearing disabilities, not only would give them difficulties in going through their everyday lives but also sometimes could be life threatening. In this research we proposed a simple, yet robust approach for helping the hearing-impaired people in identifying the important sounds around them by using two microphones as input channel that could be worn around the person’s head as a substitute for their ears. This device then could be used to record the situation of the surroundings, and then the system would estimate the Direction of Arrival (DOA) of the sound sources, then detect and classify them using Support Vector Machine (SVM) into target speech or noise category. As the results, system’s classifier could produce FAR and FRR as low as 2%, in which 274 out of 280 samples were successfully classified as target speeches and 22 from the total of 27 noise samples were successfully classified as noise</p> 2018-08-03T01:18:07+07:00 ##submission.copyrightStatement## https://talenta.usu.ac.id/index.php/JoCAI/article/view/326 Genetic Algorithms Dynamic Population Size with Cloning in Solving Traveling Salesman Problem 2018-11-05T23:27:11+07:00 Erna Budhiarti Nababan ernabrn@usu.ac.id Opim Salim Sitompul opim@usu.ac.id Yuni Cancer yuni@gmail.com <p>Population size of classical genetic algorithm is determined constantly. Its size remains constant over the run. For more complex problems, larger population sizes need to be avoided from early convergence to produce local optimum. Objective of this research is to evaluate population resizing i.e. dynamic population sizing for Genetic Algorithm (GA) using cloning strategy. We compare performance of proposed method and traditional GA employed to Travelling Salesman Problem (TSP) of A280.tsp taken from TSPLIB. Result shown that GA with dynamic population size exceed computational time of traditional GA.</p> 2018-08-03T01:34:01+07:00 ##submission.copyrightStatement## https://talenta.usu.ac.id/index.php/JoCAI/article/view/327 Study of Scheduling in Programming Languages of Multi-Core Processor 2018-09-09T11:13:10+07:00 Mina Hosseini-Rad hosseinirad.edu@gmail.com Majid Abdolrazzagh-Nezhad abdolrazzagh@buqaen.ac.ir Seyyed-Mohammad Javadi-Moghaddam smjavadim@buqaen.ac.ir <p>Over the recent decades, the nature of multi-core processors caused changing the serial programming model to parallel mode. There are several programming languages for the parallel multi-core processors and processors with different architectures that these languages have faced programmers to challenges to achieve higher performance. In addition, different scheduling methods in the programming languages for the multi-core processors have the significant impact on the efficiency of the programming languages. Therefore, this article addresses the investigation of the conventional scheduling techniques in the programming languages of multi-core processors which allows the researcher to choose more suitable programing languages by comparing efficiency than application. Several languages such as Cilk++، OpenMP، TBB and PThread were studied, and their scheduling efficiency has been investigated by running Quick-Sort and Merge-Sort algorithms as well.</p> 2018-08-03T01:46:24+07:00 ##submission.copyrightStatement## https://talenta.usu.ac.id/index.php/JoCAI/article/view/328 User Centered Design Approach to Redesign Graduate Student Management Information System 2018-08-03T02:04:28+07:00 Fanindia Purnamasari fanindia.purnama@gmail.com Noraidah Sahari Ashaari noraidah@gmail.com <p>This study conducted a user centered design approach based on user perception using the Graduate Student Information System. This study start by requirement gathering employs interview method with discussing about its interface design and its available menu. Then following as design, evaluation and delivery to actual user. The proposed design is evaluated by 30 respondent using questionnaire The findings from the analyzed result show that usability factor encountered by user that has high average mean was interface standard. The study prove that the current system needs to improve from functionality aspect. The proposed system is expected to help the administration task.</p> 2018-08-03T01:54:03+07:00 ##submission.copyrightStatement##