Articles
Simulating Shopper Behavior using Fuzzy Logic in Shopping Center Simulation
Jason Christian;
Seng Hansun
Journal of ICT Research and Applications Vol. 10 No. 3 (2016)
Publisher : LPPM ITB
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.5614/itbj.ict.res.appl.2016.10.3.6
To simulate real-world phenomena, a computer tool can be used to run a simulation and provide a detailed report. By using a computer-aided simulation tool, we can retrieve information relevant to the simulated subject in a relatively short time. This study is an extended and complete version of an initial research done by Christian and Hansun and presents a prototype of a multi-agent shopping center simulation tool along with a fuzzy logic algorithm implemented in the system. Shopping centers and all their components are represented in a simulated 3D environment. The simulation tool was created using the Unity3D engine to build the 3D environment and to run the simulation. To model and simulate the behavior of agents inside the simulation, a fuzzy logic algorithm that uses the agents' basic knowledge as input was built to determine the agents' behavior inside the system and to simulate human behaviors as realistically as possible.
Penerapan Algoritma C4.5 untuk Memprediksi Penerimaan Calon Pegawai Baru di PT WISE
Fandy Ferdian Harryanto;
Seng Hansun
JATISI (Jurnal Teknik Informatika dan Sistem Informasi) Vol 3 No 2 (2017): JATISI MARET 2017
Publisher : Lembaga Penelitian dan Pengabdian pada Masyarakat (LPPM) STMIK Global Informatika MDP
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (123.197 KB)
|
DOI: 10.35957/jatisi.v3i2.71
A company in general needs employee that have good ability, good manners and also can company. But there are difficulties in finding the qualities of people as a good employee candicacy. That’s why we need a way or method to identify peoples with the potential to become a new employee candidate. C4.5 algorithm can be used to predict and classify new employee candidate that have the potential to get into a corporation by using decision tree according to the data that we have and predict the new employee candidate qualities. According to the testing method called ten-fold cross validation, the accuracy of the prediction for the new employee candidate is 71% by using the built prediction application which implementing C4.5 algorithm.
RANCANG BANGUN APLIKASI PERAMALAN NILAI SAHAM MENGGUNAKAN ALGORITMA KALMAN FILTER
Erwin Ruslim Sia;
Seng Hansun
Komputa : Jurnal Ilmiah Komputer dan Informatika Vol 3 No 2 (2014): Komputa : Jurnal Ilmiah Komputer dan Informatika
Publisher : Program Studi Teknik Informatika - Universitas Komputer Indonesia (UNIKOM)
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (601.066 KB)
|
DOI: 10.34010/komputa.v3i2.2393
Every prediction have different probability, including prediction in stock market. In order to give the best prediction with the highest probability, we try to determine how Kalman Filter, an algorithm that uses recursive function to predict future value, produce high probability in predicting stock price. There are two set of data companies that are used in this application, namely XL Axiata Tbk. with success percentage at 95,83%, and Astra Agro Lestari Tbk. with success percentage at 95,07%. This application is developed using C# programming language and SQL SERVER.
RANCANG BANGUN APLIKASI REKOMENDASI PEMBELIAN LAPTOP DENGAN METODE FUZZY DATABASE MODEL TAHANI BERBASIS WEB
Hendry Setiawan;
Seng Hansun
Komputa : Jurnal Ilmiah Komputer dan Informatika Vol 3 No 2 (2014): Komputa : Jurnal Ilmiah Komputer dan Informatika
Publisher : Program Studi Teknik Informatika - Universitas Komputer Indonesia (UNIKOM)
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (626.617 KB)
|
DOI: 10.34010/komputa.v3i2.2395
A laptop is a computer that looks compact, small, lightweight and easy to carry anywhere. But choosing a laptop is not an easy thing for consumers who want to have a laptop as per the specifications and budget of the consumer finance. Therefore the purpose of this research is to build a web-based application that can give recommendation to purchasers or consumers as needed. The application is built by using PHP programming language and implementing the Fuzzy Database Tahani model which is still using the standard relation of fuzzy logic, and also using MySQL database for the data storage. It is found that the Fuzzy Database Tahani model can be implemented on the application built on to give a correct recommendation for the consumers.
Prediksi IHSG dengan Backpropagation Neural Network
Andy Santoso;
Seng Hansun
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 3 No 2 (2019): Agustus 2019
Publisher : Ikatan Ahli Informatika Indonesia (IAII)
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (445.667 KB)
|
DOI: 10.29207/resti.v3i2.887
IDX Composite is a combination of all common stock and preferred stock which registered on Bursa Efek Indonesia (BEI). IDX Composite is often used by investor to predict the stock price to get profit. But, to predict the stock price is not easy, hence it yields a high risk to investor. This study offers the usage of backpropagation algorithm to minimize the risk. Backpropagation is a supervised algorithm and will be made in Python programming language, in this case, backpropagation will use and learn the past 5 days data to predict the outcome. Also, this study shows that backpropagation have a high accuracy which reflects in Mean Square Error Testing value of 320.49865083640924 to predict IDX Composite using 0.3 learning rate and 3000 epoch.
SISTEM PENDUKUNG KEPUTUSAN PEMILIHAN PROGRAM STUDI DENGAN METODE SAW DAN AHP
Erikson Marbun;
Seng Hansun
ILKOM Jurnal Ilmiah Vol 11, No 3 (2019)
Publisher : Teknik Informatika Fakultas Ilmu Komputer Univeristas Muslim Indonesia
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33096/ilkom.v11i3.432.175-183
Admission to Multimedia Nusantara University (UMN) is divided into academic paths, scholarships and regular tests. The benchmarks used to accept prospective students through the academic track still see five academic grades with a minimum value of 70. There are cases where the minimum grade decreases depending on the KKM (Minimum Completeness Criteria) from the school of the prospective student. The process of changing majors at UMN can be done by going to the Student Support division and undergoing a series of tests depending on the chosen study program. The Student Support Faculty of Engineering and Informatics (FTI) does not have enough data to carry out specific tests. Based on these two problems, a decision support system ‘FTI Recommendation’ was built using the AHP and SAW methods. AHP method is the basis for evaluating prospective students, while the SAW method is for alternative ranking. and the expert reference value as a substitute for the old benchmark, which is 70 or in accordance with KKM from the prospective student's school. The decision support system built produces a satisfaction level of 77.22%.
Scratch Pemrograman Visual untuk Semuanya
Seng Hansun
ULTIMA InfoSys Vol 5 No 1 (2014): UltimaInfoSys :Jurnal Ilmu Sistem Informasi
Publisher : Universitas Multimedia Nusantara
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1268.985 KB)
|
DOI: 10.31937/si.v5i1.218
In this modern era, the need to have a more tinkerable, more meaningful, and more social programming language has arisen. One of the programming environments that catch up with this issue is Scratch. In this paper, the author tries to explain Scratch as a visual programming language, its’ basic concepts, and its’ implementations. As an example, one interactive game that has been built using Scratch is shown at the end of this paper. Index terms - game, Scratch, visual programming.
Spam Filter Situs Jejaring Sosial Mahasiswa Menggunakan Regular Expression
Simon Salomon;
Seng Hansun
ULTIMA InfoSys Vol 8 No 2 (2017): Ultima InfoSys : Jurnal Ilmu Sistem Informasi
Publisher : Universitas Multimedia Nusantara
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1354.036 KB)
|
DOI: 10.31937/si.v8i2.615
Spam is an unexpected and unsolicited email sent randomly indiscriminately, directly or indirectly by the sender who has no connection whatsoever with the recipient. The purpose of spam itself is to send information to the recipient, where the content of the sent message generally contains ads that offer nonessential products or illegal products, scams, promotional purposes, or spreading malware designed to hijack computers receiver. Based on the background of the problem, it is necessary anti-spam on a chat or dissemination of information in social networking using regular expression. From this study, the behavioral intention to use at level of 80% means that the user agrees that this website increases user interest in obtaining information and communication, and generates an immersion level of 80% which means the user is very focused when using the website. This website generates value by 98% precision and 98% recall that produce harmonic mean value of 97% so that it can be concluded that it has the precision and recall value harmonious. Index Terms—social networking, regular expression, spam, website
Rancang Bangun Aplikasi UMN Library Catalog Menggunakan Metode Rocchio Relevance Feedback
Marcel Bonar Kristanda;
Seng Hansun;
Albert Albert
ULTIMA InfoSys Vol 9 No 1 (2018): Ultima InfoSys : Jurnal Ilmu Sistem Informasi
Publisher : Universitas Multimedia Nusantara
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (2580.147 KB)
|
DOI: 10.31937/si.v9i1.684
Library catalog is a documentation or list of all library collections. Unfortunately, there is a problem identified in the process of searching a book inside library catalog in Universitas Multimedia Nusantara’s library information system regarding the relevant result based on user query input. This research aims to design and build a library catalog application on Android platform in order to increase the relvancy of searching result in a database using calculated Rocchio Relevance Feedback method along with user experience measurement. User experience analysis result presented a good respond with 91.18% score based by all factor and relevance value present 71.43% precision, 100% recall, and 83.33% F-Measure. Differences of relevant results between the Senayan Library Information system (SLiMS) and the new Android application ranged at 36.11%. Therefore, this Android application proved to give relevant result based on relevance rank. Index Terms—Rocchio, Relevance, Feedback, Pencarian, Buku, Aplikasi, Android, Perpustakaan.
Penerapan Algoritma ACO untuk Penjadwalan Kuliah Pengganti pada Perguruan Tinggi (Studi Kasus: Program Studi Informatika, Universitas Multimedia Nusantara)
Indah Noviasari;
Andre Rusli;
Seng Hansun
ULTIMA InfoSys Vol 9 No 2 (2018): Ultima InfoSys : Jurnal Ilmu Sistem Informasi
Publisher : Universitas Multimedia Nusantara
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1688.724 KB)
|
DOI: 10.31937/si.v9i2.1062
Students and scheduling are both essential parts in a higher educational institution. However, after schedules are arranged and students has agreed to them, there are some occasions that can occur beyond the control of the university or lecturer which require the courses to be cancelled and arranged for replacement course schedules. At Universitas Multimedia Nusantara, an agreement between lecturers and students manually every time to establish a replacement course. The agreement consists of a replacement date and time that will be registered to the division of BAAK UMN which then enter the new schedule to the system. In this study, Ant Colony Optimization algorithm is implemented for scheduling replacement courses to make it easier and less time consuming. The Ant Colony Optimization (ACO) algorithm is chosen because it is proven to be effective when implemented to many scheduling problems. Result shows that ACO could enhance the scheduling system in Universitas Multimedia Nusantara, which specifically tested on the Department of Informatics replacement course scheduling system. Furthermore, the newly built system has also been tested by several lecturers of Informatics UMN with a good level of perceived usefulness and perceived ease of use. Keywords—scheduling system, replacement course, Universitas Multimedia Nusantara, Ant Colony Optimization