Article Per Year (5 Year)
p-Index From 2020 - 2025
0
P-Index
This Author published in this journals
All Journal Jurnal Infra
Kartika Gunadi
Program Studi Teknik Informatika
Computer Science & IT

Published : 24 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 24 Documents
Search

 1   2   3 
Penggunaan Convolutional Recurrent Neural Network dan RLSA untuk Mengambil Data pada Akta Kelahiran Stephanie Liem; Kartika Gunadi; Alvin Nathaniel Tjondrowiguno
Jurnal Infra Vol 7, No 1 (2019)
Publisher : Jurnal Infra

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (717.503 KB)

Abstract

Birth certificate is one of the documents that is mandatory for every citizen to have. This document records the information upon someone’s birth and an official acknowledgement of a country on that person’s existence. Birth certificate is a legal document and is an acceptable form of identification for other documents such as a diploma. As one of Indonesia’s learning institute, Petra Christian University needs its students birth certificate as a solid proof upon their identification and as a base to publish a diploma. The extraction of information is being done manually but with the rapid development of technology, it is now possible to obtain the information within a birth certificate automatically. Research about information extraction on Birth Certificate hasn’t been done yet before, but similar research with the object of Identity Card has been done using Template Matching with the accuracy of 17-39%. This research uses Run Length Smoothing Algorithm and Convolutional Recurrent Neural Network as its primary methods. Run Length Smoothing Algorithm is used to segment words in a birth certificate image. The word in an image will then be translated into a text in string form by Convolutional Recurrent Neural Network. To know which words that contain the wanted information, the sequence of the words and specific keywords are being used. The result of this research will be information upon the full name, birth date, place of birth and the gender of the birth certificate holder. The result from tests that were done is an accuracy of 12.936% upon finding the wanted information and 60.086% for words translation from image to string by CRNN.
Perancangan Sistem Informasi Penjualan Perusahaan Velg PT Cahaya Citra Alumindo Kevin Kevin; Kartika Gunadi; Silvia Rostianingsih
Jurnal Infra Vol 6, No 1 (2018)
Publisher : Jurnal Infra

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (805.135 KB)

Abstract

PT Cahaya Citra Alumindo is a company engaged in rim production and located in Sidoarjo. The company is still doing the process of data management using manual methods and recording using Microsoft Excel so there are still weaknesses such as miscalculation of material needs and reports, data management process that takes a long time, as well as difficulty in searching the data.This application is created using HTML, CSS, framework PHP programming language and MySQL database. Application interface is created using Bootstrap template. Application has features including stock menu, order menu, planning menu, master database menu, and report menu.The final results of the implementation of this application are helping to calculate the income statement and display the report up to several periods ago, record all inventory of goods and materials as well as update the price of materials, manage orders received and monitor the development of ordered stock, and record production planning as well as calculating the necessary materials for each production process.
Perancangan dan Pembuatan Aplikasi Pembelajaran Vocabulary dan Grammar untuk Anak SMP Berbasis Web Bill Roger Abel; Silvia Rostianingsih; Kartika Gunadi
Jurnal Infra Vol 4, No 1 (2016)
Publisher : Jurnal Infra

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (444.474 KB)

Abstract

Vocabulary and grammar learning at junior highschool are the most important fundamental to improve student’s ability to understand English. Mastering vocabulary and grammar can make the students better and more fluent in speaking English. With the use of learning media, vocabulary and grammar learning for students will be more interesting and student’s results of learning will be increased.This learning website features various type of practices like drag and drop, swap words in sentence, match words and pictures and sound. Using the 2006 curriculum based course and with the source of 7th grade Junior Highschool teacher, this learning website is adjusted to the needs of 7th grade Junior Highschool students. Making of this website is using the PHP, HTML5 language and using the Facebook API to make the students easier to share their test results.Berdasarkan kuesioner yang di bagikan, desain tampilan serta bentuk latihan soal aplikasi ini dinilai sangat menarik, tetapi materi yang diberikan belum dipahami secara baik oleh siswa.The results obtained from the application that has been made are the design and features of this application can run well on several browser. Grammar and vocabulary practices feature on this application are easy to access and understand by the user. Based on questionnaires, the design and practices of this application is considered very interesting, but the provided courses has not been well understood by the students.
Digitalisasi Lecturing Note Listya Purnomo; Liliana -; Kartika Gunadi
Jurnal Infra Vol 3, No 1 (2015)
Publisher : Jurnal Infra

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (744.131 KB)

Abstract

The development of technology can make human being to do a lot of things more simple. Teaching method currently has many variations so that the learning process is more alive. Learning by explaining the process which can be seen is very beneficial. Sometimes in a process, hand gestures play an important role in understanding the whole process. The use of webcam can be another alternative to digitize what is written by users. This thesis aims to digitize lecturing notes on paper using a device webcam.The system includes processes like image retrieval, paper detection, projection mapping, skin detection and removal, and processing results with threshold method. Paper edge detection process uses the method of canny edge detection. In paper edge detection, webcam image becomes image with white color for area of paper. Projection mapping process is used to map the image with trapezoid shape of paper into image with rectangular shape of paper. Skin detection process uses HSV and YCbCr color space. In skin detection process, hand which still appears in image becomes image without hand. The application was created using the C# programming language with Visual C# 2010 as its IDE.The experiment results indicate that the color, ink thickness, threshold value, height of the webcam, size and distance between scratches, and lighting level will affect the final outcome of the application. In addition, the hand’s position during the writing may cause a shadow on the paper. The best result of all methods which have been tried is the result of the threshold method.
Pengenalan Karakter pada Plat Nomor Indonesia dengan Tilt Correction dan Metode Faster R-CNN Kevin Nyoto Susanto; Kartika Gunadi; Endang Setyati
Jurnal Infra Vol 7, No 1 (2019)
Publisher : Jurnal Infra

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (892.229 KB)

Abstract

The growth of the number of vehicles in Indonesia is very rapid and has caused many problems, such as the problem of parking security systems and access control of vehicles. With the development of technology, vehicles’ license plates can be detected automatically by a system with the help of Digital Image Processing and Artificial Neural Network.This study uses the Canny Edge Detection method to detect license plate objects in the image. Before classifying characters on license plates, the perspective distortion in the image can be removed using the Planar Homography method. Faster R-CNN is used to detect the position of the car in the image and classify the characters on the license plateThe results of this research program will detect the character of license plates and the color of car in the image. From the test results using the researcher’s dataset, the accuracy of detection of the characters in the license plate reached 82.14% and the accuracy of detection of the cars’ colors reached 78.54%.
Aplikasi Deteksi Orang Jatuh dengan Memanfaatkan Kinect Jonathan Tjitrokusmo; Liliana Liliana; Kartika Gunadi
Jurnal Infra Vol 5, No 1 (2017)
Publisher : Jurnal Infra

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (74.607 KB)

Abstract

This paper describes method for fall detection, because fall is a serious problem and often resulting to injury, which can endanger the safety of the person. Therefore, falling detection is crucially needed. The device that being used is Kinect, which also could be used to detect people. The detection is using the help of Microsoft Kinect SDK. Kinect can detect a person in front of it and processing it to create a skeleton of the person. The method which being used is to get a set of data on the position of the person. Next, the rate of change in position would be calculated with the available formulae. The data obtained would be selected, in order to distinguish the activities undertaken. When fall is detected, the application can provide the alert.
Pembuatan Game Cerita Rakyat Dengan Bentuk Adventure Game Harvey Tjahjono; Liliana Liliana; Kartika Gunadi
Jurnal Infra Vol 3, No 2 (2015)
Publisher : Jurnal Infra

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (677.408 KB)

Abstract

These days traditional thing has been left behind not only by adults but also by children. One of them is folklore. It disappears because its package cannot interest the people. It needs a better package that interests a lot of people, for example game. The game in this thesis took folklore theme that would teach the children about morale values. This game was made based on PC game because electronic device are increasingly in demand and with adventure game-based which is a game genre that a lot of people like including the children.This game was made by Unity3D which is can place the objects that we use easier. Besides, camera setting which is a feature of Unity3D can make the setting of the 2D graphics easier. First of all, the folklores need to be parted into the playable-part and the non-playable-part. In playable-part, the player needs to solve some tasks to play the next folklore. In non-playable-part, the game will show an animation.This folklore game can interests the children to become a better person from the morale value. But, it is hard to implement folklore into adventure game for some folklores. For example Origin of Mahakam River’s Creek that has some complicated detail to express the setting of the story.
Identifikasi Buah-buahan Menggunakan Metode Convolutional Neural Network Verrell Gunawan; Kartika Gunadi; Endang Setyati
Jurnal Infra Vol 7, No 1 (2019)
Publisher : Jurnal Infra

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (571.039 KB)

Abstract

Buah-buahan memiliki jenis yang cukup banyak sehinggaterkadang sulit untuk dibedakan oleh manusia. Denganperkembangan teknologi yang pesat terutama dalam bidangartificial neural network, maka dikembangkanlah sebuah programuntuk melakukan identifikasi buah-buahan dari gambar denganbantuan Tensorflow dalam membuat sebuah model artificialneural network.Metode yang digunakan adalah convolutional neural networkuntuk melakukan training pada model. Terdapat 4 proses utamadalam convolutional neural network yaitu convolution layer,activation layer, pooling layer, dan fully connected layer. Dalampembuatan model convolutional neural network dapat dilakukantuning dalam berbagai macam hal, beberapa diantaranya yaitujumlah epoch, activation function yang digunakan, dan jugaukuran learning rate.Penelitian ini menunjukkan bahwa jumlah epoch mempengaruhiakurasi pada model yang dibuat. Dalam hal activation function,ditunjukkan bahwa rectified linear unit (RELU) lebih baik dalamhal waktu yang dibutuhkan dalam membuat neural network modelyang paling optimal dibandingkan dengan exponential linear unit(ELU). Besar kecilnya learning rate juga mempengaruhi seberapabaik model yang dihasilkan. Dari berbagai pengujian yangdilakukan didapatkan akurasi terbaik yang dapat dicapai sebesar99,31%.
Pembuatan Game "Werewolf" pada Mobile Device dengan Near Me menggunakan GPS Albert Albert; Kartika Gunadi
Jurnal Infra Vol 6, No 1 (2018)
Publisher : Jurnal Infra

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (489.099 KB)

Abstract

One of the more famous games lately is the Werewolf game. This game requires 15-20 players once a game. In fact, it is very difficult to gather 15-20 players in one place and at the same time. In addition, from existing werewolf game apps, to play with friends around very hard. Therefore, made this Werewolf game with Near Me feature using GPS. Features Near Me itself is a feature that displays a list of game rooms that players are near the user. So the players do not need to spend time looking for the name / game room number to play with. To get the distance from Near Me this is used GPS from each player and will be measured how far distance of player in game room with user use formula to measure distance with latitude and longitude.The steps of making this thesis first is to prepare the game database using MySQL. Then create a game interface using Android Studio, create game server using Firebase. After that, connect the database and game server to Android Studio. Create support features of the game, and do an overall check on the game.The final result of this application is a Werewolf game with features Near Me. After going through several testing phases, this app can be played up to a maximum of 18 players in 1 game room and can have 10 game rooms. Based on the questionnaire results, the Near Me feature was found to facilitate the users in terms of finding the game room when the users were playing together.
Pembuatan Sistem Informasi Administrasi Manajemen Produksi Berbasis Website Pada PT. Semen Indogreen Sentosa Michelle Magdalena; Yulia Yulia; Kartika Gunadi
Jurnal Infra Vol 5, No 2 (2017)
Publisher : Jurnal Infra

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (890.165 KB)

Abstract

PT. Semen Indogreen Sentosa is a company that supply ready-mix concrete. They still record manually using Microsot Excel and physical documents for all business procedures. Sales Order  is crucial because in the first step of ordering plant division need to know the time availability. This step is causing a problem when the client must wait for the confirmation that takes a long time. Furthermore, because of the unavailability of information system, data processing is ineffective. Thus that’s why establishing information system for production management is needed.This website is created using HTML, PHP, JavaScript programming, language, and MySQL database. Application interface is created using Gentellela with Bootstrap template. Google Map is used to help measuring delivery time. The final result of the development of this website is able to integrate company information such as sales order records, purchase orders, materials stock and reports. This website also can help the compay to calculate the cost of goods. Delivery time can be measured faster and more accurate. Scheduling for production is easier and users from batching plant can see everyday orders directly.            
Co-Authors Agustinus Noertjahyana Albert Albert Alvin Nathaniel Tjondrowiguno Andrew Samuel Anita Nathania Purbowo Bambang Kurniawan Santoso Bill Roger Abel Christopher Albert Lorentius Djoni Haryadi Setiabudi Endang Setyati Erick Leonardo Gregorius Satia Budhi Harvey Tjahjono Haryanto Haryanto Jonathan Tjitrokusmo Justinus Andjarwirawan Kenny Kenny Kevin Adiputra Shianto Kevin Kevin Kevin Nyoto Susanto Kevin Pangestu Kristo Radion Purba Leo Willyanto Santoso Liliana - Liliana Liliana Listya Purnomo Michael Horax Michelle Magdalena Renardi Dewanto Cahyadi Rolly Intan Ronald Kurniawan Tjondrowiguno Silvia Rostianingsih Stephanie Liem Steven Febrian Harijanto Steven Pierretio Verrell Gunawan Yulia Yulia Yuril Adrian Manoppo