Articles
38 Documents
Search results for
, issue
"Vol 8, No 2 (2020)"
:
38 Documents
clear
<![CDATA[Penerapan Finiste State Machine dan Atreus AI Behavior pada AI Musuh dalam Fighting Game ]]>
<![CDATA[Jong Jeffrey Wicaksono]]>;
<![CDATA[Djoni Haryadi Setiabudi]]>;
<![CDATA[Hans Juwiantho]]>
<![CDATA[ Jurnal Infra Vol 8, No 2 (2020) ]]>
Publisher : <![CDATA[Jurnal Infra ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
<![CDATA[Artificial Intelligence (AI) has already become an important part in game development. AI in game have a diverse job to give a direct experience to player. The lack of strategy in enemy AI inside fighting game can make players less motivated when playing. To solve this problem, AI is made which has variety of cooperate strategy that can make attract player’s motivationGame is developed using Unity3D Engine and using C# programming language. Finite State Machine method is used to develop AI which become player enemy and Atreus AI Behavior is given in order to have variety of strategies. Probability also added in AI decision making in order to make the AI less predictable.The results show that AI can run well using FSM and Atreus Behavior merging. Testing is also carried out on 15 players which have a background as a casual player or above. These 15 players are in charge to try the game. The results show that AI is more difficult to beaten and player is motivated to defeat the AI.]]>
<![CDATA[Aplikasi Scoring System Untuk Penentuan Keputusan Kredit Pada BPR DRJ Berbasis Web ]]>
<![CDATA[David Alfredo Wiejoyo]]>;
<![CDATA[Silvia Rostianingsih]]>;
<![CDATA[Lily Puspa Dewi]]>
<![CDATA[ Jurnal Infra Vol 8, No 2 (2020) ]]>
Publisher : <![CDATA[Jurnal Infra ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
<![CDATA[In the banking world, specifically rural bank, lending a credit facility is a crucial business step. To be given a credit facility, the customer first have to pass through several assessment to determine the eligibility wether the customer met to be given a credit facility. Sales or the customer themselves can collect the requirement and sent them to the rural bank to complete the requirement of a credit facility. The assessment will be held by human and tend to have error-prone. Another obstacle is the distance, the customer have to come to the rural bank themselves or even send the requirement which takes time to send the requirement. These obstacles given the writer an idea to create the application. This application created based on web with HTML and PHP language alongside with Javascript features with MySQL database. This application can run the process needed from the beginning of collecting requirement until the score of the assessment is out. The application can aslo store the uploaded documents to the application database.The result of this thesis is the application can run the process of credit scoring until the score is out. The application can also print the required legal documents created by the application. The application can run responsively at different platform. The thesis also meet the problem statement.]]>
<![CDATA[Aplikasi Notifikasi Telegram Untuk Mengetahui Trend Forex Trading Dengan Menggunakan Pola Japanese Candlestick ]]>
<![CDATA[Ricky Kuncoro]]>;
<![CDATA[Agustinus Noertjahyana]]>;
<![CDATA[Justinus Andjarwirawan]]>
<![CDATA[ Jurnal Infra Vol 8, No 2 (2020) ]]>
Publisher : <![CDATA[Jurnal Infra ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
<![CDATA[Forex Trading is a business that promises high profit and freedom such as not needing big capital and a physical office. However, the reality is that not every trader can take a satisfying profit because of not realizing changes of trend direction in a market. Because of that, there needs to be an application that is capable of telling when there will be a change of trend direction on the market in real-time so that a trader can maximize the potential to take advantage of a large amount of profit.Expert Advisor is used as a reading of a change of trend direction automatically and inside it has a method to read the direction of market trend, which is called Japanese Candlestick. There are many types of Japanese Candlestick Pattern that already exist however in this research there will be 4 patterns that will be used, which are Hammer Pattern, Doji, Engulfing, and Custom. Then, Telegram will be used as chatbot to notify users of a change in trend direction.Testing result has proved in EUR/USD currencies in time frame H4 that the application that was made was capable of reading reversal trend of average 44,76% and continuation trend of average 67,60% in three years. To deliver the notification on Telegram, Expert Advisor will generate the reading of trend direction using Japanese Candlestick in file form for the chatbot in Telegram which will use Python programming language to get the file. Then the chatbot will read and send the file of the reading result in notification form to Telegram users.]]>
<![CDATA[Implementasi Algoritma YOLO pada Aplikasi Pendeteksi Senjata Tajam di Android. ]]>
<![CDATA[Christopher Nathanael Liunanda]]>;
<![CDATA[Silvia Rostianingsih]]>;
<![CDATA[Anita Nathania Purbowo]]>
<![CDATA[ Jurnal Infra Vol 8, No 2 (2020) ]]>
Publisher : <![CDATA[Jurnal Infra ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
<![CDATA[Advances in computing power have exceeded traditional smartphone needs. Object detection requires high computational power. Tensorflow Lite can be used to run models quickly and easily to mobile devices. The YOLO network was used because of faster and more accurate performance than other similiar networks. The object to be identified are bladed weapons that are knifes and machetes. Bladed weapons are selected because of potential applications in the real world.The trained models are YOLOv2-tiny, YOLOv3-tiny and YOLOv3. Transfer Learning is done to these models with Darknet so that YOLO can detect the desired weapon. Darknet model will be converted to Tensorflow Lite. Model testing is done by looking at some standard accuracy metrics such as precision, recall, mAP, and the average IoU. The model with the best performance will be installed in the Android application to detect bladed weapon objects knifes and machetes.The test results show that the performance of the model is very dependent on the type of network, the number of datasets, and the shape of the dataset. YOLOv2-tiny produces the worst result with mAP of 55% and average IoU of 35%. The final accuracy for Tensorflow Lite Android model are 72.7% for YOLOv3 and 63.6% for YOLOv3-tiny. The YOLOv3-tiny network is suitable for real-time detection because of fast inference time (0.9 seconds).]]>
<![CDATA[Prediksi Retensi Customer Berdasarkan Support Vector Machine dengan Preprocessing Menggunakan Hadoop ]]>
<![CDATA[Giovanni Gabriela Gunadi]]>;
<![CDATA[Silvia Rostianingsih]]>;
<![CDATA[Andre Gunawan]]>
<![CDATA[ Jurnal Infra Vol 8, No 2 (2020) ]]>
Publisher : <![CDATA[Jurnal Infra ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
<![CDATA[Nowadays, many companies often offer a discount to customer. The goal is that the company can attract new customers. However, the offer given cannot be done randomly. Offers must be directed to the right customers so the company doesn’t need to spend much money. This study will analyze to determine whether there is an influence of the association rule on customer retention. The data used is the Acquire Valued Shopper Challenge taken from the Kaggle website. As the program used is java with the Hadoop framework that uses the association rule method. Tests carried out twice using different data. The objective to be achieved from testing is that the model created can predict customers who will retain if they get an offer. With the tests carried out, the best results to answer the objective is to use data in the second experiment with the ratio of training data to testing data is 7: 3 and gamma 0.1 with accuracy obtained is 58.21%.]]>
<![CDATA[Deteksi Balon Ucapan Pada Komik Jepang Dengan Convolutional Neural Network, Canny Edge Detection dan Run Length Smooth Algorithm ]]>
<![CDATA[Ricky Setiawan Saswono]]>;
<![CDATA[Rudi Adipranata]]>;
<![CDATA[Kartika Gunadi]]>
<![CDATA[ Jurnal Infra Vol 8, No 2 (2020) ]]>
Publisher : <![CDATA[Jurnal Infra ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
<![CDATA[Comic is an entertainment media that is usually used to fill free time. Comics themselves are already very well known in the world, especially comics from Japan. Comics from Japan, commonly called Manga, have a high level of popularity. The proof is a lot of Manga that is translated into each country's language. Examples such as One Piece that has been circulating in 43 countries. Even so the translation process is quite long especially in Japanese translation.This research can be used to accelerate the translation process by using CNN and Canny Edge Detection to detect speech balloons in Manga. The detection results are segmented and with the help of OCR to digitize Japanese characters. Then use copy-paste techniques in an online dictionary or online translator to find the meaning of letters that are not understood. Because searching for letters from a physical dictionary (book) takes more time.The results of the research to segment the speech balloon from Manga were successful but to classify the image in the form of a speech balloon or not with CNN was unsuccessful. Researchers assume because the dataset created is small in number or a problem during pre-processing.]]>
<![CDATA[Pemanfaatan Teknologi Cubeacon Sebagai Media Informasi Di UK Petra ]]>
<![CDATA[Yosua Umbu Datu Kadiwanu]]>;
<![CDATA[Alexander Setiawan]]>;
<![CDATA[Rudy Adipranata]]>
<![CDATA[ Jurnal Infra Vol 8, No 2 (2020) ]]>
Publisher : <![CDATA[Jurnal Infra ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
<![CDATA[Along with the development of technology today, the communication media is switching from conventional media to new media. Although in the transition to new media, users still miss some of the information that has been given in the form of a handbook containing important information, and still questioning to others to obtain information. To overcome this, Cubeacon technology is used to help maximize the dissemination of information by sending information to the user when the user approaches or is around the beacon coverage by utilizing the Bluetooth signal emitted by the beaconCubeacon is a device that communicates with smartphone using Bluetooth signals. With Bluetooth Low Energy based wireless technology that sends bluetooth signals continuously containing minor and major values from Cubeacon, the smartphone will provide information based on what stored in the database.The test results indicate that the beacon placement can affect the quality of the emitted signal. This application can be used by users to find information from beacons within the reach of a smartphone.]]>
<![CDATA[Perbandingan Performa Tools Web Scraping pada Website dengan Data Statis dan Dinamis ]]>
<![CDATA[Michael Levi]]>;
<![CDATA[Henry Novianus Palit]]>;
<![CDATA[Silvia Rostianingsih]]>
<![CDATA[ Jurnal Infra Vol 8, No 2 (2020) ]]>
Publisher : <![CDATA[Jurnal Infra ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
<![CDATA[In scraping a website, the main concern is the type of website whether it is a static or dynamic website, and also the data structure of the website. With different website characteristics and diverse web scraping tools, it will make users quite difficult in choosing tools that suit their needs. The purpose of this research is to compare web scraping tools from different website characteristics, and to provide recommendations for web scraping tools for future research by knowing the right tools in handling each website's characteristics. Based on the results of tests that have been done, it can be concluded which tools are more effective and efficient in certain conditions.]]>
<![CDATA[Pembuatan Aplikasi Complaint Management System pada Universitas Kristen Petra dengan menggunakan Metode Support Vector Machine Multiclass One vs Rest ]]>
<![CDATA[Isak Imanuel Leong]]>;
<![CDATA[Rolly Intan]]>;
<![CDATA[Leo Willyanto Santoso]]>
<![CDATA[ Jurnal Infra Vol 8, No 2 (2020) ]]>
Publisher : <![CDATA[Jurnal Infra ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
<![CDATA[One of the facilities at Petra Christian University for the accommodation of aspirations from the academic community is the suggestion box. However, the use of suggestion boxes is considered less effective and objective because it has a reluctance to fill out and lacks strong evidence through photo documentation.To answer the above problem, an Android-based complaint management system was created that supports the aspiration process that is more effective and objective through the use of mobile devices that are more widely used by the academic community. Application supported by the model. Supported by Vector Support Engine (SVM) with the approach of multiclass One vs. Rest to classify the bureau or related units to overcome errors in determining the recipient of the aspirational recipient.The results of the research conducted show that preprocessing parameter such as normalization, stemming and stopwords removal affect the accuracy of the model. The best kernel type in SVM for aspiration text classification is linear with value of C = 1 which results in an accuracy of 95,441%. In addition, the results of a survey to administrator who manage the management of aspiration shows that the application created already answer the needs and problems, in this case supporting the objectivity and effectiveness of aspiration data delivery.]]>
<![CDATA[Menghasilkan Background Game Music dengan Menggunakan Deep Convolutional Generative Adversarial Network ]]>
<![CDATA[Daniel Widjojo]]>;
<![CDATA[Henry Novianus Palit]]>;
<![CDATA[Alvin Nathaniel Tjondrowiguno]]>
<![CDATA[ Jurnal Infra Vol 8, No 2 (2020) ]]>
Publisher : <![CDATA[Jurnal Infra ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
<![CDATA[One of many important factor in producing a good quality game is the existence of a good quality Background Game Music (BGM). But the difficulty of getting game music assets makes game developers have to pay extra money, waste more time and effort to get a good quality game music. This can hinder the process of making a game. For that reason, if there is a program that is able to produce BGM with good quality, it will greatly help the work of the game developer.The method used in this study is the Deep Convolutional Generative Adversarial Network (DCGAN). The data that being used is Musical Instrument Digital Interface (MIDI) file format which will then be converted into a pianoroll format. The pianoroll will then be converted into a matrix and entered into the DCGAN model. Before conducting training process, it is necessary to make a preprocessing, postprocessing and a model DCGAN. Testing in this study is done by finding the best parameters and architecture of DCGAN to produce Background Game Music with good quality.The test results show that DCGAN is a very sensitive model in terms of architecture and hyperparameter, therefore it needs extra attention in tuning architecture and hyperparameter for DCGAN. Besides that, music that is converted into pianoroll format lacks the ability to highlight its features and making it difficult to learn by DCGAN. From the end results, DCGAN is able to produce Background Game Music but with poor quality.]]>
