Article Per Year (5 Year)
p-Index From 2021 - 2026
1.323
P-Index
This Author published in this journals
All Journal Jurnal Infra
Rolly Intan
Program Studi Informatika
Computer Science & IT

Published : 18 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 18 Documents
Search

 1   2 
Pembuatan Aplikasi Mobile Augmentative and Alternative Communication "BerKata" dengan Menggunakan Text to Speech untuk Membantu Komunikasi Anak Penyandang Autisme Evandruce Filbert; Rolly Intan; Henry Novianus Palit
Jurnal Infra Vol 9, No 2 (2021)
Publisher : Jurnal Infra

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Children with autism who lack verbal communication skills often confuse their parents for knowing what their wants are conveniently. It takes extra effort for their parents to understand them, especially with their unclear pronunciations. Their inability to conveniently understand what is kept in their minds may affect their emotions. The children easily experience mood swings, and their parents struggle to identify their children’s needs. All of these struggles can be supported with the Augmentative and Alternative Communication (AAC) with Picture Exchange Communication System (PECS) module. With PECS, children with autism will be able to learn how to converse their needs through image media. Therefore, their parents can easily understand what they want to say. With all the problems, this research presents an AAC mobile application with PECS module called “BerKata”. The result of this research is that “BerKata” may develop children with autism’s speech ability, to decrease their anxiousness and help gaining their confidence, if only their parents consistently use it. Keep in mind to achieve the goal, requires consistency of habituation from children, parents and the people around and not an instant result.
Pembuatan Aplikasi Complaint Management System pada Universitas Kristen Petra dengan menggunakan Metode Support Vector Machine Multiclass One vs Rest Isak Imanuel Leong; Rolly Intan; Leo Willyanto Santoso
Jurnal Infra Vol 8, No 2 (2020)
Publisher : Jurnal Infra

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

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.
Sistem Rekomendasi Tempat Makan Wilayah Solo Raya Berbasis Web dengan User Based Collaborative Filtering Menggunakan Fuzzy Conditional Probability Relation Christian Suryadi; Rolly Intan; Hans Juwiantho
Jurnal Infra Vol 9, No 2 (2021)
Publisher : Jurnal Infra

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Recommendation system is a system used to predict an object for users in the form of useful information based on the rating value. Recommendation system can be applied for food places. The method commonly used for recommendation system is User-Based Collaborative Filtering. This method is a technique used to predict an item that the user likes based on the same rating, by means of user to user.This study uses User-Based Collaborative Filtering method using Fuzzy Conditional Probability Relation to perform calculations between users. Testing is done by calculating the accuracy of the recommendations generated by the system for users. The survey will be used to find the accuracy value of the method.The results of this study is the accuracy values from the User-Based Collaborative Filtering method using Fuzzy Conditional Probability Relation. Based on the survey results, the accuracy obtained is 62.78%, the accuracy using a rating limit of 2 is 47%, with a rating limit of 3 is 69%, and with a limit of 4 is 83%. From the results of this accuracy, we can summarize that User-Based Collaborative Filtering using Fuzzy Conditional Probability Relation can produce results that are quite good and satisfactory to provide recommendations.
Klasifikasi Topik dan Analisa Sentimen Terhadap Kuesioner Umpan Balik Universitas Menggunakan Metode Long Short-Term Memory Doenny Auddy Lionovan; Leo Willyanto Santoso; Rolly Intan
Jurnal Infra Vol 8, No 2 (2020)
Publisher : Jurnal Infra

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

In evaluating and improving the quality of services and facilities, Petra Christian University (PCU) took feedback questionnaires given to students via online. At this time, reading the comments in the suggestion column is still read manually. So that it becomes less effective and efficient in analyzing sentiments and classifying topics for many comments. This study will apply word2vec and Long Short-Term Memory method to create a program that can help classify topics and sentiment analysis.Word2vec is used as a method to convert a word into a vector along with mapping the meaning of existing words. The parameter tested on word2vec are the number of iterations and windows size. Whereas the Long Short-Term Memory method is used to classify sentiment and topics. The parameter tested are the number of layers, the number of units, the batch size, and the percentage of dropout.The result of this study indicates that the word2vec method along with Long Short-Term Memory can be used to analyze sentiment and topic classification. The best configuration results obtained average accuracy in the implementation of the sentiment classification is 89,16 % and for implementation of the topic classification is 92,98 %.
Sistem Rekomendasi Games menggunakan Metode Item-based Collaborative Filtering berbasis Website Fernando Febrianto; Justinus Andjarwirawan; Rolly Intan
Jurnal Infra Vol 9, No 2 (2021)
Publisher : Jurnal Infra

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Item-based Collaborative Filtering is a method that is usually used for a Recommendation System based on the items that most users choose, because this method can recommend according to the tastes of most users who choose, this method is very effective in time to recommend an item in any form.This study combines Fuzzy Similarity, Item-based Collaborative Filtering, and User-based to produce a recommendation, by calculating the similarity value using Fuzzy Similarity and User-based will make it easier to find the similarity value between users to be processed again using the Item-Based Collaborative Filtering method for recommendations that are suitable for users.The results of this study are 10 Game Recommendations that are in accordance with the implementation of Item-based Collaborative Filtering, Fuzzy Similarity, and User-based which take from the most similar people by calculating the similarity value between users and take the game that is most chosen by users. and the recommendation system works, and from the survey results, it is found that people who try to enter this website do not feel confused about the User Interface, there are also many users who like to play games, and according to the survey, the accuracy rate is quite large.
Floating Window pada Sistem Lelang Online yang Terhubung dengan Akun Instagram menggunakan Firebase Realtime Database Berbasis Android Winlian Winlian; Rolly Intan; Lily Puspa Dewi
Jurnal Infra Vol 9, No 2 (2021)
Publisher : Jurnal Infra

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Buy and sell is one of the activity that is so general in eachcountry. There are many various ways to do it. Online ouction isone of it and it help the auction opener easier to find the highestprice offer from auction bidder even they are from the distanceplaces. In Indonesia, many online auction have been done and oneof it using Instagram as their platform. But, online auction fromInstagram has so many deficiency that causes the uncomfortablefor the online auctioneer.So this application was made and it connects with Instagram,where the user can make an auction on the application and focuswith the notification from the running application. The user canalso trust the potential bidder with the social capital which isincluded in the user’s Instagram account. This application has apin feature that using floating window for choosen bidder inapplication and the process is display in realtime.According to the result of test from 20 respondents as a potentialbidder and 5 person as an auction maker, the application can helpthe process of online auction with average 89% from the potentialbidder side and 84% from auction maker side. Notification iseffective and communicative with average 83% from the bidderside and 76% from the auction maker side. Floating window helpswith average 84% from the potential bidder side and 76% fromauction maker side. So, the conclusion is this application can helpand give a place for the online auctioneer in Instagram.
Adaptive AI Pada Survival Horror Game Menggunakan Fuzzy Leonard Evan Widodo; Rolly Intan; Hans Juwiantho
Jurnal Infra Vol 8, No 2 (2020)
Publisher : Jurnal Infra

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

There are many methods used by developers to create artificial intelligence in their games. The method most often used by developers because of it’s flexibility is the scripting method. Scripting method is done by writing several rules in the source code in the form of if - then. The problem with this method is that the NPC’s artificial intelligence is easily exploited by gamer who have understood the pattern of the NPC’s behavior.Therefore the fuzzy logic is used to overcome these problems.The use of the fuzzy inference method is to make the AI to be adaptive to certain situation where depending on the situation the AI will give different decision making. In this case, Tsukamoto Fuzzy inference method is used in this design. In the method, all rules have their respective values which then will be calculated to look for the average score which then was used to determine which decision to make. Before constructing the fuzzy rules, determining the design of the game and the design of the map must be made first. After all are done, the appropriate fuzzy rules can be constructed.The results of the survey showed that the game that uses the Tsukamoto fuzzy inference method provides an adaptive decision according to the conditions at a moment in a game. Ninth of the players who played the game agreed that game A and game B had different decisions despite using the same AI as much as 77.2%, while those who said that AI was the same as much as 22.8%. From the results of this survey it can be said that the Tsukamoto fuzzy inference method can produce adaptive decisions based on the condition of the game at a certain moments.
Electrocardiogram Biometrics Recognition Menggunakan Artificial Neural Network William Sim Jayapranata; Rolly Intan; Liliana Liliana
Jurnal Infra Vol 9, No 1 (2021)
Publisher : Jurnal Infra

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Research on biometrics recognition has become popular in the last two decades. Electrocardiogram signal is one among many data that can be used in biometrics recognition purposes. It is unique for each individual, easy to obtain, and hard to forge made electrocardiogram well suited for biometrics recognition. In this research, an identifier will be made using the electrocardiogram signal of each individual.In this research, non-fiducial approach on MIT-BIH Arrhythmia Database from physionet with Artificial Neural Network as classifier was used. Non-sequential classifier offers lower computational complexity compared to sequential classifiers. Non-fiducial approach does not require feature extraction but a method of truncating the signal to each heartbeat is still required. Artificial Neural Network method uses neuron on each layer to classify digitalized electrocardiogram signal data.Experiment result using our method achieved 98.886% accuracy using MIT-BIH Arrhythmia Database. This research demonstrates Artificial Neural Network method capability as non-sequential classifier to identify electrocardiogram with non-fiducial approach.
Co-Authors Agustinus Noertjahyana Aldy Noah Alvin Nathaniel Tjondrowiguno Calvin Kamtoso Christian Suryadi Doenny Auddy Lionovan Evandruce Filbert Fernando Febrianto Giovanni Christian Antonio Hans Juwiantho Henry Novianus Palit Isak Imanuel Leong Justinus Andjarwirawan Kevin Christian Salim Kevin Oktovio Lauw Leo Willyanto Santoso Leonard Evan Widodo Liliana Liliana Lily Puspa Dewi Nathaniel Edward Rudy Adipranata Silvia Rostianingsih Sutikno Goutama Timothy Tamara Tommy Sugiarto William Sim Jayapranata Winlian Winlian Yonas Christianto