Article Per Year (5 Year)
p-Index From 2021 - 2026
2.122
P-Index
This Author published in this journals
All Journal Jurnal Infra
Djoni Haryadi Setiabudi
Program studi Teknik Informatika, Universitas Kristen Petra surabaya
Computer Science & IT

Published : 16 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 16 Documents
Search

 1   2 
Penerapan Long-Short Term Memory dengan Word2Vec Model untuk Mendeteksi Hoax dan Clickbait News pada Berita Online di Indonesia Soni Marko Nathanniel Tannady; Djoni Haryadi Setiabudi; Alvin Nathaniel Tjondrowiguno
Jurnal Infra Vol 10, No 2 (2022)
Publisher : Universitas Kristen Petra

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

Abstract

News has become information that is routinely consumed every day and can be accessed easily as technology develops. However, the easy access of readers to news also opens up space for some people to spread clickbait or hoax news to attract readers' attention for personal gain. To overcome this, one of the efforts that can be realized is with a detection model for clickbait and hoax news with machine learning methods. The method used is Long-Short Term Memory. However, with several additional applications such as adding a dropout layer, implementing a callback function and using k-fold cross validation to overcome the problem of overfitting the model which often occurs in related studies. The built model will be tested in a webpage application where users can detect news labels. On the best testing result, testing accuracy for the clickbait detection model are 72.93% and the hoax detection model are 79.17%.
Game RPG Berbasis Android untuk Mendorong Pengguna Berolahraga Wilson Mark; Henry Novianus Palit; Djoni Haryadi Setiabudi
Jurnal Infra Vol 10, No 2 (2022)
Publisher : Universitas Kristen Petra

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

Abstract

With the lockdown period due to Covid-19, maintaining stamina and body health is a priority. People are advised to reduce activities outside the home and work from home. Working from home is often done behind a desk, and after work people do activities to relieve boredom such as watching television, playing games, and other sedentary activities that cause them to be unhealthy. Playing games on a smartphone is becoming more popular because they are easily accessible and only require a smartphone that has many features already on it. This thesis research aims to create a game application on a smartphone to overcome this problem. This RPG game application, is hoped to increase people's interest in exercising by playing on a smartphone that detects motion using the accelerometer sensor and calculates calorie burned using the MET formula. The results of testing the game show that 40% of respondents are more interested in exercising. In addition, the calculation of calories is quite accurate compared to other tools. And it is also proven that this game can meet the recommended daily exercise.
Aplikasi Moblie Learning untuk Meningkatkan Interaksi Pembelajaran dalam Mendukung Penyerapan Materi Pembinaan UMKM oleh LPPM Universitas Kristen Petra dengan Menerapkan Model Learning Group Cynthia Wijaya; Djoni Haryadi Setiabudi; Justinus Andjarwirawan
Jurnal Infra Vol 10, No 2 (2022)
Publisher : Universitas Kristen Petra

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

Abstract

 Synchronous learning provided by LPPM in learning events is often limited, and makes MSME participants have to understand and develop the material that has been delivered individually after receiving the lesson. This makes the lack of interaction in learning, and reduces the interest and attention of MSMEs to improve learning from the material obtained, especially when they find difficulties in learning. This can affect the level of absorption of material by MSMEs to be not optimal. Several previous studies using mobile learning still have weaknesses, namely learning is still more focused on individual learning so there is no interaction in the learning process through mobile learning.To overcome this problem, in this study a mobile learning application was designed with a learning group model that has collaborative features, such as the task forum feature where MSMEs can choose the question to be worked on and then give each other comments on whether the answers in each question are correct, problem box to help each other provide solutions from a lack of understanding of the material, discussion forums to discuss things that have not been discussed in the material, glossary, chat with tutors and mobile push notification support to encourage MSMEs to be more active in mobile learning.The results of this study based on questionnaires and activity calculations, it can be concluded that the mobile learning application with the learning group model helps MSMEs to understand or increase the absorption of material in training. In addition, it also makes MSMEs active in participating in the training, thus indirectly helping better absorption of material.
Penerapan Convolutional Neural Network dengan Pre-Trained Model Xception untuk Meningkatkan Akurasi dalam Mengidentifikasi Jenis Ras Kucing Abraham Imanuel; Djoni Haryadi Setiabudi
Jurnal Infra Vol 10, No 2 (2022)
Publisher : Universitas Kristen Petra

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

Abstract

Raising pets is a common thing that humans often do. Cats are one of the domestic pets that are fancied by humans. But, raising a cat is not an easy task. This is because every cat’s breed has its own characteristics that will affect its type of raising. Because of that, there is a need for a system that can identify a cat’s breed to help someone in deciding which type of cat is suitable for him/her. In the past, there was also research about cat’s breed detection using SSD Mobilenet_v1 FPN method, but the accuracy was not high enough, which was 81.74%. This thesis will be done with the implementation of transfer learning method on Pre-Trained Convolutional Neural Network Xception, which is a CNN Model that is inspired by CNN Model Inception. CNN Model Xception is an Inception Model that replaces the use of Inception modules with depth wise separable convolutions. CNN Model Xception is used in this thesis with the purpose of increasing the accuracy of cat’s breed detection. Output of the system shows that the highest accuracy that could be made in detecting cat’s breeds on The Oxford-IIIT Pet Dataset is 89.58% or 0.8958. Compared to SSD Mobilenet_v1 FPN method, which accuracy was 81.74%, implementing Xception method gives an increase in the accuracy for 7.84%. Other than that, it is also found that the dataset quality has an impact on model’s accuracy.
Penerapan Ensemble Learning Menggunakan Metode Support Vector Machine, Naïve Bayes Classifier, dan Valence Aware Dictionary for Sentiment Reasoning untuk Meningkatkan Akurasi Sentiment Analysis pada Review Aplikasi Google Play Tania Sunyoto; Djoni Haryadi Setiabudi; Alvin Nathaniel Tjondrowiguno
Jurnal Infra Vol 10, No 2 (2022)
Publisher : Universitas Kristen Petra

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

Abstract

In an age where almost everyone owns a smartphone, more and more mobile applications are being developed and distributed to Google Play. To decide which application to download, customers are influenced by ratings and reviews. Reviews provide more information than ratings, but there are so many that they are difficult and take a long time to obtain. The application of sentiment analysis supported by high accuracy in reviews can make it easier for customers to get sentiment information from th e application and help them make decisions to download / use the application or not. This research uses a combination of Naïve Bayes and SVM machine learning models with the VADER lexicon model, then Ensemble Learning is carried out using Majority Voting, Majority Weighted Voting, and Stacking to improve accuracy. The results of this system indicate that by using Ensemble Learning the accuracy result increases but not significantly even decreases from SVM results of 88.88% to 88.87% using Stacking.
Sistem Pakar Diagnosa Kerusakan Pada Mobil Toyota Innova Dengan Metode Backward Chaining Dan Certainity Factor Jason Aldrian; Djoni Haryadi Setiabudi
Jurnal Infra Vol 10, No 2 (2022)
Publisher : Universitas Kristen Petra

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

Abstract

Car is one of the transportation that used commonly by human. Toyota Innova is one of the most favorite family car in Indonesia. Toyota Innova has a lot of type and variations that need to be handled. There is Manual transmission and Automatic Transmission. Damage to car cannot be taken so easily, Not only big damage that can cause breakdown. But small problems or damage to car can cause breakdown or failure, Small damage is need to handled too as important as big damage so it would not become fatal damage. Diagnostics on the car for people who don't really understand cars can be really confusing and the number of repair shops that are not honest in diagnosing damage will cause losses for car owners. If in an urgent situation this system can be used to find out what damage has occurred and make it possible to check and repair the damage to the car that occurred. This Expert System for Damage Diagnosis on Toyota Innova is using Forward Chaining and Certainty Factor as it’s method. Backward Chaining on this expert system is for collecting symptoms and facts that come into some conclusions so users don't have to answer all the questions. And the usage of Certainty Factor on this system to show the percentage of system belief on the diagnosis. So user can trust on the result of diagnose. The results of tests that have been carried out 20 times from tests by experts, There is 19 results that suitable with expert opinion. There is 1 result that is not suitable with expert opinion because of the inaccuracy of the CF percentage. As of that result user can still look for the solution in the damage encyclopedia. In this test, the percentage for detecting damage to the Toyota Innova car using the Backward Chaining method and Certainty Factor is 95% in accordance with expert opinion.
Co-Authors Abraham Imanuel Alexander Setiawan Alvin Nathaniel Tjondrowiguno Andreas Handojo Andrew Firman Saputra Andrianto Saputra Linardi Lie Cynthia Wijaya Hans Juwiantho Henry Novianus Palit Indar Sugiarto Jason Aldrian Jessica Clarensia Suko Justinus Andjarwirawan Kartika Gunadi Kevin Christian Liliana Liliana Maria Eve Angeline Regan Reinaldo Kalendesang Richard Alexander Silvia Rostianingsih Soni Marko Nathanniel Tannady Tania Sunyoto Vitalona Crysantini Paays William Tupan Wilson Mark Yoel Julianto