Article Per Year (5 Year)
p-Index From 2021 - 2026
7.93
P-Index
This Author published in this journals
All Journal Jurnal Ilmiah Merpati (Menara Penelitian Akademika Teknologi Informasi) Techno.Com: Jurnal Teknologi Informasi Jurnal Buana Informatika CESS (Journal of Computer Engineering, System and Science) Sinkron : Jurnal dan Penelitian Teknik Informatika Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Journal of Information Technology and Computer Science JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING JOURNAL OF APPLIED INFORMATICS AND COMPUTING JURIKOM (Jurnal Riset Komputer) Journal of Information Systems and Informatics Tematik : Jurnal Teknologi Informasi Komunikasi Walisongo Journal of Information Technology Jurnal Indonesia : Manajemen Informatika dan Komunikasi JITSI : Jurnal Ilmiah Teknologi Sistem Informasi Jurnal Indonesia : Manajemen Informatika dan Komunikasi Jurnal Ilmiah Teknologi dan Komputer (JITTER)
I Made Agus Dwi Suarjaya
Universitas Udayana
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Engineering Languange, Linguistic, Communication & Media Library & Information Science

Published : 45 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 45 Documents
Search

 1   2   3   4   5 
Baby Cry Classification Using Ensemble Learning and Whisper Method Comparison Dharmawan, I Putu Yogi Prasetya; Suarjaya, I Made Agus Dwi; Vihikan, Wayan Oger
Journal of Applied Informatics and Computing Vol. 9 No. 2 (2025): April 2025
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v9i2.9167

Abstract

Baby cry classification is an important topic in Machine Learning, especially in the healthcare field, as crying is the primary form of communication for infants to convey their needs or conditions. Many inexperienced parents tend to interpret baby cries in a limited way, even though each cry has unique characteristics that represent specific needs such as hunger, discomfort, sleepiness, flatulence, and abdominal pain. With the advancement of technology, identification of baby cries can now be done automatically through AI-based applications, but the implementation is still limited. This study compares the performance of ensemble learning methods, namely Random Forest and XGBoost, with the Whisper model in classifying baby cries. The results show that the Whisper-small model has the best performance with precision 0.9115 and recall 0.9007, followed by XGBoost with slightly degraded performance after hyperparameter optimization. Random Forest showed the lowest performance among the three models. Transformer-based models such as Whisper-small proved to be superior in capturing the complex patterns of infant cries, compared to tree-based models. These findings indicate the great potential of accurate and reliable models to help parents understand the needs of infants more effectively, thereby improving the quality of infant care.
Sistem Pengenalan Huruf Braille Menggunakan Metode Deep Learning Berbasis Website I Made Agus Dwi Suarjaya; Wiratama, Bayu Adhya; Ayu Wirdiani
JITSI : Jurnal Ilmiah Teknologi Sistem Informasi Vol 5 No 3 (2024)
Publisher : SOTVI - Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/jitsi.5.3.244

Abstract

Braille letters are used as a written language for people with visual impairments. To this day, Braille letters are used in in inclusive schools where they are taught to disabled students. However, there are physical capability barriers faced by teachers when correcting Braille answer sheets written by visually impaired students. The ability to read Braille letters is also important for family members to support the students' learning process. This research’s purpose was to create a system that can transliterate Braille letters into the Latin alphabet using deep learning methods. The proposed deep learning methods include Base Convolutional Neural Network (CNN), ResNet50, VGG-16, and Inception-v3. The Braille Character image dataset used consists of 12,641 data divided into 37 classes from the AEyeAlliance repository. The Base CNN model used achieved 98% training accuracy, 99% validation accuracy, and 99.1% testing accuracy.
Automatic Pet Feeder Rotational Model Using MQTT and Mobile Application Mahadiputra, Putu Gede Krisna; Suarjaya, I Made Agus Dwi; Wibawa, Kadek Suar
Jurnal Ilmiah Merpati (Menara Penelitian Akademika Teknologi Informasi) Vol 12 No 2 (2024): Vol. 12, No. 2, August 2024
Publisher : Lembaga Penelitian dan Pengabdian kepada Masyarakat Universitas Udayana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JIM.2024.v12.i02.p04

Abstract

Automatic pet feeding systems with dispenser models have limitations on the type of feed that is only accomodate dry food, while pets (cats) with a tendency consuming dry food are prone to disease in the urinary system. This research focuses on designing a rotational model automatic pet feeding system that can accommodate both dry food and wet food, also set the feeding time through mobile applications via MQTT by utilizing an ESP32 microcontroller connected to a 5V stepper motor, RTC and load cell sensor. The system has success rate about 90% on pet feeding automation, but the container upper fold has difference angel about 5.4o with the expected position (error rate 6%). Every weight sensor has the successive error rates are 1.41% (1st feed block), 1.91% (2nd feed block), and 0.68% (3rd feed block). The Android application takes only 1-1.5 seconds to displaye the latest feed weight data.
Analysis of Indonesian Public Satisfaction Towards Goods Delivery Services using the CNN-LSTM Model Sadhaka, Anak Agung Istri Prabhaisvari; Agus Dwi Suarjaya, I Made; Buana, Putu Wira
Journal of Information Technology and Computer Science Vol. 10 No. 1: April 2025
Publisher : Faculty of Computer Science (FILKOM) Brawijaya University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jitecs.2025101507

Abstract

The fast-paced development of e-commerce in Indonesia has driven the expansion and rising demand for goods delivery services. Every goods delivery service offers consultations or Q&A sessions about their services through Twitter. The number of tweets from users of goods delivery services can be used to determine the level of public satisfaction with these delivery services. The sentiment analysis process is conducted using a CNN-LSTM deep learning model. Evaluation of the CNN-LSTM model resulted in an accuracy of 0.838, an F1-score of 0.838 for the macro average and micro average, a precision of 0.840 for the macro average and 0.838 for the micro average, and a recall of 0.840 for the macro average and 0.838 for the micro average. Based on the results of analysis, it was found that Indonesian people tend to be dissatisfied with existing delivery services.
Implementation of FP-Growth Algorithms for Promo Package Determination in a Scooter Motorcycle Workshop Business I Gusti Ngurah Bagus Picessa Kresna Mandala; I Ketut Adi Purnawan; I Made Agus Dwi Suarjaya
Journal of Applied Informatics and Computing Vol. 9 No. 3 (2025): June 2025
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v9i3.9499

Abstract

This study applies the FP-Growth algorithm to design bundled promotions for a scooter motorcycle accessory store and workshop in Denpasar, Bali. FP-Growth was chosen for its efficiency in mining frequent itemsets without generating candidate sets. From 23,381 transaction records (January-August 2024), the algorithm identified 16 association rules using a minimum support of 1% and confidence of 50%. These rules were selected based on lift values and product relevance. One notable example is the association between "BAUT TITANIUM GR5 M10 X 60" and "BAUT TITANIUM GR5 M8X50", which had a lift of 47.814, indicating a very strong co-purchase relationship. These high-lift combinations present valuable opportunities for bundling and targeted point-of-sale offers. The algorithm performed efficiently, with a runtime of just 0.1354 seconds and 402.6 MB of memory usage. Bundles based on these associations were presented to customers, and feedback was collected through a Customer Satisfaction (CSAT) survey involving 56 recent buyers. The survey yielded a high CSAT score of 83.93%, demonstrating customer satisfaction with the bundles’ relevance and appeal. These results confirm that FP-Growth can effectively inform promotional strategies by identifying strong product pairings that align with actual purchasing behavior. Strategically promoting such bundles not only enhances customer experience but also encourages multi-item purchases. This data-driven bundling approach is practical and profitable for medium-sized retail businesses, ultimately supporting the goal of increasing the Average Order Value.
Analisis Sentimen Publik Terkait Kekerasan Seksual di Indonesia dengan Algoritma Naïve Bayes dan SVM Nalista, Ni Made Naila; Mandenni, Ni Made Ika Marini; Suarjaya, I Made Agus Dwi
JURIKOM (Jurnal Riset Komputer) Vol 12, No 3 (2025): Juni 2025
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/jurikom.v12i3.8556

Abstract

Semakin meningkatnya kasus kekerasan seksual yang terjadi di Indonesia, dan media sosial merupakan ruang bagi masyarakat Indonesia untuk mengekspresikan pendapat. The increasing number of sexual violence cases in Indonesia, along with the role of social media as a space for the public to express their opinions, forms the basis for this research. The study aims to classify various types of public sentiment expressed on X (formerly Twitter) and Instagram comments by applying two algorithms for comparison: Naïve Bayes and SVM. Several processes carried out, including data collection from social media, data preprocessing, manual labeling, and the implementation of both algorithms on the processed dataset. The data sources utilized are posts written in Indonesian on X (Twitter) and Instagram, focusing on issues of sexual violence in Indonesia. The sentiment analysis results were grouped into three main categories: positive, negative, and neutral. The outcomes show that SVM achieved an accuracy of 82.17% using an 80:20 data split without applying GridSearch for optimization. The SVM results outperformed those of Naïve Bayes, which achieved an accuracy of 78.92%. This investigation leads to the conclusion that SVM is more optimal in analyzing public sentiment related to sexual violence in Indonesia compared to Naïve Bayes. The sentiment analysis results from social media regarding sexual violence in Indonesia show that the majority of sentiments are neutral, with the dataset being dominated by informative content, case reports without emotional expression, and off-topic comments
Stock Sentiment Prediction of LQ-45 Based on News Articles Using LSTM Kristina, Kristina; Agus Dwi Suarjaya, I Made; Cahyawan Wiranatha, Anak Agung Ketut Agung
Journal of Applied Informatics and Computing Vol. 9 No. 4 (2025): August 2025
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v9i4.9699

Abstract

The growth in the number of investors in the financial market indicates that the investment world is currently experiencing rapid development. One of the long-term investment instruments that has experienced significant growth in the financial market is the stock market. Growth data as of September 2024 sourced from the Indonesia Stock Exchange report reveals that the number of stock market investors has reached more than 6 million single investor identification (SID). The share price of a company can be influenced by two main factors, namely internal factors and external factors. Internal factors come from within the company itself, while external factors come from conditions outside the company. Model development uses the Long Short-Term Memory (LSTM) method to predict daily stock sentiment in realtime. Labeling is done based on the history of stock price changes taken from Yahoo Finance. Stock market news data is obtained automatically every day through Really Simple Syndication (RSS) with the help of cronjob. The results of the LSTM model showed good performance, with a macro F1-Score of 0.73, a macro precision of 0.72, and a macro recall of 0.75. When compared to baseline models such as Logistic Regression, Naive Bayes, and Random Forest which only achieve a macro F1-Score of 0.58, 0.54, and 0.65, respectively, it can be concluded that the developed LSTM model has superior performance. This research can provide new considerations to investors, so as to reduce the risk of loss due to errors in choosing companies to invest in.
Esscore: An OCR-Based Android App for Scoring Short Handwritten Answer Using Levenshtein Distance Apriana, Krisna; I Made Agus Dwi Suarjaya; Ni Kadek Dwi Rusjayanthi
Journal of Applied Informatics and Computing Vol. 9 No. 4 (2025): August 2025
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v9i4.9708

Abstract

Manual evaluation of short answer tests is time-consuming and prone to subjectivity. This study presents Esscore, an Android-based application that automates the scoring of handwritten short answers using EasyOCR and the Levenshtein Distance algorithm. EasyOCR extracts text from student answers image, while Levenshtein Distance measures similarity against predefined answer keys, allowing tolerance for varied correct responses. The system was tested on 350 student’s handwritten answers, achieving 95.7% accuracy. Functional testing using 14 black box scenarios showed all features operated correctly without failure. A usability test conducted with the SUS method produced a score of 76.5, rated “Good” with a grade “B” and an “Acceptable” acceptance level. The Net Promoter Score (NPS) placed the application in the “Passive” category. These results confirm Esscore as a functional, accurate, and user-friendly solution for automated answer scoring in educational environments.
Food Recipe Recommendation System with Content-Based Filtering and Collaborative Filtering Methods Widiantari, Ni Putu Triska; Suarjaya, I Made Agus Dwi; Rusjayanthi, Ni Kadek Dwi
Sinkron : jurnal dan penelitian teknik informatika Vol. 9 No. 3 (2025): Article Research July 2025
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v9i3.14778

Abstract

Cooking your own food at home is a good step toward reducing fast food consumption. Fast food increases the risk of dangerous diseases. The diversity of recipe information available on the internet makes it difficult to choose recipes that match user preferences. Mobile technology can help with this by recommending recipes that better suit users' eating habits. This makes the transition to a healthier diet easier. Therefore, in this study, a recommendation system was developed that can recommend recipes based on the preferences of Android users. Two main recommendation methods are used in this study: content-based filtering and collaborative filtering. Using cosine similarity, a content-based recommendation system identifies the proximity between a recipe for food and its related context. The history of user comments on recipes serves as implicit feedback for the collaborative recommendation algorithm. This eliminates the need for explicit evaluations, such as ratings. This recommendation system generates recommendations in the form of the top ten food recipes with an evaluation matrix, referred to as NDCG@k and Hit-Ratio@k. The tests revealed that a content-based filtering technique may produce helpful recommendations, with the highest similarity score of 0.41 for the entry "chocolate cake that you can easily make at home." Meanwhile, in the collaborative filtering method using the Neural Collaborative Filtering (NCF) approach, the system shows consistent performance improvements, with the MAP@10 value increasing from 0.705 to 0.767 and the NDCG@10 from 0.78 to 0.83 after 10 training epochs. Keywords: Recommendation systems; content-based filtering; neural collaborative filtering; cosine similarity; implicit feedback
Analisis Sentimen Publik Terkait Kekerasan Seksual di Indonesia dengan Algoritma Naïve Bayes dan SVM Nalista, Ni Made Naila; Mandenni, Ni Made Ika Marini; Suarjaya, I Made Agus Dwi
JURNAL RISET KOMPUTER (JURIKOM) Vol. 12 No. 3 (2025): Juni 2025
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/jurikom.v12i3.8556

Abstract

Semakin meningkatnya kasus kekerasan seksual yang terjadi di Indonesia, dan media sosial merupakan ruang bagi masyarakat Indonesia untuk mengekspresikan pendapat. The increasing number of sexual violence cases in Indonesia, along with the role of social media as a space for the public to express their opinions, forms the basis for this research. The study aims to classify various types of public sentiment expressed on X (formerly Twitter) and Instagram comments by applying two algorithms for comparison: Naïve Bayes and SVM. Several processes carried out, including data collection from social media, data preprocessing, manual labeling, and the implementation of both algorithms on the processed dataset. The data sources utilized are posts written in Indonesian on X (Twitter) and Instagram, focusing on issues of sexual violence in Indonesia. The sentiment analysis results were grouped into three main categories: positive, negative, and neutral. The outcomes show that SVM achieved an accuracy of 82.17% using an 80:20 data split without applying GridSearch for optimization. The SVM results outperformed those of Naïve Bayes, which achieved an accuracy of 78.92%. This investigation leads to the conclusion that SVM is more optimal in analyzing public sentiment related to sexual violence in Indonesia compared to Naïve Bayes. The sentiment analysis results from social media regarding sexual violence in Indonesia show that the majority of sentiments are neutral, with the dataset being dominated by informative content, case reports without emotional expression, and off-topic comments
Co-Authors A.A. Ketut Agung Cahyawan W Aditama, I Putu Dede Raditya Agus Kerta Nugraha, I Wayan Almantara, I Putu Sugi Anak Agung Ketut Agung Cahyawan Wiranatha Anak Agung Ketut Agung Cahyawan Wiranatha Apriana, Krisna Astuti, Ni Nyoman Indri Wika Ayu Krisnasari Ni Komang Ayu Wirdiani Ayu Wirdiani Bakkara, Kevin Christopher Bhagaskara, I Made Bagita Bouchra, Ferhati Cahyawan Wiranatha, Anak Agung Ketut Agung Candra, I Putu Wijaya Adi Danito, Philip Datar, Fandy Kusumaraditya Dewa Gede Kesuma Yoga Dextiro, Kadek Deksy Dhananjaya, Anak Agung Ngurah Gede Dharmawan, I Putu Yogi Prasetya Diatmika, Nyoman Gede Rayka Sedana Dwi Putra Githa Dwi Rusjayanthi, Dwi Efraim William Solang Eva Martina Sitorus Ferhati Bouchra G M Arya Sasmita Gede Widya Dharma Geovaldo, I Putu Hendra Gusti Agung Ayu Putri Gusti Agung Mayun Kukuh Jaluwana Gusti Ayu Wahyu Whurapsari I Gusti Ngurah Bagus Picessa Kresna Mandala I Ketut Adi Purnawan I ketut Gede Darma Putra I Made Adhiarta Wikantyasa I Made Sukarsa I Made Sunia Raharja I Made Sunia Raharja, I Made Sunia I Nyoman Piarsa I Nyoman Prayana Trisna I Putu Agung Bayupati I Putu Agus Eka Pratama I Putu Arya Dharmaadi I Putu Wira Cahaya Pratama Yudha Ida Bagus Gde Dwipermana Sidhi Ida Bagus Kade Taruna Ida Bagus Nyoman Yoga Ligia Prapta Johan Tamin Kadek Suar Wibawa Ketut Mediana Ayu Candrayani Komang Arta Wibawa Krisnadinatha, I Gede Arya Kristina Kristina Luh Kade Devi Dwiyani Made Andika Verdiana Mahadiputra, Putu Gede Krisna Mahaputra, Putu Andre Mahayana, I Putu Gede Panji Badra Nalista, Ni Made Naila Narayana, I Putu Kevin Ari Ngeo Goa, Mario Valentino Ngurah Indra Purnayasa Ni Luh Ketut Inggitarahayu Anggasemara Ni Made Ika Marini Mandenni Ni Putu Ayu Widiari Ni Putu Viona Viandari Novenrodumetasa, Nathania nugraha, gemara adiyasa parahita Nugraha, Made Adhi Satrya Pande Nengah Purnawan Permana, Kadek Arya Putra Prabhaswara, Ilham Yoga Pratama , I Putu Agus Eka Pratama, I Putu Yoga pramesia Putu Adhika Dharmesta Putu Ayulia Setiawati Putu Ratih Wulandari Putu Rheya Ananda Savitri Putu Wira Buana Putu Yudha Yarcana Reyhan Todo Noer Yamin Ridho Hisbi Sulaiman Rusjayanthi, Ni Kadek Dwi Sadhaka, Anak Agung Istri Prabhaisvari Salsabila, Archels Ramadhany Saputra, Putu Alta Sari, Ni Kadek Ratna Sasmita, Gusti Made Arya Satriya, Rizki Dwi Shevira, Sheila Solang, Efraim William Susila, A.A Ngurah Hary Vidya Chandradev Wayan Oger Vihikan Wayan Oger Vihikan, Wayan Oger Wiartha, I Gusti Made Diva Widia Widhiasih, Ni Putu Nirmala Dewi Widiantari, Ni Putu Triska Wiranatha, A.A. Ketut Agung Cahyawan Wiranatha, Anak Agung Ketut Agung Cahyawan Wiranatha, Anak Agung Ketut Cahyawan Wiratama, Bayu Adhya Zebedeus Cheyso