Claim Missing Document
Check
Articles

Sistem Informasi Manajemen Kependudukan Desa Adat di Bali Sudana, Anak Agung Kompiang Oka; Purnawan, Abdi; Putra, I Ketut Gede Darma; Wirdiani, Ni Kadek Ayu
JST (Jurnal Sains dan Teknologi) Vol. 12 No. 2 (2023): July
Publisher : Universitas Pendidikan Ganesha

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23887/jstundiksha.v12i2.52227

Abstract

Proses pendataan kependudukan di Desa Adat masih dilakukan secara manual sehingga rentan terjadi kesalahan dalam pencatatan data. Permasalahan ini mendorong untuk mengembangkan sistem informasi yang dapat membantu pihak Desa Adat sehingga mempermudah pihak Desa Adat dalam melakukan pendataan kependudukan di lingkungannya serta terintegrasi antara satu Desa Adat dengan Desa Adat lain. Tujuan dari penelitian ini adalah untuk menciptakan sistem informasi manajemen kependudukan desa adat terintegrasi berbasis web. Pengumpulan data pada penelitian ini dilakukan dengan studi literatur beserta wawancara langsung dengan beberapa Prajuru Banjar  Adat dan/atau Prajuru Desa Adat di Bali serta Dinas Pemajuan Masyarakat Adat. Hasil dari proses studi literatur beserta wawancara tersebut diterjemahkan kedalam desain sistem, yaitu gambaran umum sistem, diagram konteks, data flow diagram, dan desain basis data. Penelitian ini dilakukan dengan menggunakan Metode SDLC (Software Development Life Cycle) Model Waterfall dan dikembangkan menggunakan Bahasa pemrograman PHP, dengan Kerangka Kerja Laravel, dan Basis Data MySQL. Hasil dari penelitian ini yaitu sebuah sistem informasi yang membantu manajemen kependudukan Desa Adat yang telah diuji dengan menggunakan Metode Black Box dan Post-Study System Usability Questionnaire (PSSUQ) dan mendapatkan nilai yang baik dibandingkan dengan norma penilaian pada Metode PSSUQ. Sehingga sistem dikategorikan mampu membantu proses pengelolaan data penduduk pada Desa Adat.
Comparing Data Preprocessing Strategy on T5 Architecture to Classify ICD-10 Diagnosis Lanang Wijayakusuma, I Gusti Ngurah; Sudarma, Made; Darma Putra, I Ketut Gede; Sudana, Oka; Astutik, Dian
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 9 No 5 (2025): October 2025
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v9i5.6919

Abstract

Manual ICD-10 coding in healthcare systems remains time-consuming, error-prone, and inefficient, particularly in resource-constrained settings. This study investigates the effect of various preprocessing strategies on the performance of the Text-to-Text Transfer Transformer (T5) model for primary diagnosis classification using structured clinical data. A total of 7,263 clinical records were collected from two high-density regions in Bali (Badung and Gianyar) between January 2023 and March 2024, then converted into descriptive text prompts for model training. Four experimental scenarios combined variations of input features and label configurations, comparing T5 with Oversampling against T5 with Easy Data Augmentation (EDA) plus Oversampling. Results showed that T5 with Random Oversampling consistently outperformed the EDA-based configuration across all scenarios, with performance gaps ranging from 8% to 19%. Scenario 4, which excluded body system features and the semantically overlapping E860 label, achieved the highest balance, reaching 84.7% accuracy, 85.1% precision, 84.7% recall, and 84.3% F1-score. Conversely, the EDA-based approach reduced training time by up to 72%, indicating a clear trade-off between performance and efficiency. Both configurations frequently misclassified semantically similar codes within the same ICD-10 categories, underscoring the difficulty of distinguishing clinically related diagnoses. Overall, the results suggest that careful selection of preprocessing strategies can enhance transformer-based medical text classification, while striking a balance between model performance and training efficiency. This work may serve as an initial reference for developing more efficient semi-automated medical coding systems in the Indonesian regional healthcare context.
Rancang Bangun Sistem Informasi Rumah Tradisional Bali Berdasarkan Asta Kosala-Kosali Berbasis Web Sudana, Oka; Suryadana, Agus; Bayupati, Agung
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 7 No 5: Oktober 2020
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jtiik.2020711787

Abstract

Rumah tradisional Bali adalah bangunan yang memiliki ciri khas khusus yang difungsikan sebagai hunian yang merupakan salah satu cerminan kebudayaan yang tumbuh dan berkembang di Bali. Panduan pembangunan Rumah Tradisional Bali tertuang dalam Lontar Asta Kosala-Kosali dan Asta Bumi. Modernisasi berdampak dalam perubahan bentuk dan kebutuhan bangunan perumahan yang mengakibatkan penerapan Arsitektur Tradisional Bali semakin berkurang dan tidak memperhatikan nilai filosofis yang seharusnya, sehingga dikembangkan sistem informasi sebagai media pengenalan dan panduan penerapan Arsitektur Tradisional Bali. Sistem yang dikembangkan disesuaikan dengan konsep Asta Kosala-Kosali dan Asta Bumi. Sistem Informasi Rumah Tradisional Bali menyajikan berbagai macam informasi dan fitur mengenai penerapan Asta Kosala-Kosali dan Asta Bumi dalam Rumah Tradisional Bali yang dihadirkan dalam bentuk pemodelan 2 dimensi dan 3 dimensi. Sistem dapat memudahkan dalam pemahaman filosofi, aturan, tata cara, tata letak, dan tata bangunan Rumah Tradisional Bali serta mampu menjadi media pelestarian warisan budaya Bali khususnya dibidang arsitektur. Persentase tingkat kepuasan pengguna terhadap sistem rata-rata sebesar 87.24%.AbstractA traditional Balinese house is a building that has special characteristics that function as a residence which is a reflection of the culture that grew and developed in Bali. Guide to building Balinese Traditional Houses contained in Lontar Asta Kosala-Kosali and Asta Bumi. Modernization has an impact on changes in the shape and needs of residential buildings which have resulted in the application of Balinese Traditional Architecture diminishing and not paying attention to philosophical values that should be, so that information systems are developed as a medium of introduction and guidance on the application of Balinese Traditional Architecture. The system developed was adapted to the concept of Asta Kosala-Kosali and Asta Bumi. The Traditional Balinese House Information System presents various kinds of information and features regarding the application of Asta Kosala-Kosali and Asta Bumi in Balinese Traditional Houses which are presented in the form of 2-dimensional and 3-dimensional modeling. The system is expected to facilitate the understanding of the philosophy, rules, procedures, layout, and structure of traditional Balinese Houses as well as being able to become a medium for preserving the Balinese cultural heritage, especially in the field of architecture. Percentage of satisfaction level of users of the system by an average of 87.24%.
E-Dharmagita Learning Model Innovation with Mobile and Multimedia Technology Sudana, Oka; Sukma, Kd. Vigyan Melati; Wirdiani, Ayu; Putri, Gusti Agung Ayu
Scientific Journal of Informatics Vol 11, No 1 (2024): February 2024
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v11i1.46653

Abstract

Purpose: Yadnya ceremony is a sacred sacrifice performed with sincere and wholehearted devotion by Hindus to God, spiritual leaders or teachers, fellow humans, the ancestors, and Bhuta_Kala. The implementation of the Yadnya ceremony is_usually accompanied by a spiritual chant of the Hindus known as Dharmagita. Nowadays, a lot of young generations do not know and are even more indifferent to the Dharmagita. Using books as a source of Dharmagita information is less attractive since there are no audio examples or recordings of correct songs that can be listened to. The Android-based e-Dharmagita application was built to overcome these problems to facilitate the younger generation in getting more interesting information about Dharmagita.Methods: e-Dharmagita was constructed with the support of mobile and multimedia technology. In addition, the information presented was related to the Yadnya Ceremony by implementing a complex Tree Algorithm.Results: This research produced an e-Dharmagita Application, of which user acceptance testing using the PSSUQ Method resulted in a score incudes in the excellent category. Therefore, the application could be accepted well in the implementation the Information Technology in Balinese Culture and Hinduism, especially the innovation of a more modern and attractive Dharmagita learning model.Novelty: The Dharmagita learning model using a mobile application is a new model that has not existed before.
Integrated Information System Smart E: Hospital the Innovation and Improvement of the Services and Management Hospital Oka Sudana; Dewa Made Sri Arsa; R. Arif Yudarmawan; I.D.A. Manik Mas Astawastini
Lontar Komputer : Jurnal Ilmiah Teknologi Informasi Vol. 14 No. 03 (2023): Vol. 14, No. 03 December 2023
Publisher : Institute for Research and Community Services, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/LKJITI.2023.v14.i03.p01

Abstract

The use of technology can transform conventional systems into electronic-based systems. Electronic systems have been widely used in governance, organizations, and companies where administration is carried out electronically (e-Government). Hospitals usually already have systems in place, but they are not yet integrated, including integration with BPJS Services, EClaim, and the SATUSEHAT Platform, a new policy from the Ministry of Health Republic of Indonesia starting July 2022. BPJS integration includes diagnosis standards guided by Minister of Health Regulation No. 76 of 2016 concerning INA-CBGs Technical Guidelines, funds application to BPJS, cost proportions, and medical personnel fees. Another service at the Teaching Hospital is the management of Education for Professional Doctors (Co-ass) and Specialists (Residents). Another service at the Teaching Hospital is the management of Education for Professional Doctors (Co-ass) and Specialists (Residents). The solution provided is to create E-Hospital. It is an integrated hospital management information system with an SSO Model and Multi-Channel Access Technology for notification. This system consists of Front Office Modules, including Admission Queues, Medical Services, Pharmacy, Employment, Payroll and Medical Personnel Fees, Automatic integration with BPJS, EClaim, SATUSEHAT, Finance, and Warehouse and Equipment.
Game Recommendation System Using Transformer with Remastered Feature Putra, I Made Suwija; Arturito, Made Jiyestha; Sudana, Anak Agung Kompiang Oka; Dewi, Ni Wayan Emmy Rosiana
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol. 11 No. 4 (2025): December
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/jiteki.v11i4.31345

Abstract

The rapidly growing game industry makes it difficult for players to find games that match their preferences. Conventional recommendation methods are often unsatisfactory due to a lack of personalization. This study aims to design and build a web-based game recommendation system using the content-based filtering method by leveraging a fine-tuned Transformer embedding model, all-MPNet-base-v2, to deeply analyze the textual content of games. The research methodology included data collection from the Steam API (43,900 games), text preprocessing with TF-IDF for keyword extraction, and significantly, fine-tuning the all-MPNet-base-v2 model using the Knowledge Distillation method with jina-embedding-v3 as the teacher model. A novel game series identification feature using fuzzy string matching was also implemented. The resulting embedding vectors were indexed using LanceDB and deployed in a Flask web application. The research contributions are the successful domain-specific adaptation of MPNet via Knowledge Distillation and the implementation of the series identification feature. Quantitative evaluation demonstrated the fine-tuned model's superiority, achieving substantial improvements over the baseline in MRR@10 (0.5857), MAP@10 (0.5149), and Hit Rate@3 (0.90). User Acceptance Testing (UAT) with 15 respondents showed high acceptance (92.89%). Limitations include the Steam-only dataset, potential information loss from TF-IDF, and the small UAT sample size. This study confirms that fine-tuned Transformer embeddings within a content-based framework, enhanced by Knowledge Distillation, can produce effective, accurate, and well-received game recommendations, further improved by context-aware features like series identification.
Fine-tuned LayoutLMv3 for Indonesian receipts extraction Sudana, Oka; Wirdiani, Ayu; Winama Putra, Andre Dwi
Bulletin of Electrical Engineering and Informatics Vol 15, No 2: April 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v15i2.10127

Abstract

Shopping is a transaction that generates a record as a payment receipt. Typically, a receipt is given as a small piece of paper that can be easily lost. It is essential to store the transaction information in the receipt digitally. Keeping the information in a digital form will make it easily accessible and will overcome the problem of easily lost receipts. Currently, the process of transferring receipt information into digital form is still being done manually. Having a system that can extract this information helps speed up the digitalization process tremendously. This research proposes a method that applies finetuning to the LayoutLMv3 model and with the help of optical character recognition (OCR) from Google Vision, can be used to extract transaction information contained in the receipt. The system works by using Google Vision to parse and segment every word contained within the receipt and its bounding box The LayoutLMv3 model will then assign labels to each word, and important words will be extracted. The finetuned LayoutLMv3 model successfully achieved an accuracy of 97.98% on training data and 90% accuracy on real-time test scenarios for extracting information on receipts written in the Indonesian.
Design and Development of a Web-Based Information System for Sapta Kanda Ramayana Using the Laravel Framework Arnawa, I Putu Riko Putra; Sudana, Anak Agung Kompiang Oka; Putra, Yogiswara Dharma
Decode: Jurnal Pendidikan Teknologi Informasi Vol. 6 No. 1: MARET 2026
Publisher : Program Studi Pendidikan Teknologi Infromasi UMK

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51454/decode.v6i1.1631

Abstract

The Ramayana is a story written by Rsi Valmiki that consists of seven parts called Sapta Kanda. The Ramayana is a cultural heritage rich in knowledge, but faces accessibility challenges in the modern era. This study contributes a novel web-based platform specifically designed to digitize and disseminate the Sapta Kanda Ramayana, integrating bilingual content (Old Javanese and Indonesian) with multi-role user interaction—an approach not found in prior cultural information systems. This development aims to design a website-based information system that can present the Sapta Kanda Ramayana story through a digital and interactive platform. The Laravel framework makes the system development process more structured and efficient. The system development uses the waterfall method, which goes through a series of processes such asnalysis, design, implementation, and testing, so that the system development process runs smoothly. The resulting system includes features for managing Sapta Kanda content, Ramayana characters, and user-contributed content. System testing uses the black box testing method to test system functionality and usability testing with the System Usability Scale (SUS) method to determine user satisfaction levels. The results of the system testing showed that the functionality of the features in the system worked well through black box testing and obtained a score of 85.4 from 21 respondents through testing using the SUS method, which indicates that the developed system is well accepted by users. This study is limited to web-based access and does not yet cover mobile application deployment or offline accessibility.
Strategi Penyetelan Hyperparameter untuk YOLOv8n dalam Pemantauan Lalu Lintas Pasca-Kecelakaan Real-Time I Nyoman Eddy Indrayana; Made Sudarma; I Ketut Gede Darma Putra; Anak Agung Kompiang Oka Sudana
Jurnal Teknologi Informasi dan Pendidikan Vol. 19 No. 2 (2026): Jurnal Teknologi Informasi dan Pendidikan
Publisher : Universitas Negeri Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24036/jtip.v19i2.1132

Abstract

Traffic accidents continue to provide a considerable difficulty in contemporary transportation systems, frequently leading to vehicle damage and heightened risks for pedestrians on streets. Precise and instantaneous identification of post-accident scenarios is thus crucial for facilitating swift response and sophisticated traffic management. This research introduces a streamlined object detection methodology utilizing YOLOv8n to recognize six essential traffic-related categories: bus, automobile, damaged vehicle, motorbike, pedestrian, and truck. The main aim is to examine the impact of hyperparameter modification on detection efficacy, specifically in recognizing damaged automobiles as signs of post-accident situations. Twelve model configurations were created by systematically altering three hyperparameters: learning rate (0.01, 0.001, and 0.0001), batch size (32 and 64), and optimizer type (Adam and MuSGD). All models underwent training for 200 epochs with a dataset derived from actual traffic situations, augmented by techniques such as grayscale transformation, blurring, and rotation. The performance evaluation utilized precision, recall, F1-score, mAP50, and mAP50:95. The findings indicate that hyperparameter selection substantially influences convergence stability and detection accuracy. The optimal model attained a mAP50 of 0.905 and a mAP50:95 of 0.751, utilizing a learning rate of 0.01, a batch size of 64, and the Adam optimizer. Moreover, substantial items like cars, buses, and trucks were identified with high precision, whereas damaged vehicles and pedestrians necessitated more meticulous calibration due to increased visual variability.The findings indicate that optimized lightweight models can attain competitive performance, rendering them appropriate for real-time intelligent traffic monitoring applications.
Co-Authors A. A. Raka Onny Diar Danur C. A.A Primaningrat Gita Puspita A.A. Gede Brampramana Putra A.A. Ketut Agung Cahyawan W AA.Kt.Agung Cahyawan Wiranatha Adi, Ngurah Adityaksa, I Gede Made Abhi Agung Jodi Pratama Agus Ghana Putra Partama Akane Sasaoka Anak Agung Ketut Agung Cahyawan Wiranatha Ananda Paramartha Angga Kusuma, Angga Anjela Faye M. Basco Arnawa, I Putu Riko Putra Arsa, Dewa Made Sri Arturito, Made Jiyestha Astutik, Dian Awen Hariwijaya Ayu Wirdiani Ayu Wirdiani Bagus Yudistira Bayupati, Agung Daniel Hadi Darma Putra Desy Purnami S.P Dewa Made Wiharta Dewi, Ida Ayu Pradita Dewi, Ni Wayan Emmy Rosiana Dharma Dyatmika Dwi Putra Githa Dwi Rusjayanthi, Dwi Erna Yulianti Gusti Agung A. Putri Gusti Agung Ayu Putri I Dewa Nym. Nurweda P., I Gede Totok Suryawan I Ketut Adi Purnawan I Ketut Gede Darma Putra I ketut Gede Darma Putra I Made Sukarsa I Made Sunia Raharja, I Made Sunia I Made Suwija Putra I Made Wahyu Saputra I Nyoman Artha Wijaya I Nyoman Eddy Indrayana I Nyoman Piarsa I Pt. Pradnya Pratisditha Ning Parwa I Putu Agung Bayupati I Putu Arya Dharmaadi I Putu Arya Dharmadi I Putu Putra Diyastama I Putu Sura Sanjaya I Wayan Gunaya I. A. K. Sita Laksmita I.D.A. Manik Mas Astawastini I.W. Wahyu Ivan M.J Ida Ayu Wahyu Kumara Putri Ida Bagus Brama Barnawa Irwansyah Cahya Irwansyah Cahya Adha L Kadek Bagus Budi Sasmara Kadek Suar Wibawa Ketut Nila Arta Kevin Wijaya Krisna Cahaya Putra I Putu Krissna Bayu Kusuma Putra, I Gede Angga Lennia Savitri Azzahra Lofiana Made Praditha Gutama Made Sudarma Made Sudarma Made Sukarsa Mahardhika Tirta Mahardika, Oka Minho Jo Ni Kadek Ary Indah Suryani Ni Kadek Giofanni Chandra Devi Ni Kadek Riska Sadini Ni Komang Surya Cahyani Putri Ni Made Ika Marini Mandenni Ni Putu Ratna Gangga Dewi Ni Putu Sutramiani Ni Putu Utari Dyani Laksmi Paramartha, Ary Pratama, I Putu Adi Merta Pratiwi, Putu Ayu Citra Primanggara Gamaswara Purba, Maria Br Purnawan, Abdi Putra, I Made Suwija Putra, Yogiswara Dharma Putu Anantha Prasetya Yogantara Putu Wira Buana R. Arif Yudarmawan Raharja, Sunia Rahayu Widasari, Made Bandem Yosita Rukmi Sari Hartati Rusjayanthi, Ni Kadek Dwi Shilta Inda Qurroti A'yun Achmadi Sukma, Kd. Vigyan Melati Suryadana, Agus Taradhita, Dewa Ayu Nadia Wahyu Hardinugraha Wayan Galih Pratama Wijayakusuma, I Gusti Ngurah Lanang Winama Putra, Andre Dwi Wiranatha, Agung Agung Ketut Cahyawan Yonatan Adiwinata