APA. A. Gede Yudhi Paramartha

A. A. Gede Yudhi Paramartha

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


A. A. Gede Yudhi Paramartha has a total of 27 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    River Area Segmentation Using Sentinel-1 SAR Imagery with Deep-Learning Approach

    by Ni Putu Karisma Dewi, Putu Hendra Suputra, A.A. Gede Yudhi Paramartha, Luh Joni Erawati Dewi, Pariwate Varnakovida, Kadek Yota Ernanda Aryanto

    River segmentation is important in delivering essential information for environmental analytics such as water management, flood/disaster management, observations of climate change, or human activities. Advances in remote-sensing technology have provided more complex features that limit the traditional approaches’ effectiveness. This work uses deep-learning-based models to enhance river extractions from satellite imagery. With Resnet-50 as the backbone network, CNN U-Net and DeepLabv3+ were utilized to perform the river segmentation of the Sentinel-1 C-Band synthetic aperture radar (SAR) imagery. The SAR data was selected due to its capability to capture surface details regardless of weather conditions, with VV+VH band polarizations being employed to improve water surface reflectivity. A total of 1080 images were utilized to train and test the models. The models’ performance was measured using the Dice coefficient. The CNN U-Net architecture achieved an accuracy of 0.94, while DeepLabv3+ attained an accuracy of 0.92. Although DeepLabv3+ showed more stability during the training and performed better on wider rivers, CNN U-Net excelled at identifying narrow rivers. In conclusion, a river-segmentation model was conducted using Sentinel-1 C-Band SAR data, with CNN U-Net outperforming DeepLabv3+; this enabled detailed river mapping for irrigationand flood-monitoring applications – particularly in cloud-prone tropical regions.


  • Open Access

    IMPLEMENTASI GOOGLE DRIVE CLOUD STORAGE PADA SISTEM REPOSITORI AL-DARING

    by Ketut Agus Seputra, A.A. Gede Yudhi Paramartha, I Nyoman Saputra Wahyu Wijaya

    One of the steps of accreditation for institutions and study programs during the epidemic is online assessment (AL-Daring). The availability of suitable information and communication technologies to enable the AL-Daring process is one of the consequences of AL-Daring. Supporting data must be provided in the form of a soft copy in the University Information System that assessors may access appropriately. How the Information System can help Study Program Managers and Accreditation Applicants complete documentation more quickly and efficiently is also crucial. It's also important to note that each Study Program and Study Program Manager will upload a large number of papers of various types and sizes. As a result, various factors that affect the quality of information systems, such as data and storage space availability, ease of access, and timeliness, must be satisfied. The AL-Daring Information System is being developed using agile methodologies in the aim of completing it faster so that it can be utilized right away and adapt to user needs. To perform successfully, this system was built using the Codeigniter framework and Google Drive Cloud Storage as a document storage medium via the Google Drive API service. SUS rates the repository system an excellent score on an adjective rating claiming the system is very useful and well-received by users.


  • Towards Healthcare Data Sharing: An e-Health Integration Effort in Indonesian District

    by Kadek Yota Ernanda Aryanto, Ketut Agus Seputra, I Nyoman Saputra Wahyu Wijaya, I Wavan Abyong, Gede Aditra Pradnyana, A.A. Gede Yudhi Paramartha

    The purpose of this work was to provide an integration scheme of healthcare systems, connecting the public health centres to the general hospital and provide the required data aggregation to entitled government institutions. A middle-ware-based system has been developed using a rapid application development model and tested using several scenarios. The results have shown that the developed system could deliver the expected process while the newly provided executive dashboard system provided insight into the processed data. The developed web services are ready to be used in further data exchanges, but several steps must be ascertained beforehand. Problems, challenges, and opportunities regarding the future of data sharing among institutions in Indonesia were also discussed. The services that have been developed in this work shows a promising implementation of an integrated system, especially in healthcare, as part of the implementation of the broader e-Gov-ernance enactment. The emphasis on the role of patients in the built system becomes an essential key for further development.


  • Open Access

    The Development of search engine service for official academic documents

    by A A G Y Paramartha, L J E Dewi

    Document search engines are necessary in educational institutions, where search engines are expected to find the right document quickly. Academic official documents are generally private so that public search engines such as Google cannot index and search these documents. Therefore, we need a specific search engine developed for educational institutions’ needs, in this case, Universitas Pendidikan Ganesha. This article discussed how to develop an academic official document search engine, starting from data retrieval and extraction, query parser development, and search engine evaluation. The query parser developed utilized the field annotation mapping mechanism and n-gram keyword mapping. The evaluation results showed a significant increase in performance compared to only using Solr’s Standard Query Parser.

  • Open Access

    Comparison of classification model and annotation method for Undiksha’s official documents

    by A A G Y Paramartha, N W Marti, K Y E Aryanto

    Shakuntala is a system that manages official documents and letters at UniversitasPendidikanGanesha. The system stores various documents in PDF format which are categorized by type of document. But Shakuntala can only receive scanned documents, and document categorization were done manually by the operator. Documents uploaded to Shakuntalaalso generally contain information about people who were manually tagged by the operator. This causes inefficiencies that should be carried out automatically by machine. This study aimed at finding the best classification model for determining document categories. In addition, this research also intent to figure out the best method for tagging the people listed on the document. The results of the study showed that the Decision Tree classification model was the best model with an accuracy of 83.06% compared to KNN and Naive Bayes. As for the annotation of the person’s name, the Levenshtein distance method with a similarity threshold of 95% obtained an accuracy of 68.20%.


  • Integration of Region-based Open Data Using Semantic Web

    by A.A.Gede Yudhi Paramartha, Kadek Yota Ernanda Aryanto, Gede Rasben Dantes

    This article discusses about an effort toward open data implementation in Indonesia by using semantic web technology. This proposed open data are classified based on administrative region in Indonesia by integrating various data sources that linked to their administrative region. Data was discovered by implementing web scraper with a certain rule, and the result was mapped into the graph database by utilizing ontology structure that we built. The data can be used by client using SPARQL endpoint that linked to the graph database. The data also can be integrated with other data source by utilizing semantic web technology that has been done by two case studies which are discussed by the end of this article.


  • Open Access

    The effect of problem-based e-learning content on the learning achievement in basic computer system course (DSK) of the student of informatics engineering education department

    by I Gede, Partha Sindu, A A Gede, Yudhi Paramartha

    This study was aimed at finding out the difference in learning achievement in basic computer system course (DSK) between the students who learned from content e-problem-based learning in experiment class and those who learned from conventional model in control class in learning basic computer system course. This study used quasi-experimental non-equivalent Pretest Post-test Control Group Design. There were three variables involved in this study. Two of them were independent variable and dependent variable. The independent variable was e-problem-based learning and the dependent variable was learning achievement. Another variable which functioned as covariate was students’prior learning achievement. The population consisted of all students of the first semester in Informatics Engineering Education Department. The sample was selected by using simple group random sampling technique. An essay test was used to know the students’basic computer system learning achievement (DSK). The hypothesis was tested by one-way analysis of co-variance (ANACOVA). The results showed that the mean score in the learning achievement of the students who learned from content e-problem-based learning was higher than that of those who learned from using conventional model. Content e-problem-based learning plays the role in improving students’ learning achievement.


  • Open Access

    IMPLEMENTASI WEB SERVICE PADA SISTEM PENGINDEKSAN DAN PENCARIAN DOKUMEN TUGAS AKHIR, SKRIPSI, DAN PRAKTIK KERJA LAPANGAN

    by A.A. Gede Yudhi Paramartha, Gusti Ketut Suryaningsih, Kadek Yota Ernanda Aryanto

    Implementasi Web service pada sistem pengindeksan dan pencarian dokumen merupakan sistem yang dikembangkan dengan tujuan untuk menyempurnakan kekurangan yang ada pada sistem pengindeksan dan pencarian dokumen yang telah dikembangkan sebelumnya. Adapun kekurangan yang dimaksud meliputi sistem pengindeksan dan pencarian dokumen tersebut bersifat standalone dimana data yang digunakan masih disediakan dan dikelola pada sistem itu sendiri, hal tersebut tentu membutuhkan waktu yang lama bagi pengembang dalam hal manajemen datanya. Selain itu dalam proses pengindeksan, hasil index yang telah dibuat belum bisa diperbaharui atau dilakukan update index apabila terjadi perubahan maupun penambahan dokumen. Berdasarkan hal tersebut dikembangkan sistem pengindeksan dan pencarian dokumen dengan memanfaatkan layanan penyedia data yang disediakan oleh Web service pada sistem yang berbeda sebagai sumber data yang digunakan dalam proses pengindeksan dan pencarian dokumen, dimana pada proses pengindeksan, hasil index yang telah dibuat dapat dilakukan proses update yang meliputi proses tambah dan hapus dokumen pada file index. Selain tujuan tersebut diatas, pada sistem ini juga diimplementasikan teknologi Web service sebagai penyedia layanan yang dapat digunakan oleh pengembang maupun sistem yang berbeda. Layanan yang disediakan berupa layanan pencarian dokumen tugas akhir, skripsi dan praktik kerja lapangan. dengan parameter sebagai keyword pencarian. Keluaran dari layanan pencarian dokumen berupa dokumen yang sudah diberikan skor serta diurutkan berdasarkan relevansi dokumen dengan parameter inputan.

  • Applying open content concept by synchronizing lecture video and slide

    by A.A. Gede Yudhi Paramartha, I Gede Partha Sindu, Kadek Yota Ernanda Aryanto

    Open content is a concept where the learning content can be shared freely and openly. Video lecture can be used as open content by recording any lecture in the classroom and share them through the learning management system. However, video lectures have some disadvantages, such as (a) the focus of the video cannot cover all objects in the class. (b) one lecture video has a lot of frames so that it is difficult for the students to find the desired sub-topics in the video. This article discusses how to overcome both these problems by combining video and slide into one learning content so that it can cover the weaknesses of learning videos as the main medium of learning. In addition, the developed system also allows users to use them offline so that it can be distributed to anyone who do not have internet access.