Article Per Year (5 Year)
p-Index From 2021 - 2026
3.247
P-Index
This Author published in this journals
All Journal Jurnal Ilmiah Merpati (Menara Penelitian Akademika Teknologi Informasi) Lontar Komputer: Jurnal Ilmiah Teknologi Informasi Majalah Ilmiah Teknologi Elektro Jurnal Sains dan Teknologi Jurnal Buana Informatika Jurnal Teknologi Informasi dan Ilmu Komputer Jurnal Edukasi dan Penelitian Informatika (JEPIN) JUITA : Jurnal Informatika Jurnal Teknologi dan Sistem Komputer Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) JOURNAL OF APPLIED INFORMATICS AND COMPUTING Indonesian Journal of Electrical Engineering and Computer Science Walisongo Journal of Information Technology Jurnal Ilmiah Teknologi dan Komputer (JITTER) Majalah Ilmiah Teknologi Elektro Lontar Komputer: Jurnal Ilmiah Teknologi Informasi
I Putu Agung Bayupati
Program Studi Teknologi Informasi, Fakultas Teknik, Universitas Udayana
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering Energy Engineering

Published : 66 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 66 Documents
Search

 3   4   5   6   7 
Klasifikasi Citra Daging Menggunakan Deep Learning dengan Optimisasi Hard Voting Kade Bramasta Vikana Putra; I Putu Agung Bayupati; Dewa Made Sri Arsa
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 5 No 4 (2021): Agustus 2021
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (616.603 KB) | DOI: 10.29207/resti.v5i4.3247

Abstract

Meat is a staple food for some Indonesian people, apart from the taste, meat also contains vitamins and minerals that are good for the human body, however, not all meat can be consumed by the Indonesian people. the texture and color of beef, pork and mutton have similarities and tend to be similar, therefore a system is needed to recognize the three types of meat. In this study, the authors use various types of Deep Learning architecture such as Resnet-50, VGG-16, VGG-19 and Densenet-121 with Hard Voting to improve the performance of Deep Learning in recognizing the three types of meat. The results show that Resnet-50 with Hard Voting can outperform Deep Learning Resnet-50, VGG-16, VGG-19 and Densenet-121- with f1 score 98.88%, precision 98.89% and recall 98.88%. in image classification of pork, beef and mutton.
Data storage model in low-cost mobile applications I Made Sukarsa; I Kadek Ari Melinia Antara; Putu Wira Buana; I Putu Agung Bayupati; Ni Wayan Wisswani; Dina Wahyuni Puteri
Indonesian Journal of Electrical Engineering and Computer Science Vol 28, No 2: November 2022
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v28.i2.pp1128-1138

Abstract

Mobile applications that have data transactions between users require a database relational database management system (RDBMS) and RESTful API operating on the hosting service so that all users can access the data. Renting a hosting service is not cheap and creating a RESTful API takes plenty of time. As an alternative to hosting, a free version of the Cloud Firestore service gives full access rights to the database and has an application programming interface (API) to manage data or access data. However, the free version of Cloud Firestore has limitations in terms of storage capacity, read, write, and delete processes. Therefore, redesigning process of the database was carried out into a low-cost version of the database model consisting of SQLite database and a low-cost version of the NoSQL database to overcome this problem. The goal is to reduce storage space usage and read, write, and delete processing on Cloud Firestore. The low-cost version of the database was tested with 6,030 data. The results obtained were savings of 47.27% storage usage, 83.08% write usage, 91.26% read process usage, and 83.19% delete process usage compared to the test results of the relational database model.
Rancang Bangun Penyedot Debu Berbasis Internet of Things Ni Luh Ketut Inggitarahayu Anggasemara; I Made Agus Dwi Suarjaya; I Putu Agung Bayupati
Walisongo Journal of Information Technology Vol 5, No 1 (2023)
Publisher : Universitas Islam Negeri Walisongo Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21580/wjit.2023.5.1.16123

Abstract

AbstractThe floor cleaning tools that we usually use, such as a broom or duster, cause dust to fly which can leave dust in the room. The thing that can be done to overcome this problem is to develop a system that can receive a command to clean the dust, either automatically or manually controlled. This tool is made using the Arduino Uno microcontroller with streaming video using the ESP32-CAM, also HC-SR04 Ultrasonic Sensor and Infrared Sensor as obstacle detectors so that the robot can walk on the floor or table. This research was developed using the Prototyping Method starting from the data collection stage to the system testing stage. The data collection technique is by observing and studying the literature. The test results show that the robot is able to vacuum effectively at speeds of 50-100 with an average effectiveness of 98.27% at speeds of 100 and 83.32% at speeds of 60. Sensor testing of the robot's motion in automatic mode has shown suitability, and the robot can move actively for 25 minutes. Keyword : Arduino Uno, Infrared Sensors, Ultrasonic Sensors, Vacuum Cleaner AbstrakAlat pembersih lantai yang biasa kita gunakan seperti sapu atau kemoceng membuat debu berterbangan yang bisa membuat debu masih tertinggal di ruangan. Adapun hal yang dapat dilakukan untuk mengatasi permasalahan tersebut ialah mengembangkan sebuah sistem yang bisa menerima sebuah perintah untuk memberishkan debu, baik dengan cara otomatis maupun dikontrol secara manual. Alat ini dibuat menggunakan mikrokontroler Arduino UNO dengan streaming video menggunakan ESP32-CAM, serta Sensor Ultrasonik HC-SR04 dan Sensor Infrared sebagai pendeteksi halangan agar robot dapat berjalan di lantai maupun meja. Adapun penelitian ini dekembangkan dengan menggunakan Metode Prototyping mulai dari tahap pengumpulan data hingga tahap pengujian sistem. Teknik pengumpulna data yang digunakan yaitu dengan melakukan pengamatan dan studi literatur. Hasil pengujian menunjukkan robot sudah mampu menyedot debu secara efektif pada kecepatan 50-100 dengan efektivitas rata-rata 98,27% pada kecepatan 100 dan 83,32% pada kecepatan 60. Pengujian sensor terhadap gerakan robot pada mode otomatis sudah menunjukkan kesesuaian, serta robot dapat bergerak secara aktif selama 25 menit.  Kata Kunci : Arduino Uno, Penyedot Debu, Sensor Infrared, Sensor Ultrasonik
Design and Development of an Internet of Things Based Package Reception Box System Eva Martina Sitorus; I Made Agus Dwi Suarjaya; I Putu Agung Bayupati
Jurnal Ilmiah Merpati (Menara Penelitian Akademika Teknologi Informasi) Vol 11 No 2 (2023): Vol. 11, No. 2, August 2023
Publisher : Lembaga Penelitian dan Pengabdian kepada Masyarakat Universitas Udayana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JIM.2023.v11.i02.p02

Abstract

Parkage delivery services play a crucial role in facilitating the easy and prompt sending and receiving of goods to the public. The package delivery sector has witnessed significant growth of 33.62% since the outbreak of the Covid-19 pandemic. However, package receipt often presents challenges, including instances of damaged or lost packages. To address these issues, a system for package reception was designed and developed utilizing the Internet of Things (IoT) technology. The system operates by incorporating a UART GM66 Barcode Scanner, ESP-32CAM, Solenoid Door Lock, and Motor Stepper Nema 17. The primary objective of this research is to construct an automated package-reception system that can be controlled securely through a smartphone, thus ensuring protection against theft and package damage. System testing was performed on the functionality of the tool and communication with the telegram bot.
Analisis Sentimen Review Hotel Menggunakan Metode Deep Learning BERT Vidya Chandradev; I Made Agus Dwi Suarjaya; I Putu Agung Bayupati
Jurnal Buana Informatika Vol. 14 No. 02 (2023): Jurnal Buana Informatika, Volume 14, Nomor 2, Oktober 2023
Publisher : Universitas Atma Jaya Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24002/jbi.v14i02.7244

Abstract

Pandemi COVID-19 telah menyebabkan penurunan kunjungan pariwisata dan okupansi hotel. Penting bagi pengusaha hotel untuk memantau gaya hidup pengunjung guna menjaga kelangsungan bisnis. Salah satu cara untuk melakukannya adalah dengan memahami sentimen pengunjung hotel melalui analisis review agar mendapatkan pemahaman yang lebih baik dalam pengambilan keputusan terkait layanan dan aspek bisnis di sektor perhotelan. Penelitian ini menerapkan model deep learning natural language processing BERT untuk menganalisis sentimen positif dan negatif dari review pengunjung hotel di Indonesia. Model BERT yang digunakan telah menjalani proses pretrained dan diterapkan metode fine-tuning untuk menghasilkan analisis sentimen yang akurat. Hasil evaluasi menunjukkan bahwa model fine-tuning SmallBERT yang dilatih menggunakan dataset 515k review hotel selama 5 epoch memberikan performa yang baik. Model SmallBERT mencapai akurasi sebesar 91,40%, presisi 90,51%, recall 90,51%, dan skor f1 90,51% saat dievaluasi dengan dataset yang diberi label secara manual. Visualisasi hasil perbandingan sentimen yang didominasi oleh sentimen positif, dilakukan menggunakan Tableau
Associative Classification with Classification Based Association (CBA) Algorithm on Transaction Data with Rshiny Alesia Arum Frederika; I Putu Agung Bayupati; Wira Buana
Lontar Komputer : Jurnal Ilmiah Teknologi Informasi Vol 14 No 1 (2023): Vol. 14, No. 1 April 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.i01.p03

Abstract

Data mining can be used for businesses with large amounts of data. One of the data mining techniques is Associative Classification. It is a new strategy in data processing that combines association and classification techniques to build a classification model. This research used an associative classification technique on sales transaction data of Frozen Food Stores, which had sales transaction data on their business activities. It would be used in sales strategies to find items often purchased by class customers, namely, members and general. This research aimed to classify based on association rules using the CBA (Classification based Association) algorithm on sales transaction data. The application used the R programming language that business owners could use. The results of the rules obtained from the trial had the value of support, confidence, coverage, and lift ratio, which were the best value levels of a rule. The results of the rules that had the highest lift ratio value from all the data that have been inputted can be used as a reference to be implemented in sales strategies in knowing consumer needs.
Prediksi Curah Hujan Dasarian dengan Metode Vanilla RNN dan LSTM untuk Menentukan Awal Musim Hujan dan Kemarau Ni Made Meriliana Candra Devi; I Putu Agung Bayupati; Ni Kadek Ayu Wirdiani
JEPIN (Jurnal Edukasi dan Penelitian Informatika) Vol 8, No 3 (2022): Volume 8 No 3
Publisher : Program Studi Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26418/jp.v8i3.56606

Abstract

Indonesia dijuluki sebagai negara agraris dimana perekonomian nasional bergantung pada sektor pertanian. Kualitas pertanian sangat dipengaruhi oleh perubahan iklim. BMKG memperkirakan datangnya musim di Indonesia didasari pada curah hujan dasarian. Curah hujan dasarian merupakan total curah hujan selama sepuluh hari. Curah hujan dasarian diatas 50 mm berturut-turut dalam tiga dasarian maka dasarian pertama akan ditentukan sebagai awal musim hujan. Sedangkan curah hujan dasarian dibawah 50 mm dalam tiga dasarian berturut-turut maka dasarian pertama akan ditentukan sebagai awal musim kemarau. Penelitian ini bertujuan untuk melakukan prediksi curah hujan dasarian untuk menentukan awal musim hujan dan musim kemarau. Metode Vanilla Recurrent Neural Network (Vanilla RNN) dan Long Short-Term Memory (LSTM) merupakan jenis dari jaringan saraf berulang yang baik digunakan dalam pemrosesan data sekuensial. Seleksi fitur (feature selection) dengan metode Backward Elimination dilakukan untuk meningkatkan akurasi dari prediksi. Fitur yang digunakan untuk prediksi curah hujan dasarian yaitu kecepatan angin, suhu udara, kelembaban udara, jarak pandang, dan tekanan udara. Adapun fitur hasil seleksi yaitu kelembaban, tekanan, dan jarak pandang. Hasil penelitian yang diperoleh yaitu metode Vanilla RNN dengan seleksi fitur memperoleh hasil terbaik dengan nilai R-Squared sebesar 0,6139 dan RMSE sebesar 28,4308. 
Segmentasi Buah Apel Menggunakan Framework YOLACT Arsitektur Resnet-101 gunawan, i kadek; Bayupati, I Putu Agung; Wibawa, Kadek Suar
JITTER : Jurnal Ilmiah Teknologi dan Komputer Vol 1 No 2 (2020): JITTER, Vol.1, No.2, December 2020
Publisher : Program Studi Teknologi Informasi, Fakultas Teknik, Universitas Udayana

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (551.184 KB) | DOI: 10.24843/jitter.v1i2.69675

Abstract

Apel merupakan salah satu buah yang populer di dunia. Apel pertama kali tumbuh di Kawasan Asia tengah kemudian berkembang luas ke wilayah yang lebih dingin. Apel dapat diolah menjadi minuman kemasan. Produksi pengolahan apel, dibutuhkan proses untuk memilah apel baik berdasarkan kematangan, kondisi buah, ataupun ukuran buah apel sesuai dengan kebutuhan. Pada produksi skala besar hal ini menjadi tantangan karena membutuhkan tenaga kerja yang tidak sedikit. Penelitian ini mengusulkan sistem segmentasi buah apel dengan menggunakan Framework YOLACT dengan arsitektur Resnet-101 yang merupakan salah satu arsitektur Convolutional Neural Network. Sistem yang dibuat diharapkan mempermudah pemilahan ataupun penghitungan apel pada manufaktur skala besar. Proses segmentasi menggunakan YOLACT teridiri dari Feature backbone, Feature Pyramid Network, Protonet, Prediction Head, NMS, cropping dan thresholding. Tiga jenis apel digunakan dalam penelitian ini yaitu Fuji, Red Delicious, dan Gala Apple. mAP rata rata tertinggi diperoleh dengan model YOLACT iterasi 10000, yaitu sebesar 83,12%
Perancangan Enterprise Architecture Menggunakan TOGAF Architecture Development Method pada Kantor Pertanahan Nasional Kabupaten Badung Yustisia, Putu Visvani; Bayupati, I Putu Agung; Susila, Anak Agung Ngurah Hary
JITTER : Jurnal Ilmiah Teknologi dan Komputer Vol 3 No 1 (2022): JITTER, Vol.3, No.1, April 2022
Publisher : Program Studi Teknologi Informasi, Fakultas Teknik, Universitas Udayana

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (641.304 KB) | DOI: 10.24843/JTRTI.2022.v03.i01.p12

Abstract

Rancangan enterprises architectures dilaksanakan dalam peningkatan kegiatan operasi serta layanan dari institusi pemerintah kemudian membuat keselarasan dari informas serta bisnis. BPN Kabupaten Badung memiliki wewenang melakukan aktivitas di sector urusan tanah. Audit memperdayakan TOGAF ADM bisa mempermudah untuk penemuan masalah dan penyelesaiannya. Studi memiliki tujuaan dalam membuat rancangan enterprises architectures di sistematik informasi serta layanan publik dengan kerangka TOGAF ADM. Hasil dalam bentuk cetak biru enterprises architectures layanan pertanahan BPN Badung, menambahkan aplikasi Pelayanan Pertanahan serta Pengaduan Masyarakat dalam menyokokong aktivitas kerja di BPN Badung.
Business Process Re-engineering and ERP System Implementation in Design Company Bimantara, Ranggashakti; Bayupati, I Putu Agung; Rusjayanthi, Ni Kadek Dwi
JITTER : Jurnal Ilmiah Teknologi dan Komputer Vol 3 No 1 (2022): JITTER, Vol.3, No.1, April 2022
Publisher : Program Studi Teknologi Informasi, Fakultas Teknik, Universitas Udayana

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (528.415 KB) | DOI: 10.24843/JTRTI.2022.v03.i01.p27

Abstract

Data and information integration has an essential role in a business that every business actor needs to compete in the digitalization era. CV. Triloka is a company in design and development services that are currently proliferating but does not yet have a capable and integrated system. The company's operational activities are still carried out manually without using an integrated system which causes a decrease in work performance due to inefficient. Based on these problems, improvements were made to business processes from analysis to implementation by utilizing the Odoo system to produce best practice business processes following Enterprise Resource Planning (ERP). The research results are in the form of analysis of existing business processes, new business processes, implementation of Odoo modules, and results of system implementation questionnaires
Co-Authors Adie Wahyudi Oktavia Gama Aditya, I Nyoman Tri Agus Gede Adi Prayoga Akane Sasaoka Alesia Arum Frederika Anak Agung Ketut Agung Cahyawan Wiranatha Anak Agung Kompiang Oka Sudana Arsa, Dewa Made Sri Audrey Tilanov Pramasa Ayu Wirdiani Bimantara, Ranggashakti Christine Regilia Suwu Deria Dwi Antari Desak Ayu Sista Dewi Desy Purnami Singgih Putri Dewi, Anak Agung Ayu Sintya Dina Wahyuni Puteri Dwi Rusjayanthi, Dwi Dwi Suarjaya, I Made Agus Ekanyana Nugraha, I Gede Bagus Erha Syaifuddin Hassant’R Eva Martina Sitorus Frederika, Alesia Arum G M Arya Sasmita Gede Indra Raditya Martha Gunawan, I Kadek Gusti Agung Ayu Putri I Dewa Nym. Nurweda P., I G A A Diah Indrayani I Gede Sujana Eka Putra, I Gede Sujana Eka I Gusti Ayu Agung Diatri Indradewi I Gusti Lanang Trisna Sumantara I Kadek Ari Melinia Antara I Kadek Gunawan I Ketut Adi Purnawan I ketut Gede Darma Putra I Made Agus Dwi Suarjaya I Made Budi Adnyana I Made Mertha Prayuda I Made Sukarsa I Made Suryanata I Made Suwija Putra I Nyoman Piarsa I Putu Ade Ambara Putra I Putu Arya Dharmaadi I Putu Bayu Krisnawan I Putu Cahya Prawira I Putu Pratama Andika I Putu Yudha Ariatmaja I Wayan Agus Krisna Apriana I Wayan Agus Surya Darma I Wayan Andis Indrawan I Wayan Dharma Satriawan I Wayan Widiana Ida Ayu Putu Febri Imawati Imelda Alvionita Tarigan Kade Bramasta Vikana Putra Kadek Suar Wibawa Komang Gede Kurniadi Kurniawan, Laurensius Adi Laurensius Adi Kurniawan Made Sudarma Made Wibawa Minho Jo Nandita, Ida Ayu Widya Ni Kadek Ariasih, Ni Kadek Ni Kadek Ayu Anggraeni Ni Kadek Ayu Wirdiani Ni Kadek Rahayu Widya Utami Ni Luh Ketut Inggitarahayu Anggasemara Ni Made Meriliana Candra Devi Ni Putu Sutramiani Ni Wayan Wisswani Nyoman Purnama, Nyoman Philipus Novenando M Weking Putu Ary Setiyawan Putu Satya Saputra Putu Wira Buana Putu Wulan Dewi Prihandani Putu Yudha Yarcana Putut Rendra Wismawan Rusjayanthi, Ni Kadek Dwi Saputra, I Made Ari Saragih, Evan Himawan Susila, Anak Agung Ngurah Hary Vidya Chandradev Wira Buana Y. Haryo Sulistyanto Sunaryo Yonatan Adiwinata Yustisia, Putu Visvani