Article Per Year (5 Year)
p-Index From 2020 - 2025
3.816
P-Index
This Author published in this journals
All Journal Buletin Udayana Mengabdi Jurnal BETA (Biosistem dan Teknik Pertanian) Jurnal Keteknikan Pertanian Jurnal Ilmiah Rekayasa Pertanian dan Biosistem Jurnal Abdi Masyarakat Indonesia Journal of Agricultural and Biosystem Engineering Research
I Putu Surya Wirawan
Program Studi Teknik Pertanian Dan Biosistem, Fakultas Teknologi Pertanian, Universitas Udayana, Badung, Bali, Indonesia
Agriculture, Biological Sciences & Forestry Humanities Biochemistry, Genetics & Molecular Biology Control & Systems Engineering Economics, Econometrics & Finance Education Energy Engineering Industrial & Manufacturing Engineering Mechanical Engineering Public Health

Published : 27 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : Journal of Agricultural and Biosystem Engineering Research

 1 
Klasifikasi Kematangan Buah Kelapa Sawit Menggunakan Model Yolov8 Berbasis Deep Learning Muna, Mukhes Sri; Setiyo, Yohanes; Wirawan, I Putu Surya; Syarovy, Muhdan; Jaya, Gigieh Henggar
Journal of Agricultural and Biosystem Engineering Research Vol 6 No 1 (2025): Journal of Agricultural and Biosystem Engineering Research: Regular Issue
Publisher : Program Studi Teknik Pertanian, Fakultas Pertanian, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20884/1.jaber.2025.6.1.15953

Abstract

Determining the ripeness level of oil palm fruit is a crucial aspect in enhancing the efficiency and quality of palm oil production. To date, most ripeness classification processes are still manually conducted, leading to inconsistencies and human error. This study aims to develop an oil palm fruit ripeness classification model using YOLOv8, a state-of-the-art deep learning architecture known for its excellence in computer vision tasks. The dataset consists of six ripeness classes, divided into training, validation, and testing sets sourced from the Roboflow platform. The training process involved five YOLOv8 sub-models with optimized parameter configurations. Evaluation was carried out using MAPE and confidence score metrics to measure prediction accuracy. The results showed that all sub-models successfully classified fruit ripeness with high accuracy, with YOLOv8l-cls achieving the lowest MAPE value of 0.01167. These, confirm that the YOLOv8-based approach is highly effective in supporting automated classification of oil palm fruit ripeness, offering faster, more accurate, and consistent results, and holds strong potential for widespread application in the plantation industry.
Co-Authors Ana, Ni Kadek Tia Putri Angga Mahendra Arta, I Wayan Roli Aviantara, I Gusti Ngurah Apriadi Dinda Mar'atuzzahwa Fhergie Dwi Lestari Matasik Handayani Nofiyanti, Sri Henggar Jaya, Gigieh I Dewa Ketut Sastrawidana I Gede Yoga Juni Sastrawan I Gusti Ketut Arya Arthawan I Gusti Ngurah Apridi Aviantara I Ketut Trisna Adi Putra I Made Anom Sutrisna Wijaya I MADE SUPARTHA UTAMA I MADE SUPARTHA UTAMA I Nengah Suastawa I Putu Ari Susila Aditya I Putu Cahya Windu Adi I Wayan Eko Candra Deva I. A. G. Bintang Madrini Ida Ayu Gede Bintang Madrini Ida Ayu Rina Pratiwi Pudja Joshua Christianto KOMANG AYU NOCIANITRI Luh Gede Gita Gowinda Mulyana Utami Maharani, Ni Putu Dewi Pradnya Maria Wardiani Popi Muhdan Syarovy Muna, Mukhes Sri Ni Luh Yulianti Ni Made Rahayu Chintya Dewi Dewi NIZAR NASRULLAH Pande Ketut Diah Kencana pande ketut diah kencana Pande Putu Raditya Premananda Meranggi Rina Pratiwi Pudja I. A Sihombing, Mistiyeni P Sihombing Situmorang, Rosurya Sumiyati Sumiyati Tarigan, Hardiano Vebiulina Simanjuntak Wayan Tika Yogi, I Putu Karisma Yohanes Setiyo Yosika, Nur Ida Winni Zafansyah, Muhamad Ragil