1Jurusan Teknik Elektro, Universitas Borneo Tarakan, Jl. Amal Lama No.1 Tarakan, Indonesia 77123, Indonesia
2Program Studi Teknik Elektro, Fakultas Teknik, Universitas Borneo Tarakan, Tarakan, Indonesia 77123, Indonesia
BibTex Citation Data :
@article{JTSISKOM14529, author = {Sumardi Sumardi and Syahfrizal Tahcfulloh}, title = {Metode k-means clustering dan morfologi berbasis computer vision dan analisis regresi untuk aplikasi sistem grading udang Vaname}, journal = {Jurnal Teknologi dan Sistem Komputer}, volume = {11}, number = {1}, year = {2024}, keywords = {analisa regresi;k-means clustering;morfologi;sistem grading udang}, abstract = {Penentuan mutu udang secara konvensional menggunakan visual mata memiliki beberapa kelemahan, salah satunya adalah tingkat persepsi manusia yang berbeda-beda. Solusi yang ditawarkan adalah menggunakan teknologi computer vision dalam menentukan ukuran udang berdasarkan citra yang ditangkap kamera. Penelitian ini bertujuan untuk menerapkan kombinasi metode dari pengelompokan k-rata-rata dan morfologi untuk menentukan ukuran udang Vaname yaitu berdasarkan perbandingan area dalam dimensi piksel dari hasil olah citra dengan teknologi computer vision terhadap massa dalam dimensi gram. Analisis regresi digunakan untuk mendapatkan persamaan yang mengkonversi antar nilai piksel tersebut ke dalam massa udang. Keefektifan kombinasi metode ini dibandingkan dengan hanya menggunakan metode pengelompokkan k-rata-rata dan nilai ambang. Hasil evaluasi dari metode yang diusulkan menunjukkan bahwa nilai RMSE yang diperoleh sebesar 0,68 yang lebih baik dari dua metode terdahulu berturut-turut adalah 0,73 dan 2,89. Sementara akurasi sistemnya untuk pengukuran massa diperoleh sebesar 93,64%, akurasi ukuran/besar sebesar 93,37% dan akurasi klaster dari ukuran sebesar 95,45%.}, issn = {2338-0403}, doi = {10.14710/jtsiskom.2023.14529}, url = {https://jtsiskom.undip.ac.id/article/view/14529} }
Refworks Citation Data :
Note: This article has supplementary file(s).
Article Metrics:
Last update:
Last update: 2024-11-20 03:30:46
Starting from 2021, the author(s) whose article is published in the JTSiskom journal attain the copyright for their article and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. By submitting the manuscript to JTSiskom, the author(s) agree with this policy. No special document approval is required.
The author(s) guarantee that:
The author(s) retain all rights to the published work, such as (but not limited to) the following rights:
Suppose the article was prepared jointly by more than one author. Each author submitting the manuscript warrants that all co-authors have given their permission to agree to copyright and license notices (agreements) on their behalf and notify co-authors of the terms of this policy. JTSiskom will not be held responsible for anything arising because of the writer's internal dispute. JTSiskom will only communicate with correspondence authors.
Authors should also understand that their articles (and any additional files, including data sets and analysis/computation data) will become publicly available once published. The license of published articles (and additional data) will be governed by a Creative Commons Attribution-ShareAlike 4.0 International License. JTSiskom allows users to copy, distribute, display and perform work under license. Users need to attribute the author(s) and JTSiskom to distribute works in journals and other publication media. Unless otherwise stated, the author(s) is a public entity as soon as the article is published.