Melola Discovery

← Melola Discovery

Akses terbuka Jurnal SINTA 1

Image-based Quality Identification of Black Soybean (Glycine soja) Using Convolutional Neural Network

Industria Jurnal Teknologi dan Manajemen Agroindustri · Vol. 12 No. 1 (2023) · hlm. 73–88

DOI
10.21776/ub.industria.2023.012.01.7
ISSN
2252-7877, 2549-3892
Terbit
2023-06-13
Penerbit
Brawijaya University
Bahasa
en
Lisensi
creativecommons.org/licenses/by-sa/4.0/

Abstrak

The problem faced in identifying the quality of black soybeans is that the quality of the assessment is inconsistent and it takes a relatively long time. This study aims to determine the best convolutional neural network architecture by comparing the performance of Custom CNN, MobileNetV2, and ResNet-34 architectures in identifying the quality level (grade) of black soybeans. The quality of black soybean is split into 4 different classes based on physical characteristics (split, damaged, other colors, wrinkles, dirt) and moisture content test. The number of images used is 1300 images, with the ratio of training data, validation data, and testing data are 50:25:25, 60:25:15, and 70:20:10. The best model for identifying the quality based on the physical characteristics is the MobileNetV2 architecture with a ratio of 50:25:25 which produces an accuracy of 90.18%. Morover, the best model for identifying the quality based on the moisture content is the ResNet-34 architecture with a ratio of 70:20:10, which produces an accuracy of 78.12%. The best overall accuracy in identifying the quality based on both physical characteristics and moisture content is the ResNet-34 architecture, with a ratio of 70:20:10, with an average accuracy of testing data of 79.21%.

Kata kunci

Jaringan kolaborasi para penulis

40 penulis · 103 tautan kepenulisan bersama · 13 lintas organisasi · menampilkan 40 yang paling banyak terhubung

Arahkan kursor atau ketuk sebuah nama untuk menyorot rekan penulisnya. Klik dua kali untuk membuka halaman penulis.

  • University of Brawijaya
  • State University of Semarang
  • State University of Malang
  • Universitas Islam Negeri Sultan Syarif Kasim Riau
  • Sapienza University of Rome
  • Afiliasi tidak diketahui
  • Organisasi berbeda
  • Organisasi sama
  • Afiliasi tidak diketahui
  • Garis lebih tebal = lebih banyak artikel bersama · lingkaran lebih besar = lebih banyak artikel
Tampilkan sebagai tabel
Rekan penulisOrganisasiArtikel bersama
Retno AstutiUniversity of Brawijaya6
Usman EffendiUniversity of Brawijaya5
Sri KumalaningsihUniversity of Brawijaya5
Dodyk PranowoUniversity of Brawijaya4
Imam SantosoUniversity of Brawijaya4
Panji DeorantoUniversity of Brawijaya4
Nur HidayatUniversity of Brawijaya4
Rindia Fanny KusmaningtyasAfiliasi tidak diketahui3
Dewi SulistianingsihState University of Semarang3
Maimunah Hindun PulunganUniversity of Brawijaya3
Sucipto SuciptoUniversity of Brawijaya3
Sukardi SukardiUniversity of Brawijaya3
Martitah MartitahState University of Semarang2
Tegar Islami PutraState University of Semarang2
Sang Ayu Putu RahayuState University of Semarang2
Pujiono PujionoState University of Semarang2
Adzraa TaqiyaahState University of Semarang2
Endah Rahayu LestariUniversity of Brawijaya2
Claudia Gadizza PerdaniUniversity of Brawijaya2
Siti Asmaul MustanirohUniversity of Brawijaya2
Widya Dwi Rukmi PutriUniversity of Brawijaya2
Erni Sofia MurtiniUniversity of Brawijaya2
Riska SeptifaniUniversity of Brawijaya2
Wignyanto WignyantoUniversity of Brawijaya2
Susinggih WijanaUniversity of Brawijaya2
Sri RahayuState University of Malang1
P. SetyosariAfiliasi tidak diketahui1
Dedi KuswandiState University of Malang1
Eko SujarwantoState University of Malang1
Wartono WartonoUniversitas Islam Negeri Sultan Syarif Kasim Riau1
Slamet SumartoState University of Semarang1
Pujiono PujionoState University of Semarang1
Triska Rahmatul AiniSapienza University of Rome1
Dinda Dinda Annisha KurnianingtyasAfiliasi tidak diketahui1
Moh. Imam GusthomiState University of Semarang1
Niken SeptianiState University of Semarang1

Afiliasi berasal dari OpenAlex; metadata OAI-PMH jurnal tidak memuatnya. Penulis tanpa ID OpenAlex dicocokkan berdasarkan nama, sehingga dua orang bisa tergabung atau satu orang bisa terpisah.

Sumber metadata: OpenAlex API (jurnal SINTA, ADR 0048) https://openalex.org/S4210180819, pertama di-harvest 21 Nov 2026, terakhir terlihat 21 Nov 2026.
Metadata asli (oai_dc)
<oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/"><dc:title xml:lang="en">Image-based Quality Identification of Black Soybean (Glycine soja) Using Convolutional Neural Network</dc:title><dc:creator>Universitas Brawijaya</dc:creator><dc:creator>Mas’ud Effendi</dc:creator><dc:creator>Naufal Hilmi Ramadhan</dc:creator><dc:creator>Universitas Brawijaya</dc:creator><dc:creator>Arif Hidayat</dc:creator><dc:creator>Universitas Brawijaya</dc:creator><dc:subject>black soybean</dc:subject><dc:subject>Glycine soja</dc:subject><dc:subject>image-based quality assessment</dc:subject><dc:subject>convolutional neural network architecture comparison</dc:subject><dc:subject>MobileNetV2</dc:subject><dc:subject>ResNet34</dc:subject><dc:subject>custom CNN</dc:subject><dc:subject>moisture content</dc:subject><dc:subject>physical defects</dc:subject><dc:description xml:lang="en">The problem faced in identifying the quality of black soybeans is that the quality of the assessment is inconsistent and it takes a relatively long time. This study aims to determine the best convolutional neural network architecture by comparing the performance of Custom CNN, MobileNetV2, and ResNet-34 architectures in identifying the quality level (grade) of black soybeans. The quality of black soybean is split into 4 different classes based on physical characteristics (split, damaged, other colors, wrinkles, dirt) and moisture content test. The number of images used is 1300 images, with the ratio of training data, validation data, and testing data are 50:25:25, 60:25:15, and 70:20:10. The best model for identifying the quality based on the physical characteristics is the MobileNetV2 architecture with a ratio of 50:25:25 which produces an accuracy of 90.18%. Morover, the best model for identifying the quality based on the moisture content is the ResNet-34 architecture with a ratio of 70:20:10, which produces an accuracy of 78.12%. The best overall accuracy in identifying the quality based on both physical characteristics and moisture content is the ResNet-34 architecture, with a ratio of 70:20:10, with an average accuracy of testing data of 79.21%.</dc:description><dc:publisher>Brawijaya University</dc:publisher><dc:date>2023-06-13</dc:date><dc:type>info:eu-repo/semantics/article</dc:type><dc:format>application/pdf</dc:format><dc:identifier>http://dx.doi.org/10.21776/ub.industria.2023.012.01.7</dc:identifier><dc:identifier>10.21776/ub.industria.2023.012.01.7</dc:identifier><dc:source>Industria Jurnal Teknologi dan Manajemen Agroindustri; Vol 12 No 1 (2023); 73-88</dc:source><dc:source>2252-7877</dc:source><dc:source>2549-3892</dc:source><dc:language>en</dc:language><dc:relation>https://industria.ub.ac.id/index.php/industri/article/download/5420/820</dc:relation><dc:rights>https://creativecommons.org/licenses/by-sa/4.0/</dc:rights></oai_dc:dc>