Implementation of ResNet-50 in a Fresh Fruit Bunch (FFB) Ripeness Detection System for Oil Palm

M. Rafli Al Thoriq Mustafa, Muhammad Fikry, Said Fadlan Anshari

Abstract


The quality of Crude Palm Oil (CPO) is highly dependent on the accuracy of sorting the ripeness level of oil palm Fresh Fruit Bunches (FFB). Manual sorting processes currently used in factories are vulnerable to human error and subjectivity. This study aims to automate the objectivity of the sorting process using a deep learning model based on the ResNet-50 architecture with a transfer learning approach to classify FFB into three categories: Unripe, Ripe, and Overripe. The computational model was integrated into a web-based application using the Flask framework to support wireless operational use in factories. Experimental results showed a validation accuracy of 90.94% and an F1-score of 91%. Direct field validation using 42 primary data samples achieved a classification success rate of 83.33%. The implementation of a 75% confidence threshold proved effective in preventing prediction errors (zero misclassification), while the Cohen’s Kappa reliability test achieved a score of 0.769, indicating Substantial Agreement with expert evaluators. In conclusion, the ResNet-50-based system demonstrated reliable and objective performance and is considered ready for replication to maintain quality consistency in the palm oil processing industry.

Keywords


deep learning; Flask; oil palm; ResNet-50; transfer learning

Full Text:

PDF

References


P. R. Indonesia, Undang-Undang Nomor 39 Tahun 2014 tentang Perkebunan. Jakarta: Sekretariat Negara, 2014.

M. L. F. Sitorus, E. N. Akoeb, R. Sembiring, dan M. A. Siregar, “Peningkatan Produksi Crude Palm Oil (CPO) melalui Kriteria Matang Panen Tandan Buah Segar (TBS) untuk Optimalisasi Pendapatan Perusahaan,” Jurnal Ilmiah Magister Agribisnis, Vol. 2, No. 1, hlm. 26–32, 2020, DOI: 10.31289/agrisains.v2i1.251.

F. Rahmadhania, P. Sembiring, dan M. A. Sinaga, “Pengaruh Kematangan Buah Kelapa Sawit Varietas Dxp Bah Lias terhadap Kadar Minyak Sawit Mentah (CPO),” Jurnal Agro Estate, Vol. 3, No. 1, hlm. 1–9, 2019, DOI: 10.47199/jae.v3i1.56.

Z. Bahri, J. Risanto, dan H. Gussyafri, “Pengembangan Sistem Realtime Deteksi Tingkat Kematangan Tandan Buah Segar Kelapa Sawit menggunakan Metode Centernet berbasis Mobile Android,” dalam Grant Riset Sawit 2024 Ringkasan Penelitian, Badan Pengelola Dana Perkebunan Kelapa Sawit, 2024, hlm. 155–156.

E. Widodo, Widyastuti, R. Widyaningrum, B. Al Kindhi, R. S. Dewi, dan F. N. Setiowati, “Egrek Digital: Peningkatan Efisiensi Panen dan Substitusi Impor,” dalam Grant Riset Sawit 2024 Ringkasan Penelitian, Badan Pengelola Dana Perkebunan Kelapa Sawit, 2024, hlm. 99–100.

J. Zulkarnain, Kusrini, dan T. Hidayat, “Klasifikasi Tingkat Kematangan Tandan Buah Segar Kelapa Sawit menggunakan Pendekatan Deep Learning,” JST (Jurnal Sains dan Teknologi), Vol. 12, No. 3, hlm. 748–758, 2024, DOI: 10.23887/jstundiksha.v12i3.59140.

S. Ashari, G. J. Yanris, dan I. Purnama, “Oil Palm Fruit Ripeness Detection using Deep Learning,” Sinkron: Jurnal dan Penelitian Teknik Informatika, Vol. 6, No. 2, hlm. 649–656, 2022, DOI: 10.33395/sinkron.v7i2.11420.

R. Triyogi, R. Magdalena, dan B. Hidayat, “Mendeteksi Kematangan Buah Kelapa Sawit menggunakan Convolutional Neural Network Deep Learning,” Jurnal Nasional Sains dan Teknik, Vol. 1, No. 1, hlm. 22–27, 2023, DOI: 10.25124/jnst.v1i1.6732.

M. Minarni, R. Salumbae, dan Z. Hasbi, “Implementasi Jaringan Syaraf Tiruan (JST) dan Pengolahan Citra untuk Klasifikasi Kematangan TBS Kelapa Sawit,” Indonesian Physics Communication, Vol. 15, No. 1, hlm. 36–45, 2018.

M. A. Syahira, M. Khoiriah, dan R. S. Harahap, “Rancang Bangun Alat Pendeteksi Kematangan Buah Sawit dengan menggunakan Metode Image Processing berdasarkan Komposisi Warna,” Jurnal Garuda Pengabdian Kepada Masyarakat, Vol. 1, No. 2, hlm. 78–87, 2023, DOI: 10.55537/gabdimas.v1i2.827.

M. Andri, Jasmir, dan W. Riyadi, “Rancang Bangun Prototype Sortir Buah Kelapa Sawit berdasarkan Tingkat Kematangan berbasis Arduino Uno,” Jurnal Informatika dan Rekayasa Komputer (JAKAKOM), Vol. 3, No. 1, hlm. 501–510, 2023, DOI: 10.33998/jakakom.2023.3.1.812.

I. Aryadi dan A. Suhendar, “Implementasi Arsitektur Xception dalam menentukan Kematangan Tandan Buah Segar Kelapa Sawit,” Jutisi: Jurnal Ilmiah Teknik Informatika dan Sistem Informasi, Vol. 13, No. 3, hlm. 2235–2247, 2024, DOI: 10.35889/jutisi.v13i3.2337.

K. P. R. Indonesia, Peraturan Menteri Pertanian Nomor 13 Tahun 2024 tentang Pembelian Tandan Buah Segar Kelapa Sawit Produksi Pekebun Mitra. Jakarta: Kementerian Pertanian Republik Indonesia, 2024.

E. A. M. Iqbal, “Hybrid Model Transfer Learning ResNet50 dengan Support Vector Machine untuk Deteksi Masker pada Image Wajah,” 2023.

M. A. N. Hidayat, “Convolutional Neural Network pada Identifikasi Varian Tanaman Anggur menggunakan Resnet-50,” JATISI (Jurnal Teknik Informatika dan Sistem Informasi), Vol. 10, No. 3, hlm. 61–70, 2023, DOI: 10.35957/jatisi.v10i3.4789.

F. Nashrullah, S. A. Wibowo, dan G. Budiman, “Investigasi Parameter Epoch pada Arsitektur Resnet-50 untuk Klasifikasi Pornografi,” Journal of Computer, Electronic, and Telecommunication, Vol. 1, No. 1, hlm. 1–8, 2020, DOI: 10.52435/complete.v1i1.51.

D. F. Ningtyas dan N. Setiyawati, “Implementasi Flask Framework pada Pembangunan Aplikasi Purchasing Approval Request,” Jurnal Janitra Informatika dan Sistem Informasi, Vol. 1, No. 1, hlm. 19–34, 2021, DOI: 10.25008/janitra.v1i1.120.

M. G. L. Putra dan M. I. A. Putera, “Analisis Perbandingan Metode SOAP dan REST yang digunakan pada Framework Flask untuk membangun Web Service,” Scan: Jurnal Teknologi Informasi dan Komunikasi, Vol. 14, No. 2, hlm. 1–7, 2019, DOI: 10.33005/scan.v14i2.1480.

G. N. Elwirehardja, J. S. Prayoga, dan Suharjito, “Oil Palm Fresh Fruit Bunch Ripeness Classification on Mobile Devices using Deep Learning Approaches,” Comput. Electron. Agric., Vol. 188, hlm. 106359, 2021, DOI: 10.1016/j.compag.2021.106359.

J. W. Lai, H. R. Ramli, L. I. Ismail, dan W. Z. W. Hasan, “Real-Time Detection of Ripe Oil Palm Fresh Fruit Bunch based on YOLOv4,” IEEE Access, Vol. 10, hlm. 95763–95770, 2022, DOI: 10.1109/ACCESS.2022.3204762.




DOI: https://doi.org/10.32520/stmsi.v15i5.6331

Article Metrics

Abstract view : 0 times
PDF - 0 times

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.