Classification of Palm Oil Ripeness Level using DenseNet201 and Rotational Data Augmentation
DOI:
https://doi.org/10.30865/klik.v4i6.1937Keywords:
Palm Oil; DenseNet201; Classification; Augmentation; RotateAbstract
Indonesia is a country in Southeast Asia with the largest palm oil production in the world. Based on Indonesian Central Statistics Agency data, in 2022 Indonesia produced 46,8 million Tons of Crude Palm Oil (CPO). To produce a high-quality oil, palm oil fruit must be harvested in an optimal condition. But, even a experienced and trained person found it difficult to identify whether the fruit is ripe or raw. In this research theres two type of classification which is ripe and raw, this is because palm oil milling factory only accept pure ripe palm oil fruit and not half ripe or almost ripe. The data that is used in this reseacrh was collected from two sources, the first source is from https://www.kaggle.com/datasets/ahmadfathan/kematangansawit and the second source was collected manually by going to palm oil plantation. The total of data that is used for this research is 1000 data and 1000 augmented data. Dense Convolutional Network (DenseNet) that is used in this research is a CNN architecture that was first introduced in 2017. Compared to DenseNet121 and DenseNet169, DenseNet201 is proven to have a higher level of accuracy. The 90:10 data scheme succeeded in getting the highest accuracy with a total accuracy of 97.50% with a learning rate of 0.001 and a dropout of 0.01
Downloads
References
D. Suryani, A. Yulianti, E. L. Maghfiroh, and J. Alber, “Klasifikasi Kualitas Produk Kelapa Sawit Menggunakan Metode Naïve Bayes” 2022
F. Murgianto, E. Edyson, A. Ardiyanto, S. K. Putra, and L. Prabowo, “Potential Content of Palm Oil at Various Levels of Loose Fruit in Oil Palm Circle,” Jurnal Agro Industri Perkebunan, pp. 91–98, Oct. 2021, doi: 10.25181/jaip.v9i2.2161.
R. Sinambela, “A RIPENESS STUDY OF OIL PALM FRESH FRUIT AT THE BUNCH DIFFERENT POSITIONS,” Jurnal Keteknikan Pertanian, vol. 8, no. 1, pp. 9–14, Aug. 2020, doi: 10.19028/jtep.08.1.9-14.
K. O. Purnama, D. Setyaningsih, E. Hambali, and D. Taniwiryono, “Processing, Characteristics, and Potential Application of Red Palm Oil - A review,” International Journal of Oil Palm, vol. 3, no. 2, pp. 40–55, May 2020, doi: 10.35876/ijop.v3i2.47.
D. Cherie, R. Rini, and M. Makky, “Determination of the optimum harvest window and quality attributes of oil palm fresh fruit bunch using non-destructive shortwave infrared spectroscopy,” in AIP Conference Proceedings, American Institute of Physics Inc., Sep. 2019. doi: 10.1063/1.5125538.
M. Rifqi, “DETEKSI KEMATANGAN TANDAN BUAH SEGAR (TBS) KELAPA SAWIT BERDASARKAN KOMPOSISI WARNA MENGGUNAKAN DEEP LEARNING,” Jurnal Teknik Informatika, vol. 14, no. 2, 2021, doi: 10.15408/jti.v14i2.23295.
M. Y. M. A. Mansour, K. D. Dambul, and K. Y. Choo, “Object Detection Algorithms for Ripeness Classification of Oil Palm Fresh Fruit Bunch,” International Journal of Technology, vol. 13, no. 6, pp. 1326–1335, 2022, doi: 10.14716/ijtech.v13i6.5932.
Z. Ibrahim, N. Sabri, and D. Isa, “Palm Oil Fresh Fruit Bunch Ripeness Grading Recognition Using Convolutional Neural Network” 2018
N. Giarsyani, A. Fathan Hidayatullah, and R. Rahmadi, “KOMPARASI ALGORITMA MACHINE LEARNING DAN DEEP LEARNING UNTUK NAMED ENTITY RECOGNITION?: STUDI KASUS DATA KEBENCANAAN,” 2020.
D. Hindarto and H. Santoso, “Plat Nomor Kendaraan dengan Convolution Neural Network.”, 2021
A. Fahrezantara, S. Rizal, N. Kumalasari, and C. Pratiwi, “Pemanfaatan Convolutional Neural Network Dalam Klasifikasi Penyakit Tanaman Singkong Menggunakan Arsitektur Densenet.”, 2023
A. M. Simarmata, P. Salim, N. J. Waruwu, and J. Jessica, “Densenet Architecture Implementation for Organic and Non-Organic Waste,” sinkron, vol. 8, no. 4, pp. 2444–2449, Oct. 2023, doi: 10.33395/sinkron.v8i4.12765.
M. K. Bohmrah and H. Kaur, “Classification of Covid-19 patients using efficient fine-tuned deep learning DenseNet model,” Global Transitions Proceedings, vol. 2, no. 2, pp. 476–483, Nov. 2021, doi: 10.1016/j.gltp.2021.08.003.
A. Tiwari, M. Poduval, and V. Bagaria, “Evaluation of artificial intelligence models for osteoarthritis of the knee using deep learning algorithms for orthopedic radiographs,” World J Orthop, vol. 13, no. 6, pp. 603–614, 2022, doi: 10.5312/WJO.V13.I6.603.
S. Ashari, G. J. Yanris, and I. Purnama, “Oil Palm Fruit Ripeness Detection using Deep Learning,” Sinkron, vol. 7, no. 2, pp. 649–656, May 2022, doi: 10.33395/sinkron.v7i2.11420.
L. Perez and J. Wang, “The Effectiveness of Data Augmentation in Image Classification using Deep Learning,” Dec. 2017, [Online]. Available: http://arxiv.org/abs/1712.04621
K. Alomar, H. I. Aysel, and X. Cai, “Data Augmentation in Classification and Segmentation: A Survey and New Strategies,” J Imaging, vol. 9, no. 2, Feb. 2023, doi: 10.3390/jimaging9020046.
M. E. H. Chowdhury et al., “Can AI Help in Screening Viral and COVID-19 Pneumonia?,” IEEE Access, vol. 8, pp. 132665–132676, 2020, doi: 10.1109/ACCESS.2020.3010287.
U. Khultsum and G. Taufik, “Komparasi Kinerja DenseNet 121 dan MobileNet untuk Klasifikasi Citra Penyakit Daun Kentang,” JURIKOM (Jurnal Riset Komputer), vol. 10, no. 2, p. 558, Apr. 2023, doi: 10.30865/jurikom.v10i2.6047.
D. Alamsyah and D. Pratama, “IMPLEMENTASI CONVOLUTIONAL NEURAL NETWORKS (CNN) UNTUK KLASIFIKASI EKSPRESI CITRA WAJAH PADA FER-2013 DATASET,” Jurnal Teknologi Informasi, vol. 4, no. 2, 2020.
R. A. Saputra and dan D. Faisal Adhinata, “Model Deteksi Kebakaran Hutan dan Lahan Menggunakan Transfer Learning DenseNet201,” vol. 05, p. 2023, 2023, doi: 10.52985/insyst.v5i2.317.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Classification of Palm Oil Ripeness Level using DenseNet201 and Rotational Data Augmentation
ARTICLE HISTORY
Issue
Section
Copyright (c) 2024 Nabyl Alfahrez Ramadhan Amril, Febi Yanto, Elvia Budianita, Suwanto Sanjaya, Fadhilah Syafria
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).
