Optimasi Sistem Klasifikasi Biji Tanaman Cabai Menggunakan CNN: Pendekatan Inovatif dalam Agribisnis
Sari
Cabai memiliki peran yang sangat vital sebagai jenis sayuran di Indonesia, digunakan baik untuk kebutuhan perdagangan di dalam negeri maupun ekspor. Selain kandungan gizinya, cabai juga memiliki nilai ekonomi yang tinggi. Mengingat fluktuasi harga cabai yang seringkali tinggi, klasifikasi biji tanaman cabai menjadi sangat penting untuk menjaga kualitas hasil panen dan meningkatkan produksi. Fokus penelitian ini adalah mengklasifikasikan biji tanaman cabai menggunakan metode convolutional neural network, dengan melalui sejumlah tahap perancangan dan implementasi. Tujuan utama penelitian ini adalah membantu dalam klasifikasi biji tanaman cabai untuk memastikan kualitas cabai tetap terjaga di pasar dan menghindari kesalahan dalam penanaman benih cabai. Klasifikasi biji tanaman cabai dilakukan menggunakan convolutional neural network dengan memanfaatkan data latih dan data uji. Dalam pembentukan model klasifikasi, diperlukan pelatihan data dan penggunaan 3 kategori biji, yaitu biji paprika, biji cabai besar, dan biji cabai rawit. Proses latihan data dilakukan dengan komputer dalam mode GPU tunggal, dan data validasi tidak dimasukkan dalam proses pelatihan. Hasil label klasifikasi yang dihasilkan oleh jaringan menjadi pedoman untuk mengenali jenis objek biji tanaman cabai yang sulit dibedakan dengan jelas.Hasil penelitian ini menunjukkan bahwa arsitektur CNN mampu memisahkan tiga jenis biji pada tanaman cabai dengan tingkat akurasi sekitar 90%.
Chili peppers play a vital role as a type of vegetable in Indonesia, used both for domestic trade and export purposes. In addition to their nutritional value, chili peppers also hold high economic significance. Given the often-high price fluctuations of chili peppers, the classification of chili plant seeds becomes crucial in maintaining the quality of harvests and boosting production. The main focus of this research is to classify chili plant seeds using the convolutional neural network method, employing several stages of design and implementation. The primary goal of this study is to assist in the classification of chili plant seeds to ensure that the quality of chili remains preserved in the market and to avoid errors in chili seed planting. The classification of chili plant seeds is carried out using convolutional neural networks, utilizing training and testing data. To form a classification model, data training and the utilization of 3 seed categories—namely, paprika seeds, large chili seeds, and bird's eye chili seeds—are necessary. The training data process is conducted using a computer in single GPU mode, with validation data not included in the training process. The resulting classification labels generated by the network serve as a guide to identify types of chili plant seed objects that are challenging to distinguish clearly.The results of this research show that the CNN architecture is able to separate three types of seeds in chili plants with an accuracy rate of around 90%.
Teks Lengkap:
PDFReferensi
Adi, & Muhammad. (2018). Analisis Daya Saing Ekspor Karet Indonesia, Malaysia dan Thailand ke Pasar Amerika Serikat Periode 2005-2015.
Alfianika, N. (2018). Buku Ajar Metode Penelitian Pengajaran Bahasa Indonesia. Deepublish.
Chen, H.-P., & Yeh, Z.-M. (2000). Extended fuzzy Petri net for multi-stage fuzzy logic inference. In Ninth IEEE International Conference on Fuzzy SystemsFUZZ- IEEE 2000 (Cat. No.00CH37063), 1, 441–446.
Eka Putra, W. S. (2016). Klasifikasi Citra Menggunakan Convolutional Neural Network (CNN) pada Caltech 101. Jurnal Teknik ITS, 5(1). https://doi.org/10.12962/j23373539.v5i1.15696
Ewelina Hallmann. (2019). Polyphenols and carotenoids in pickled bell pepper from organic and conventional production. Food Chemistry, 278, 254–260. https://www.sciencedirect.com/science/article/abs/pii/S0308814618319885
F, H., I, S., TI, N., & EP, Y. (2021). Analisis Potensi Sektor Unggulan Dan Perubahan Struktur Ekonomi Di Kabupaten Serang Provinsi Banten. Jurnal Pemikiran Masyarakat Ilmiah Berwawasan Agribisnis, 1(7), 947–960.
Gholamy, A., Kreinovich, V., & Kosheleva, O. (2018). Why 70/30 or 80/20 Relation Between Training and Testing Sets : A Pedagogical Explanation. Departmental Technical Reports (CS), 1209, 1–6. https://scholarworks.utep.edu/cgi/viewcontent.cgi?article=2202&context=cs_techrep
Jiang, J., Cen, H., Zhang, C., Lyu, X., Weng, H., & Xu, H. (2018). Postharvest Biology and Technology Nondestructive quality assessment of chili peppers using near-infrared hyperspectral imaging combined with multivariate analysis. Postharvest Biol. Techno, 146, 147–154.
Kong, Xi manZhou, Q., Luo, Feng Wei, B. dong, Wang, Ya juan Sun, H. jun, & Zhao, Ying bo Ji, S. juan. (2019). Transcriptome analysis of harvested bell peppers (Capsicum annuum L.) in response to cold stress. Plant Physiology and Biochemistry, 139, 314–324. https://doi.org/10.1016/j.plaphy.2019.03.033
Kusumaningrum, T. F. (2018). Implementasi Convolution Neural Network (Cnn) Untuk Klasifikasi Jamur Konsumsi Di Indonesia Menggunakan Keras. Journal of Materials Processing Technology, 1(1), 1–8. https://dspace.uii.ac.id/handle/123456789/7781
Muddin, M. I. U., Soedibyo, D. W., & Wahyuningsih, S. (2019). Identifikasi Varietas Benih Jagung (Zea Mays L.) Menggunakan Pengolahan Citra Digital Berbasis Jaringan Syaraf Tiruan. Teknika, 8(2), 78–85. https://doi.org/10.34148/teknika.v8i2.173
Nusantara, D. O., Pamungkas, S. W., Syaifudin, N. R., Kusuma, L. W., & Fikri, J. (2017). Sistem pakar analisa penyakit pada tanaman cabai merah menggunakan metode backward chaining. Seminar Nasional Teknologi Informasi Dan Multimedia, 73–78.
Olaes, E. J., Arboleda, E. R., Dioses, J. L., & Dellosa, R. M. (2020). Bell pepper and chili pepper classification: An application of image processing and fuzzy logic. International Journal of Scientific and Technology Research, 9(2), 4832–4839.
Perlindungan, I., & Risnawati. (2020). Pengenalan Tanaman Cabai Dengan Teknik Klasifikasi Menggunakan Metode CNN. Seminar Nasional Mahasiswa Ilmu Komputer Dan Aplikasinya (SENAMIKA), 15–22. https://conference.upnvj.ac.id/index.php/senamika/article/view/694/420
Purwaningsih, T., Anjani, I. A., & Utami, P. B. (2019). Convolutional Neural Networks Implementation for Chili Classification. Proceeding - 2018 International Symposium on Advanced Intelligent Informatics: Revolutionize Intelligent Informatics Spectrum for Humanity, SAIN 2018, 190–194. https://doi.org/10.1109/SAIN.2018.8673373
Sabilla, S. I., & Sarno, R. (2017). Development of wavelet transforms to predict methane in chili using the electronic nose. 7 International Conference on Advanced Mechatronics, Intelligent Manufacture, and Industrial Automation (ICAMIMIA), 271–276.
Sun, T., Xu, Z., C.-T., Wu, M., Janes, W., Prinyawiwatkul, No, & K., H. (2007). Antioxidant Activities of Different Colored Sweet Bell Peppers (Capsicum annuum L.). J. Food Sci, 72, S98–S102.
Ureña, R., Rodrıguez, F., & Berengue, M. (2001). A machine ́ vision system for seeds quality evaluation using fuzzy logic. Comput. Electron. Agric, 32(1), 1–20.
Y. Wang, L. Gao, Q. Wang, and J. Z. (2019). Low temperature conditioning combined with methyl jasmonate can reduce chilling injury in bell pepper. Scientia Horticulturae, 243, 434–439.
Zufar, M., & Setiyono, B. (2016). Convolutional Neural Networks Untuk Pengenalan Wajah Secara Real-Time. Jurnal Sains Dan Seni ITS, 5(2), 128862. https://doi.org/10.12962/j23373520.v5i2.18854
DOI: https://doi.org/10.31294/ijcit.v8i2.17907
##submission.copyrightStatement##
##submission.license.cc.by-sa4.footer##
P-ISSN: 2527-449X E-ISSN: 2549-7421
Statistik Pengunjung Jurnal IJCIT
