Pengembangan Model Klasifikasi Citra Penyakit Daun Lada Menggunakan Jaringan Syaraf Tiruan Learning Vector Quantization (LVQ)

Andrian Sah; Mulyadi Mulyadi; Allan Desi Alexander; Adam M Tanniewa

doi:10.58602/jima-ilkom.v4i1.53

Andrian Sah Universitas Yapis Papua
Mulyadi Mulyadi Universitas Nurdin Hamzah
Allan Desi Alexander Universitas Bhayangkara Jakarta Raya
Adam M Tanniewa Universitas Sulawesi Barat

DOI: https://doi.org/10.58602/jima-ilkom.v4i1.53

Keywords: Daun Lada, GLCM, Learning Vector Quantization, Mean Color, Pengolahan Citra

Abstract

Lada (Piper nigrum) adalah komoditas pertanian bernilai tinggi, namun rentan terhadap penyakit daun akibat infeksi jamur, bakteri, atau hama. Identifikasi dini penting untuk mencegah penurunan hasil panen, namun metode konvensional berbasis observasi visual sering subjektif dan membutuhkan keahlian khusus. Oleh karena itu, penelitian ini bertujuan untuk mengembangkan model klasifikasi penyakit daun lada menggunakan jaringan syaraf tiruan Learning Vector Quantization (LVQ) berbasis pengolahan citra digital. Proses penelitian dimulai dengan preprocessing, yang mencakup konversi ke ruang warna CIELAB untuk meningkatkan kontras, segmentasi menggunakan Otsu Thresholding, serta ekstraksi fitur warna dengan Mean Color dan fitur tekstur menggunakan Gray Level Co-occurrence Matrix (GLCM). Hasil ekstraksi fitur ini kemudian digunakan sebagai masukan untuk algoritma LVQ, yang melakukan klasifikasi berdasarkan pembelajaran vektor prototipe. Hasil evaluasi menunjukkan bahwa model LVQ yang dikembangkan mencapai tingkat akurasi keseluruhan sebesar 90,83%. Model menunjukkan performa terbaik dalam mengenali daun sehat dengan Precision, Recall, dan F1-Score sebesar 96,67%. Sementara itu, kelas Anthracnose memiliki Precision terendah sebesar 87,01%, dan kelas Leaf Blight menunjukkan Recall terendah sebesar 86,67% serta F1-Score terendah sebesar 88,14%. Meskipun terdapat variasi kinerja antar kelas, model ini terbukti efektif dalam menangani dataset terbatas, memiliki kemampuan klasifikasi yang baik terhadap data non-linear, serta memungkinkan interpretasi keputusan klasifikasi yang lebih jelas.

Downloads

Download data is not yet available.

References

Y. I. Nurhakim, Budidaya & Bisnis Lada: Skala Kecil & Besar. Jakarta Selatan: BCI Media, 2021.

R. Ropalia, R. Apriyadi, and H. M. Saputra, “Penyakit Utama Tanaman Lada di Kabupaten Bangka Selatan,” Argosaintek JurnalJurnal Ilmu dan Teknol. Pertan., vol. 6, no. 1, pp. 53–60, 2022, doi: 10.33019/agrosainstek.v6i1.217.

R. Rosmiati, Penanganan dan Pengendalian Jamur Phytophthora Capsici: Implementasi Pada Tanaman Lada. Gowa: CV. Ruang Tentor, 2024.

L. N. Sahenda, A. A. Ubaidillah, Z. E. Fitri, A. Madjid, and A. M. N. Imron, “Application of Feature Selection for Identification of Cucumber Leaf Diseases (Cucumis sativa L.),” JISA (Jurnal Inform. dan Sains), vol. 04, no. 02, pp. 173–178, 2021.

Y. Sari, A. R. Baskara, and R. Wahyuni, “Classification of Chili Leaf Disease Using the Gray Level Co-occurrence Matrix (GLCM) and the Support Vector Machine (SVM) Methods,” in International Conference on Informatics and Computing (ICIC), IEEE, 2021, pp. 1–4.

R. S. Septarini, M. Tonggiroh, and S. Nurhayati, “Identification of Potato Leaf Diseases Using Artificial Neural Networks With Extreme Learning Machine,” Pilar Nusa Mandiri J. Comput. Inf. Syst., vol. 20, no. 1, pp. 60–68, 2024, doi: 10.33480/pilar.v20i1.5307.

Y. Lu et al., “Recognition of rice sheath blight based on a backpropagation neural network,” Electron., vol. 10, no. 23, 2021, doi: 10.3390/electronics10232907.

R. I. Borman, Y. Fernando, and Y. Egi Pratama Yudoutomo, “Identification of Vehicle Types Using Learning Vector Quantization Algorithm with Morphological Features,” J. RESTI (Rekayasa Sist. dan Teknol. Informasi), vol. 6, no. 2, pp. 339–345, 2022, doi: 10.29207/resti.v6i2.3954.

R. I. Borman, Y. Fernando, and Y. E. P. Yudoutomo, “Identification of Vehicle Types Using Learning Vector Quantization Algorithm with Morphological Features,” J. RESTI (Rekayasa Sist. dan Teknol. Informasi), vol. 5, no. 158, pp. 339–345, 2022, doi: 10.29207/resti.v6i2.3954.

K. Azhari, “Klasifikasi Jenis-Jenis Bauh Nanas Menggunakan Learning Vector Quantization (LVQ),” KONSTELASI Konvergensi Teknol. dan Sist. Inf., vol. 1, no. 2, pp. 357–368, 2021, doi: 10.24002/konstelasi.v1i2.4261.

A. Sah, S. Suhardi, and S. Nurhayati, “Geographic Information System of Patient Development in Jayapura Hospital During Pandemic,” J. Teknol. Dan Open Source, vol. 4, no. 2, pp. 149–154, 2021, doi: 10.36378/jtos.v4i2.1412.

R. I. Borman and M. Wati, “Penerapan Data Maining Dalam Klasifikasi Data Anggota Kopdit Sejahtera Bandarlampung Dengan Algoritma Naïve Bayes,” J. Ilm. Fak. Ilmu Komput., vol. 9, no. 1, pp. 25–34, 2020.

I. Ahmad, Y. Rahmanto, R. I. Borman, F. Rossi, Y. Jusman, and A. D. Alexander, “Identification of Pineapple Disease Based on Image Using Neural Network Self-Organizing Map (SOM) Model,” in International Conference on Electronic and Electrical Engineering and Intelligent System (ICE3IS), IEEE, 2022, pp. 12–17.

R. Nuraini, T. G. Soares, P. Dayurni, and M. Mulyadi, “Tomato Ripeness Detection Using Linear Discriminant Analysis Algorithm with CIELAB and HSV Color Spaces,” Build. Informatics, Technol. Sci., vol. 5, no. 2, pp. 523–531, 2023, doi: 10.47065/bits.v5i2.4192.

V. Veriarinal and C. Gunawan, “Identifikasi Nilai Mata Uang Logam Menggunakkan Metode Otsu Thresholding,” Kohesi J. Multidisiplin Saintek, vol. 2, no. 11, pp. 1–9, 2024, doi: 10.3785/kohesi.v2i11.2670.

R. I. Borman, D. E. Kurniawan, Styawati, I. Ahmad, and D. Alita, “Classification of Maturity Levels of Palm Fresh Fruit Bunches Using the Linear Discriminant Analysis Algorithm,” AIP Conf. Proc., vol. 2665, no. 1, pp. 30023.1-30023.8, 2023, doi: 10.1063/5.0126513.

R. I. Borman, F. Rossi, Y. Jusman, A. A. A. Rahni, S. D. Putra, and A. Herdiansah, “Identification of Herbal Leaf Types Based on Their Image Using First Order Feature Extraction and Multiclass SVM Algorithm,” in International Conference on Electronic and Electrical Engineering and Intelligent System (ICE3IS), IEEE, 2021, pp. 12–17.

D. Ayuningtyas, E. Suryani, and W. Wiharto, “Identification of Tomato Maturity Based on HIS Color Space Using The K-Nearest Neighbour Method,” in International Conference on Artificial Intelligence and Computer Science Technology (ICAICST), IEEE, 2021, pp. 73–78. doi: 10.1109/ICAICST53116.2021.9497843.

A. Herdiansah, R. I. Borman, D. Nurnaningsih, A. A. J. Sinlae, and R. R. Al Hakim, “Klasifikasi Citra Daun Herbal Dengan Menggunakan Backpropagation Neural Networks Berdasarkan Ekstraksi Ciri Bentuk,” JURIKOM (Jurnal Ris. Komputer), vol. 9, no. 2, pp. 388–395, 2022, doi: 10.30865/jurikom.v9i1.3846.

M. Kaden et al., “Learning vector quantization as an interpretable classifier for the detection of SARS-CoV-2 types based on their RNA sequences,” Neural Comput. Appl., vol. 34, no. 1, pp. 67–78, 2022, doi: 10.1007/s00521-021-06018-2.

M. S. Sormin, H. Rumapea, I. K. Jaya, and D. R. Manalu, “Penerapan Metode Learning Vector Quantization Pada Sistem Pakar Identifikasi Penyakit Dan Hama Tanaman Kubis Berdasarkan Citra Daun Berbasis Mobile,” METHOTIKA J. Ilm. Tek. Inform., vol. 2, no. 1, pp. 61–67, 2022.

R. I. Borman, F. Rossi, D. Alamsyah, R. Nuraini, and Y. Jusman, “Classification of Medicinal Wild Plants Using Radial Basis Function Neural Network with Least Mean Square,” in International Conference on Electronic and Electrical Engineering and Intelligent System (ICE3IS), IEEE, 2022.

R. I. Borman, I. Ahmad, and Y. Rahmanto, “Klasifikasi Citra Tanaman Perdu Liar Berkhasiat Obat Menggunakan Jaringan Syaraf Tiruan Radial Basis Function,” Bull. Informatics Data Sci., vol. 1, no. 1, pp. 6–13, 2022.

Z. Abidin, R. I. Borman, F. B. Ananda, P. Prasetyawan, F. Rossi, and Y. Jusman, “Classification of Indonesian Traditional Snacks Based on Image Using Convolutional Neural Network (CNN) Algorithm,” in International Conference on Electronic and Electrical Engineering and Intelligent System (ICE3IS), IEEE, 2022, pp. 18–23.

R. I. Borman, Y. Fernando, and Y. E. P. Yudoutomo, “Identification of Vehicle Types Using Learning Vector Quantization Algorithm with Morphological Features,” J. RESTI (Rekayasa Sist. dan Teknol. Informasi), vol. 5, no. 2, pp. 339–345, 2022.

R. R. Wahid, F. T. Anggraeni, and B. Nugroho, “Implementasi Metode Extreme Learning Machine untuk Klasifikasi Tumor Otak pada Citra Magnetic Resonance Imaging,” in Seminar Nasional Informatika Bela Negara (SANTIKA), 2023, pp. 16–20. doi: 10.33005/santika.v1i0.45.