DETEKSI PENYAKIT CABAI MERAH BESAR BERDASARKAN CITRA DAUN MENGGUNAKAN METODE SUPPORT VECTOR MACHINE (SVM) DAN LEARNING VECTOR QUANTIZATION (LVQ)

Rossa, Shevia (2024) DETEKSI PENYAKIT CABAI MERAH BESAR BERDASARKAN CITRA DAUN MENGGUNAKAN METODE SUPPORT VECTOR MACHINE (SVM) DAN LEARNING VECTOR QUANTIZATION (LVQ). Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5003201003-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2026. Download (3MB) | Request a copy

Abstract

Salah satu tantangan utama yang menyebabkan rendahnya produksi cabai merah besar adalah gangguan penyakit yang dapat menyerang tanaman mulai dari tahap persemian hingga hasil panen. Gejala visual kunci suatu penyakit menjadi petunjuk kritis dalam menentukan patogen penyebabnya. Beberapa penyakit yang secara signifikan mempengaruhi produksi cabai merah besar di Indonesia meliputi penyakit kuning, embun tepung, mosaik keriting, dan kuning keriting. Penyebaran cepat penyakit ini terjadi karena kurangnya perhatian khusus dari petani, yang mengakibatkan kurangnya pemahaman mereka tentang karakteristik dan penanganan penyakit ini. Oleh karena itu, sangat penting untuk mengembangkan sistem deteksi yang akurat, cepat, dan efisien dalam mengidentifikasi penyakit pada tanaman cabai. Salah satu cara pendeteksian adalah dengan mengklasifikasikan citra daun. Data penelitian bersumber dari pertanian di Kabupaten Bener Meriah Provinsi Aceh pada 21 September hingga 1 Oktober tahun 2023. Teknologi rekognisi citra dilakukan untuk mengenali jenis hama dan penyakit pada tanaman cabai merah besar. Langkah pertama dalam penelitian adalah mengumpulkan citra daun, kemudilan melakukan preprocessing dan dilanjutkan tahap proses ekstraksi fitur warna, fitur tekstur dan fitur bentuk, hasil ekstraksi citra digunakan sebagai input dalam proses klasifikasi menggunakan algoritma Support Vector Machine (SVM) dan Learning Vector Quantization (LVQ). Accuracy hasil prediksi data training dan testing dengan metode SVM kernel polynolial adalah 95% dan 97%, sedangkan accuracy data training dan testing menggunakan metode LVQ adalah 53% dan 57%. Model terbaik dalam memprediksi penyakit cabai adalah model SVM dengan kernel polynomial.
========================================================================================================================
One of the primary challenges contributing to the low production of large red chili peppers is the prevalence of diseases that can affect plants from the seedling stage to the harvest. Key visual symptoms of a disease serve as critical indicators in determining the causative pathogen. Several diseases significantly impact the production of large red chili peppers in Indonesia, including yellowing disease, powdery mildew, mosaic curl, and yellow curl. The rapid spread of these diseases is attributed to the insufficient specific attention from farmers, resulting in a lack of understanding regarding the characteristics and management of these diseases. Therefore, it is crucial to develop an accurate, rapid, and efficient detection system to identify diseases in chili plants. One method of detection involves classifying leaf images. The research data is sourced from agricultural activities in the Bener Meriah Regency, Aceh Province, from September 21 to October 1, 2023. Image recognition technology is employed to identify types of pests and diseases affecting large red chili plants. The first step in the research involves collecting leaf images, followed by preprocessing and subsequent stages of color feature extraction, texture feature extraction, and shape feature extraction. The extracted image features serve as parameters in the classification process using the Support Vector Machine (SVM) and Learning Vector Quantization (LVQ) algorithms. The accuracy of the prediction results for the training and testing data using the SVM with a polynomial kernel method is 95% and 97%, respectively. In contrast, the accuracy of the training and testing data using the LVQ method is 53% and 57%, respectively. Therefore, the best model for predicting chili plant diseases is the SVM model with a polynomial kernel.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Daun Cabai, Klasifikasi, Learning Vector Quantization (LVQ), Support Vector Machine (SVM), Chili leaves, Classification, Learning Vector Quantization (LVQ), Support Vector Machine (SVM)
Subjects:	Q Science > Q Science (General) Q Science > Q Science (General) > Q325.5 Machine learning. Support vector machines. Q Science > QK Botany S Agriculture > S Agriculture (General) T Technology > T Technology (General) > T57.8 Nonlinear programming. Support vector machine. Wavelets. Hidden Markov models. T Technology > TA Engineering (General). Civil engineering (General) > TA1637 Image processing--Digital techniques
Divisions:	Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis
Depositing User:	Shevia Rossa
Date Deposited:	08 Aug 2024 13:52
Last Modified:	08 Aug 2024 13:52
URI:	http://repository.its.ac.id/id/eprint/114982

Actions (login required)

View Item