PAMUNGKAS, YUDHA ERIC (2023) IMPLEMENTASI ALGORITMA CONVOLUTIONAL NEURAL NETWORK UNTUK KLASIFIKASI PENYAKIT LEAF SCORCH PADA DAUN STROBERI MENGGUNAKAN METODE TRANSFER LEARNING MOBILE NET V1 DAN KFOLD CROSS VALIDATION. S1 thesis, Universitas Mercu Buana Jakarta.
|
Text (HAL COVER)
01 COVER.pdf Download (285kB) | Preview |
|
|
Text (ABSTRAK)
02 ABSTRAK.pdf Download (46kB) | Preview |
|
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (BAB I)
03 BAB 1.pdf Restricted to Registered users only Download (91kB) |
|
|
Text (BAB II)
04 BAB 2.pdf Restricted to Registered users only Download (115kB) |
|
|
Text (BAB III)
05 BAB 3.pdf Restricted to Registered users only Download (66kB) |
|
|
Text (BAB IV)
06 BAB 4.pdf Restricted to Registered users only Download (462kB) |
|
|
Text (BAB V)
07 BAB 5.pdf Restricted to Registered users only Download (43kB) |
|
|
Text (DAFTAR PUSTAKA)
08 DAFTAR PUSTAKA.pdf Restricted to Registered users only Download (48kB) |
|
|
Text (LAMPIRAN)
09 LAMPIRAN.pdf Restricted to Registered users only Download (956kB) |
Abstract
Strawberries are a type of subtropical plant and are classified as herbaceous fruit plants, which were first discovered in Chile, Latin America. There are several diseases that can affect strawberry leaves, leaf scorch is one of the most common leaf diseases of strawberry plants, caused by fungal species. Signs of leaf scorch disease consist of many small, irregular purple spots that appear on the outer surface of the leaf. Control of leaf scorch disease on strawberry leaves is important, because if it is ignored it will make the leaves more damaged and will cause losses for farmers. Deep learning is a branch of artificial intelligence that can perform image processing and data classification with promising results and great potential. Classification will be carried out with two classes in the form of images of healthy strawberry leaves and images of leaves affected by leaf scorch disease using the Convolutional Neural Network (CNN) algorithm with the MobileNet v1 pre-trained model. Based on the results of evaluating the model with the k-fold cross validation method, the highest average accuracy was obtained at 98.5%, obtained at the 5th iteration. While the lowest average accuracy value is obtained at the 2nd iteration, which is equal to 95.7%. The accuracy value of the average results of each iteration reached 96.7%. Key words: Convolutional Neural Network, Classification, Deep Learning, Strawberry Leaf Disease. Stroberi merupakan jenis tanaman subtropis dan tergolong tanaman buah berupa herba, yang pertama kali ditemukan di Chili, Amerika Latin. Terdapat beberapa penyakit yang dapat mempengaruhi daun stroberi, leaf scorch merupakan salah satu penyakit daun yang paling umum pada tanaman stroberi yang disebabkan oleh spesies jamur. Tanda penyakit leaf scorch terdiri dari banyak bintik-bintik kecil berwarna ungu tidak beraturan yang muncul di permukaan luar daun. Pengendalian penyakit leaf scorch pada daun stroberi penting, karena apabila diabaikan akan membuat daun menjadi lebih rusak dan akan menyebabkan kerugian oleh para petani. Deep learning merupakan salah satu cabang dari kecerdasan buatan yang dapat melakukan pemrosesan gambar dan klasifikasi data dengan menjanjikan hasil dan potensi yang besar. Klasifikasi akan dilakukan dengan dua kelas berupa citra daun stroberi sehat dan citra daun yang terkena penyakit leaf scorch menggunakan algoritma Convolutional Neural Network (CNN) dengan pre-trained model MobileNet v1. Berdasarkan hasil evaluasi model dengan metode k-fold cross validation, mendapatkan hasil rata-rata akurasi tertinggi yaitu sebesar 98,5%, didapat pada iterasi ke-5. Sedangkan untuk rata-rata nilai akurasi terendah didapat pada iterasi ke-2 yaitu sebesar 95,7%. Nilai akurasi dari hasil rata-rata setiap iterasi sebesar 96,7%. Kata kunci: Convolutional Neural Network, Deep Learning, Klasifikasi, Penyakit Daun Stroberi
Actions (login required)
 |
View Item |
