Image of IDENTIFIKASI HAMA DAN PENYAKIT PADA TANAMAN JAGUNG MENGGUNAKAN METODE RANDOM FOREST DAN FUZZY DECISION TREE

Skripsi

IDENTIFIKASI HAMA DAN PENYAKIT PADA TANAMAN JAGUNG MENGGUNAKAN METODE RANDOM FOREST DAN FUZZY DECISION TREE

Penilaian

0,0

dari 5
Penilaian anda saat ini :  

The rate of increasing national demand for corn is not matched by the rate of corn production. Pests and diseases are one of the factors that cause corn production to decline. To solve the problem, early identification of pests and diseases of corn crops is required. This study aims to identify pests and diseases in corn crops using digital image processing techniques in the form of RGB colors with machine learning where in the processing will be done classification process with random forest and fuzzy decision tree (FDT) method. The data used amounted to 761 images of diseases and pests of corn crops consisting of 108 locust pests, 298 pests of frugiperda spodoptera, 120 pests of cob borer, 88 leaf rust diseases, 48 bulai diseases, and 98 leaf blight diseases. Random forest is done by combining the trees (ensemble-tree) so that the forest is formed and FDT utilizes fuzzy set theory to describe the level of connectedness of a predictor variable and use the decision tree method for the decision tree formation process. In the classifying process, it is obtained that the red color has a greater effect compared to Green and Blue colors in the selection of the first node. FDT method is better in classifying pests and diseases in corn crops compared to Random Forest method where the best result for FDT method is at 80:20 ratio with accuracy of 90.1271%, sensitivity of 70.3812%, specificity of 94.0762%, and precision of 94.0762%.

Availability
Inventory Code Barcode Call Number Location Status
2107003420T51831T518312021Central Library (Referens)Available but not for loan - Not for Loan
Detail Information
Series Title
-
Call Number
T518312021
Publisher
Inderalaya : Prodi Ilmu Matematika, Fakultas Matematika dan Ilmu Pengetahuan Alam.,
Collation
xvi, 76 hlm,: ilus.; 29 cm
Language
Indonesia
ISBN/ISSN
-
Classification
518.107
Content Type
Text
Media Type
-
Carrier Type
-
Edition
-
Subject(s)
Prodi Ilmu Matematika
Algoritma, Metode Random Forest
Specific Detail Info
-
Statement of Responsibility
Other version/related

No other version available

File Attachment
Comments
You must be logged in to post a comment