Text

KLASIFIKASI HAMA DAN PENYAKIT PADA TANAMAN JAGUNG MENGGUNAKAN METODE RANDOM FOREST BERDASARKAN REPEATED K-FOLD CROSS VALIDATION

---

Penilaian

---

Corn has a fairly high economic value, because it can be used as the main food ingredient for humans, animal feed and raw materials for various other industries. However, corn production is not commensurate with the existing needs. This is because in the corn cultivation process there are obstacles, namely attacks from pests and diseases. Early detection of pests and diseases in maize can help farmers to control the quality and quantity of maize production. In this study, the classification of pests and diseases on corn plants will be carried out using the random forest method based on repeated K-fold cross validation. The data used is in the form of images of corn plants that are attacked by pests and diseases. So to obtain the dataset, the RGB color feature extraction process is carried out first, which produces an average image from the R layer, G layer, and B layer. Then the dataset is discretized to adjust for the possibility of the appearance of the continue value in the dataset feature being very small so that it will affect the classification process using the random forest method. From the discretization results, the dataset is further divided into train data and test data using repeated K-fold cross validation with K=5 and 10 repetitions, resulting in 50 sets of train and test data respectively. The classification process is carried out using the random forest method and to measure the accuracy of the classification a confusion matrix is used. The results of this study indicate that by using the random forest method based on repeated K-fold cross validation, it can obtain an accuracy level of 90.5%, precision of 57.2%, and recall of 73%.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2207004391	T81220	T812202022	Central Library (Referens)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T812202022

Publisher

Inderalaya : Jurusan Matematika, Fakultas Matematika Dan Ilmu Pengetahuan Alam Universitas Sriwijaya., 2022

Collation

xiii, 51 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

519.507

Content Type

-

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Jurusan Matematika
Matematika Statistikal

Specific Detail Info

-

Statement of Responsibility

SEPTA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment