Skripsi

KLASIFIKASI HAMA DAN PENYAKIT TANAMAN JAGUNG DENGAN PENDEKATAN ONE AGAINST ALL DAN ONE AGAINST ONE MULTICLASS CLASSIFICATION SUPPORT VECTOR MACHINE

---

Penilaian

---

Pests and diseases of corn plants are one of the factors that cause sub-optimal yields. To maximize corn production, proper cultivation processes are needed to anticipate corn plant pests and diseases. The purpose of this study was to classify pests and diseases of maize based on feature extraction of Red Green Blue (RGB) color using statistical learning multiclass Support Vector Machine method with One Against All and One Against One approaches. The research methods used include extracting RGB color features with Python programming, obtaining research datasets by taking the mean of RGB color feature extraction, performing split validation with a composition of 80% training dataset: 20% testing dataset, classification with multiclass Support Vector Machine One Against All and One Against One approaches, and calculates the level of classification accuracy with a multiclass confusion matrix. The accuracy of the multiclass Support Vector Machine classification with the One Against All approach is 77,75% average precision, 81,82% average recall, 78,79% average Fscore, 94,59% average accuracy, and 83,77% overall accuracy. The multiclass Support Vector Machine approach One Against One shows a relatively similar level of accuracy, namely, average precision of 77,88%, average recall of 81,4%, average Fscore of 79,4%, average accuracy of 94,81%, and overall accuracy of 84,42%.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2107003431	T55006	T550062021	Central Library (Referens)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T550062021

Publisher

Indralaya : Prodi Ilmu Matematika, Fakultas Matematika dan Ilmu Pengetahuan Alam., 2021

Collation

xv, 81 hlm,: ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

515.207

Content Type

Text

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Prodi Ilmu Matematika
Aspek Umum Analisis

Specific Detail Info

-

Statement of Responsibility

MURZ

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment