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

PRATAMA, AGUNG and Resti, Yulia (2021) KLASIFIKASI HAMA DAN PENYAKIT TANAMAN JAGUNG DENGAN PENDEKATAN ONE AGAINST ALL DAN ONE AGAINST ONE MULTICLASS CLASSIFICATION SUPPORT VECTOR MACHINE. Undergraduate thesis, Sriwijaya University.

	Text RAMA_44201_08011181722001.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_44201_08011181722001_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (11MB) | Request a copy
Preview	Text RAMA_44201_08011181722001_0019077302_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (938kB) | Preview
	Text RAMA_44201_08011181722001_0019077302_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (813kB) | Request a copy
	Text RAMA_44201_08011181722001_0019077302_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (307kB) | Request a copy
	Text RAMA_44201_08011181722001_0019077302_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_44201_08011181722001_0019077302_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (304kB) | Request a copy
	Text RAMA_44201_08011181722001_0019077302_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (543kB) | Request a copy
	Text RAMA_44201_08011181722001_0019077302_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (286kB) | Request a copy

Abstract

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%.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	RGB extraction, Multiclass Support Vector Machine
Subjects:	Q Science > QA Mathematics > QA273-280 Probabilities. Mathematical statistics > QA279.C663 Response surfaces (Statistics)
Divisions:	08-Faculty of Mathematics and Natural Science > 44201-Mathematics (S1)
Depositing User:	AGUNG PRATAMA
Date Deposited:	28 Sep 2021 02:30
Last Modified:	28 Sep 2021 02:30
URI:	http://repository.unsri.ac.id/id/eprint/55006

Actions (login required)

View Item