Image of KLASIFIKASI KEJADIAN HUJAN KOTA PRABUMULIH MENGGUNAKAN METODE DECISION TREE TANPA DAN DENGAN SYNTHETIC MINORITY OVER-SAMPLING TECHNIQUE (SMOTE)

Skripsi

KLASIFIKASI KEJADIAN HUJAN KOTA PRABUMULIH MENGGUNAKAN METODE DECISION TREE TANPA DAN DENGAN SYNTHETIC MINORITY OVER-SAMPLING TECHNIQUE (SMOTE)

Penilaian

0,0

dari 5
Penilaian anda saat ini :  

Classification of rainfall events in Prabumulih City is important because it affects the agricultural and plantation sectors, especially oil palm and rice. Ecologically, oil palm and rice require a lot of water in the growth process and will thrive in an environment with sufficient soil moisture. In addition to its benefits to the agricultural and plantation sectors, the classification of rainfall events is also useful for preparing solutions to the impact of extreme weather that has the potential to cause disasters such as landslides and floods that result in disrupted community activities. This research uses secondary data obtained from Visual Grossing which has 17 variables with 2556 data. In this data there is class imbalance, the class balancing technique used is Synthetic Minority Oversampling Technique (SMOTE). The method used for the classification of rainfall events is the Decision Tree C4.5 method. The results of this study obtained a value on Decision Tree C4.5 without SMOTE with accuracy of 75.62%, precision of 74.07% and recall of 87.07%. While using SMOTE in the Decision Tree method results in an accuracy value of 74.38%, precision of 70.84% and recall of 92.44%. Keywords : Rainfall Events, Decision Tree, SMOTE, Prabumulih City

Availability
Inventory Code Barcode Call Number Location Status
2407005207T145959T1459592024Central Library (References)Available but not for loan - Not for Loan
Detail Information
Series Title
-
Call Number
T1459592024
Publisher
Indralaya : Prodi Ilmu Matematika, Fakultas Matematika Dan Ilmu Pengetahuan Alam Universitas Sriwijaya.,
Collation
xiii, 56 hlm.; ilus.; tab, 29 cm.
Language
Indonesia
ISBN/ISSN
-
Classification
512.107
Content Type
Text
Media Type
unmediated
Carrier Type
other (computer)
Edition
-
Subject(s)
Prodi Ilmu Matematika
Aljabar digabung dengan cabang lain Matematika
Specific Detail Info
-
Statement of Responsibility
Other version/related
File Attachment
Comments
You must be logged in to post a comment