PERBANDINGAN SELEKSI FITUR TEKNIK WRAPPER MENGGUNAKAN FORWARD SELECTION DENGAN TEKNIK FILTER MENGGUNAKAN SINGULAR VALUE DECOMPOSITION TERHADAP HASIL PENGKLASTERAN DOKUMEN

MORIKAWA, DIVINDA and Jambak, M. Ihsan and Rodiah, Desty (2020) PERBANDINGAN SELEKSI FITUR TEKNIK WRAPPER MENGGUNAKAN FORWARD SELECTION DENGAN TEKNIK FILTER MENGGUNAKAN SINGULAR VALUE DECOMPOSITION TERHADAP HASIL PENGKLASTERAN DOKUMEN. Undergraduate thesis, Sriwijaya University.

	Text RAMA_55201_09021181520121.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy
	Text RAMA_55201_09021181520121_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (13MB) | Request a copy
Preview	Text RAMA_55201_09021181520121_0205046801_8802870018_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (628kB) | Preview
	Text RAMA_55201_09021181520121_0205046801_8802870018_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (177kB) | Request a copy
	Text RAMA_55201_09021181520121_0205046801_8802870018_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (551kB) | Request a copy
	Text RAMA_55201_09021181520121_0205046801_8802870018_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_55201_09021181520121_0205046801_8802870018_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (506kB) | Request a copy
	Text RAMA_55201_09021181520121_0205046801_8802870018_06.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (20kB) | Request a copy
	Text RAMA_55201_09021181520121_0205046801_8802870018_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (148kB) | Request a copy
	Text RAMA_55201_09021181520121_0205046801_8802870018_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (459kB) | Request a copy

Abstract

k-Means is the simple clustering algorithm that has fast time of processing data. However, k-Means can cause curse of dimentionality on high dimentional data. From previsious study, feature selection using filter techcnique in Singular Value Decomposition can reduce dimentional data and improve kmeans clustering results. Besides, there is also wrapper technique in fitur selection. Forward Selection is wrapper approaches used in feature selection oftenly. It can remove irrelevant feature, develope and immprove the quality of data, performance and accurateness of the model. The results obtained by the combination of forward selection and K-Means improve the performance of text clustering by 29,3%, while combination of SVD and k-Means just improve the performance of text clustering by 17,9%. On the other hand, SVD has a faster time compared to forward selection and SVD can reduce the number of repetitions of processes.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	K-Means, fitur selection, forward selection, singular value decomposition.
Subjects:	Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation.
Divisions:	09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User:	Users 7771 not found.
Date Deposited:	01 Sep 2020 07:49
Last Modified:	01 Sep 2020 07:49
URI:	http://repository.unsri.ac.id/id/eprint/34338

Actions (login required)

View Item