PENGARUH PARTICLE SWARM OPTIMIZATION (PSO) PADA ALGORITMA C4.5 UNTUK KLASIFIKASI HARAPAN HIDUP PASIEN HEPATITIS

ARIZALDI, ARIZALDI and Rini, Dian Palupi and Rodiah, Desty (2020) PENGARUH PARTICLE SWARM OPTIMIZATION (PSO) PADA ALGORITMA C4.5 UNTUK KLASIFIKASI HARAPAN HIDUP PASIEN HEPATITIS. Undergraduate thesis, Sriwijaya University.

	Text RAMA_55201_09021181520123_0023027804_8802870018.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (6MB) | Request a copy
	Text RAMA_55201_09021181520123_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (9MB) | Request a copy
Preview	Text RAMA_55201_09021181520123_0023027804_8802870018_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (8MB) | Preview
	Text RAMA_55201_09021181520123_0023027804_8802870018_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (312kB) | Request a copy
	Text RAMA_55201_09021181520123_0023027804_8802870018_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55201_09021181520123_0023027804_8802870018_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55201_09021181520123_0023027804_8802870018_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (171kB) | Request a copy
	Text RAMA_55201_09021181520123_0023027804_8802870018_06.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (92kB) | Request a copy
	Text RAMA_55201_09021181520123_0023027804_8802870018_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (101kB) | Request a copy
	Text RAMA_55201_09021181520123_0023027804_8802870018_07_lamp.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (157kB) | Request a copy

Abstract

Hepatitis is all types of inflammation of the liver cells caused by infection (viruses, bacteria, parasites), drugs, alcohol consumption, excess fat, and autoimmune diseases. Data mining clinic is the application of data mining methods with the aim of extracting information on medical data and clinical data. C4.5 algorithm is a supervised learning method that has a decision tree scheme. C4.5 algorithm has good accuracy, it also has weaknesses in reading large amounts of data, it needs to be optimized using Particle Swarm Optimization (PSO) method for attribute selection to improve accuracy results. The data used has 20 attributes including decision labels and 155 records or 3100 total of data. In this case, testing the classification results used the Confusion Matrix concept. From the test results, it was found that C4.5 algorithm produced an average accuracy value of 56% and an increase in the average accuracy value of 70.2% after attribute selection using PSO method. It can be concluded that the combination of PSO and C4.5 methods has better accuracy in classifying the life expectancy of hepatitis patients compared to using C4.5 algorithm without PSO.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Hepatitis, C4.5, Particle Swarm Optimization, Seleksi Atribut.
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 9809 not found.
Date Deposited:	13 Jan 2021 05:15
Last Modified:	13 Jan 2021 05:15
URI:	http://repository.unsri.ac.id/id/eprint/39835

Actions (login required)

View Item