OPTIMASI METODE LEARNING VECTOR QUANTIZATION MENGGUNAKAN PARTICLE SWARM OPTIMIZATION UNTUK KLASIFIKASI DATA PENDERITA PENYAKIT STROKE

NADAPDAP, BETHA RIANTI and Rini, Dian Palupi (2024) OPTIMASI METODE LEARNING VECTOR QUANTIZATION MENGGUNAKAN PARTICLE SWARM OPTIMIZATION UNTUK KLASIFIKASI DATA PENDERITA PENYAKIT STROKE. Undergraduate thesis, Sriwijaya University.

	Text RAMA_55201_09021282025035.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy
	Text RAMA_55201_09021282025035_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (6MB) | Request a copy
	Text RAMA_55201_09021282025035_0023027804_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (2MB)
	Text RAMA_55201_09021282025035_0023027804_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (290kB) | Request a copy
	Text RAMA_55201_09021282025035_0023027804_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (404kB) | Request a copy
	Text RAMA_55201_09021282025035_0023027804_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (636kB) | Request a copy
	Text RAMA_55201_09021282025035_0023027804_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (272kB) | Request a copy
	Text RAMA_55201_09021282025035_0023027804_06.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (10kB) | Request a copy
	Text RAMA_55201_09021282025035_0023027804_07_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (89kB) | Request a copy
	Text RAMA_55201_09021282025035_0023027804_08_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (265kB) | Request a copy

Abstract

Stroke is a functional disorder condition that occurs due to blockage in blood vessels that transport oxygen and blood to the brain, causing in the death of brain cells, paralysis, and even death. Essentially, stroke can be prevented if treated quickly. However, stroke treatment is often too late because many people are unaware of the risk of stroke beforehand. Therefore, a method is needed that is able to carry out early detection of stroke by classifying whether the patient is at risk of stroke or not. Learning Vector Quantization (LVQ) is a classification method with a simple structure and fast learning process. However, LVQ has a weakness in initialization the learning vector weight. The process of initializing non-optimal weights can result in poor model and suboptimal classification results. Therefore, optimization is performed using Particle Swarm Optimization (PSO) to find the best weights to improve LVQ accuracy. This research also applies oversampling to overcome the imbalance of class distribution in the data. The test results show that the LVQ method optimized using PSO produces better accuracy than the LVQ method alone. The best performance for classification with LVQ optimized using PSO was achieved with number of iterations = 50, number of particles = 20, c1 = 0.5, c2 = 1, and w value = 0.8, which resulted in average accuracy, precision, recall and f1-score values of 76.57%, 73.28%, 84.34% and 78.29%, respectively. Meanwhile, the average results of accuracy, precision, recall and f1-score from the LVQ method alone were 70.46%, 68.70%, 77.11% and 72.41%, respectively.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Stroke, Klasifikasi, Learning Vector Quantization, Optimasi Bobot, Particle Swarm Optimization
Subjects:	R Medicine > R Medicine (General) > R858-859.7 Computer applications to medicine. Medical informatics T Technology > T Technology (General) > T1-995 Technology (General)
Divisions:	09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User:	Betha Rianti Nadapdap
Date Deposited:	01 Jul 2024 02:07
Last Modified:	01 Jul 2024 02:07
URI:	http://repository.unsri.ac.id/id/eprint/148500

Actions (login required)

View Item