Skripsi

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

---

Penilaian

---

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.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2407003902	T148500	T1485002024	Central Library (REFERENCES)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T1485002024

Publisher

Indralaya : Prodi Teknik Informatika, Fakultas Ilmu Komputer., 2024

Collation

xviii, VI-2 hlm.; ilus.; tab.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

006.307

Content Type

Text

Media Type

unmediated

Carrier Type

unspecified

Edition

-

Subject(s)

Learning Vector Quantization (LVQ)
Prodi Teknik Informatika

Specific Detail Info

-

Statement of Responsibility

UIN Farrah

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment