Skripsi

KLASIFIKASI PENYAKIT HEPATITIS MENGGUNAKAN METODE LEARNING VECTOR QUANTIZATION DAN PARTICLE SWARM OPTIMIZATION (PSO)

---

Penilaian

---

The Learning Vector Quantization (LVQ) method is a classification method that is quite effective and widely used. However, this method has a weakness, namely, each attribute needs to be calculated distance, and the resulting accuracy depends on the initialization of the model, input parameters, and the amount of training data. This affects the resulting accuracy value. Therefore, it is necessary to optimize the LVQ method with attribute weighting using Particle Swarm Optimization (PSO). The data used are recorded data of hepatitis patients, totaling 155 data. The data was tested with 3 experimental configurations. The first experimental configuration was done by tuning the population which resulted in the best population size, namely 35 populations. The configuration of the second experiment performs tuning on the number of generations with the optimal number of generations being 20 generations. The third experimental configuration compares the optimization results using optimal parameters with the classification before optimization. The configuration of this third experiment resulted in an average accuracy value of data classification for Hepatitis sufferers of 84.71%. The increase in the average classification accuracy reached 5.32% from the accuracy value before optimization. The maximum accuracy value when the LVQ method is optimized with PSO reaches 87.02%. PSO's attribute weighting has succeeded in increasing the accuracy of the LVQ method in classifying data on hepatitis patients.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2107002500	T52784	T527842021	Central Library (Referens)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T527842021

Publisher

Inderalaya : Prodi Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya., 2021

Collation

xvi, 68 hlm,: ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

004.07

Content Type

Text

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Pemrosesan Data, Teknik Informatika
Prodi Teknik Informatika

Specific Detail Info

-

Statement of Responsibility

MURZ

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment