Text

OPTIMASI PARAMETER LVQ MENGGUNAKAN ALGORITMA PSO UNTUK KLASIFIKASI PENYAKIT DIABETES

---

Penilaian

---

Classification of diabetes data can be implemented using several different methods, one of which is Learning Vector Quantization. Nevertheless, the output obtained from this method could not always achieve the optimal results, because Learning Vector Quantization classification process relies on the weight values being used for the system. Therefore, modification was made to further enhance Learning Vector Quantization method in the case of diabetes classification, by utilizing the Particle Swarm Optimization algorithm. This research was conducted using as many as 768 diabetes data from a public resource. The testing of Learning Vector Quantization method without Particle Swarm Optimization managed to yield the average accuracy, precision, recall and f-measure respectively as follows: 74,14%, 61,85%, 61,76%, and 66,31%. However, diabetes data classification using Learning Vector Quantization which was later optimized using the Particle Swarm Optimization algorithm was able to yield the average accuracy, precision, recall and f-measure as much as 78,22%, 73,17%, 67,31%, and 74,63% respectively. The results that have been obtained prove that Particle Swarm Optimization algorithm is capable of providing an increase in accuracy for classification system based on Learning Vector Quantization.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2307002963	T118453	T1184532023	Central Library (Referens)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T1184532023

Publisher

Inderalaya : Jurusan Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya., 2023

Collation

xxi, 117 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

006.307

Content Type

-

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Sistem Pakar
Jurusan Teknik Informatika

Specific Detail Info

-

Statement of Responsibility

SEPTA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment