Text

KLASIFIKASI PENYAKIT JANTUNG MENGGUNAKAN LEARNING VECTOR QUANTIZATION DAN PARTICLE SWARM OPTIMIZATION

---

Penilaian

---

The Learning Vector Quantization method can be used to classify heart disease data. However, the accuracy produced by the Learning Vector Quantization method is still less than optimal because the resulting accuracy depends on the initialization of the model and input parameters. This method can be developed by optimizing the weight of the input parameters using Particle Swarm Optimization to get better classification results. This test was carried out using 270 heart disease dataset resulting in an average accuracy of 83.46%, precision 88.29%, recall 72.57% and f-measure 90.06% using the best Particle Swarm Optimization parameter, namely the number of iterations is 30, the number of particles is 20, the value of c1 is 2 and c2 is 1 and the comparison of training data and test data used is 70: 30. While the average accuracy before optimization using Particle Swarm Optimization is 74.81%, precision is 77, 73%, recall 63.43% and f-measure 79.29%. These results prove that there is an increase in the average accuracy of the Learning Vector Quantization method after being optimized using the Particle Swarm Optimization method. Keywords: Classification, Heart Disease, Particle Swarm Optimization, Learning Vector Quantization.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2207002355	T74876	T748762022	Central Library (Referens)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T748762022

Publisher

Inderalaya : Jurusan Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya., 2022

Collation

xv, 102 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

005.360 7

Content Type

-

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Jurusan Teknik Informatika
Program untuk Komputer Personal

Specific Detail Info

-

Statement of Responsibility

SEPTA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment