Text

PENINGKATAN AKURASI KLASIFIKASI PENYAKIT JANTUNG MENGGUNAKAN BACKPROPAGATION DENGAN SELEKSI FITUR ABC DAN K-NN

---

Penilaian

---

One of the non-communicable diseases that is susceptible to occur, especially when an individual is of a productive age, is heart disease. Death cases caused by heart disease based on data obtained from the World Health Organization (WHO) experienced more than 17 million victims in the world, a large enough number so that is the basis for researchers to process medical data on heart disease. The method to be applied for classification data mining was using the backpropagation algorithm because this algorithm had a simplicity and a fairly good performance. The backpropagation algorithm worked by adjusting the interconnected weights of neurons to achieve the minimum error between the output of the classification results and the real output. However, the Backpropagation Algorithm in achieving convergence tended to be slow when it got optimal accuracy, so the artificial bee colony algorithm was applied which usually converges to the global optimal efficiently to be used as feature selection from the applied Cleveland heart disease dataset. Then the k-nearest neighbor algorithm would be used to get the fitness value during the feature selection process because it was effective in reducing data dimensions while maintaining high classification accuracy. The results of the classification experiment with backpropagation without a combination resulted in an accuracy of 92.88%, while the combination classification experiment with backpropagation with artificial bee colony and k-nearest neighbor experienced an increase in accuracy by 95.93%.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2007000887	T42554	T425542020	Central Library (REFERENCES)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T425542020

Publisher

Indralaya : Prodi Magister Ilmu Komputer., 2020

Collation

xvii, 150 hlm.; ill.; 28 cm.

Language

Indonesia

ISBN/ISSN

-

Classification

005.07

Content Type

Text

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Prodi Magister Ilmu Komputer
Akurasi Klasifikasi

Specific Detail Info

-

Statement of Responsibility

TUTI

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment