JURNAL MEDIA INFORMATIKA BUDIDARMA
Vol 5, No 1 (2021): Januari 2021

Klasifikasi Coronary Heart Disease (CHD) Berbasis Optimasi DNN dan Inisialisasi Kaiming He

Lia Andiani (Universitas Sriwijaya, Palembang)
Sukemi Sukemi (Universitas Sriwijaya, Palembang)
Dian Palupi (Universitas Sriwijaya, Palembang)
Nurul Afifah (Universitas Sriwijaya, Palembang)

Article Info

Publish Date
22 Jan 2021

Abstract

CHD is chest pain or discomfort that occurs if the area of the heart muscle does not get enough oxygen-rich blood. CHD is also known as coronary artery disease. CHD is increasing every year with a significant number of deaths. A learning algorithm is proposed to get better performance in accuracy, sensitivity, and specificity in CHD interpretation. Accuracy can be improved by adding a Kaiming He (2015) weight initialization optimization technique to the DNN structure. Therefore we propose that DNN is optimized with a Kaiming He weight initialization technique so that it can overcome weaknesses in the data variant. This is evidenced by the results of the accuracy performance of 98.73%. Initialization of kaiming he weights is proven to improve accuracy and overcome the problem of large data variants between classes

Copyrights © 2021




Citation Download
RIS
EndNote, Reference Manager, ProCite
BibTex
Latex, Jabref
Original Source
Download Original
Google Scholar
Check in Google Scholar
Journal Info
JURNAL MEDIA INFORMATIKA BUDIDARMA
Website

Abbrev

mib

Publisher

Sekolah Tinggi Manajemen Informatika dan Komputer Budi Darma

Subject

Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering

Description

Decission Support System, Expert System, Informatics tecnique, Information System, Cryptography, Networking, Security, Computer Science, Image Processing, Artificial Inteligence, Steganography etc (related to informatics and computer ...