Text

IMPLEMENTASI SISTEM DETEKSI ATRIAL FIBRILASI BERBASIS KOMPUTASI AWAN MENGGUNAKAN METODE CONVOLUTIONAL NEURAL NETWORK

---

Penilaian

---

Atrial Fibrillation (AF) is a rhythm disorder in the heart where the consecutive irregular rhythm occurs due to atrial depolarization. Electrocardiogram (ECG) signals present the electrical activity of the heart. The ECG signals can be identified to classify varying the heart disease. In this study, deep learning based on a convolutional neural network algorithm is used to determine the condition of the heart, it can be extracted by the features. In addition, the process is not only to generate the deep learning model but also can be deployed. Hence, this study generates the design of a system-web based on cloud computing to detect the presence of heart disease, specifically AF. This study conducts three experiments using four public datasets. Among three experiments, the best model is the first experiment that used unseen data, and it was obtained the 96.40% accuracy, 94.75% sensitivity, 93.52% precision,93,52 specificity, and 94% F1 score. As the results, it can be concluded by using the cloud computing services, the best results show while using GPU devices with an inference time of 0.048 seconds, and a server throughput of 20 predictions per second.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2207001871	T72783	T727832022	Central Library (Referens)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T727832022

Publisher

Inderalaya : Jurusan Sistem Komputer, Fakultas Ilmu Komputer Universitas Sriwijaya., 2022

Collation

xiv, 74 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

004.650 7

Content Type

-

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Jurusan Sistem Komputer
Jaringan Komunikasi Komputer

Specific Detail Info

-

Statement of Responsibility

SEPTA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment