Skripsi

KLASIFIKASI KELAS PENYAKIT JANTUNG BERDASARKAN SINYAL ELEKTROKARDIOGRAM MENGGUNAKAN METODE CONVOLUTIONAL NEURAL NETWORK 1-DIMENSI

---

Penilaian

---

Heart disease can be identified based on the pattern of electrical current activity in the heart using an electrocardiogram. The data generated through the electrocardiogram will be in the form of a signal that represents the human heartbeat or is called an electrocardiograph. This study aims to classify classes of heart disease based on the signal morphology of each class using the convolutional neural network method. Based on previous studies, the 1-dimensional CNN method has advantages because it has feature extraction or feature learning in the learning process. In this study, the ECG signal classification process will be divided into five scenarios, with the first four scenarios dividing the signal segmentation into 1000 nodes, 2000 nodes, 3000 nodes, and 4000 nodes. Then in scenario five using 2000 nodes segmentation with the addition of three new datasets, each of which is the china physiological signal challenge 2018, MIT-BIH Normal Sinus Rhythm Database, BIDMC Congestive Heart Failure Database. From the 5th experimental scenario, the best performance results in training data fold 9 with accuracy, sensitivity, specificity, precision, F1score, and error which are 100.00%, 99.98%, 100.00%, 100.00% and 00.00%, respectively.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2101002256	T52182	T521822021	Central Library (REFERENSI)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T521822021

Publisher

Inderalaya : Jurusan Sistem Komputer, Fakultas Ilmu Komputer Universitas Sriwijaya., 2021

Collation

xiv, 69 hlm.; illuss.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

005.707

Content Type

Text

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Jurusan sistem Komputer D3
Data Sistem Komputer

Specific Detail Info

-

Statement of Responsibility

NO

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment