Skripsi

KLASIFIKASI 15 KELAS BEATS ARITMIA MENGGUNAKAN GATED RECURRENT UNIT (GRU)

---

Penilaian

---

Arrhythmia is a pattern of sudden fluctuations in heart rate from the normal heart rate. Cardiologists often have difficulty explaining electrocardiogram information when manually diagnosing cardiac arrhythmias. Gated Recurrent Unit (GRU) architecture is an effective method in processing time series type data. GRU has the advantage of optimizing the structure of LSTM network, GRU network only has two gate structures including update gate and reset gate which can solve the problem of long time interval prediction. Therefore, GRU aims to identify dependencies on various time scales. The data used is data containing ECG recordings of 48 patients in the MIT-BIH Arrhytmia Database. Classification of ECG signals using the Gated Recurrent Unit (GRU) approach by finding the most effective data model using the splitting method and the k-fold method. From the experiments conducted with the k-fold method, the best results were obtained with batch size parameters of 32 and learning rate of 0.00001, namely accuracy 99.92%, sensitivity 96.92%, specificity 99.90%, precision 93.38%, and f1-Score 92.88%. The GRU method successfully classifies arrhythmia signals.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2307003002	T126816	T1268162023	Central Library (REFERENS)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T1268162023

Publisher

Indralaya : Jurusan Sistem Komputer, Fakultas Ilmu Komputer Universitas Sriwijaya., 2023

Collation

xv, 90 hlm.; Ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

570.285 07

Content Type

-

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Jurusan Sistem Komputer
Pengolahan dan Analisa Data

Specific Detail Info

-

Statement of Responsibility

ANUG

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment