Image of KLASIFIKASI GANGGUAN IRAMA JANTUNG ARITMIA MENGGUNAKAN METODE CONVOLUTIONAL NEURAL NETWORK 1-DIMENSI

Text

KLASIFIKASI GANGGUAN IRAMA JANTUNG ARITMIA MENGGUNAKAN METODE CONVOLUTIONAL NEURAL NETWORK 1-DIMENSI

Penilaian

0,0

dari 5
Penilaian anda saat ini :  

Arrhythmias are considered to be the most frequently observed cases of cardiac abnormalities. Cardiac abnormalities such as arrhythmias affecting the electrical activity of the heart can be detected using an analysis of the ECG waveform that differs from the normal ECG waveform. Classification of ECG Arrhythmias automatically using deep learning can help doctors because of human errors in manually annotating ECG signals. 1 Dimensional CNN is commonly used to solve difficult image-based pattern recognition but with a simple and precise architecture. CNN 1 Dimensions has a very good performance with data processing related to image data, computer vision. In this study, the classification scenario carried out is on the 1 Dimensional CNN model with optimized parameter values including epoch, batch size, and learning rate resulting in a total of 22 models. Based on 22 tested models, the best classification model with parameter values of 64 batch size, 0.001 learning rate, and 200 epochs. The CNN 1 Dimension model has the highest evaluation results in the classification of arrhythmic heart rhythm disturbance signals with sensitivity, precision, accuracy and F1 values of 99.4%, 95%, 99% and 99.69%.

Availability
Inventory Code Barcode Call Number Location Status
2207000006T61824T618242022Central Library (Referens)Available but not for loan - Not for Loan
Detail Information
Series Title
-
Call Number
T618242022
Publisher
Inderalaya : Jurusan Sistem Komputer, Fakultas Ilmu Komputer Universitas Sriwijaya.,
Collation
xvi, 120 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
Other version/related

No other version available

File Attachment
Comments
You must be logged in to post a comment