Normal view MARC view ISBD view

Development of deep learning framework for prediction of cardiovascular disease / Mohd Syafiq Asyraf Bin Suhaimi

By:

Mohd Syafiq Asyraf Bin Suhaimi [author.]

Material type: Text

text

Media type:

unmediated

Carrier type:

volume

ISBN:

THE0010204 (Local)

Subject(s):

Dissertation note: Thesis (Master of Science) -- Universiti Malaysia Pahang Al Sultan Abdullah– 2025 Abstract: Cardiovascular disease (CVD) remains the leading cause of death worldwide and our country, Malaysia. Hence, early detection is critical for effective intervention. This study aims to develop a deep learning framework for predicting CVD using data from smartwatches, which offer non-invasive and real-time health monitoring capabilities. The research employs two deep learning techniques: convolutional neural networks (CNN) and Long Short-Term Memory (LSTM) networks. Electrocardiogram (ECG) and heart rate data were collected from 20 volunteers using local smartwatches supplemented with a publicly available dataset from Kaggle. Data pre-processing involved denoising ECG signals and normalizing heart rate readings to ensure accuracy. The models were evaluated using precision, recall, F1-score, and accuracy metrics, achieving over 99 percent across all measures. While both models demonstrated high predictive power, the LSTM model outperformed CNN in computational efficiency, with 31 minutes to complete model training compared to CNN, which took 87 minutes. The study highlights the potential for wearable devices for real-time CVD monitoring and early diagnosis. Future work will explore including additional data sources and advanced modeling involving ensemble techniques.

Tags from this library: No tags from this library for this title. Log in to add tags.

Average rating: 0.0 (0 votes)

Holdings ( 2 )
Title notes ( 4 )

Holdings
Item type	Current library	Call number	Status	Date due	Barcode
Thesis	UMPLIB GAMBANG	PSM .A89 2025 r Thesis (Browse shelf(Opens below))	Not for loan		T000003871
Thesis	UMPLIB GAMBANG	CD13806 (Browse shelf(Opens below))	In Transit		T000003872

Centre for Mathematical Sciences

Thesis (Master of Science) -- Universiti Malaysia Pahang Al Sultan Abdullah– 2025

Includes bibliographical references

Cardiovascular disease (CVD) remains the leading cause of death worldwide and our country, Malaysia. Hence, early detection is critical for effective intervention. This study aims to develop a deep learning framework for predicting CVD using data from smartwatches, which offer non-invasive and real-time health monitoring capabilities. The research employs two deep learning techniques: convolutional neural networks (CNN) and Long Short-Term Memory (LSTM) networks. Electrocardiogram (ECG) and heart rate data were collected from 20 volunteers using local smartwatches supplemented with a publicly available dataset from Kaggle. Data pre-processing involved denoising ECG signals and normalizing heart rate readings to ensure accuracy. The models were evaluated using precision, recall, F1-score, and accuracy metrics, achieving over 99 percent across all measures. While both models demonstrated high predictive power, the LSTM model outperformed CNN in computational efficiency, with 31 minutes to complete model training compared to CNN, which took 87 minutes. The study highlights the potential for wearable devices for real-time CVD monitoring and early diagnosis. Future work will explore including additional data sources and advanced modeling involving ensemble techniques.