Event-driven ECG signal feature detection on single/multi-channel data via neuromorphic approach
Cardiovascular diseases (CVDs) stand as the primary cause of death worldwide, highlighting the critical need for enhanced diagnostic tools for early detection and intervention. This project is dedicated to advancing Electrocardiogram (ECG) signal analysis by applying deep learning techniques, specif...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project |
| Language: | English |
| Published: |
Nanyang Technological University
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/177048 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Nanyang Technological University |
| Language: | English |
| Summary: | Cardiovascular diseases (CVDs) stand as the primary cause of death worldwide, highlighting the critical need for enhanced diagnostic tools for early detection and intervention. This project is dedicated to advancing Electrocardiogram (ECG) signal analysis by applying deep learning techniques, specifically Multi-Layer Perceptrons (MLPs) and Long Short-Term Memory (LSTM) networks. Moving away from the traditional linear and threshold-based analysis methods, this study employs the computational prowess of neural networks to achieve precise identification of ECG signal features such as R-peaks and to accurately classify heartbeat normality, achieving both tasks with remarkable efficiency and precision. |
|---|