Blood Pressure Estimation from PPG Signals using a Hybrid CNN–BiLSTM Deep Learning Framework
Fuente:
Zenodo
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Recurso digital |
| Language: | English |
| Published: |
Zenodo
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866902181427281920 |
|---|---|
| author | Sharma, Arjun Kumar Gupta, Ashish Sahu, Saket |
| author_facet | Sharma, Arjun Kumar Gupta, Ashish Sahu, Saket |
| contents | <p>This research presents a hybrid deep learning framework for non-invasive blood pressure estimation using photoplethysmography (PPG) signals. The proposed model combines Convolutional Neural Networks (CNN) for spatial feature extraction with Bidirectional Long Short-Term Memory (BiLSTM) networks for temporal sequence learning. The system was trained on preprocessed PPG data using a 300-sample window and evaluated for Systolic, Diastolic, and Mean Arterial Pressure. The hybrid CNN-BiLSTM architecture achieved promising accuracy with lower MAE and RMSE values, demonstrating its potential for real-time, cuff-less blood pressure monitoring applications.</p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_17275828 |
| institution | Zenodo |
| language | eng |
| publishDate | 2025 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | Blood Pressure Estimation from PPG Signals using a Hybrid CNN–BiLSTM Deep Learning Framework Sharma, Arjun Kumar Gupta, Ashish Sahu, Saket Blood pressure estimation PPG SIGNALS CNN-BiLSTM Signal Processing <p>This research presents a hybrid deep learning framework for non-invasive blood pressure estimation using photoplethysmography (PPG) signals. The proposed model combines Convolutional Neural Networks (CNN) for spatial feature extraction with Bidirectional Long Short-Term Memory (BiLSTM) networks for temporal sequence learning. The system was trained on preprocessed PPG data using a 300-sample window and evaluated for Systolic, Diastolic, and Mean Arterial Pressure. The hybrid CNN-BiLSTM architecture achieved promising accuracy with lower MAE and RMSE values, demonstrating its potential for real-time, cuff-less blood pressure monitoring applications.</p> |
| title | Blood Pressure Estimation from PPG Signals using a Hybrid CNN–BiLSTM Deep Learning Framework |
| topic | Blood pressure estimation PPG SIGNALS CNN-BiLSTM Signal Processing |
| url | https://doi.org/10.5281/zenodo.17275828 |