Related Experiment Video
Updated: Oct 10, 2025

A Novel Digital Platform for a Monitored Home-based Cardiac Rehabilitation Program
Published on: April 19, 2019
Energy-efficient Blood Pressure Monitoring based on Single-site Photoplethysmogram on Wearable Devices
This study presents an accurate, energy-efficient cuffless blood pressure monitoring (BPM) system using a single Photoplethysmographic (PPG) sensor and Artificial Neural Network (ANN) on edge devices. The novel approach enhances accuracy by optimizing signal preprocessing for continuous BPM readings.
Area of Science:
- Biomedical Engineering
- Artificial Intelligence in Healthcare
- Wearable Technology
Background:
- Traditional blood pressure monitoring (BPM) often relies on invasive cuff-based methods.
- There is a growing need for continuous, cuffless, and energy-efficient BPM solutions for wearable devices.
- Existing cuffless BPM methods using Photoplethysmography (PPG) face challenges in accuracy and real-time edge implementation.
Purpose of the Study:
- To develop an accurate and energy-efficient cuffless blood pressure monitoring (BPM) system.
- To leverage Artificial Neural Networks (ANN) for processing single-site PPG signals on edge wearable devices.
- To improve BPM accuracy through advanced signal preprocessing techniques.
Main Methods:
- Utilized a single-site Photoplethysmographic (PPG) sensor to capture continuous physiological data.
- Implemented an Artificial Neural Network (ANN) model for analyzing preprocessed PPG signals.
- Employed outlier removal and whole-signal based inputs for enhanced accuracy compared to parameter-based methods.
Main Results:
- Achieved competitive accuracy with Mean Absolute Error (MAE) ± Root Mean Square Deviation (RMSD) of 3.42 ± 5.42 mmHg for systolic BP (SBP), 1.92 ± 3.29 mmHg for diastolic BP (DBP), and 2.21 ± 3.50 mmHg for mean arterial BP (MAP).
- Demonstrated an energy-efficient edge computing solution with an average energy consumption of 2.1 mJ per reading.
- Real-time hardware evaluation showed processing time of 42.2 ms and memory usage of 18.2 KB RAM per reading.
Conclusions:
- The proposed single-site PPG-based BPM system offers a highly accurate and energy-efficient solution for cuffless monitoring on edge devices.
- This represents a novel advancement in edge computing artificial intelligence for continuous blood pressure assessment.
- The method's performance and resource efficiency make it suitable for integration into next-generation wearable health trackers.
Related Concept Videos
Equipments Used To Measure Blood Pressure
This invasive approach involves cannulating a peripheral artery. During each cardiac contraction, pressure generates mechanical motion within the catheter, transmitted through rigid, fluid-filled tubing to a transducer. This transducer converts mechanical motion into electrical signals displayed as waveforms on a monitor. An automatic flushing system prevents blood backflow. Due to the potential risk of unexpected arterial blood loss, this method is primarily used in intensive...
Sites for measruring blood pressure
The Brachial Artery: Primary Site for Blood Pressure Measurement
Pulse rhythm
Conversely, an irregular pulse pattern is termed dysrhythmia, stemming from disruptions in cardiac...
Holter Monitor: 24-Hour Monitoring
Assessing Blood pressure using a doppler ultrasound
Pre-Procedural Guidelines for Doppler Ultrasound Blood Pressure Assessment:
Preparation of Equipment:
Assessment of blood pressure in brachial artery(one-step method)
Prepare for the Procedure:

