Related Experiment Video
Updated: Jun 29, 2025
08:05
Design and Analysis for Fall Detection System Simplification
Published on: April 6, 2020
10.7K
Comparison of Machine Learning Algorithms for Heartbeat Detection Based on Accelerometric Signals Produced by a Smart
Minh Long Hoang1, Guido Matrella1, Paolo Ciampolini1
1Department of Engineering and Architecture, University of Parma, 43124 Parma, Italy.
Sensors (Basel, Switzerland)
|March 28, 2024
Summary
Random Forest machine learning excels at non-intrusive heartbeat detection using smart bed accelerometers. This AI approach offers high accuracy for continuous sleep monitoring, outperforming deep learning models.
Area of Science:
- Biomedical Engineering
- Artificial Intelligence
- Wearable Technology
Background:
- Non-intrusive, continuous heart monitoring during sleep is crucial for healthcare and wellness.
- Smart beds equipped with accelerometers offer a promising platform for unobtrusive physiological signal acquisition.
- Existing methods often require direct contact or are limited in continuous monitoring capabilities.
Purpose of the Study:
- To compare the performance of Machine Learning (ML) and Deep Learning (DL) algorithms for heartbeat detection using smart bed accelerometer data.
- To evaluate the efficacy of various Artificial Intelligence (AI) algorithms in a real-world sleep monitoring setup.
- To identify the most accurate and efficient algorithm for real-time ballistocardiographic heartbeat detection.
Main Methods:
- Data acquisition using a 3D solid-state accelerometer on a smart bed, with photoplethysmography for ground truth.
- Processing acceleration signals via an STM 32-bit microcontroller and transmitting to a PC for recording.
- Training and evaluating multiple ML and DL algorithms using a dataset from 10 participants (120 min) with K-fold cross-validation.
Main Results:
- The Random Forest algorithm achieved the highest accuracy (>90%) among all tested ML and DL models.
- Random Forest demonstrated superior performance metrics, including recall, precision, and F1-scores.
- While training time was longer than some simpler ML models, Random Forest was significantly faster than Support Vector Machine and DL models.
Conclusions:
- The Random Forest algorithm is a highly effective solution for real-time ballistocardiographic heartbeat detection using smart bed data.
- Its high accuracy and robust performance metrics make it suitable for long-term, non-intrusive sleep monitoring.
- This approach shows significant potential for future healthcare and wellness monitoring applications.
Related Concept Videos
01:30Pulse rhythm
795
Pulse rhythm refers to the pattern of pulsations within specific intervals, offering valuable insights into the regularity or irregularity of the heart's beats as observed through the pattern of pulsation within specific intervals. A regular pulse exhibits a consistent heart rate with uniform waveforms and pulsation force, variations of which can be classified as normal, weak, or bounding.
Conversely, an irregular pulse pattern is termed dysrhythmia, stemming from disruptions in cardiac...
Conversely, an irregular pulse pattern is termed dysrhythmia, stemming from disruptions in cardiac...
795
01:30Equipments Used To Measure Blood Pressure
966
Direct Method
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...
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...
966