Reliable ECG Anomaly Detection on Edge Devices for Internet of Medical Things Applications
The advent of Tiny Machine Learning (TinyML) has unlocked the potential to deploy machine learning models on resource-constrained edge devices, revolutionizing real-time monitoring in Internet of Medical Things (IoMT) applications. This study introduces a novel approach to real-time electrocardiogra...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-04-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/8/2496 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850180419210706944 |
|---|---|
| author | Moez Hizem Leila Bousbia Yassmine Ben Dhiab Mohamed Ould-Elhassen Aoueileyine Ridha Bouallegue |
| author_facet | Moez Hizem Leila Bousbia Yassmine Ben Dhiab Mohamed Ould-Elhassen Aoueileyine Ridha Bouallegue |
| author_sort | Moez Hizem |
| collection | DOAJ |
| description | The advent of Tiny Machine Learning (TinyML) has unlocked the potential to deploy machine learning models on resource-constrained edge devices, revolutionizing real-time monitoring in Internet of Medical Things (IoMT) applications. This study introduces a novel approach to real-time electrocardiogram (ECG) anomaly detection by integrating TinyML with edge Artificial Intelligence (AI) on low-power embedded systems. We demonstrate the feasibility and effectiveness of deploying optimized models on edge devices, such as the Raspberry Pi and Arduino, to detect ECG anomalies, including arrhythmias. The proposed workflow encompasses data preprocessing, feature extraction, and model inference, all executed directly on the edge device, eliminating the need for cloud resources. To address the constraints of memory and power consumption in wearable devices, we applied advanced optimization techniques, including model pruning and quantization, achieving an optimal balance between accuracy and resource utilization. The optimized model achieved an accuracy of 92.3% while reducing the power consumption to 0.024 mW, enabling continuous, long-term health monitoring with minimal energy requirements. This work highlights the potential of TinyML to advance edge AI for real-time medical applications. |
| format | Article |
| id | doaj-art-dc336212dc8c49db8c9e10918d563dcb |
| institution | OA Journals |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-dc336212dc8c49db8c9e10918d563dcb2025-08-20T02:18:10ZengMDPI AGSensors1424-82202025-04-01258249610.3390/s25082496Reliable ECG Anomaly Detection on Edge Devices for Internet of Medical Things ApplicationsMoez Hizem0Leila Bousbia1Yassmine Ben Dhiab2Mohamed Ould-Elhassen Aoueileyine3Ridha Bouallegue4Innov’COM Laboratory, Higher School of Communication of Tunis, University of Carthage, Tunis 1054, TunisiaInnov’COM Laboratory, Higher School of Communication of Tunis, University of Carthage, Tunis 1054, TunisiaInnov’COM Laboratory, Higher School of Communication of Tunis, University of Carthage, Tunis 1054, TunisiaInnov’COM Laboratory, Higher School of Communication of Tunis, University of Carthage, Tunis 1054, TunisiaInnov’COM Laboratory, Higher School of Communication of Tunis, University of Carthage, Tunis 1054, TunisiaThe advent of Tiny Machine Learning (TinyML) has unlocked the potential to deploy machine learning models on resource-constrained edge devices, revolutionizing real-time monitoring in Internet of Medical Things (IoMT) applications. This study introduces a novel approach to real-time electrocardiogram (ECG) anomaly detection by integrating TinyML with edge Artificial Intelligence (AI) on low-power embedded systems. We demonstrate the feasibility and effectiveness of deploying optimized models on edge devices, such as the Raspberry Pi and Arduino, to detect ECG anomalies, including arrhythmias. The proposed workflow encompasses data preprocessing, feature extraction, and model inference, all executed directly on the edge device, eliminating the need for cloud resources. To address the constraints of memory and power consumption in wearable devices, we applied advanced optimization techniques, including model pruning and quantization, achieving an optimal balance between accuracy and resource utilization. The optimized model achieved an accuracy of 92.3% while reducing the power consumption to 0.024 mW, enabling continuous, long-term health monitoring with minimal energy requirements. This work highlights the potential of TinyML to advance edge AI for real-time medical applications.https://www.mdpi.com/1424-8220/25/8/2496TinyMLedge AIIoMTanomaly detectionECGlow-power |
| spellingShingle | Moez Hizem Leila Bousbia Yassmine Ben Dhiab Mohamed Ould-Elhassen Aoueileyine Ridha Bouallegue Reliable ECG Anomaly Detection on Edge Devices for Internet of Medical Things Applications Sensors TinyML edge AI IoMT anomaly detection ECG low-power |
| title | Reliable ECG Anomaly Detection on Edge Devices for Internet of Medical Things Applications |
| title_full | Reliable ECG Anomaly Detection on Edge Devices for Internet of Medical Things Applications |
| title_fullStr | Reliable ECG Anomaly Detection on Edge Devices for Internet of Medical Things Applications |
| title_full_unstemmed | Reliable ECG Anomaly Detection on Edge Devices for Internet of Medical Things Applications |
| title_short | Reliable ECG Anomaly Detection on Edge Devices for Internet of Medical Things Applications |
| title_sort | reliable ecg anomaly detection on edge devices for internet of medical things applications |
| topic | TinyML edge AI IoMT anomaly detection ECG low-power |
| url | https://www.mdpi.com/1424-8220/25/8/2496 |
| work_keys_str_mv | AT moezhizem reliableecganomalydetectiononedgedevicesforinternetofmedicalthingsapplications AT leilabousbia reliableecganomalydetectiononedgedevicesforinternetofmedicalthingsapplications AT yassminebendhiab reliableecganomalydetectiononedgedevicesforinternetofmedicalthingsapplications AT mohamedouldelhassenaoueileyine reliableecganomalydetectiononedgedevicesforinternetofmedicalthingsapplications AT ridhabouallegue reliableecganomalydetectiononedgedevicesforinternetofmedicalthingsapplications |