Edge-AI Enabled Wearable Device for Non-Invasive Type 1 Diabetes Detection Using ECG Signals
Diabetes is a chronic condition, and traditional monitoring methods are invasive, significantly reducing the quality of life of the patients. This study proposes the design of an innovative system based on a microcontroller that performs real-time ECG acquisition and evaluates the presence of diabet...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Bioengineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2306-5354/12/1/4 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589025050886144 |
|---|---|
| author | Maria Gragnaniello Vincenzo Romano Marrazzo Alessandro Borghese Luca Maresca Giovanni Breglio Michele Riccio |
| author_facet | Maria Gragnaniello Vincenzo Romano Marrazzo Alessandro Borghese Luca Maresca Giovanni Breglio Michele Riccio |
| author_sort | Maria Gragnaniello |
| collection | DOAJ |
| description | Diabetes is a chronic condition, and traditional monitoring methods are invasive, significantly reducing the quality of life of the patients. This study proposes the design of an innovative system based on a microcontroller that performs real-time ECG acquisition and evaluates the presence of diabetes using an Edge-AI solution. A spectrogram-based preprocessing method is combined with a 1-Dimensional Convolutional Neural Network (1D-CNN) to analyze the ECG signals directly on the device. By applying quantization as an optimization technique, the model effectively balances memory usage and accuracy, achieving an accuracy of 89.52% with an average precision and recall of 0.91 and 0.90, respectively. These results were obtained with a minimal memory footprint of 347 kB flash and 23 kB RAM, showcasing the system’s suitability for wearable embedded devices. Furthermore, a custom PCB was developed to validate the system in a real-world scenario. The hardware integrates high-performance electronics with low power consumption, demonstrating the feasibility of deploying Edge-AI for non-invasive, real-time diabetes detection in resource-constrained environments. This design represents a significant step forward in improving the accessibility and practicality of diabetes monitoring. |
| format | Article |
| id | doaj-art-0fea317a81c8414c8e28ec135df5d54e |
| institution | Kabale University |
| issn | 2306-5354 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Bioengineering |
| spelling | doaj-art-0fea317a81c8414c8e28ec135df5d54e2025-01-24T13:22:55ZengMDPI AGBioengineering2306-53542024-12-01121410.3390/bioengineering12010004Edge-AI Enabled Wearable Device for Non-Invasive Type 1 Diabetes Detection Using ECG SignalsMaria Gragnaniello0Vincenzo Romano Marrazzo1Alessandro Borghese2Luca Maresca3Giovanni Breglio4Michele Riccio5Department of Electrical Engineering and Information Technology (DIETI), University of Naples Federico II, 80125 Naples, ItalyDepartment of Electrical Engineering and Information Technology (DIETI), University of Naples Federico II, 80125 Naples, ItalyDepartment of Electrical Engineering and Information Technology (DIETI), University of Naples Federico II, 80125 Naples, ItalyDepartment of Electrical Engineering and Information Technology (DIETI), University of Naples Federico II, 80125 Naples, ItalyDepartment of Electrical Engineering and Information Technology (DIETI), University of Naples Federico II, 80125 Naples, ItalyDepartment of Electrical Engineering and Information Technology (DIETI), University of Naples Federico II, 80125 Naples, ItalyDiabetes is a chronic condition, and traditional monitoring methods are invasive, significantly reducing the quality of life of the patients. This study proposes the design of an innovative system based on a microcontroller that performs real-time ECG acquisition and evaluates the presence of diabetes using an Edge-AI solution. A spectrogram-based preprocessing method is combined with a 1-Dimensional Convolutional Neural Network (1D-CNN) to analyze the ECG signals directly on the device. By applying quantization as an optimization technique, the model effectively balances memory usage and accuracy, achieving an accuracy of 89.52% with an average precision and recall of 0.91 and 0.90, respectively. These results were obtained with a minimal memory footprint of 347 kB flash and 23 kB RAM, showcasing the system’s suitability for wearable embedded devices. Furthermore, a custom PCB was developed to validate the system in a real-world scenario. The hardware integrates high-performance electronics with low power consumption, demonstrating the feasibility of deploying Edge-AI for non-invasive, real-time diabetes detection in resource-constrained environments. This design represents a significant step forward in improving the accessibility and practicality of diabetes monitoring.https://www.mdpi.com/2306-5354/12/1/4real-time diabetes detectionEdge-AIdeep learningECG32-bit microcontrollerspectrogram |
| spellingShingle | Maria Gragnaniello Vincenzo Romano Marrazzo Alessandro Borghese Luca Maresca Giovanni Breglio Michele Riccio Edge-AI Enabled Wearable Device for Non-Invasive Type 1 Diabetes Detection Using ECG Signals Bioengineering real-time diabetes detection Edge-AI deep learning ECG 32-bit microcontroller spectrogram |
| title | Edge-AI Enabled Wearable Device for Non-Invasive Type 1 Diabetes Detection Using ECG Signals |
| title_full | Edge-AI Enabled Wearable Device for Non-Invasive Type 1 Diabetes Detection Using ECG Signals |
| title_fullStr | Edge-AI Enabled Wearable Device for Non-Invasive Type 1 Diabetes Detection Using ECG Signals |
| title_full_unstemmed | Edge-AI Enabled Wearable Device for Non-Invasive Type 1 Diabetes Detection Using ECG Signals |
| title_short | Edge-AI Enabled Wearable Device for Non-Invasive Type 1 Diabetes Detection Using ECG Signals |
| title_sort | edge ai enabled wearable device for non invasive type 1 diabetes detection using ecg signals |
| topic | real-time diabetes detection Edge-AI deep learning ECG 32-bit microcontroller spectrogram |
| url | https://www.mdpi.com/2306-5354/12/1/4 |
| work_keys_str_mv | AT mariagragnaniello edgeaienabledwearabledevicefornoninvasivetype1diabetesdetectionusingecgsignals AT vincenzoromanomarrazzo edgeaienabledwearabledevicefornoninvasivetype1diabetesdetectionusingecgsignals AT alessandroborghese edgeaienabledwearabledevicefornoninvasivetype1diabetesdetectionusingecgsignals AT lucamaresca edgeaienabledwearabledevicefornoninvasivetype1diabetesdetectionusingecgsignals AT giovannibreglio edgeaienabledwearabledevicefornoninvasivetype1diabetesdetectionusingecgsignals AT michelericcio edgeaienabledwearabledevicefornoninvasivetype1diabetesdetectionusingecgsignals |