Deep Learning-Based Noninvasive Blood Glucose Estimation
Estimating blood glucose levels (BGLs) noninvasively is a rapidly advancing field driven by the need for effective and painless glucose monitoring solutions for diabetic patients. This study explores deep learning (DL) models applied to noninvasive techniques for accurate BGL estimation. Thermal ima...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2025-01-01
|
| Series: | Journal of Engineering |
| Online Access: | http://dx.doi.org/10.1155/je/1134023 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Estimating blood glucose levels (BGLs) noninvasively is a rapidly advancing field driven by the need for effective and painless glucose monitoring solutions for diabetic patients. This study explores deep learning (DL) models applied to noninvasive techniques for accurate BGL estimation. Thermal images were collected for Type I diabetes after confirming BGLs using a glucometer. DL techniques were then employed to classify the thermal images into three BGL classes (low, high, and normal). DarkNet and ShuffleNet convolutional neural networks (CNNs) are used to classify the thermal image and get the best performance, with an overall accuracy of 98% for DarkNet and 100% for ShuffleNet CNN. |
|---|---|
| ISSN: | 2314-4912 |