Deep Learning‐Driven Robust Glucose Sensing and Fruit Brix Estimation Using a Single Microwave Split Ring Resonator
Extracting the desired information from sensor data with various internal and external effects is a significant challenge in sensor applications. Difficult‐to‐control factors such as temperature, humidity, and sample position can significantly affect the stability and reliability of sensor data. In...
Saved in:
Published in | Laser & photonics reviews Vol. 18; no. 8 |
---|---|
Main Authors | , , , , , , |
Format | Journal Article |
Language | English |
Published |
Weinheim
Wiley Subscription Services, Inc
01.08.2024
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | Extracting the desired information from sensor data with various internal and external effects is a significant challenge in sensor applications. Difficult‐to‐control factors such as temperature, humidity, and sample position can significantly affect the stability and reliability of sensor data. In this paper, a deep learning‐based glucose sensing method that is robust to variations in sample position is proposed. It is shown that the variations in sample position affect the sensor data measured by the designed split ring resonator‐based microwave sensor. Then, artificial neural network and 1D convolutional neural network (CNN) models are evaluated for extracting glucose concentration information from the sensor data measured at random sample positions. The concentration of the glucose solution ranged from 1% to 23% (2% increments). The 1D CNN with all frequencies (0.5–18 GHz) of the and datasets outperformed the other model, with a mean absolute error (MAE) of 0.695% and a mean squared error (MSE) of 0.876 evaluated via cross‐validation. The study demonstrated that the sensor system can be applied in real life by performing fruit Brix estimation based on transfer learning of the previous 1D CNN network, and the MAE and MSE are 0.450% and 0.305, respectively.
This study presents a robust glucose sensing method using deep learning, resilient to sample position variations. Data measured in random sample position using split ring resonator microwave sensors are calibrated by a 1D convolutional neural network. With an MAE of 0.695% and MSE of 0.876%, the model exhibits superior performance. Transfer learning facilitates fruit Brix estimation, demonstrating practical applicability. |
---|---|
ISSN: | 1863-8880 1863-8899 |
DOI: | 10.1002/lpor.202300768 |