Cross-compensation of FET sensor drift and matrix effects in the industrial continuous monitoring of ion concentrations

Margarit, Josep Maria; Martín-Ezquerra, Miquel; Escudé-Pujol, Roger; Jiménez-Jorquera, Cecilia; Liu, Shih-Chii

doi:10.1016/j.snb.2021.131123

Cited by 12 publications

(9 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared to using a single biomarker, using all biomarkers did not always give a lower MAE. This result is in line with the findings in literature that more sensor readings did not necessarily lead to better prediction accuracy [36]. Furthermore, no specific combination of biomarkers consistently gave the lowest MAE on all datasets.…”

Section: Discussionsupporting

confidence: 92%

“…We found that hydration complicated the relationship between biomarkers and %BWL. An extended study in the future with multiple subjects and intensity variations, especially with data collected from wearable devices, will allow further investigation of machine learning models including state-of-the-art deep learning models [36], [41], to provide continuous monitoring of the hydration status of athletes.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Predicting Hydration Status Using Machine Learning Models From Physiological and Sweat Biomarkers During Endurance Exercise: A Single Case Study

Wang

Lafaye²,

Saubade³

et al. 2022

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

Improper hydration routines can reduce athletic performance. Recent studies show that data from noninvasive biomarker recordings can help to evaluate the hydration status of subjects during endurance exercise. These studies are usually carried out on multiple subjects. In this work, we present the first study on predicting hydration status using machine learning models from single-subject experiments, which involve 32 exercise sessions of constant moderate intensity performed with and without fluid intake. During exercise, we measured four noninvasive physiological and sweat biomarkers including heart rate, core temperature, sweat sodium concentration, and whole-body sweat rate. Sweat sodium concentration was measured from six body regions using absorbent patches. We used three machine learning models to determine the percentage of body weight loss as an indicator of dehydration with these biomarkers and compared the prediction accuracy. The results on this single subject show that these models gave similar mean absolute errors, while in general the nonlinear models slightly outperformed the linear model in most of the experiments. The prediction accuracy of using the whole-body sweat rate or heart rate was higher than using core temperature or sweat sodium concentration. In addition, the model trained on the sweat sodium concentration collected from the arms gave slightly better accuracy than from the other five body regions. This exploratory work paves the way for the use of these machine learning models to develop personalized health monitoring together with emerging, noninvasive wearable sensor devices.

show abstract

Section: Discussionsupporting

confidence: 92%

Section: Discussionmentioning

confidence: 99%

Predicting Hydration Status Using Machine Learning Models From Physiological and Sweat Biomarkers During Endurance Exercise: A Single Case Study

Wang

Lafaye²,

Saubade³

et al. 2022

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

show abstract

“…Later, it stabilized and then it decreased again. However, the variation of the intercept estimated considering the 15 consecutive calibrations was 35.8 ± 9.2 mV on average, which is in accordance with the sensor temporal drift [36].…”

Section: Sensor Batch Characterizationsupporting

confidence: 80%

Analytical Assessment of Sodium Isfet Based Sensors for Sweat Analysis

Rovira¹,

Lafaye

Wang

et al. 2023

Preprint

View full text Add to dashboard Cite

“…They therefore give reason to hope that the open question may be addressed by numerically-based methods. Among the most widespread ML methods in sensor calibration are artificial neural networks (ANNs) in the form of multilayer perceptrons (MLPs) [66]- [68], convolutional neural networks (CNNs) [69], [70], and fuzzy neural networks (FNNs) [71]. Other approaches have relied on random forests (RFs) [67], [72], [73], Gaussian process regression (GPR) [73]- [75], and Bayesian neural networks [76].…”

Section: Introductionmentioning

confidence: 99%

“…Other approaches have relied on random forests (RFs) [67], [72], [73], Gaussian process regression (GPR) [73]- [75], and Bayesian neural networks [76]. These methods have been applied for temperature compensation [66], [67], temporal drift compensation of field effect transistor sensors [70], and for compensating commercial water quality sensors in order to extend the calibration lifetime [69]. ANNs are much appreciated for their effectiveness in classification tasks [77]- [79].…”

Section: Introductionmentioning

confidence: 99%

Bayesian Sensor Calibration of a CMOS-Integrated Hall Sensor Against Thermomechanical Cross-Sensitivities

Berger

Schott²,

Oliver

2023

IEEE Sensors J.

View full text Add to dashboard Cite

For the first time, Bayesian sensor calibration is used to identify efficient calibration procedures for a sensor cross-sensitive to 2 parasitic influences. The object under study is a thermomechanically cross-sensitive sensor system for determining the magnetic induction B. The packaged system comprises a Hall sensor, a stress sensor, and a temperature sensor. The three sensor signals are combined in a polynomial sensor response model with 11 parameters to determine B compensated for offset and cross-sensitivities. For the calibration, sensors are exposed to mechanical stress values between 0 and −68 MPa, temperatures between −40 and 100 °C, and B values between and 25 mT. A sample of 35 sensors serves to extract the prior model parameter distribution of their fabrication run. Bayesian experimental design is applied to identify sets of 2 to 8 optimal calibration conditions under Ioptimality and G-optimality. Bayesian inference then allows to obtain the posterior model parameter distribution of any uncalibrated sensor from the same run. Any such sensor is thereby turned into a B measuring device with individually quantified accuracy. The method was successfully applied to 15 validation sensors. In the case of I-optimality, the median root-mean-square (rms) σ values of the ±1σ confidence intervals for the extracted B values were found to be 113 to 71 µT after near-I-optimal calibrations based on 2 to 8 measurements, respectively. Over the entire range of temperature and mechanical stress and for applied |B| ≤25 mT, corresponding experimentally determined medians of the rms deviations between predicted and applied B values were found to be 89 to 71 µT. Analogous observations apply to G-optimality. In short, Bayesian calibration made it possible to obtain functional B sensors of known accuracy with significantly fewer calibration measurements than model parameters. This was enabled by prior knowledge collected by the thorough characterization of 35 prior-generating specimens.

show abstract

Cross-compensation of FET sensor drift and matrix effects in the industrial continuous monitoring of ion concentrations

Cited by 12 publications

References 25 publications

Predicting Hydration Status Using Machine Learning Models From Physiological and Sweat Biomarkers During Endurance Exercise: A Single Case Study

Predicting Hydration Status Using Machine Learning Models From Physiological and Sweat Biomarkers During Endurance Exercise: A Single Case Study

Analytical Assessment of Sodium Isfet Based Sensors for Sweat Analysis

Bayesian Sensor Calibration of a CMOS-Integrated Hall Sensor Against Thermomechanical Cross-Sensitivities

Contact Info

Product

Resources

About