Unsupervised calibration for noninvasive glucose-monitoring devices using mid-infrared spectroscopy

Explore this paper's citation graph

Summary

A truly noninvasive, glucose-monitoring technique using mid-infrared spectroscopy that does not require blood collection for calibration is developed by applying domain adaptation (DA) using deep neural networks to train a model that associates blood glucose concentration with mid- Infrared spectral data without requiring a training dataset labeled with invasive blood sample measurements.

Type
article
Published
2018-11-01
Cited by
11
References
46
Access
Open access

Keywords

Calibration, Near-infrared spectroscopy, Blood collection, Spectroscopy, Infrared

References

Cited by

Related papers