Hostname: page-component-54dcc4c588-trf7k Total loading time: 0 Render date: 2025-09-27T16:08:25.235Z Has data issue: false hasContentIssue false
  • English
  • Français

A rapid and accurate noninvasive glucose detection based on microwave time-domain signals and the extreme learning machine

Published online by Cambridge University Press:  15 September 2025

Yan Wang Open the ORCID record for Yan Wang [Opens in a new window] ,
Xia Xiao  and
Zengxiang Wang
Yan Wang
Affiliation:
Tianjin Key Laboratory of Imaging and Sensing Microelectronic Technology, School of Microelectronics, Tianjin University, Tianjin, PR China
Xia Xiao*
Affiliation:
Tianjin Key Laboratory of Imaging and Sensing Microelectronic Technology, School of Microelectronics, Tianjin University, Tianjin, PR China
Zengxiang Wang
Affiliation:
Tianjin Key Laboratory of Imaging and Sensing Microelectronic Technology, School of Microelectronics, Tianjin University, Tianjin, PR China
*
Corresponding author: Xia Xiao; Email: xiaxiao@tju.edu.cn
Get access Rights & Permissions [Opens in a new window]

Abstract

Diabetes is increasingly recognized as a serious, worldwide public health concern. In this paper, an extreme learning machine (ELM) based on time-domain pulses was introduced to obtain noninvasive glucose detection. To validate the method, time-domain signals from different concentrations of glucose solutions were detected in the model. Considering that the glucose levels of diabetic patients range from 30 to 500 mg/dL, the glucose solution concentration was set to 10−500 mg/dL, with an interval of 10 mg/dL. The received signals were trained using the ELM algorithm, which was able to accurately predict solutions of unknown concentration with an average relative error of 1.45%. The proposed method is rapid to process, simple to operate, and highly accurate for noninvasive glucose detection. The results demonstrated that microwave detection technology combined with the ELM algorithm has the potential to become a valuable tool for noninvasive glucose monitoring in clinical settings.

Keywords

concentration predictionextreme learning machineglucose sensormicrowave detection

Information

Type
Research Paper
Information
International Journal of Microwave and Wireless Technologies , First View , pp. 1 - 9
Check for updates
Copyright
© The Author(s), 2025. Published by Cambridge University Press in association with The European Microwave Association.

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

Article purchase

Temporarily unavailable

References

Pouya, S, Inga, P, Paraskevi, S, Belma, M, Suvi, K, Nigel, U, Stephen, C, Leonor, G, Ayesha, M, Katherine, O, Jonathan, S, Dominic, B and Rhys, W (2019) Global and regional diabetes prevalence estimates for 2019 and projections for 2030 and 2045: Results from the International Diabetes Federation Diabetes Atlas, 9th edition. Diabetes Research and Clinical Practice 157, .Google Scholar
International Diabetes Federation (2021) IDF Diabetes Atlas, 10th Edn. Brussels, Belgium: International Diabetes Federation.Google Scholar
Association A D (2020) 7. Diabetes Technology: Standards of Medical Care in Diabetes—2020. Diabete Care 43(Supplement_1), S77–S88.10.2337/dc20-S007CrossRefGoogle Scholar
Christopher, P, Suvi, K, Paraskevi, S, Pouya, S, Gisela, D, Gyula, S and Graham, O (2019) Worldwide estimates of incidence, prevalence and mortality of type 1 diabetes in children and adolescents: Results from the International Diabetes Federation Diabetes Atlas, 9th edition ScienceDirect. Diabetes Research and Clinical Practice 157, .Google Scholar
Safar, M, Blacher, J and Protogerou, A (2017) Patient management of hypertensive subjects without and with diabetes mellitus type II. Medical Clinics of North America 101(1), 159–167.10.1016/j.mcna.2016.08.014CrossRefGoogle ScholarPubMed
Rachim, VP and Chung, WY (2019) Wearable-band type visible-near infrared optical biosensor for non-invasive blood glucose monitoring. Sensors and Actuators, B: Chemical 286, 173–180.10.1016/j.snb.2019.01.121CrossRefGoogle Scholar
Choi, H, Naylon, J, Luzio, S, Beutler, J, Birchall, J, Martin, C and Porch, A (2015) Design and in vitro interference test of microwave noninvasive blood glucose monitoring sensor. IEEE Transactions on Microwave Theory & Techniques 63(10), 3016–3026.10.1109/TMTT.2015.2472019CrossRefGoogle ScholarPubMed
Choudhary, A, Pal, S and Sarkhel, G (2023) Broadband millimeter-wave absorbers: A review. International Journal of Microwave and Wireless Technologies 15 (2), 347–363.CrossRefGoogle Scholar
Brovoll, S, Berger, T, Paichard, Y, Aardal, O, Lande, T.S and Hamran, S.-E (2014) Time-lapse imaging of human heart motion with switched array UWB radar. IEEE Transactions on Biomedical Circuits and Systems 8(5), 704–715.10.1109/TBCAS.2014.2359995CrossRefGoogle ScholarPubMed
Matovi, V, Trbojevi-Stankovi, J, Jefti, B and Matija, L (2020) Glucose concentration monitoring using near- infrared spectrum of spent dialysis fluid in hemodialysis patients. Srpski Arhiv Za Celokupno Lekarstvo 148 (12), 706–710.10.2298/SARH200215090MCrossRefGoogle Scholar
Delbeck, S and Heise, HM (2021) Evaluation of opportunities and limitations of mid-infrared skin spectroscopy for noninvasive blood glucose monitoring. Journal of Diabetes Science and Technology 15(1), 19–27.10.1177/1932296820936224CrossRefGoogle ScholarPubMed
Hu, S, Jiang, Y, Wu, Y, Guo, X, Ying, Y, Wen, Y and Yang, H (2020) Enzyme-free tandem reaction strategy for surface-enhanced Raman scattering detection of glucose by using the composite of Au nanoparticles and porphyrin-based metal-organic framework. ACS Applied Materials & Interfaces 12(49), 55324–55330.10.1021/acsami.0c12988CrossRefGoogle ScholarPubMed
Pathirage, K, Roopasinghe, P, Sooriyaarachchi, J, Weththasinghe, R and Nanayakkara, N (2019) Removing subject dependencies on non- invasive blood glucose measurement using hybrid techniques. Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 7197–7200.Google ScholarPubMed
Xia, X, Li, X and Qin-Wei, L (2013) A double constrained robust capon beamforming-based imaging method for early breast cancer detection. Chinese Physics B 22(9), .Google Scholar
Xiao, X and Li, Q (2016) A non-invasive measurement of blood glucose concentration by UWB microwave spectrum. IEEE Antennas and Wireless Propagation Letters 16, 1040–1043.10.1109/LAWP.2016.2618946CrossRefGoogle Scholar
Li, Z, Li, G, Yan, W and Lin, L (2016) Classification of diabetes and measurement of blood glucose concentration noninvasively using near infrared spectroscopy. Infrared Physics & Technology 67, 574–582.10.1016/j.infrared.2014.09.040CrossRefGoogle Scholar
Hwang, ES, Lichtensztajn, DY and Gomez, SL (2017) Survival after lumpectomy and mastectomy for early stage invasive breast cancer: the effect of age and hormone receptor status. Breast Diseases 119 (7), 1402–1412.Google Scholar
Mansour, E, Allam, A and Abdel-Rahman, AB (2023) A novel approach to non-invasive blood glucose sensing based on a single-slot defected ground structure. International Journal of Microwave and Wireless Technologies 15 (1), 32–40.10.1017/S1759078722000174CrossRefGoogle Scholar
Zhang, R, Liu, S, Jin, H, Luo, Y, Zheng, Z, Gao, F and Zheng, Y (2019) Noninvasive electromagnetic wave sensing of glucose. Sensors 19 (5), .Google ScholarPubMed
Turgul, V and Kale, I (2017) Simulating the effects of skin thickness and fingerprints to highlight problems with non-invasive RF blood glucose sensing from fingertips. IEEE Sensors Journal 17(22), 7553–7560.10.1109/JSEN.2017.2757083CrossRefGoogle Scholar
Sasaki, K, Wake, K and Watanabe, S (2015) Development of best fit Cole-Cole parameters for measurement data from biological tissues and organs between 1 MHz and 20 GHz. Radio Science 49(7), 459–472.10.1002/2013RS005345CrossRefGoogle Scholar
Karacolak, T, Moreland, EC and Topsakal, E (2013) Cole-Cole model for glucose-dependent dielectric properties of blood plasma for continuous glucose monitoring. Microwave and Optical Technology Letters 55(5), 1160–1164.10.1002/mop.27515CrossRefGoogle Scholar
Yang, L, Zhang, J, Wang, X, Li, Z and He, Y (2021) An improved ELM-based and data preprocessing integrated approach for phishing detection considering comprehensive features. Expert Systems with Applications 165, .10.1016/j.eswa.2020.113863CrossRefGoogle Scholar
Zheng, D, Hong, Z, Wang, N and Chen, P (2020) An Improved LDA-based ELM classification for intrusion detection algorithm in IoT application. IEEE Sensors 20(6), .Google ScholarPubMed
Huang, SY , Yoshida, Y, Inda, AJG, Xavier, CX, Mu, WC, Meng, YS and Yu, W (2019) Microstrip line-based glucose sensor for noninvasive continuous monitoring using the main field for sensing and multivariable crosschecking. IEEE Sensors Journal 19(2), 535–547.10.1109/JSEN.2018.2877691CrossRefGoogle Scholar
Hu, S, Nagae, S and Hirose, A (2019) Millimeter-wave adaptive glucose concentration estimation with complex-valued neural networks. IEEE Transactions on Biomedical Engineering 66(7), 2065–2071.10.1109/TBME.2018.2883085CrossRefGoogle Scholar
Baghelani, M, Abbasi, Z, Daneshmand, M and Light, PE (2020) Noninvasive continuous-time glucose monitoring system using a chipless printable sensor based on split ring microwave resonators. Scientific Reports 10(1), .10.1038/s41598-020-69547-1CrossRefGoogle ScholarPubMed
Li, QW, Xiao, X and Kikkawa, T (2019) Absorption spectrum for non-invasive blood glucose concentration detection by microwave signals. Journal of Electromagnetic Waves and Applications 33(9), 1093–1106.10.1080/09205071.2019.1596168CrossRefGoogle Scholar
Xiao, X, Qun, Y, Qinwei, L, Song, H and Kikkawa, T (2021) Precise noninvasive estimation of glucose using UWB microwave with improved neural networks and hybrid optimization. IEEE Transactions on Instrumentation and Measurement 70, 1–10.Google Scholar
Yang, C, Xiao, X, Hu, M and Wang, Z (2022) Non-invasive microwave blood glucose monitoring based on the diffusion limited aggregation earlobe model. International Journal of RF and Microwave Computer-Aided Engineering 32(12), .10.1002/mmce.23443CrossRefGoogle Scholar