Smart ring resonator–based sensor for multicomponent chemical analysis via machine learning

Zhenyu Li; Hui Zhang; Binh Thi Thanh Nguyen; Shaobo Luo; Patricia Yang Liu; Jun Zou; Yuzhi Shi; Hong Cai; Zhenchuan Yang; Yufeng Jin; Yilong Hao; Yi Zhang; Ai Qun Liu

doi:10.1364/PRJ.411825

Smart ring resonator–based sensor for multicomponent chemical analysis via machine learning

Zhenyu Li, Hui Zhang, Binh Thi Thanh Nguyen, Shaobo Luo, Patricia Yang Liu, Jun Zou, Yuzhi Shi, Hong Cai, Zhenchuan Yang, Yufeng Jin, Yilong Hao, Yi Zhang, Ai Qun Liu

Research output: Journal article publication › Journal article › Academic research › peer-review

8 Citations (Scopus)

Abstract

We demonstrate a smart sensor for label-free multicomponent chemical analysis using a single label-free ring resonator to acquire the entire resonant spectrum of the mixture and a neural network model to predict the composition for multicomponent analysis. The smart sensor shows a high prediction accuracy with a low root-mean-squared error ranging only from 0.13 to 2.28 mg/mL. The predicted concentrations of each component in the testing dataset almost all fall within the 95% prediction bands. With its simple label-free detection strategy and high accuracy, the smart sensor promises great potential for multicomponent analysis applications in many fields.

Original language	English
Pages (from-to)	B38-B44
Journal	Photonics Research
Volume	9
Issue number	2
DOIs	https://doi.org/10.1364/PRJ.411825
Publication status	Published - Feb 2021
Externally published	Yes

ASJC Scopus subject areas

Electronic, Optical and Magnetic Materials
Atomic and Molecular Physics, and Optics

More information

10.1364/PRJ.411825

Cite this

@article{26a65c5c734145f8906448846d2b9016,

title = "Smart ring resonator–based sensor for multicomponent chemical analysis via machine learning",

abstract = "We demonstrate a smart sensor for label-free multicomponent chemical analysis using a single label-free ring resonator to acquire the entire resonant spectrum of the mixture and a neural network model to predict the composition for multicomponent analysis. The smart sensor shows a high prediction accuracy with a low root-mean-squared error ranging only from 0.13 to 2.28 mg/mL. The predicted concentrations of each component in the testing dataset almost all fall within the 95% prediction bands. With its simple label-free detection strategy and high accuracy, the smart sensor promises great potential for multicomponent analysis applications in many fields.",

author = "Zhenyu Li and Hui Zhang and {Thanh Nguyen}, {Binh Thi} and Shaobo Luo and Liu, {Patricia Yang} and Jun Zou and Yuzhi Shi and Hong Cai and Zhenchuan Yang and Yufeng Jin and Yilong Hao and Yi Zhang and Liu, {Ai Qun}",

note = "Funding Information: National Research Foundation Singapore (PUB-1804-0082, NRF-CRP13-2014-01); Ministry of Education—Singapore (MOE2017-T3-1-001). Publisher Copyright: {\textcopyright} 2021 Chinese Laser Press.",

year = "2021",

month = feb,

doi = "10.1364/PRJ.411825",

language = "English",

volume = "9",

pages = "B38--B44",

journal = "Photonics Research",

issn = "2327-9125",

publisher = "OSA Publishing",

number = "2",

}

TY - JOUR

T1 - Smart ring resonator–based sensor for multicomponent chemical analysis via machine learning

AU - Li, Zhenyu

AU - Zhang, Hui

AU - Thanh Nguyen, Binh Thi

AU - Luo, Shaobo

AU - Liu, Patricia Yang

AU - Zou, Jun

AU - Shi, Yuzhi

AU - Cai, Hong

AU - Yang, Zhenchuan

AU - Jin, Yufeng

AU - Hao, Yilong

AU - Zhang, Yi

AU - Liu, Ai Qun

N1 - Funding Information: National Research Foundation Singapore (PUB-1804-0082, NRF-CRP13-2014-01); Ministry of Education—Singapore (MOE2017-T3-1-001). Publisher Copyright: © 2021 Chinese Laser Press.

PY - 2021/2

Y1 - 2021/2

N2 - We demonstrate a smart sensor for label-free multicomponent chemical analysis using a single label-free ring resonator to acquire the entire resonant spectrum of the mixture and a neural network model to predict the composition for multicomponent analysis. The smart sensor shows a high prediction accuracy with a low root-mean-squared error ranging only from 0.13 to 2.28 mg/mL. The predicted concentrations of each component in the testing dataset almost all fall within the 95% prediction bands. With its simple label-free detection strategy and high accuracy, the smart sensor promises great potential for multicomponent analysis applications in many fields.

AB - We demonstrate a smart sensor for label-free multicomponent chemical analysis using a single label-free ring resonator to acquire the entire resonant spectrum of the mixture and a neural network model to predict the composition for multicomponent analysis. The smart sensor shows a high prediction accuracy with a low root-mean-squared error ranging only from 0.13 to 2.28 mg/mL. The predicted concentrations of each component in the testing dataset almost all fall within the 95% prediction bands. With its simple label-free detection strategy and high accuracy, the smart sensor promises great potential for multicomponent analysis applications in many fields.

UR - http://www.scopus.com/inward/record.url?scp=85102193914&partnerID=8YFLogxK

U2 - 10.1364/PRJ.411825

DO - 10.1364/PRJ.411825

M3 - Journal article

AN - SCOPUS:85102193914

SN - 2327-9125

VL - 9

SP - B38-B44

JO - Photonics Research

JF - Photonics Research

IS - 2

ER -

Smart ring resonator–based sensor for multicomponent chemical analysis via machine learning

Abstract

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this