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

作     者：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 

作者机构：National Key Laboratory of Science and Technology on Micro/Nano FabricationInstitute of MicroelectronicsPeking University Quantum Science and Engineering CentreNanyang Technological University Institute of MicroelectronicsA*STAR Agency for ScienceTechnology and Research School of Mechanical and Aerospace EngineeringNanyang Technological University 

出 版 物：《Photonics Research》 (光子学研究（英文版）)

年 卷 期：2021年第9卷第2期

页      面：I0031-I0037页

核心收录：

学科分类：12[管理学] 0808[工学-电气工程] 0809[工学-电子科学与技术（可授工学、理学学位）] 08[工学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 080202[工学-机械电子工程] 081104[工学-模式识别与智能系统] 0805[工学-材料科学与工程（可授工学、理学学位）] 0802[工学-机械工程] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0702[理学-物理学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：National Research Foundation Singapore(PUB-1804-0082,NRF-CRP13-2014-01) Ministry of Education—Singapore(MOE2017-T3-1-001) 

主　　题：Smart neural smart 

摘      要：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 rootmean-squared error ranging only from 0.13 to 2.28 mg/m L. 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.