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.
Highlights
Ring resonators are in an emerging class of versatile and highly sensitive photonic sensors that use recirculating light confined within a microcavity to detect the changes in surrounding biological, physical, and chemical environments [1,2,3]
We demonstrate a machine learning–enabled smart sensor based on a ring resonator for multicomponent chemical analysis
The ring resonator–based smart sensor [Fig. 1(a)] consisted of a silicon ring resonator chip that was integrated with a microfluidic network, a 1550 nm light source, a polarization controller, an optical spectrum analyzer (OSA), and a data acquisition (DAQ) circuit, all packaged into a portable system
Summary
Ring resonators are in an emerging class of versatile and highly sensitive photonic sensors that use recirculating light confined within a microcavity to detect the changes in surrounding biological, physical, and chemical environments [1,2,3] They are well suited for integrated sensing systems because of their high sensitivity, compact size, label-free detection, real-time monitoring capability, low sample consumption, multiplexing capability, and resistance to electromagnetic interference [4,5]. When target molecules come into proximity of the ring resonator, the resonant peak shifts to a different wavelength, and the degree of this resonant shift reflects the target concentration This label-free sensing strategy works well for single-component analysis but shows poor performance for multicomponent analysis due to its lack of specificity.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.