Machine learning and silicon photonic sensor for complex chemical components determination

We propose an integrated microring resonator sensing system based on Backward-Propagation Neural Networks (BPNN)-Adaboost algorithm to predict component fraction in binary liquid mixtures. A minimum absolute error of 0.0023 and mean squared error of 0.000345 is achieved by this training model.

Bibliographic Details
Main Authors: Zhang, Hui, Karim, Muhammad Faeyz, Zheng, Shaonan, Cai, Hong, Gu, Yuandong, Chen, Shoushun, Yu, Hao, Liu, Ai Qun
Other Authors: School of Electrical and Electronic Engineering
Format: Conference Paper
Language:English
Published: 2021
Subjects:
Online Access:https://hdl.handle.net/10356/151454
Description
Summary:We propose an integrated microring resonator sensing system based on Backward-Propagation Neural Networks (BPNN)-Adaboost algorithm to predict component fraction in binary liquid mixtures. A minimum absolute error of 0.0023 and mean squared error of 0.000345 is achieved by this training model.