TY - GEN
T1 - Design and spectral reconstruction assisted by intelligent algorithms for high-resolution Fourier transform spectrometer
AU - Luo, Huaijian
AU - Huang, Zhuili
AU - Xu, Chuang
AU - Lau, Alan Pak Tao
AU - Yu, Changyuan
N1 - Funding Information:
This work was supported by the HK RGC GRF (15211619 B-Q73A) and National Natural Science Foundation of China Programs under Grant 62005030.
Publisher Copyright:
© 2021 IEEE.
PY - 2021/10
Y1 - 2021/10
N2 - A miniature Fourier transform spectrometer is designed with tailored optical path differences for visible spectral reconstruction. The combination of intelligent algorithms, the convex optimization algorithm (CVX) and the one-dimension modified convolutional neural network (Unet), is used to retrieve spectra under measurement with noise. This scheme recovers four kinds of spectra accurately with the mean-square error of 8.32 × 10-4.
AB - A miniature Fourier transform spectrometer is designed with tailored optical path differences for visible spectral reconstruction. The combination of intelligent algorithms, the convex optimization algorithm (CVX) and the one-dimension modified convolutional neural network (Unet), is used to retrieve spectra under measurement with noise. This scheme recovers four kinds of spectra accurately with the mean-square error of 8.32 × 10-4.
KW - Fourier transform spectrometer
KW - High resolution
KW - Intelligent algorithm
KW - Mach-Zehnder interferometer
KW - Spectroscopy
UR - http://www.scopus.com/inward/record.url?scp=85123411298&partnerID=8YFLogxK
U2 - 10.1109/WOCC53213.2021.9603127
DO - 10.1109/WOCC53213.2021.9603127
M3 - Conference article published in proceeding or book
AN - SCOPUS:85123411298
T3 - 2021 30th Wireless and Optical Communications Conference, WOCC 2021
SP - 153
EP - 156
BT - 30th Wireless and Optical Communications Conference, WOCC 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 30th Wireless and Optical Communications Conference, WOCC 2021
Y2 - 7 October 2021 through 8 October 2021
ER -