Reconstructing computational spectra using deep learning’s self-attention method

• Autorzy: Hao Wu , Hui Wu , Xinyu Su , Jingjun Wu , Shuangli Liu

Identyfikatory

DOI

10.37190/oa240308

• Języki publikacji: EN

Abstrakty

EN

Miniaturized computational spectrometers have become a new research hotspot due to their portability and miniaturization. However, there are several issues, like low precision and poor stability. Because the problem of spectrum reconstruction accuracy is very evident, we suggested a novel approach to raise the reconstruction accuracy. A library of optical filtering functions was acquired using the time-domain finite-difference (FDTD) method. A cross-correlation algorithm was then used to choose 100 sparse filter functions, which were then built as an encoding matrix and then, based on the encoding matrix, a self-attention mechanism algorithm to improve the accuracy. The reconstructed spectrum’s mean square error (MSE) is 0.0019, and its similarity coefficient (R2) is 0.9780. This self-attention mechanism spectral reconstruction technique will open up new possibilities for high-accuracy reconstruction for various computational spectrometer types.

Słowa kluczowe

EN

spectral reconstruction; self-attention; encoding matrix; cross-correlation

• Wydawca: Oficyna Wydawnicza Politechniki Wrocławskiej
• Czasopismo: Optica Applicata
• Rocznik: 2024
• Tom: Vol. 54, nr 3
• Strony: 395--407
• Opis fizyczny: Bibliogr. 19 poz., rys., tab.

Twórcy

autor

Hao Wu

• School of Information Engineering, Southwest University of Science and Technology, Mianyang 621010, China

autor

Hui Wu

• School of Information Engineering, Southwest University of Science and Technology, Mianyang 621010, China

autor

Xinyu Su

• School of Information Engineering, Southwest University of Science and Technology, Mianyang 621010, China

autor

Jingjun Wu

• School of Electronic and Optical Engineering, Nanjing University of Science and Technology, Nanjing 210094, China

autor

Shuangli Liu

• School of Information Engineering, Southwest University of Science and Technology, Mianyang 621010, China

Bibliografia

• [1] YANG Z., ALBROW-OWEN T., CUI H., ALEXANDER-WEBBER J., GU F., WANG X., WU T.-C., ZHUGE M., WILLIAMS C., WANG P., ZAYATS A.V., CAI W., DAI L., HOFMANN S., OVEREND M., TONG L., YANG Q., SUN Z., HASAN T., Single-nanowire spectrometers, Science 365(6457), 2019: 1017-1020. https://doi.org/10.1126/science.aax8814
• [2] LI W., LIU Y., LING L., SHENG Z., CHENG S., YI Z., WU P., ZENG Q., TANG B., AHMAD S., The tunable absorber films of grating structure of AlCuFe quasicrystal with high Q and refractive index sensitivity, Surfaces and Interfaces 48, 2024: 104248. https://doi.org/10.1016/j.surfin.2024.104248
• [3] LI W., LIU M., CHENG S., ZHANG H., YANG W., YI Z., ZENG Q., TANG B., AHMAD S., SUN T., Polarization independent tunable bandwidth absorber based on single-layer graphene, Diamond and Related Materials 142, 2024: 110793. https://doi.org/10.1016/j.diamond.2024.110793
• [4] LIANG S., XU F., LI W., YANG W., CHENG S., YANG H., CHEN J., YI Z., JIANG P., Tunable smart mid infrared thermal control emitter based on phase change material VO2 thin film, Applied Thermal Engineering 232, 2023: 121074. https://doi.org/10.1016/j.applthermaleng.2023.121074
• [5] MA J., WU P., LI W., LIANG S., SHANGGUAN Q., CHENG S., TIAN Y., FU J., ZHANG L., A five-peaks graphene absorber with multiple adjustable and high sensitivity in the far infrared band, Diamond and Related Materials 136, 2023: 109960. https://doi.org/10.1016/j.diamond.2023.109960
• [6] SHANGGUAN Q., ZHAO Y., SONG Z., WANG J., YANG H., CHEN J., LIU C., CHENG S., YANG W., YI Z., High sensitivity active adjustable graphene absorber for refractive index sensing applications, Diamond and Related Materials 128, 2022: 109273. https://doi.org/10.1016/j.diamond.2022.109273
• [7] SCHULER L.P., MILNE J.S., DELL J.M., FARAONE L., MEMS-based microspectrometer technologies for NIR and MIR wavelengths, Journal of Physics D: Applied Physics 42(13), 2009: 133001. https://doi.org/10.1088/0022-3727/42/13/133001
• [8] MALINEN J., RISSANEN A., SAARI H., KARIOJA P., KARPPINEN M., AALTO T., TUKKINIEMI K., Advances in miniature spectrometer and sensor development, Proceedings of the SPIE, Vol. 9101, Next-Generation Spectroscopic Technologies VII, 2014: 91010C. https://doi.org/10.1117/12.2053567
• [9] EBERMANN M., NEUMANN N., HILLER K., SEIFERT M., MEINIG M., KURTH S., Tunable MEMS Fabry-Pérot filters for infrared microspectrometers: A review, Proceedings of the SPIE, Vol. 9760, MOEMS and Miniaturized Systems XV, 2016: 97600H. https://doi.org/10.1117/12.2209288
• [10] CROCOMBE R.A., Portable spectroscopy, Applied Spectroscopy 72(12), 2018: 1701-1751. https://doi.org/10.1177/0003702818809719
• [11] WOLFFENBUTTEL R.F., MEMS-based optical mini- and microspectrometers for the visible and infrared spectral range, Journal of Micromechanics and Microengineering 15, 2005: S145-S152. https://doi.org/10.1088/0960-1317/15/7/021
• [12] KUROKAWA U., CHOI B.I., CHANG C.C., Filter-based miniature spectrometers: Spectrum reconstruction using adaptive regularization, IEEE Sensors Journal 11(7), 2011: 1556-1563. https://doi.org/ 10.1109/jsen.2010.2103054
• [13] ZHANG S., DONG Y., FU H., HUANG S.-L., ZHANG L., A spectral reconstruction algorithm of miniature spectrometer based on sparse optimization and dictionary learning, Sensors 18(2), 2018: 644. https://doi.org/10.3390/s18020644
• [14] YANG Z., ALBROW-OWEN T., CAI W., HASAN T., Miniaturization of optical spectrometers, Science 371(6528), 2021: eabe0722. https://doi.org/10.1126/science.abe0722
• [15] XIONG J., CAI X., CUI K., HUANG Y., YANG J., ZHU H., ZHENG Z., XU S., HE Y., LIU F., FENG X., ZHANG W., One-shot ultraspectral imaging with reconfigurable metasur faces, Optica Open, Preprint, 2020. https://doi.org/10.48550/arXiv.2005.02689
• [16] YANG J., CUI K., CAI X., XIONG J., ZHU H., RAO S., XU S., HUANG Y., LIU F., FENG X., ZHANG W., Ultraspectral imaging based on metasurfaces with freeform shaped meta‐atoms, Laser & Photonics Reviews 16(7), 2022: 2100663. https://doi.org/10.1002/lpor.202100663
• [17] SONG H., MA Y., HAN Y., SHEN W., ZHANG W., LI Y., LIU X., PENG Y., HAO X., Deep-learned broadband encoding stochastic fifilters for computational spectroscopic instruments, Advanced Theory and Simulations 4(3), 2021: 2000299. https://doi.org/10.1002/adts.202000299
• [18] NIE S., GU L., ZHENG Y., LAM A., ONO N., SATO I., Deeply learned filter response functions for hyperspectral reconstruction, [In] 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 2018: 4767-4776. https://doi.org/10.1109/CVPR.2018.00501
• [19] FRINTROP S., VOCUS: A Visual Attention System for Object Detection and Goal-Directed Search, Springer Berlin Heidelberg, Vol. 3899, 2006. https://link.springer.com/book/10.1007/11682110