High-resolution recognition of FOAM modes via an improved EfficientNet V2 based convolutional neural network

doi:10.1007/s11467-023-1373-4

Front. Phys.

2024, Vol. 19

Issue (3) : 32205 https://doi.org/10.1007/s11467-023-1373-4

RESEARCH ARTICLE

High-resolution recognition of FOAM modes via an improved EfficientNet V2 based convolutional neural network

Youzhi Shi¹, Zuhai Ma¹, Hongyu Chen¹, Yougang Ke³, Yu Chen¹(

), Xinxing Zhou²(

)

¹. International Collaborative Laboratory of 2D Materials for Optoelectronics Science and Technology, Institute of Microscale Optoelectronics, Shenzhen University, Shenzhen 518060, China
². Key Laboratory of Low-Dimensional Quantum Structures and Quantum Control of Ministry of Education, Synergetic Innovation Center for Quantum Effects and Applications, School of Physics and Electronics, Hunan Normal University, Changsha 410081, China
³. Key Laboratory of Hunan Province on Information Photonics and Freespace Optical Communications, School of Information Science and Engineering, Hunan Institute of Science and Technology, Yueyang 414006, China

Download: PDF(5192 KB) HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks

Abstract

Vortex beam with fractional orbital angular momentum (FOAM) is the excellent candidate for improving the capacity of free-space optical (FSO) communication system due to its infinite modes. Therefore, the recognition of FOAM modes with higher resolution is always of great concern. In this work, through an improved EfficientNetV2 based convolutional neural network (CNN), we experimentally achieve the implementation of the recognition of FOAM modes with a resolution as high as 0.001. To the best of our knowledge, it is the first time this high resolution has been achieved. Under the strong atmospheric turbulence (AT) ( $C n 2 = 10 − 15 m − 2 / 3$ ), the recognition accuracy of FOAM modes at 0.1 and 0.01 resolution with our model is up to 99.12% and 92.24% for a long transmission distance of 2000 m. Even for the resolution at 0.001, the recognition accuracy can still remain at 78.77%. This work provides an effective method for the recognition of FOAM modes, which may largely improve the channel capacity of the free-space optical communication.

Keywords OAM free-space optical communication deep learning convolutional neural network

Corresponding Author(s): Yu Chen,Xinxing Zhou

Issue Date: 27 December 2023

Cite this article:

Youzhi Shi,Zuhai Ma,Hongyu Chen, et al. High-resolution recognition of FOAM modes via an improved EfficientNet V2 based convolutional neural network[J]. Front. Phys. , 2024, 19(3): 32205.

URL:

https://academic.hep.com.cn/fop/EN/10.1007/s11467-023-1373-4
https://academic.hep.com.cn/fop/EN/Y2024/V19/I3/32205

Fig.1 Diagram of the experimental setup. L₁, L₂: Lens; GL: Glan prism polarizer; SLM: Spatial light modulator; CCD: Charge-coupled device; PH: Phase hologram of FOAM; AT: Atmospheric turbulence; AD: Aperture diaphragm.

Fig.2 (a) The structure of the AD. (b) Intensity distribution of original OAM modes (l = 1−5) by simulation. (c) Intensity distribution of OAM modes (l = 1−5) diffracting after the AD by simulation. (d) Intensity distribution of original OAM modes (l = 1−5) by experiment. (e) Intensity distribution of OAM modes (l = 1−5) diffracting after the AD by experiment.

Fig.3 Intensity of FOAM modes (l = 4.1, 4.3, 4.5, 4.7, 4.9) under three different intensities of AT and transmission distance (z = 2000 m). Rows (a?c) show the intensity of the FOAM modes under AT (

C n 2 = 10 − 17 m − 2 / 3

C n 2 = 10 − 16 m − 2 / 3

and

C n 2 = 10 − 15 m − 2 / 3

), respectively.

Fig.4 Schematic diagram of the structure of the EfficientNet V2 model. (a) Flowchart of the EfficientNet V2 model. (b) Structure diagram of the Fused-MBConv module (Expansion = 1). (c) Structure diagram of the Fused-MBConv module (Expansion ≠ 1). (d) Structure diagram of the MBConv module.

Fig.5 Test results of 0.1 and 0.01 resolution FOAM modes at z = 500 m. (a, e) Original FOAM modes of 0.1 and 0.01 resolution at

C n 2 = 10 − 16 m − 2 / 3

. (b, f) Diffraction patterns detected by CCD of 0.1 and 0.01 resolution. (c, g) Accuracy curves of 0.1 and 0.01 resolution FOAM modes in test set under different AT. (d, h) Loss curves of 0.1 and 0.01 resolution FOAM modes in test set under different AT.

Fig.6 Test results of 0.001 resolution FOAM modes at z = 500 m. (a) Original FOAM modes and (b) diffraction patterns detected by CCD (

C n 2 = 10 − 16 m − 2 / 3

; l = 4.001, 4.003, 4.005, 4.007, 4.009). (c) Accuracy and (d) loss curves in test set under different AT.

Fig.7 Test accuracy of FOAM modes for different resolution under different AT and distances. (a) 0.1 resolution. (b) 0.01 resolution. (c) 0.001 resolution.

Tab.1 Comparison of the improved EfficientNet V2 and ResNet 50 for the recognition of FOAM modes at 0.01 resolution under strong AT (

C n 2 = 10 − 15 m − 2 / 3

) and long transmission distance (z = 1500 m).

1	Allen L., W. Beijersbergen M., J. C. Spreeuw R., P. Woerdman J.. Orbital angular momentum of light and the transformation of Laguerre−Gaussian laser modes. Phys. Rev. A, 1992, 45(11): 8185 https://doi.org/10.1103/PhysRevA.45.8185
2	C. G. Berkhout G., P. J. Lavery M., Courtial J., W. Beijersbergen M., J. Padgett M.. Efficient sorting of orbital angular momentum states of light. Phys. Rev. Lett., 2010, 105(15): 153601 https://doi.org/10.1103/PhysRevLett.105.153601
3	Liu K., Q. Cheng Y., Li X., Gao Y.. Microwave-sensing technology using orbital angular momentum: Overview of its advantages. IEEE Veh. Technol. Mag., 2019, 14(2): 112 https://doi.org/10.1109/MVT.2018.2890673
4	Yan L., Kristensen P., Ramachandran S.. Vortex fibers for STED microscopy. APL Photonics, 2019, 4(2): 022903 https://doi.org/10.1063/1.5045233
5	W. Zhuang X.. Unraveling DNA condensation with optical tweezers. Science, 2004, 305(5681): 188 https://doi.org/10.1126/science.1100603
6	Y. Zhou Z., S. Ding D., K. Jiang Y., Li Y., Shi S., S. Wang X., S. Shi B.. Orbital angular momentum light frequency conversion and interference with quasi-phase matching crystals. Opt. Express, 2014, 22(17): 20298 https://doi.org/10.1364/OE.22.020298
7	J. Li S., Y. Li Z., S. Huang G., B. Liu X., Q. Li R., Y. Cao X.. Digital coding transmissive metasurface for multi-OAM-beam. Front. Phys., 2022, 17(6): 62501 https://doi.org/10.1007/s11467-022-1179-9
8	Zou L., Wang L., M. Zhao S.. Turbulence mitigation scheme based on spatial diversity in orbital-angular-momentum multiplexed system. Opt. Commun., 2017, 400: 123 https://doi.org/10.1016/j.optcom.2017.05.022
9	M. Amhoud E.Chafii M.Nimr A.Fettweis G., OFDM with index modulation in orbital angular momentum multiplexed free space optical links, in: IEEE 93rd Vehicular Technology Conference (VTC-Spring), Electr Network, 2021
10	E. Willner A., Pang K., Song H., H. Zou K., B. Zhou H.. Orbital angular momentum of light for communications. Appl. Phys. Rev., 2021, 8(4): 041312 https://doi.org/10.1063/5.0054885
11	H. Zhang X., Xia T., B. Cheng S., H. Tao S.. Free-space information transfer using the elliptic vortex beam with fractional topological charge. Opt. Commun., 2019, 431: 238 https://doi.org/10.1016/j.optcom.2018.09.035
12	V. Kotlyar V., A. Kovalev A., G. Nalimov A., P. Porfirev A.. Evolution of an optical vortex with an initial fractional topological charge. Phys. Rev. A, 2020, 102(2): 023516 https://doi.org/10.1103/PhysRevA.102.023516
13	S. Li S., F. Shen B., P. Wang W., G. Bu Z., Zhang H., Zhang H., H. Zhai S.. Diffraction of relativistic vortex harmonics with fractional average orbital angular momentum. Chin. Opt. Lett., 2019, 17(5): 050501 https://doi.org/10.3788/COL201917.050501
14	I. Dedo M., Wang Z., Guo K., Sun Y., Shen F., Zhou H., Gao J., Sun R., Ding Z., Guo Z.. Retrieving performances of vortex beams with GS algorithm after transmitting in different types of turbulences. Appl. Sci. (Basel), 2019, 9(11): 2269 https://doi.org/10.3390/app9112269
15	Yan X., F. Zhang P., H. Zhang J., X. Feng X., H. Qiao C., Y. Fan C.. Effect of atmospheric turbulence on entangled orbital angular momentum three-qubit state. Chin. Phys. B, 2017, 26(6): 064202 https://doi.org/10.1088/1674-1056/26/6/064202
16	J. Yang Y., Zhao Q., L. Liu L., D. Liu Y., Rosales-Guzman C., W. Qiu C.. Manipulation of orbital-angular-momentum spectrum using pinhole plates. Phys. Rev. Appl., 2019, 12(6): 064007 https://doi.org/10.1103/PhysRevApplied.12.064007
17	C. Zhang Z., C. Pei J., P. Wang Y., G. Wang X.. Measuring orbital angular momentum of vortex beams in optomechanics. Front. Phys., 2021, 16(3): 32503 https://doi.org/10.1007/s11467-020-1030-0
18	Forbes A., Dudley A., McLaren M.. Creation and detection of optical modes with spatial light modulators. Adv. Opt. Photonics, 2016, 8(2): 200 https://doi.org/10.1364/AOP.8.000200
19	Yu J.F. Wang Z., 3D facial motion tracking by combining online appearance model and cylinder head model in particle filtering, Sci. China Inf. Sci. 57(7), 029101 (2014)
20	Uribe-Patarroyo N., Fraine A., S. Simon D., Minaeva O., V. Sergienko A.. Object identification using correlated orbital angular momentum states. Phys. Rev. Lett., 2013, 110(4): 043601 https://doi.org/10.1103/PhysRevLett.110.043601
21	Zhu J., Zhang P., Z. Fu D., X. Chen D., F. Liu R., N. Zhou Y., Gao H., L. Li F.. Probing the fractional topological charge of a vortex light beam by using dynamic angular double slits. Photon. Res., 2016, 4(5): 187 https://doi.org/10.1364/PRJ.4.000187
22	Deng D., C. Lin M., Li Y., Zhao H.. Precision measurement of fractional orbital angular momentum. Phys. Rev. Appl., 2019, 12(1): 014048 https://doi.org/10.1103/PhysRevApplied.12.014048
23	Zheng S., Wang J.. Measuring orbital angular momentum (OAM) states of vortex beams with annular gratings. Sci. Rep., 2017, 7(1): 40781 https://doi.org/10.1038/srep40781
24	Bayoudh K.Knani R.Hamdaoui F.Mtibaa A., A survey on deep multimodal learning for computer vision: Advances, trends, applications, and datasets, Vis. Comput. 38(8), 2939 (2022)
25	O’Mahony N.Campbell S.Carvalho A. Harapanahalli S.V. Hernandez G.Krpalkova L.Riordan D.Walsh J., Deep learning vs. traditional computer vision, in: Computer Vision Conference (CVC), Springer International Publishing Ag, Las Vegas, NV, 2019, pp 128–144
26	J. Long, E. Shelhamer, and T. Darrell, Fully convolutional networks for semantic segmentation, in: IEEE Conference on Computer, Vision and Pattern Recognition (CVPR), IEEE, Boston, MA, 2015, pp 3431–3440
27	Le N., S. Rathour V., Yamazaki K., Luu K., Savvides M.. Deep reinforcement learning in computer vision: a comprehensive survey. Artif. Intell. Rev., 2022, 55(4): 2733 https://doi.org/10.1007/s10462-021-10061-9
28	Yamashita R., Nishio M., K. G. Do R., Togashi K.. Convolutional neural networks: An overview and application in radiology. Insights Imaging, 2018, 9(4): 611 https://doi.org/10.1007/s13244-018-0639-9
29	Michalski P.Ruszczak B.Tomaszewski M., Convolutional neural networks implementations for computer vision, in: 3rd International Scientific Conference on Brain-Computer Interfaces (BCI), Springer International Publishing Ag, Opole Univ Technol, Opole, POLAND, 2018, pp 98–110
30	W. Liu Z., Yan S., G. Liu H., F. Chen X.. Superhigh-resolution recognition of optical vortex modes assisted by a deep-learning method. Phys. Rev. Lett., 2019, 123(18): 183902 https://doi.org/10.1103/PhysRevLett.123.183902
31	Cao M., L. Yin Y., W. Zhou J., H. Tang J., P. Cao L., Xia Y., P. Yin J.. Machine learning based accurate recognition of fractional optical vortex modes in atmospheric environment. Appl. Phys. Lett., 2021, 119(14): 141103 https://doi.org/10.1063/5.0061365
32	Zhou J., Yin Y., Tang J., Ling C., Cao M., Cao L., Liu G., Yin J., Xia Y.. Recognition of high-resolution optical vortex modes with deep residual learning. Phys. Rev. A, 2022, 106(1): 013519 https://doi.org/10.1103/PhysRevA.106.013519
33	W. Song W., T. Li S., Y. Fang L., Lu T.. Hyperspectral image classification with deep feature fusion network. IEEE Trans. Geosci. Remote Sens., 2018, 56(6): 3173 https://doi.org/10.1109/TGRS.2018.2794326
34	X. Tan M.V. Le Q., EfficientNetV2: Smaller models and faster training, in: International Conference on Machine Learning (ICML), Electr Network, 2021, pp 7102–7110
35	L. Huang M.C. Liao Y., A lightweight CNN-based network on COVID-19 detection using X-ray and CT images, Comput. Biol. Med. 146, 105604 (2022)
36	Karthik R., S. Vaichole T., K. Kulkarni S., Yadav O., Khan F.. Eff2Net: An efficient channel attention-based convolutional neural network for skin disease classification. Biomed. Signal Process. Control, 2022, 73: 103406 https://doi.org/10.1016/j.bspc.2021.103406
37	Zhang H., Zeng J., Y. Lu X., Y. Wang Z., L. Zhao C., J. Cai Y.. Review on fractional vortex beam. Nanophotonics, 2022, 11(2): 241 https://doi.org/10.1515/nanoph-2021-0616
38	Belafhal A., Dalil-Essakali L.. Collins formula and propagation of Bessel-modulated Gaussian light beams through an ABCD optical system. Opt. Commun., 2000, 177(1−6): 181 https://doi.org/10.1016/S0030-4018(00)00600-3
39	J. Yang Y., Dong Y., L. Zhao C., J. Cai Y.. Generation and propagation of an anomalous vortex beam. Opt. Lett., 2013, 38(24): 5418 https://doi.org/10.1364/OL.38.005418
40	H. F. Mesquita P., J. Jesus-Silva A., J. S. Fonseca E., M. Hickmann J.. Engineering a square truncated lattice with light’s orbital angular momentum. Opt. Express, 2011, 19(21): 20616 https://doi.org/10.1364/OE.19.020616
41	Rodenburg B., P. J. Lavery M., Malik M., N. O’Sullivan M., Mirhosseini M., J. Robertson D., Padgett M., W. Boyd R.. Influence of atmospheric turbulence on states of light carrying orbital angular momentum. Opt. Lett., 2012, 37(17): 3735 https://doi.org/10.1364/OL.37.003735
42	Y. Fu S., Q. Gao C.. Influences of atmospheric turbulence effects on the orbital angular momentum spectra of vortex beams. Photon. Res., 2016, 4(5): B1 https://doi.org/10.1364/PRJ.4.0000B1
43	C. Andrews L.. An analytical model for the refractive index power spectrum and its application to optical scintillations in the atmosphere. J. Mod. Opt., 1992, 39(9): 1849 https://doi.org/10.1080/09500349214551931
44	Cheng W., W. Haus J., W. Zhan Q.. Propagation of vector vortex beams through a turbulent atmosphere. Opt. Express, 2009, 17(20): 17829 https://doi.org/10.1364/OE.17.017829
45	M. Zhao S., Leach J., Y. Gong L., Ding J., Y. Zheng B.. Aberration corrections for free-space optical communications in atmosphere turbulence using orbital angular momentum states. Opt. Express, 2012, 20(1): 452 https://doi.org/10.1364/OE.20.000452
46	Kim Y., Ohn I., Kim D.. Fast convergence rates of deep neural networks for classification. Neural Netw., 2021, 138: 179 https://doi.org/10.1016/j.neunet.2021.02.012

[1]	Xinqin Meng, Chengbing Qin, Xilong Liang, Guofeng Zhang, Ruiyun Chen, Jianyong Hu, Zhichun Yang, Jianzhong Huo, Liantuan Xiao, Suotang Jia. Deep learning in two-dimensional materials: Characterization, prediction, and design[J]. Front. Phys. , 2024, 19(5): 53601-.
[2]	Jingwen Zhou, Yaling Yin, Jihong Tang, Yong Xia, Jianping Yin. Information transmission through parallel multi-task-based recognition of high-resolution multiplexed orbital angular momentum[J]. Front. Phys. , 2024, 19(5): 52202-.
[3]	Linwei Sai, Li Fu, Qiuying Du, Jijun Zhao. Graph attention network for global search of atomic clusters: A case study of Ag_n (n = 14−26) clusters[J]. Front. Phys. , 2023, 18(1): 13306-.
[4]	Meng-Qin Jiang, Nan Yang, Jin Li. Identify real gravitational wave events in the LIGO-Virgo catalog GWTC-1 and GWTC-2 with convolutional neural network[J]. Front. Phys. , 2022, 17(5): 54501-.
[5]	Shurui Li, Jianqin Xu, Jing Qian, Weiping Zhang. Revisiting the dynamics of Bose–Einstein condensates in a double well by deep learning with a hybrid network[J]. Front. Phys. , 2022, 17(2): 22504-.
[6]	Hua-Mei Luo, Wenbin Lin, Zu-Cheng Chen, Qing-Guo Huang. Extraction of gravitational wave signals with optimized convolutional neural network[J]. Front. Phys. , 2020, 15(1): 14601-.

Viewed

Full text

Abstract

Cited

Shared

Discussed