ELECTROMAGNETISM, OPTICS, ACOUSTICS, HEAT TRANSFER, CLASSICAL MECHANICS, AND FLUID DYNAMICS |
Prev
Next
|
|
|
Diffraction deep neural network-based classification for vector vortex beams |
Yixiang Peng(彭怡翔)1, Bing Chen(陈兵)1, Le Wang(王乐)1, and Shengmei Zhao(赵生妹)1,2,3,† |
1 Institute of Signal Processing and Transmission, Nanjing University of Posts and Telecommunications (NJUPT), Nanjing 210003, China; 2 Key Laboratory of Broadband Wireless Communication and Sensor Network Technology, Ministry of Education, Nanjing 210003, China; 3 National Laboratory of Solid State Microstructures, Nanjing University, Nanjing 210093, China |
|
|
Abstract The vector vortex beam (VVB) has attracted significant attention due to its intrinsic diversity of information and has found great applications in both classical and quantum communications. However, a VVB is unavoidably affected by atmospheric turbulence (AT) when it propagates through the free-space optical communication environment, which results in detection errors at the receiver. In this paper, we propose a VVB classification scheme to detect VVBs with continuously changing polarization states under AT, where a diffractive deep neural network (DDNN) is designed and trained to classify the intensity distribution of the input distorted VVBs, and the horizontal direction of polarization of the input distorted beam is adopted as the feature for the classification through the DDNN. The numerical simulations and experimental results demonstrate that the proposed scheme has high accuracy in classification tasks. The energy distribution percentage remains above 95% from weak to medium AT, and the classification accuracy can remain above 95% for various strengths of turbulence. It has a faster convergence and better accuracy than that based on a convolutional neural network.
|
Received: 25 June 2023
Revised: 26 September 2023
Accepted manuscript online: 09 October 2023
|
PACS:
|
42.30.Sy
|
(Pattern recognition)
|
|
42.79.Ta
|
(Optical computers, logic elements, interconnects, switches; neural networks)
|
|
42.68.-w
|
(Atmospheric and ocean optics)
|
|
84.35.+i
|
(Neural networks)
|
|
Fund: Project supported by the National Natural Science Foundation of China (Grant Nos. 62375140 and 62001249) and the Open Research Fund of National Laboratory of Solid State Microstructures (Grant No. M36055). |
Corresponding Authors:
Shengmei Zhao
E-mail: zhaosm@njupt.edu.cn
|
Cite this article:
Yixiang Peng(彭怡翔), Bing Chen(陈兵), Le Wang(王乐), and Shengmei Zhao(赵生妹) Diffraction deep neural network-based classification for vector vortex beams 2024 Chin. Phys. B 33 034205
|
[1] Milione G, Nguyen T A, Leach J, Nolan D A and Alfano R R 2015 Opt. Lett. 40 4887 [2] Ndagano B, Nape I, Cox M A, Guzman C R and Forbes A 2018 J. Lightwave Technol. 36 292 [3] McLaren M, Konrad T and Forbes A 2015 Phys. Rev. A 92 23833 [4] Giordani T, Suprano A, Polino E, Acanfora F, Innocenti L, Ferraro A, Paternostro M, Spagnolo N and Sciarrino F 2020 Phys. Rev. Lett. 124 160401 [5] lin X, Rivenson Y, Yardimci N T, Veli M, Luo Y, Jarrahi M and Ozcan A 2018 Science 361 1004 [6] Huang Z, Wang P P, Liu J, Xiong W J, He Y L, Xiao J N, Ye H P, Li Y, Chen S Q and Fan D Y 2021 Phys. Rev. Appl. 15 014037 [7] Zhao Q S, Hao S Q, Wang Y, Wang L and Xu C L 2019 Opt. Commun. 443 245 [8] Wang P P, Xiong W J, Huang Z B, He Y L, Liu J M, Ye H P, Xiao J N, Li Y, Fan D Y and Chen S Q 2021 IEEE J. Sel. Top. Quantum Electron. 28 1 [9] Huang Z, He Y L, Wang W N, Wang P P, Xiong W J, Wu H S, Liu J M, Ye H P, Li Y, Fan D Y and Chen S Q 2022 Opt. Express 30 5569 [10] Wang P P, Xiong W J, Huang Z B, He Y L, Xie Z Q, Liu J M, Ye H P, Li Y, Fan D Y and Chen S Q 2021 Photon. Res. 9 2116 [11] Zhan H C, Peng Y X, Chen B, Wang L, Wang W N and Zhao S M 2022 Opt. Express 30 23305 [12] Zhan H C, Chen B, Peng Y X, Wang L, Wang W N and Zhao S M 2023 Chin. Phys. B 32 044208 [13] Zhan H C, Wang L, Wang W N and Zhao S M 2023 J. Opt. Soc. Am. B 40 187 [14] Chen S Z, Zhou X X, Liu Y C, Ling X H, Luo H L and Wen S C 2014 Opt. Lett. 39 5274 [15] Zhao S M, Wang B, Gong L Y, Sheng Y B, Cheng W W, Dong X L and Zheng B Y 2013 J. Lightwave Technol. 31 2823 [16] Zhao S M, Leach J, Gong L Y, Ding J and Zheng B Y 2012 Opt. Express 20 452 [17] Jones R C 1941 J. Opt. Soc. Am. 31 488 [18] Rosales-Guzmán C, Ndagano B, Forbes A 2018 J. Opt. 20 123001 [19] Zhai Y W, Fu S Y, Zhang J Q, Liu X T, Zhou H and Gao C Q 2020 Opt. Express 28 7515 [20] Cheng W, Haus J W and Zhan Q W 2009 Opt. Express 17 17829 [21] Nape I, Singh K, Klug A, Buono W, Rosales-Guzman C, McWilliam A, Franke-Arnold S, Kritzinger A, Forbes P, Dudley A and Forbes A 2022 Nat. Photonics 16 538 [22] Cai Y J, Lin Q, Eyyuboğlu H T and Baykal Y 2008 Opt. Express 16 7665 [23] Zhan Q W 2009 Adv. Opt. Photon. 1 1 [24] Cox M A, Rosales-Guzmán C, Lavery M P J, Versfeld D J and Forbes A 2016 Opt. Express 24 18105 [25] Hearst M A, Dumais S T, Osuna E, Platt J and Scholkopf B 1998 IEEE Intell. Syst. Their Appl. 13 18 [26] Chapelle O, Haffner P and Vapnik V N 1999 IEEE Trans. Neural Netw. 10 1055 [27] Foody G M and Mathur A 2004 IEEE Trans. Geosci. Remote Sens. 42 1335 [28] Cervantes J, Garcia-Lamont F and Rodr\i guez-Mazahua L 2020 Neurocomputing 408 189 |
No Suggested Reading articles found! |
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
Altmetric
|
blogs
Facebook pages
Wikipedia page
Google+ users
|
Online attention
Altmetric calculates a score based on the online attention an article receives. Each coloured thread in the circle represents a different type of online attention. The number in the centre is the Altmetric score. Social media and mainstream news media are the main sources that calculate the score. Reference managers such as Mendeley are also tracked but do not contribute to the score. Older articles often score higher because they have had more time to get noticed. To account for this, Altmetric has included the context data for other articles of a similar age.
View more on Altmetrics
|
|
|