Turn off MathJax
Article Contents
YU Hai-yang, SHANG Fan-hua, WANG Yu-xing, WANG Da-tao, CHEN Chun-yi. Recognition method for vortex beams orbital angular momentum with imbalanced label[J]. Chinese Optics. doi: 10.37188/CO.2024-0155
Citation: YU Hai-yang, SHANG Fan-hua, WANG Yu-xing, WANG Da-tao, CHEN Chun-yi. Recognition method for vortex beams orbital angular momentum with imbalanced label[J]. Chinese Optics. doi: 10.37188/CO.2024-0155

Recognition method for vortex beams orbital angular momentum with imbalanced label

cstr: 32171.14.CO.2024-0155
Funds:  Supported by the National Natural Science Foundation of China (No. 62305030, No. 62275033); Science and Technology Development Project of Jilin Province (No. 20240602123RC)
More Information
  • Corresponding author: custhaiyang@126.com
  • Received Date: 02 Sep 2024
  • Accepted Date: 29 Oct 2024
  • Available Online: 27 Nov 2024
  • To identify orbital angular momentum (OAM) with imbalanced label, a derived model based on global cost SMOTE and deep extreme learning machine (DELM) has been proposed. Different from typical machine learning methods, the proposed model can obtain the analytical expression of the mapping model. It will avoid the repeated parameter optimization process, thus building a suitable model for time-varying engineering applications. In the data generation stage, the inverse matrix of covariance is used to remove the dimension influence, and the differences of the same sample set are measured effectively. In the model selection stage, considering the transmission characteristics of light signal in atmosphere turbulence, the DELM is adopted to quantify the mapping relationship between light spots and labels. Then the FISTA algorithm helps to calculate the analytical expression of the model. Experiments are carried out on different intensity atmospheric turbulence data sets. The representative comparative methods include WELM and K-nearest neighbor. Experimental results show that the root mean square error(RMSE) of the proposed method achieve 0.2049 and 0.0894, which are superior to the comparison method under different turbulence intensities. It is proved that the proposed method can fully explore the characteristics of OAM spot collection and has better recognition effect.

     

  • loading
  • [1]
    ARYA S, CHUNG Y H. A comprehensive survey on optical scattering communications: current research, new trends, and future vision[J]. IEEE Communications Surveys & Tutorial, 2024, 26(2): 1446-1477.
    [2]
    CHEN R, ZHOU J X, LONG W X, et al. Hybrid circular array and Luneberg lens for long-distance OAM wireless communications[J]. IEEE Transactions on Communications, 2023, 71(1): 485-497. doi: 10.1109/TCOMM.2022.3223697
    [3]
    YU H, YANG B W, HU H Y, et al. Propagation characteristics of the vortex beam array through anisotropic non-Kolmogorov maritime atmospheric turbulence[J]. Frontiers in Physics, 2023, 11: 1277132. doi: 10.3389/fphy.2023.1277132
    [4]
    LECUN Y, BENGIO Y, HINTON G. Deep learning[J]. Nature, 2015, 521(7553): 436-444. doi: 10.1038/nature14539
    [5]
    JING G Q, CHEN L ZH, WANG P P, et al. Recognizing fractional orbital angular momentum using feed forward neural network[J]. Results in Physics, 2021, 28: 104619. doi: 10.1016/j.rinp.2021.104619
    [6]
    FU X, BAI Y H, YANG Y J. Measuring OAM by the hybrid scheme of interference and convolutional neural network[J]. Optical Engineering, 2021, 60(6): 064109.
    [7]
    娄岩, 陈纯毅, 赵义武, 等. 高斯涡旋光束在大气湍流传输中的特性研究[J]. 中国光学,2017,10(6):768-776. doi: 10.3788/co.20171006.0768

    LOU Y, CHEN CH Y, ZHAO Y W, et al. Characteristics of Gaussian vortex beam in atmospheric turbulence transmission[J]. Chinese Optics, 2017, 10(6): 768-776. (in Chinese). doi: 10.3788/co.20171006.0768
    [8]
    ZHOU H Q, WANG Y T, LI X, et al. A deep learning approach for trustworthy high-fidelity computational holographic orbital angular momentum communication[J]. Applied Physics Letters, 2021, 119(4): 044104. doi: 10.1063/5.0051132
    [9]
    吴鹏飞, 贾致远, 雷思琛, 等. 改进CNN-Transformer结合双缝干涉的轨道角动量模态识别方法[J]. 光学学报,2024,10:1-17.

    WU P F, JIA ZH Y, LEI S CH, et al. A method for orbital angular momentum mode recognition employing an enhanced CNN-transformer model integrated with double-slit interference[J]. Acta Optica Sinica, 2024, 10: 1-17. (查阅网上资料, 未找到本条文献卷期信息, 请确认) .
    [10]
    ZHU CH X, ZHOU X X, GUO G C, et al. Simulating electrical fields in the orbital angular momentum space of light[J]. Optics Express, 2022, 30(2): 972-985. doi: 10.1364/OE.446276
    [11]
    郑崇辉, 王天枢, 刘哲绮, 等. 深度迁移学习方法识别轨道角动量光束[J]. 光电工程,2022,49(6):210409.

    ZHENG CH H, WANG T SH, LIU ZH Q, et al. Deep transfer learning method to identify orbital angular momentum beams[J]. Opto-Electronic Engineering, 2022, 49(6): 210409. (in Chinese).
    [12]
    周旭, 陈纯毅, 于海洋, 等. 基于注意力机制的轨道角动量多叠加态识别方法[J]. 激光与光电子学进展,2023,60(23):2306003.

    ZHOU X, CHEN CH Y, YU H Y, et al. Orbital angular momentum multi-superposition identification method based on attention mechanism[J]. Laser & Optoelectronics Progress, 2023, 60(23): 2306003. (in Chinese).
    [13]
    CHEN CH Y, YANG H M. Characterizing the statistical distribution for transmission coefficient of turbulent optical orbital-angular-momentum channels[J]. Optics Express, 2019, 27(20): 28968-28982. doi: 10.1364/OE.27.028968
    [14]
    GONG CH L, GU L X. A novel SMOTE-based classification approach to online data imbalance problem[J]. Mathematical Problems in Engineering, 2016, 2016: 5685970.
    [15]
    王忠震, 黄勃, 方志军, 等. 改进SMOTE的不平衡数据集成分类算法[J]. 计算机应用,2019,39(9):2591-2596.

    WANG ZH ZH, HUANG B, FANG ZH J, et al. Improved SMOTE unbalanced data integration classification algorithm[J]. Journal of Computer Applications, 2019, 39(9): 2591-2596. (in Chinese).
    [16]
    ZHANG A M, YU H L, HUAN ZH J, et al. SMOTE-RkNN: a hybrid re-sampling method based on SMOTE and reverse k-nearest neighbors[J]. Information Sciences, 2022, 595: 70-88. doi: 10.1016/j.ins.2022.02.038
    [17]
    HUANG G, HUANG G B, SONG SH J, et al. Trends in extreme learning machines: a review[J]. Neural Networks, 2015, 61: 32-48. doi: 10.1016/j.neunet.2014.10.001
    [18]
    YAN D Q, CHU Y H, ZHANG H Y, et al. Information discriminative extreme learning machine[J]. Soft Computing, 2018, 22(2): 677-689. doi: 10.1007/s00500-016-2372-y
    [19]
    YU H Y, CHEN CH Y, HU X J, et al. An efficient recognition method for orbital angular momentum via adaptive deep ELM[J]. Sensors, 2023, 23(21): 8737. doi: 10.3390/s23218737
    [20]
    BECK A, TEBOULLE M. A fast iterative shrinkage-thresholding algorithm for linear inverse problems[J]. SIAM Journal on Imaging Sciences, 2009, 2(1): 183-202. doi: 10.1137/080716542
    [21]
    DELGADO-VENCES F J, FLANDOLI F. A spectral-based numerical method for Kolmogorov equations in Hilbert spaces[J]. Infinite Dimensional Analysis, Quantum Probability and Related Topics, 2016, 19(3): 1650020. doi: 10.1142/S021902571650020X
    [22]
    LAI J, WANG X D, XIANG Q, et al. Multilayer discriminative extreme learning machine for classification[J]. International Journal of Machine Learning and Cybernetics, 2023, 14(6): 2111-2125. doi: 10.1007/s13042-022-01749-7
    [23]
    陈纯毅, 杨华民, 任斌, 等. 激光大气湍流传输数值实验建模与计算机模拟[J]. 系统仿真学报,2018,30(6):2133-2143.

    CHEN CH Y, YANG H M, REN B, et al. Modeling and computer simulation of numerical experiments on laser propagation through atmospheric turbulence[J]. Journal of System Simulation, 2018, 30(6): 2133-2143. (in Chinese).
    [24]
    姜楠, 李晓英, 牛春晖, 等. 大气湍流对激光空间传输特性影响的实验研究[J]. 激光技术,2022,46(5):708-712.

    JIANG N, LI X Y, NIU CH H, et al. Experimental study on the influence of atmospheric turbulence on laser spatial transmission characteristics[J]. Laser Technology, 2022, 46(5): 708-712. (in Chinese).
  • 加载中

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Figures(5)  / Tables(3)

    Article views(52) PDF downloads(7) Cited by()
    Proportional views
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return