标签分布不平衡的涡旋光束轨道角动量识别  

Recognition method for vortex beams orbital angular momentum with imbalanced label

作　　者：于海洋[1,2,3] 尚凡华 王宇兴[2] 王大涛 陈纯毅 YU Hai-yang;SHANG Fan-hua;WANG Yu-xing;WANG Da-tao;CHEN Chun-yi(College of Intelligence and Computing,Tianjin University,Tianjin 300000,China;Bona Zhilian(Ningbo)Technology Company Limited,Ningbo 315000,China;School of Computer Science and Technology,Changchun University of Science and Technology,Changchun 130022,China)

机构地区：[1]天津大学智能与计算学部,天津300000 [2]博纳智联(宁波)科技有限公司,浙江宁波315000 [3]长春理工大学计算机科学技术学院,吉林长春130022

出　　处：《中国光学(中英文)》2025年第2期207-215,共9页Chinese Optics

基　　金：国家自然科学基金(No.62305030,No.62275033);吉林省科技发展计划项目(No.20240602123RC)。

摘　　要：针对标签分布不平衡的涡旋光束轨道角动量(OAM)识别问题,提出了一种基于全局代价的合成少数类过采样技术(SMOTE)的深度极限学习机(DELM)的衍生模型。与典型的机器学习方法不同,本文所提方法能够获得映射模型解析表达,避免了反复的参数优化过程,使模型适用于工程应用。在数据生成阶段,利用协方差的逆矩阵去除量纲的影响,有效度量了同一类样本的差异性。在模型选择阶段,考虑了光信号在大气湍流中的传输特性,采用DELM表征光斑样本和标签之间的映射关系,并用快速迭代收缩阈值FISTA算法计算模型的解析表达式。在不同强度的大气湍流数据集上进行实验,对比了WELM、k近邻等代表性方法性能。实验结果表明,在不同的湍流强度下,所提方法均方根误差达到0.2049和0.0894,各项评价指标均优于对比方法。证明了所提方法能够充分挖掘了OAM光斑集合的特征,具有更好的识别效果。To identify the vortex beams orbital angular momentum(OAM)with imbalanced labels,this paper proposes a derived model based on global cost SMOTE and deep extreme learning machine(DELM).Unlike typical machine learning methods,the proposed model can obtain the analytical expression of the mapping model.It avoids repeated parameter optimization,thus building a suitable model for time-varying engineering applications.In the data generation stage,the inverse matrix of covariance was used to remove the influence of dimensions,and the differences among samples within the same category were effectively measured.In the model selection stage,considering the transmission characteristics of light signals in atmospheric turbulence,the DELM was adopted to quantify the mapping relationship between light spots and labels.Then the FISTA algorithm was used to calculate the model’s analytical expression.Experiments were carried out on different intensity atmospheric turbulence data sets.The representative comparative methods include WELM and k-nearest neighbor.Experimental results show that the proposed method’s root mean square error(RMSE)achieves 0.2049 and 0.0894,which are superior to the comparison methods under different turbulence intensities.This proves that the proposed method can fully explore the characteristics of OAM spot collection and has a better recognition effect.

关 键 词：大气湍流 轨道角动量 不平衡数据 深度极限学习机 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]