Identifying orbital angular momentum modes in turbulence with high accuracy via machine learning

The orbital angular momentum (OAM) of a Laguerre–Gaussian beam (LGB) is classified using the support vector machine (SVM) model. The scintillation index, beam width, and beam wander of the Gaussian beam and the LGB at the receiving site are taken as feature vectors, and the OAM number of a LGB is taken as the label in the training and test samples. The influences on the detection accuracy of the number of training samples, the transmission distance, and the different ways of grouping OAM values are analyzed, where the detection accuracy is defined as the percentage of correctly detected OAM. The results show that only a few training samples are needed up to a range of 4000 m to achieve saturation accuracy. When the transmission distance is within 2500 m, the detection accuracy of a single SVM model in four turbulent environments ( 10−14, 10−15, ) is close to 100%. When the distance increases, detection accuracy decreases gradually, and in the range of 4000 m the detection accuracy is more than 91%. Compared with the traditional spiral spectrum expansion method, the SVM model has obvious advantages. In addition, when the range of OAM to be detected is large, the OAM values may be grouped thereby improving the accuracy when using the multi-SVM models for joint detection.

[1]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[2]  Anting Wang,et al.  Detecting the topological charge of optical vortex beams using a sectorial screen. , 2017, Applied optics.

[3]  Aboul Ella Hassanien,et al.  A BA-based algorithm for parameter optimization of Support Vector Machine , 2017, Pattern Recognit. Lett..

[4]  Wathiq Laftah Al-Yaseen,et al.  Multi-level hybrid support vector machine and extreme learning machine based on modified K-means for intrusion detection system , 2017, Expert Syst. Appl..

[5]  Y. Baykal,et al.  Scintillation behavior of Laguerre Gaussian beams in strong turbulence , 2011 .

[6]  Umberto Castellani,et al.  Classification of first-episode psychosis in a large cohort of patients using support vector machine and multiple kernel learning techniques , 2017, NeuroImage.

[7]  Jian Wang,et al.  Adaptive free-space optical communications through turbulence using self-healing Bessel beams , 2017, Scientific Reports.

[8]  Li-xin Guo,et al.  Propagation properties of an optical vortex carried by a Bessel-Gaussian beam in anisotropic turbulence. , 2016, Journal of the Optical Society of America. A, Optics, image science, and vision.

[9]  Chunqing Gao,et al.  Influences of atmospheric turbulence effects on the orbital angular momentum spectra of vortex beams , 2016 .

[10]  Xin Zhang,et al.  Condition multi-classification and evaluation of system degradation process using an improved support vector machine , 2017, Microelectron. Reliab..

[11]  Yixin Zhang,et al.  Analysis of modal crosstalk for communication in turbulent ocean using Lommel-Gaussian beam. , 2017, Optics express.

[12]  Lixin Guo,et al.  Propagation of an optical vortex carried by a partially coherent Laguerre-Gaussian beam in turbulent ocean. , 2016, Applied optics.

[13]  Shan Suthaharan,et al.  Machine Learning Models and Algorithms for Big Data Classification: Thinking with Examples for Effective Learning , 2015 .

[14]  Shan Suthaharan,et al.  Machine Learning Models and Algorithms for Big Data Classification , 2016 .

[15]  Shuang Zheng,et al.  Measuring Orbital Angular Momentum (OAM) States of Vortex Beams with Annular Gratings , 2017, Scientific Reports.

[16]  Yangjian Cai,et al.  Optimization of the probability of orbital angular momentum for Laguerre-Gaussian beam in Kolmogorov and non-Kolmogorov turbulence. , 2018, Optics express.

[17]  L. Andrews,et al.  Laser Beam Propagation Through Random Media , 1998 .

[18]  Bernhard Schölkopf,et al.  New Support Vector Algorithms , 2000, Neural Computation.

[19]  Timothy Doster,et al.  Machine learning approach to OAM beam demultiplexing via convolutional neural networks. , 2017, Applied optics.

[20]  Nguyen Quoc Thanh,et al.  Spatial prediction of rainfall-induced landslides for the Lao Cai area (Vietnam) using a hybrid intelligent approach of least squares support vector machines inference model and artificial bee colony optimization , 2017, Landslides.

[21]  Takuo Tanemura,et al.  An InP-based vortex beam emitter with monolithically integrated laser , 2018, Nature Communications.

[22]  Cory J. Butz,et al.  Rough set based 1-v-1 and 1-v-r approaches to support vector machine multi-classification , 2007, Inf. Sci..

[23]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[24]  Effects of Asymmetry Atmospheric Eddies on Spreading and Wander of Bessel–Gaussian Beams in Anisotropic Turbulence , 2018, IEEE Photonics Journal.

[25]  Juan P. Torres.  Optical communications: Multiplexing twisted light , 2012 .

[26]  Min Zhang,et al.  Joint atmospheric turbulence detection and adaptive demodulation technique using the CNN for the OAM-FSO communication. , 2018, Optics express.

[27]  Y. Baykal,et al.  Scintillations of Laguerre Gaussian beams , 2010 .

[28]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machine Classifiers , 1999, Neural Processing Letters.

[29]  Li-xin Guo,et al.  Controlling abruptly autofocusing vortex beams to mitigate crosstalk and vortex splitting in free-space optical communication. , 2018, Optics express.