Broad Bandwidth and Highly Efficient Recognition of Optical Vortex Modes Achieved by the Neural-Network Approach

Mao, Zhixiang; Yu, Haiyu; Xia, Meng; Pan, Shengzhe; Wu, Di; Yin, Yin; Xia, Yong; Yin, Jianping

doi:10.1103/physrevapplied.13.034063

Cited by 22 publications

(9 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Data augmentation is a technique to artificially create new data from a given training set in the training phase of neural networks, which is implemented by applying various transformations, such as translation, rotation, and scaling 24 , 45 . Data augmentation randomly sets the degree of these transformations every epoch, effectively improving the generalization performance of neural networks.…”

Section: Resultsmentioning

confidence: 99%

“…Artificial neural networks comprised of multiple processing layers have been widely applied as a precise, efficient tool for detecting OAM modes 17 – 24 . Deep-learning models directly recognize transmitted spatial modes without any optical mode sorter for extracting phase information 18 , 20 and provide reliable performance against distorting factors such as optical misalignment 18 , 24 , 25 . Adaptive demodulation 21 – 23 and turbulence correction 26 , 27 for integer vortex beams have been studied in depth by pioneering researchers.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Adaptive demodulation by deep-learning-based identification of fractional orbital angular momentum modes with structural distortion due to atmospheric turbulence

2021

Sci Rep

View full text Add to dashboard Cite

Since the great success of optical communications utilizing orbital angular momentum (OAM), increasing the number of addressable spatial modes in the given physical resources has always been an important yet challenging problem. The recent improvement in measurement resolution through deep-learning techniques has demonstrated the possibility of high-capacity free-space optical communications based on fractional OAM modes. However, due to a tiny gap between adjacent modes, such systems are highly susceptible to external perturbations such as atmospheric turbulence (AT). Here, we propose an AT adaptive neural network (ATANN) and study high-resolution recognition of fractional OAM modes in the presence of turbulence. We perform simulations of fractional OAM beams propagating through a 1-km optical turbulence channel and analyze the effects of turbulence strength, OAM mode interval, and signal noise on the recognition performance of the ATANN. The recognition of multiplexed fractional modes is also investigated to demonstrate the feasibility of high-dimensional data transmission in the proposed deep-learning-based system. Our results show that the proposed model can predict transmitted modes with high accuracy and high resolution despite the collapse of structured fields due to AT and provide stable performance over a wide SNR range.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Adaptive demodulation by deep-learning-based identification of fractional orbital angular momentum modes with structural distortion due to atmospheric turbulence

2021

Sci Rep

View full text Add to dashboard Cite

show abstract

“…As shown in Figure 10c, researchers proposed a hybrid structured light with a new controllable DoF on shape that they call "the angular ratio" in addition to OAM. 108 This DoF induces an intensity change that can be sensed by neural networks despite for beams with the same OAM, which consequently increase the available states to encode different information. In fact, one does not have to create new structured light with new DoFs for an increased communication capacity because two-dimensional structured beams are already rich in members.…”

Section: Information Carriersmentioning

confidence: 99%

Ultra-Degree-of-Freedom Structured Light for Ultracapacity Information Carriers

et al. 2023

View full text Add to dashboard Cite

Structured light recently highlighted the higher-dimensional control with many tailored degrees of freedom (DoFs) such as amplitude, wavelength, polarization, and orbital angular momentum (OAM), spurring the extension of fundamental science and advanced applications, especially as the novel information carrier to meet the requirement of everlastingly increasing communication bandwidth and security. In addition to the basic DoFs in light, there are also several complex DoFs hidden in spin−orbital coupled vector beams, ray-wave geometric modes, spatiotemporal vortex rings, etc., extending the structured light manipulation. In this Review, we summarize a systematic technical roadmap on how to extend multiple DoFs step-by-step beyond the conventional OAM beams, creating new forms of ultra-DoF structured light, and present a tutorial on how to exploit multiple DoFs of light as advanced information carriers, especially with the recent assistance of artificial intelligence or deep learning method, enhancing the capacity, security, and dimension for the next-generation information technologies.

show abstract

“…Recently, a convolutional neural network (CNN), the most preferred solution for image classification 32 , 33 , has drawn attention as an efficient tool for recognizing OAM modes and correcting phase distortion caused by atmospheric turbulence 34 – 39 . End-to-end recognition of the deep-learning allows the classification process to be performed with only the intensity profile of the target modes, which is the most distinctive feature compared to the existing methods that require additional components to extract phase information 35 .…”

Section: Introductionmentioning

confidence: 99%

“…End-to-end recognition of the deep-learning allows the classification process to be performed with only the intensity profile of the target modes, which is the most distinctive feature compared to the existing methods that require additional components to extract phase information 35 . Translation invariance of CNN provides stable recognition performance regardless of lateral displacement of a detector to the optical axis, and even it is possible to impart several transform invariances, such as rotation and scaling, through preparation and augmentation of proper data samples 35 , 39 – 41 . Moreover, a recent study has experimentally demonstrated that fractional OAM modes can be precisely recognized with a resolution of 0.01 41 .…”

Section: Introductionmentioning

confidence: 99%

Deep-learning-based high-resolution recognition of fractional-spatial-mode-encoded data for free-space optical communications

2021

Sci Rep

View full text Add to dashboard Cite

Structured light with spatial degrees of freedom (DoF) is considered a potential solution to address the unprecedented demand for data traffic, but there is a limit to effectively improving the communication capacity by its integer quantization. We propose a data transmission system using fractional mode encoding and deep-learning decoding. Spatial modes of Bessel-Gaussian beams separated by fractional intervals are employed to represent 8-bit symbols. Data encoded by switching phase holograms is efficiently decoded by a deep-learning classifier that only requires the intensity profile of transmitted modes. Our results show that the trained model can simultaneously recognize two independent DoF without any mode sorter and precisely detect small differences between fractional modes. Moreover, the proposed scheme successfully achieves image transmission despite its densely packed mode space. This research will present a new approach to realizing higher data rates for advanced optical communication systems.

show abstract

Broad Bandwidth and Highly Efficient Recognition of Optical Vortex Modes Achieved by the Neural-Network Approach

Cited by 22 publications

References 47 publications

Adaptive demodulation by deep-learning-based identification of fractional orbital angular momentum modes with structural distortion due to atmospheric turbulence

Adaptive demodulation by deep-learning-based identification of fractional orbital angular momentum modes with structural distortion due to atmospheric turbulence

Ultra-Degree-of-Freedom Structured Light for Ultracapacity Information Carriers

Deep-learning-based high-resolution recognition of fractional-spatial-mode-encoded data for free-space optical communications

Contact Info

Product

Resources

About