Identification of hybrid orbital angular momentum modes with deep feedforward neural network

Huang, Zebin; Wang, Peipei; Liu, Junmin; Xiong, Wenjie; He, Yanliang; Zhou, Xinxing; Xiao, Jiangnan; Liu, Ying; Chen, Shuqing; Fan, Dianyuan

doi:10.1016/j.rinp.2019.102790

Cited by 25 publications

(4 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The FNN model succeeded in quickly recognizing OAM modes ranging from −25 to +25 with the accuracy up to 99.55% and 90.29% under the meter-level transmission distance with moderate and strong turbulences respectively. In the same year, Huang et al used a similar deep FNN model with 7 hidden layers to construct a 120-ary OAM-SK communication link [90] Although these results seem promising, however a real boost in FNN-based OAM mode recognition came in 2021 when FNN was applied to recognize fractional OAM (FOAM) modes with the recognition accuracy reaching over 99% at the mode interval of 0.1 under the turbulence of C n 2 = 1 × 10 − 14 m −2/3 [91]. The proposed deep FNN model (figure 5(d)) was trained to learn the mapping relationship between FOAM mode and the intensity profile of the diffraction array to accurately identify FOAM modes.…”

Section: Deep Fnn-based Oam Mode Recognitionmentioning

confidence: 99%

Top three intelligent algorithms for OAM mode recognitions in optical communications

Wang,

Zhang,

Shah

et al. 2024

Eng. Res. Express

View full text Add to dashboard Cite

Vortex optical communication employing orbital angular momentum (OAM) has been a hot research field in recent years. Thanks to the orthogonality of the OAM, several multiplexing and modulation techniques have been developed that can effectively improve communication capacity. However, to achieve this, accurate mode recognition in the OAM-based free-space optical (FSO) communication system is essential. Generally, perturbations in the free space link significantly affect the transmission efficiency and distort the helical phase-front of OAM beams, which will result in intermodal crosstalk and poses a critical challenge in the recognition of OAM modes. To date, artificial intelligence (AI) technologies have been widely applied to address the aforementioned bottleneck of insufficient accuracy of existing techniques for OAM mode detection. Therefore, a review paper that discusses the recent developments and challenges of the most widely used AI algorithms for OAM mode recognition schemes, i.e., feedforward neural network (FNN), convolutional neural network (CNN), and diffractive deep neural networks (D2NN) is urgently required. By elaborating on the principles of these algorithms and analyzing recent reports, encompassing both experimental and simulated results, we established their profound importance in enhancing the accuracy of OAM mode recognition. Moreover, this work provides an outlook on the recent trends in this newly developed field and the critical challenges faced in effectively using AI for improving the reliability of the OAM-based FSO communication system in near future.

show abstract

Section: Deep Fnn-based Oam Mode Recognitionmentioning

confidence: 99%

Top three intelligent algorithms for OAM mode recognitions in optical communications

Wang,

Zhang,

Shah

et al. 2024

Eng. Res. Express

View full text Add to dashboard Cite

show abstract

“…Neurons in two adjacent layers are interconnected with variable weights. The hidden layer enables the modeling of complex relationships between the input and output parameters of an FNN [79]. So far, FNN has been widely applied as a precise, efficient tool for detecting OAM modes.…”

Section: Oam Detection Enabled By Deep Fnnmentioning

confidence: 99%

Orbital angular momentum optical communications enhanced by artificial intelligence

Li¹,

Luan²,

Li³

et al. 2022

J. Opt.

View full text Add to dashboard Cite

Angular momentum of light can be divided into spin angular momentum (SAM) and orbital angular momentum (OAM). Due to the theoretically unlimited orthogonal states, the physical dimension of OAM provides a potential solution to boost the information capacity. The OAM multiplexing and modulation techniques have been implemented to meet the continuous growth of bandwidth requirements, resulting in the concept of OAM optical communication. However, the performances of the traditional optical OAM detection techniques degrade seriously in the practical application of OAM optical communications. Thanks to the powerful data analysis advantages, the cutting-edge machine learning (ML) algorithms have been widely used in the field of image processing, laying the technical foundation for OAM recognition. This paper reviews the recent advances on OAM optical communications that are enhanced by ML methods. More than the traditional OAM detection methods, the OAM demodulation methods based on multiple network architectures, including the support vector machine (SVM), self-organizing map (SOM), feed-forward neural network (FNN), convolutional neural network (CNN), and diffractive deep optical neural network (D2NN), have been summarized. We also discuss the development of the spiking neural network and on-chip D2NN, opening a possible way to facilitate the future ultra-low power and ultra-fast OAM demodulation technology.

show abstract

“…The first ML algorithm implemented in optical communications can be dated back to self-organizing map, allowing for the detection of 16 superposed OAM modes after a 3 km transmission distance with an error rate around 1.7% [33]. Benefiting from the deep learning (DL) technology containing complex structures including the deep feed-forward neural network (NN) [34] and convolutional neural network (CNN) [35], recent years have witnessed the improvement of the OAM demodulation performances, such as remarkable capabilities to cope with the strong AT [36], the long propagation distance [37] and the ultra-fine fractional OAM beams [38]. Moreover, various CNNs have been utilized in OAM-SK free space optical communication systems with large OAM bit numbers, ranging from 8-ary [39], 16-ary [40], 32-ary [41], 100-ary [42] to our recent experiment demonstration of 768-ary [43].…”

Section: Introductionmentioning

confidence: 99%

Ultralow-power spiking neural networks for 1024-ary orbital angular momentum shift keying free-space optical communication

Chen

et al. 2023

J. Opt.

View full text Add to dashboard Cite

The theoretical unbounded orbital angular momentum (OAM) states can be exploited as data bits in the OAM shift keying (OAM-SK) free-space optical (FSO) communications. In order to cope with the atmospheric turbulence (AT) and misalignment in practical applications, various machine learning algorithms, or neural networks (NNs), have been put forward to decode the OAM states. However, to recognize the hybrid spatial modes representing a large bit states, the massive learnable nodes, longer computation time and more training parameters are required to improve the capability of the NNs, resulting in energy efficiency burden to the hardware device. In this paper, the event-based Spiking Neural Network (SNN) is utilized to recognize the hybrid spatial modes consisting of superposed coaxial LG modes with l ranging from 0 to 9 and p=0, which is termed as Spiking OAM-recognition neural network (Spiking-ORNN). In comparison to the previous solution of running deep neural networks (DNNs) on graphics processing units (GPUs), the neuromorphic solution of running Spiking-ORNN on neuromorphic chips exhibits 4300x higher energy efficiency without obvious sacrifice of recognition accuracy (less than 0.5%). Moreover, we experimentally demonstrate a 10-meter 1024-ary OAM-SK FSO communication for the transmission of an image with a 10-bit grey level, wherein the peak signal-to-noise ratio of the received image can exceed 41.4 dB under the AT of =1e−15 m−2/3. We anticipate that our results can stimulate further researches on the utilization of the brain-like SNN chips to reduce the energy consumptions based on the artificial-intelligence-enhanced optoelectronic systems.

show abstract

Identification of hybrid orbital angular momentum modes with deep feedforward neural network

Cited by 25 publications

References 35 publications

Top three intelligent algorithms for OAM mode recognitions in optical communications

Top three intelligent algorithms for OAM mode recognitions in optical communications

Orbital angular momentum optical communications enhanced by artificial intelligence

Ultralow-power spiking neural networks for 1024-ary orbital angular momentum shift keying free-space optical communication

Contact Info

Product

Resources

About