Article
Engineering, Electrical & Electronic
Xu Yan, Changqing Cao, Wenrui Zhang, Zhejun Feng, Xiaodong Zeng, Zengyan Wu
Summary: In this study, a modulation format identification (MFI) scheme based on a searching cluster boundary (SCB) algorithm is proposed for space optical communication. The SCB algorithm uses a clustering algorithm based on local low-density samples as the boundaries of clusters to accurately identify different modulation formats. Experimental results show that the SCB algorithm achieves good results with clusters of different shapes, demonstrating the effectiveness of the designed MFI scheme in identifying modulation formats of different orders with few symbols.
JOURNAL OF LIGHTWAVE TECHNOLOGY
(2023)
Review
Nanoscience & Nanotechnology
Apostolos Argyris
Summary: Machine learning and neuromorphic computing have played a crucial role in optical communications, especially in signal processing. The latest breakthroughs involve advanced digital signal processing techniques and hardware implementations in photonics. These approaches have the potential to improve data recovery and transmission reliability, expand the reach of optical networks, and offer new solutions in photonics.
Article
Engineering, Electrical & Electronic
Jia Ye, Zongxin Gan, Lianshan Yan, Tao Zhou, Wei Pan, Xihua Zou
Summary: A photonic-assisted approach for modulation format identification (MFI) on RF signals under low sampling rate is proposed. It utilizes a photonic-assisted interferometer (PAI) for computation-free data augmentation by transforming phase and frequency variations into modulation format-sensitive amplitude features. A fully connected neural network (FCNN) is used for end-to-end MFI implementation. Experimental results show that the proposed photonic-assisted modulation format identifier (PA-MFI) achieves higher identification accuracy compared to direct MFI without PAI processing.
JOURNAL OF LIGHTWAVE TECHNOLOGY
(2022)
Article
Optics
Mengyao Han, Muguang Wang, Yuchuan Fan, Shiyi Cai, Yuxiao Guo, Naihan Zhang, Richard Schatz, Sergei Popov, Oskars Ozolins, Xiaodan Pang
Summary: This paper proposes an approach for simultaneous modulation format identification (MFI) and optical signal-to-noise ratio (OSNR) monitoring based on optoelectronic reservoir computing (RC) and signal's amplitude histograms (AHs). The proposed method achieves 100% MFI accuracy and accurate OSNR estimation for different modulation formats. The approach also exhibits good robustness in the presence of noise interference.
Article
Optics
Maochun Wang, Jie Liu, Junwei Zhang, Dongpeng Zhang, Changjian Guo
Summary: In this work, a high-performance, low-complexity modulation format identification (MFI) technique is proposed based on phase statistics in Stokes space. Numerical simulations and long-haul experiments validate the proposed MFI scheme, successfully identifying various modulation formats with excellent recognition performance and low computational complexity compared to existing methods.
OPTICS COMMUNICATIONS
(2021)
Article
Engineering, Electrical & Electronic
Waddah S. Saif, Amr M. Ragheb, Bernd Nebendahl, Tariq Alshawi, Mohamed Marey, Saleh A. Alshebeili
Summary: This study investigates the problem of automatic modulation format identification in super-channel optical networks. Through experiments and simulations, it validates the potential of using machine learning algorithms to accurately identify modulation formats under different signal-to-noise ratio conditions, and explores the impact of various interference factors on the identification accuracy.
IEEE PHOTONICS JOURNAL
(2022)
Article
Engineering, Electrical & Electronic
Xing Xing Guo, Shui Ying Xiang, Ya Hui Zhang, Bi Ling Gu, Yanan Han, Lin Lin, Yue Hao
Summary: We propose a simple experimental approach based on a photonic time delay reservoir computing system for modulation format recognition. By training an optically injected vertical cavity surface emitting laser with the cross sequence of modulation signals' instantaneous characteristics, we can efficiently identify all three modulation formats with the highest accuracy of 100% using multiple gradient-like boosting operations for post-processing.
IEEE JOURNAL OF SELECTED TOPICS IN QUANTUM ELECTRONICS
(2023)
Article
Chemistry, Multidisciplinary
Yutaro Yamazaki, Kentaro Kinoshita
Summary: This study develops a memristor that can respond to both electrical and optical stimuli, and demonstrates that the timescale of the transient current response of the device can be controlled by applying a small voltage. The computational performance of the device as a physical reservoir is evaluated in an image classification task, showing the potential for optimizing learning accuracy by tuning the device characteristics.
Article
Optics
Sendy Phang
Summary: Artificial intelligence (AI) drives the creation of disruptive future technologies that change the way we live and work. A new computing platform based on the photonic reservoir computing architecture, exploiting the dynamics of stimulated Brillouin scattering, is reported here. This passive optical system is suitable for use with high performance optical techniques, enabling real-time AI.
Article
Optics
Ming Hao, Xuedong Jiang, Xingzhong Xiong, Roger Giddings, Wei He, Jianming Tang
Summary: This work proposes a modulation format identification scheme based on amplitude histogram distributions, which is prior-training-free and low-complexity. The proposed scheme classifies incoming PDM signals into different modulation formats using their ratios defined by specific features of their amplitude histograms. The scheme achieves 100% correct identification rate for all five modulation formats without requiring prior information and being insensitive to carrier phase noise. Numerical and experimental results demonstrate its effectiveness and robustness against fiber nonlinearities.
Article
Computer Science, Artificial Intelligence
Piotr Antonik, Nicolas Marsal, Daniel Brunner, Damien Rontani
Summary: Reservoir computing is a growing paradigm for training recurrent neural networks. This work proposes the use of Bayesian optimization for efficient exploration of hyper-parameter space in a large-scale photonic system, resulting in notable improvements in performance.
COGNITIVE COMPUTATION
(2023)
Article
Engineering, Electrical & Electronic
Shi Li, Sourav Dev, Sebastian Kuehl, Kambiz Jamshidi, Stephan Pachnicke
Summary: Photonic reservoir computing allows for the use of artificial neural networks in time-sensitive areas like optical communications, with a focus on reducing training complexity. This paper numerically evaluates the requirements of a photonic RC and compares its performance with digital signal processing methods.
IEEE PHOTONICS TECHNOLOGY LETTERS
(2021)
Article
Optics
Xiaojie Fan, Ya Jin, Xuhua Cao, Yinfang Chen, Xin Wang, Ming LI, Ninghua Zhu, Wei LI
Summary: We present a photonic approach for generating background-free multi-format dual-band microwave signals based on a single modulator, which can efficiently and accurately detect radars in complex electromagnetic environments. The experimental results demonstrate the generation of dual-band dual-chirp signals and dual-band phase-coded pulse signals centered at 10 and 15.5 GHz using a polarization-division multiplexing Mach-Zehnder modulator (PDM-MZM). This system offers the advantage of being unaffected by chromatic-dispersion induced-power fading (CDIP) for the dual-band dual-chirp signals and enables direct emission of the high pulse compression ratio (PCR) dual-band phase-encoded signals without additional truncation operations. With its compact structure, reconfigurability, and polarization independence, this proposed system shows great potential for multi-functional dual-band radar systems.
Article
Optics
Peng Zhou, Ye Lu, Dong Chen, Chuanqi Li
Summary: The study proposed a method to identify modulation formats through calculating KL values, successfully distinguishing different transmission formats under certain conditions. The results show that the method exhibits a certain tolerance to fiber nonlinearity and sample size.
OPTICAL ENGINEERING
(2021)
Article
Multidisciplinary Sciences
Luis Gonzalez-Guerrero, Guillermo Carpintero
Summary: We introduce a novel approach to coherent photonic THz systems that support complex modulation. Our proposed scheme utilizes a single optical path to overcome the issues present in current implementations and enables direct modulation of the output of an optical frequency comb, simplifying the system and increasing the transmitted RF power.
SCIENTIFIC REPORTS
(2022)
Article
Optics
Adonis Bogris, Thomas Nikas, Radan Slavik
Article
Engineering, Electrical & Electronic
Thomas Nikas, Evangelos Pikasis, Adonis Bogris, Dimitris Syvridis
IEEE PHOTONICS TECHNOLOGY LETTERS
(2019)
Article
Computer Science, Hardware & Architecture
Charidimos Chaintoutis, Adonis Bogris, Dimitris Syvridis
JOURNAL OF OPTICAL COMMUNICATIONS AND NETWORKING
(2019)
Article
Optics
George Sarantoglou, Menelaos Skontranis, Adonis Bogris, Charis Mesaritakis
Summary: In this study, experimental results show that a quantum-dot laser can be tuned to operate as either a leaky integrate and fire or resonant and fire neuron by adjusting the bias. The multiband emission of quantum-dot devices enhances neurocomputational capabilities, leading to increased spike firing rate and suppressed neural spike duration. These new operation regimes, combined with thermal insensitivity and silicon cointegration, make these neuromorphic nodes a promising platform for large-scale photonic spiking neural networks.
PHOTONICS RESEARCH
(2021)
Article
Engineering, Electrical & Electronic
Adonis Bogris, Charis Mesaritakis, Stavros Deligiannidis, Pu Li
Summary: By utilizing optical injection and feedback, FP lasers show potential in neuromorphic computing by enhancing processing power at longitudinal mode granularity and performing real-time signal equalization in optical communication systems. Increasing the number of modes improves classification performance and allows for simultaneous processing of multiple data streams.
IEEE JOURNAL OF SELECTED TOPICS IN QUANTUM ELECTRONICS
(2021)
Article
Engineering, Electrical & Electronic
Stavros Deligiannidis, Charis Mesaritakis, Adonis Bogris
Summary: The study investigates the complexity and performance of RNN models as post-processing units for compensating fiber nonlinearities in digital coherent systems. The results show that Vanilla-RNN units are the preferred choice due to their simplicity. Bi-directional Vanilla-RNN outperforms Volterra nonlinear equalizers in terms of both performance and complexity, indicating that RNN processing is a promising pathway for upgrading long-haul optical communication systems.
JOURNAL OF LIGHTWAVE TECHNOLOGY
(2021)
Article
Engineering, Electrical & Electronic
Kostas Sozos, Charis Mesaritakis, Adonis Bogris
Summary: The paper proposes a neuromorphic computing scheme utilizing delay-based reservoir computing in a laser system with two mutually coupled phase modulated lasers, which can be monolithically integrated and performs well in dispersion compensation tasks. The scheme can recover severely distorted 25 Gbaud PAM-4 signals for transmission distances exceeding 50 km and outperforms other delay-based reservoir computing systems relying on optical feedback.
IEEE JOURNAL OF QUANTUM ELECTRONICS
(2021)
Article
Materials Science, Multidisciplinary
M. Skontranis, G. S. Sarantoglou, A. Bogris, C. Mesaritakis
Summary: In this work, a numerical study on a time-delayed reservoir computing scheme is presented, utilizing a quantum-dot spin polarized vertical cavity surface-emitting laser (QD s-VCSEL) as the single nonlinear node. The scheme exploits the complex temporal dynamics of multiple energy states in quantum dot materials and utilizes dual emission to enhance computational efficiency.
OPTICAL MATERIALS EXPRESS
(2022)
Article
Engineering, Electrical & Electronic
Yang Hong, Stavros Deligiannidis, Natsupa Taengnoi, Kyle R. H. Bottrill, Naresh K. Thipparapu, Yu Wang, Jayanta K. Sahu, David J. Richardson, Charis Mesaritakis, Adonis Bogris, Periklis Petropoulos
Summary: We propose and demonstrate a bidirectional Vanilla-RNN based equalization scheme for O-band CWDM transmission. The Vanilla-RNN equalizer exhibits significantly better BER performance over the conventional DFE for both OOK and PAM4 formats, and is capable of compensating for linear and nonlinear impairments. Our results show that the Vanilla-RNN scheme is a viable solution for simple and effective equalization.
IEEE JOURNAL OF SELECTED TOPICS IN QUANTUM ELECTRONICS
(2022)
Article
Engineering, Electrical & Electronic
George Sarantoglou, Adonis Bogris, Charis Mesaritakis, Sergios Theodoridis
Summary: This study proposes a Bayesian learning framework for silicon photonic accelerators, which can significantly reduce operational power consumption while slightly sacrificing classification accuracy. The full Bayesian scheme also provides information about the sensitivity of phase shifters, which can simplify the driving system.
IEEE JOURNAL OF SELECTED TOPICS IN QUANTUM ELECTRONICS
(2022)
Article
Engineering, Electrical & Electronic
Kostas Sozos, Stavros Deligiannidis, Charis Mesaritakis, Adonis Bogris
Summary: This article proposes a neuromorphic receiver based on recurrent optical spectrum slicing for detection and equalization of coherent modulation formats. The receiver has low power consumption and high data transmission rates.
JOURNAL OF LIGHTWAVE TECHNOLOGY
(2023)
Article
Engineering, Electrical & Electronic
Dimitris Dermanis, Adonis Bogris, Panagiotis Rizomiliotis, Charis Mesaritakis
Summary: This work presents a physical unclonable function implemented using an integrated photonic neuromorphic device. The physical security feature relies on the complex relation between hardware implemented complex weights and digital trainable weights. The concept paves the way for photonic devices capable of efficient computation and security operations.
JOURNAL OF LIGHTWAVE TECHNOLOGY
(2022)
Article
Engineering, Electrical & Electronic
Kostas Sozos, Stavros Deligiannidis, George Sarantoglou, Charis Mesaritakis, Adonis Bogris
Summary: The transition to the edge-cloud era demands ultra-high data rate signals and power efficient optical modules. Addressing the challenges of non-linearities and power fading is crucial for high symbol rate systems. In this article, machine learning techniques and neuromorphic processing are proposed as promising solutions for mitigating transmission impairments. The article presents recent work on bidirectional recurrent neural networks and neuromorphic recurrent optical spectrum slicers for non-linearity compensation and power fading mitigation respectively. Evaluations are conducted to compare the performance of these techniques with the state-of-the-art methods in high-speed optical communication systems.
JOURNAL OF LIGHTWAVE TECHNOLOGY
(2023)
Article
Engineering, Electrical & Electronic
Stavros Deligiannidis, Adonis Bogris, Charis Mesaritakis, Yannis Kopsinis
JOURNAL OF LIGHTWAVE TECHNOLOGY
(2020)