检索结果-内蒙古大学图书馆

Learnable digital signal processing:a new benchmark of linearity compensation for optical fiber communications

Light(Science & Applications) 2024年第9期13卷 1931-1943页

作者： Zekun Niu Hang Yang Lyu Li Minghui Shi Guozhi Xu Weisheng Hu Lilin Yi State Key Lab of Advanced Optical Communication Systems and Networks School of Electronic Information and Electrical EngineeringShanghai Jiao Tong UniversityShanghai 200240PR China

The surge in interest regarding the next generation of optical fiber transmission has stimulated the development of digital signal processing(DSP)schemes that are highly cost-effective with both high performance and low *** benchmarks for nonlinear compensation methods,however,traditional DSP designed with block-by-block modules for linear compensations,could exhibit residual linear effects after compensation,limiting the nonlinear compensation *** we propose a high-efficient design thought for DSP based on the learnable perspectivity,called learnable DSP(LDSP).LDSP reuses the traditional DSP modules,regarding the whole DSP as a deep learning framework and optimizing the DSP parameters adaptively based on backpropagation algorithm from a global *** method not only establishes new standards in linear DSP performance but also serves as a critical benchmark for nonlinear DSP *** comparison to traditional DSP with hyperparameter optimization,a notable enhancement of approximately 1.21 dB in the Q factor for 400 Gb/s signal after 1600 km fiber transmission is experimentally demonstrated by combining LDSP and perturbation-based nonlinear compensation *** from the learnable model,LDSP can learn the best configuration adaptively with low complexity,reducing dependence on initial *** proposed approach implements a symbol-rate DSP with a small bit error rate(BER)cost in exchange for a 48%complexity reduction compared to the conventional 2 samples/symbol *** believe that LDSP represents a new and highly efficient paradigm for DSP design,which is poised to attract considerable attention across various domains of optical communications.

关键词： fiber signal optical

来源：评论

学校读者我要写书评

暂无评论

Performance Improvement of Adaptive N-Square PS-QAM Based on LUT for Flexible Coherent PON

引用

Journal of Lightwave Technology 2025年第12期43卷 5569-5578页

作者： Lin, Gengming Zhu, Yixiao Yan, Zijun Cheng, Ziyu Zhuge, Qunbi Hu, Weisheng Shanghai Jiao Tong University State Key Lab of Advanced Optical Communication Systems and Networks School of Electronic Information and Electrical Engineering Department of Electronic Engineering Shanghai200240 China

Flexible coherent passive optical network (PON) is recognized as an advanced capacity optimization strategy for beyond 100G PON due to its flexibility and adaptability, which are pivotal for the evolution of high-capacity optical access networks. In this study, we propose an adaptive N-square QAM scheme compatible with probabilistic shaping (PS), enabling a more continuous variation of shaping entropy compared to standard 2M -QAM shaping scheme and improved frequency offset estimation (FOE) accuracy in blind 4th-power Fast-Fourier-transform (FFT) algorithm. In experimental demonstrations, dynamic-range and data-rate product (DRDRP) of uniform N2-QAM surpasses that of uniform 2M -QAM by 86 dB·Gbps. The DRDRP of PS N2-QAM also outperforms that of PS 2N -QAM by around 41 dB·Gbps. The development of PON optimization scheme for multi-carrier transmission is achieved through the generation of a look-up table (LUT) based on channel signal-to-noise ratio (SNR) conditions. The feasibility of the LUT is demonstrated under different super-Gaussian filter parameter settings at the back-to-back (B2B) scenario. After 20-km standard single-mode fiber (SSMF) transmission, the normalized generalized mutual information (NGMI) is greater than 0.985 across four subcarriers with varying received optical power (ROP) from −16 to −11 dBm. © 1983-2012 IEEE.

关键词： Single mode fibers

来源：评论

学校读者我要写书评

暂无评论

Design of Large-Scale OXC for the Next-Generation ROADM 16

Design of Large-Scale OXC for the Next-Generation ROADM

引用

16th Pacific Rim Conference on Lasers and Electro-Optics, CLEO-PR 2024

作者： Ye, Tong Luo, Jiayi Li, Herui Yao, Yibei Shanghai Jiao Tong University State Key Lab of Advanced Optical Communication Systems and Networks Shanghai China

Using multiple MEMSes sandwiched between two columns of WSSes, this paper designs a low-loss, nonblocking, and scalable OXC that is suitable for the future SDM optical network with a smaller number of wavelengths per ... 详细信息

ISBN: (纸本)9798350372076

关键词： Optical fiber communication

来源：评论

学校读者我要写书评

暂无评论

Silicon thermo-optic switch based on photonic crystal nanobeam cavity with doped-silicon heaters

Silicon thermo-optic switch based on photonic crystal nanobe...

引用

2025 IEEE Silicon Photonics Conference, SiPhotonics 2025

作者： Zhong, Hua Li, Jingchi He, Yu Tian, Meng Zhang, Yong Su, Yikai Shanghai Jiao Tong University State Key Lab of Advanced Optical Communication Systems and Networks Department of Electronic Engineering Shanghai China

We demonstrate a silicon TO switch based on photonic crystal nanobeam cavity with doped-silicon heaters. The insertion loss and crosstalk are less than 2.01 dB and -9.78 dB, respectively. The thermo-optic tuning effic... 详细信息

ISBN: (纸本)9798331506186

关键词： Nanowires

来源：评论

学校读者我要写书评

暂无评论

Net 8×250 Gbit/s/λ PAM6/8 Optical Interconnect Over High-Density Eight-Core Fiber and Low-Crosstalk Laser Direct Writing FI/FO Devices

Net 8×250 Gbit/s/λ PAM6/8 Optical Interconnect Over High-D...

引用

2023 Asia communications and Photonics Conference/2023 International Photonics and Optoelectronics Meetings, ACP/POEM 2023

作者： Yang, Yu Xu, Zhaopeng Ji, Honglin Qiao, Gang Liu, Lulu Wang, Shangcheng Cheng, Ruiting Yu, Jinyi Yang, Chuanchuan He, Zhixue He, Yongqi Chen, Zhangyuan Hu, Weisheng Li, Juhao Peng Cheng Laboratory Shenzhen China Peking University State Key Lab of Advanced Optical Communication Systems and Networks Beijing China Shanghai Jiao Tong University State Key Lab of Advanced Optical Communication Systems and Networks Shanghai China

ISBN: (纸本)9798350312614

We experimentally demonstrate a net 8×250 Gbit/s/λ PAM6 and PAM8 transmission over 200-m standard-125μm-cladding high-density eight-core fiber and low-crosstalk femtosecond laser direct writing fan-in/fan-out devices. The proposed prototype system is promising for high-speed optical interconnection applications. © 2023 IEEE.

关键词： Fan-in/fan-out High-speed optical interconnects MCF SDM

来源：评论

学校读者我要写书评

暂无评论

Multi-Task Learning: Towards Low-Complexity Neural Network Nonlinearity Compensation in Coherent Optical systems

Multi-Task Learning: Towards Low-Complexity Neural Network N...

引用

2024 Asia communications and Photonics Conference, ACP 2024 and International Conference on Information Photonics and Optical communications, IPOC 2024

作者： Ji, Tonghui Wu, Qi Xu, Zhaopeng Ji, Honglin Yang, Yu Liu, Lulu Wang, Shangcheng Sun, Zhongliang Liang, Junpeng Fan, Linsheng Tang, Jianwei Wei, Jinlong Li, Juhao Hu, Weisheng Pengcheng Laboratory Shenzhen China State Key Lab of Advanced Optical Communication System and Networks Shanghai Jiao Tong University Shanghai China State Key Laboratory of Advanced Optical Communication Systems & Networks Peking University Beijing China

We propose multi-task learning based NN equalization for nonlinearity compensation in coherent optical system. Compared with conventional NN equalization, 30% complexity reduction is achieved in an 800-Gb/s PDM-16QAM ... 详细信息

ISBN: (纸本)9798350379266

关键词： Equalizers

来源：评论

学校读者我要写书评

暂无评论

DECEPT-CTI: A Framework for Enhancing Cyber Deception Strategies through NLP-based Extraction of CTI from Unstructured Reports 22

DECEPT-CTI: A Framework for Enhancing Cyber Deception Strate...

引用

22nd International Symposium on Network Computing and Applications, NCA 2024

作者： Sayari, Amal Rekhis, Slim Djemaiel, Yacine Mabrouk, Ali Mahouachi, Wiem LR11TIC04 Communication Networks and Security Research Lab. & LR11TIC02 Green and Smart Communication Systems Research Lab Tunisia SAMA PARTNERS Tunisia

ISBN: (纸本)9798331510183

In today’s dynamic threat landscape, organizations encounter significant challenges when dealing with the vast, evolving, unregulated landscape of cyber threat intelligence (CTI). Firstly, the verbosity of CTI resources infused with a significant amount of irrelevant and unstructured text. Secondly, there is a need for automated systems capable of synthesizing information about threat entities, attack semantics, and malicious actions, which can help rapidly identify and understand emerging threats. Thirdly, organizations face the challenge of injected poisoned or noisy data by threat actors, which can affect not only the quality of CTI but also the efficacy of threat mitigation strategies. Finally, they must harmonize CTI data from various resources and understand the interactions between different threat elements, to understand their threat profiles better, determine the presence of attack vectors related to existing and emerging cyber-attacks, and mount effective cyber defense strategies. To address these challenges, we introduce DECEPT-CTI, a framework that recommends the appropriate cyber deception strategies based on the provided CTI knowledge. First, we automatically extract relevant CTI sentences and identify low-level and high-level IoCs from unstructured CTI reports. Then, we propose a multi-label classification-based model for automated mapping of extracted CTI data to MITRE ATT&CK tactics and techniques. Subsequently, we apply an analytical scheme based on MITRE D3FEND and MITRE Engage to select the most suitable cyber deception strategies using the extracted CTI data. Our evaluation encompasses various transformers: SecBERT, SecRoBERTa, SecBERT-BiLSTM-CRF, and SecRoBERTa-BiLSTM-CRF to perform the low-level and high-level IoCs identification and extraction task, and the multi-label classification task, demonstrating good results. ©2024 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

Fast and Accurate Estimation of MDL-Induced SNR Penalty in SDM Link with Non-uniform Noise Loading

Fast and Accurate Estimation of MDL-Induced SNR Penalty in S...

引用

2024 Asia communications and Photonics Conference, ACP 2024 and International Conference on Information Photonics and Optical communications, IPOC 2024

We propose a fast and accurate estimation method of MDL-induced SNR penalty with non-uniform noise loading in SDM *** proposed approach substantially saves the time cost while maintaining an estimation error within 0.... 详细信息

ISBN: (纸本)9798350379266

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Improve the Fitting Accuracy of Deep Learning for the Nonlinear Schrödinger Equation Using Linear Feature Decoupling Method

Improve the Fitting Accuracy of Deep Learning for the Nonlin...

引用

2024 Asia communications and Photonics Conference, ACP 2024 and International Conference on Information Photonics and Optical communications, IPOC 2024

作者： Zhang, Yunfan Niu, Zekun Shi, Minghui Hu, Weisheng Yi, Lilin State Key Lab of Advanced Communication Systems and Networks School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China

We utilize the Feature Decoupling Distributed (FDD) method to enhance the capability of deep learning to fit the Nonlinear Schrödinger Equation (NLSE), significantly reducing the NLSE loss compared to non decoupl... 详细信息

ISBN: (纸本)9798350379266

关键词： Optical fibers

来源：评论

学校读者我要写书评

暂无评论

Channel Power Control for Full C-band Generalized Signal-to-Noise Ratio Optimization Based on Deep Reinforcement Learning

Channel Power Control for Full C-band Generalized Signal-to-...

引用

2024 Asia communications and Photonics Conference, ACP 2024 and International Conference on Information Photonics and Optical communications, IPOC 2024

作者： Xiao, Junzhe Niu, Zekun Li, Lyu Shi, Minghui Hu, Weisheng Yi, Lilin State Key Lab of Advanced Communication Systems and Networks School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China

A model-free method based on deep reinforcement learning is implemented to control channel power for GSNR optimization. Flat GSNR covering entire C-band is achieved across 1440 km transmission with uneven gain profile... 详细信息

ISBN: (纸本)9798350379266

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：