检索结果-内蒙古大学图书馆

Recurrent Neural Network Based joint equalization and decoding Method for Trellis Coded Modulated Optical Communication System

引用

JOURNAL OF LIGHTWAVE TECHNOLOGY 2023年第6期41卷 1734-1741页

作者： Qin, Xin Yang, Chuanchuan Guo, Haipeng Gao, Yunfeng Zhou, Qingyi Wang, Xinyue Wang, Ziyu Peking Univ State Key Lab Adv Opt Commun Syst & Networks Beijing 100871 Peoples R China China Telecom Res Inst Beijing 100032 Peoples R China Univ Wisconsin Madison Dept Elect & Comp Engn Madison WI 53706 USA China Agr Univ Coll Informat & Elect Engn Beijing 100083 Peoples R China

In this paper, a joint equalization and decoding method based on recurrent neural networks (RNNs) is proposed for trellis coded modulation (TCM) systems. For traditional methods based on concatenated equalizers and Viterbi decoder, the information may be lost between the equalization and decoding. However, our proposed joint method can obtain the information bits directly from the received symbols and the error also can be corrected in iterations. In two-dimensional eight-level pulse amplitude modulation (2D-PAM8) links, we experimentally demonstrate that, compared with the traditional method based on Volterra filter and Viterbi decoder, the proposed joint method based on RNNs with similar complexity can achieve bit-error rate (BER) performance improvements of 1 dB, 1 dB, and 2 dB in 87.5 Gb/s, 100 Gb/s, and 112.5 Gb/s transmissions at 7% hard-decision forward-error-correction (HD-FEC) limit, respectively. For the 10 km standard single-mode fiber (SSMF) link at 87.5 Gb/s, the traditional method cannot get the BER below the 7% HD-FEC limit whereas the joint RNNs method with similar complexity can get the BER below the 7% HD-FEC limit. As the nonlinearity increases, the proposed joint method can achieve greater improvement of BER performance.

关键词： Optical fiber communication Viterbi algorithm Symbols Equalizers Complexity theory Modulation Recurrent neural networks joint equalization and decoding recurrent neural network trellis coded modulation

来源：评论

学校读者我要写书评

暂无评论

Hidden Feature Extraction Learning and End-to-End joint equalization With LDPC decoding Method for Optical Interconnect

引用

JOURNAL OF LIGHTWAVE TECHNOLOGY 2025年第4期43卷 1746-1758页

作者： Yang, Chuanchuan Qin, Hao Lan, Tianxiang Gao, Yunfeng Wang, Jiaxing Zhao, Yuping Chang-Hasnain, Constance J. Peking Univ Dept Elect State Key Lab Adv Opt Commun Syst & Networks Beijing 100871 Peoples R China Peking Univ Shenzhen Grad Sch Shenzhen 518055 Peoples R China CITIC Grp Corp Beijing 100020 Peoples R China Berxel Photon Co Ltd Shenzhen 518055 Peoples R China

The vertical-cavity surface-emitting lasers and multimode fiber (VCSEL-MMF) solution has successfully emerged in optical interconnects (OIs), which meets the challenges of signal impairments in ultra-high-speed scenarios. Deep learning (DL) techniques, which can approximate any nonlinear function, enable the design of communication systems by carrying out the optimization in a single end-to-end (E2E) process including the transceivers as well as communication channels. In this paper, we propose a hidden feature extraction learning method for neural network equalization to improve training efficiency without increasing computational burden. Superior bit error rate (BER) is demonstrated in achieving 288 Gb/s 100 m VCSEL-MMF interconnect compared with black-box training strategy. Furthermore, an E2E joint equalization and low-density parity-check (LDPC) decoding method is proposed to improve the overall performance. Based on the autoencoder (AE) architecture, the E2E network involves a digital pre-distorter (DPD), a digital optical link model, a feed forward equalizer (FFE) and a deep learning based Normalized Offset Min-Sum (DL-NOMS) LDPC decoder. Experimental results demonstrate that the BER performance of the proposed E2E scheme is two-magnitude lower than the E2E equalization and FFE+DL-NOMS decoding method in back-to-back (BTB) and 100 m VCSEL-MMF links.

关键词： decoding Training Vertical cavity surface emitting lasers Optical fiber communication Parity check codes Optical interconnections Feature extraction Artificial neural networks Modulation Forward error correction End-to-end learning joint equalization and decoding LDPC codes neural network optical interconnect VCSEL

来源：评论

学校读者我要写书评

暂无评论

joint Blind equalization and decoding in OFDM Systems Using Particle Filtering

引用

WIRELESS PERSONAL COMMUNICATIONS 2017年第3期97卷 3875-3889页

作者： Sabahi, Mohamad Farzan Ghasemi, Negin Univ Isfahan Dept Elect Engn Esfahan Iran

In this paper a sequential algorithm is proposed for joint blind channel equalization and decoding for orthogonal frequency-division multiplexing (OFDM) in frequency selective channels. This algorithm offers a recursive method to sequentially calculate the posterior probability for maximum a posteriori detection. Recursive calculations are done along the indexes in each OFDM symbol using a particle filter. By defining an appropriate importance function, and a proper prior probability distribution function for the channel tap coefficients (and marginalizing it), an efficient method is presented for joint equalization and channel decoding in OFDM based systems. Performance of the proposed detector is evaluated using computer simulations and its bit error rate is compared with the trained turbo equalizer and a conventional particle filter-based method. The results show that the proposed method outperforms the previously presented particle filter-based method without a need for training data.

关键词： Blind equalization joint equalization and decoding Particle filtering OFDM

来源：评论

学校读者我要写书评

暂无评论

Particle filters for joint blind equalization and. decoding in frequency-selective channels

引用

IEEE TRANSACTIONS ON SIGNAL PROCESSING 2008年第6期56卷 2395-2405页

作者： Bordin, Claudio J., Jr. Bruno, Marcelo G. S. Inst Tecnol Aeronaut BR-12228900 Sao Jose Dos Campos Brazil

This paper introduces new algorithms for joint blind equalization and decoding of convolutionally coded communication systems operating on frequency-selective channels. The proposed method is based on particle filters (PF), recursively approximating maximum a posteriori (MAP) estimates of the transmitted data without explicitly determining channel parameters. Further elaborating on previous works, we assume that both the channel order and the noise variance are unknown random variables, and develop a new formulation for PIT weight propagation which allows these quantities to be analytically integrated out. We verify via numerical simulations that the proposed methods lead to near optimal performance, closely approximating that of algorithms that require exact knowledge of all channel, parameters.

关键词： Bayesian estimation blind equalization joint equalization and decoding particle filters (PFs)

来源：评论

学校读者我要写书评

暂无评论

Robust iterative tree-pruning detection and LDPCC decoding

引用

IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS 2005年第5期23卷 1013-1025页

作者： Lee, HN Hu, XD Univ Pittsburgh Dept Elect & Comp Engn Pittsburgh PA 15261 USA

A novel suboptimal low-complexity equalization and turbo-iterative decoding scheme is proposed in this paper. The scheme is developed for multiple transmit- and multiple receive-antenna systems operating over severe frequency-selective fading intersymbol interference channels. The signal-processing complexity may be of a concern for such systems. The complexity of a full-search equalization grows in a power-law manner O(M-NtL), where M denotes for M-ary channel symbols, N-t the number of transmit-antennas, and L the number of delay channel taps. A low-complexity solution can be obtained by pruning an equalizer tree. The two main operations include a sphere list detection and a threshold-based tree-search. In the operation of extracting extrinsic messages from the pruned tree, a set of explored paths with different survival lengths poses a fairness problem: a longer-lived path naturally builds a larger discrepancy-metric than a shorter lived path does. A novel survival-length compensation-rule is devised so that all explored paths with different survival lengths are utilized fairly in generating the output message. Simulation results are obtained for multi-input and multi-output systems equipped with four transmit and four receive antennas. They indicate the performance of the receiver is very robust.

关键词： joint equalization and decoding low-density parity-check (LDPC) codes maximum a posteriori (MAP) multi-input and multi-output (MIMO) systems reduced complexity receiver turbo-iteration

来源：评论

学校读者我要写书评

暂无评论

joint equalization and decoding of trellis-encoded signals using the Generalized Viterbi Algorithm

Joint equalization and decoding of trellis-encoded signals u...

引用

52nd IEEE Vehicular Technology Conference (VTC 2000)

作者： Visoz, R Berthet, A Tortelier, P France Telecom R&D DMR IIM F-92794 Issy Les Moulineaux France

ISBN: (纸本)0780365070

In this paper, a new receiver structure is described for trellis-encoded signals transmitted over frequency selective channels. This receiver is based on the use of the Generalized Viterbi Algorithm (GVA). Several applications are presented involving convolutional or polynomial block codes. Simulation results show that the proposed receiver structure provides close to optimal performances with reasonable complexity.

关键词： Generalized Viterbi Algorithm joint equalization and decoding sub-optimal trellis decoding of polynomial block codes

来源：评论

学校读者我要写书评

暂无评论

Comparative study of turbo equalization schemes using convolutional, convolutional turbo, and block-turbo codes

引用

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS 2002年第2期1卷 266-273页

作者： Yeap, BL Liew, TH Hámorsky, J Hanzo, L Univ Southampton Dept Elect & Comp Sci Southampton SO9 5NH Hants England

Turbo equalizers have been shown to be successful in mitigating the effects of inter-symbol interference introduced by partial response modems and by dispersive channels for code rates of R less than or equal to 1/2. In this contribution, we comparatively studied the performance of a range of binary phase-shift keying turbo equalizers employing block-turbo codes, namely Bose-Chaudhuri-Hocquenghen turbo codes, convolutional codes, and convolutional turbo codes having high code rates, such as R = 3/4 and R = 5/6, over a dispersive five-path Gaussian channel. and an equally weighted symbol-spaced five-path Rayleigh fading channel. These turbo equalization schemes were combined with an iterative channel estimation scheme in order to characterize a realistic scenario. The simulation results demonstrated that the turbo-equalized system using convolutional turbo codes was the most robust system for all code rates investigated.

关键词： Bose-Chaudhuri-Hocquenghen codes convolutional codes iterative decoding iterative equalization joint equalization and decoding turbo codes turbo decoding turbo equalization

来源：评论

学校读者我要写书评

暂无评论

A decoder for low-complexity equalization of coded frequency selective MIMO channels

A decoder for low-complexity equalization of coded frequency...

引用

13th IEEE International Symposium on Personal, Indoor and Mobile Radio Communications

作者： Sellami, N Fijalkow, I France Telecom R&D F-92794 Issy Les Moulineaux France

ISBN: (纸本)0780375890

In this paper, we propose a decoder for low-complexity equalization of coded frequency selective multiple-input multiple-output channels. The decoder combines the Parallel Decision Feedback decoding (PDFD) and the List-type approach. This alternative achieves a good trade-off between performance and complexity even when the channel is not minimum phase.

关键词： Space-time coded MIMO channel joint equalization and decoding reduced-state algorithms per-survivor processing list-type approach

来源：评论

学校读者我要写书评

暂无评论

Improved interference cancellation for turbo-equalization 25

Improved interference cancellation for turbo-equalization

引用

IEEE International Conference on Acoustics, Speech, and Signal Processing

作者： Fijalkow, I Roumy, A Ronger, S Pirez, D Vila, P UCP ENSEA ETIS F-95014 Cergy Pontoise France

ISBN: (纸本)0780362934

Sub-optimal joint equalization and decoding is performed by iterated equalization and decoding. This processing is named turbo-equalization with reference to the turbo-decoding of serially concatenated codes. We propose to optimize the equalizer structure (an interference canceler) thanks to the training sequence available to estimate the channel impulse response. The interference canceler, optimized at each iteration, permits to reduce the number of iterations needed to achieve a given performance. The gain is all the more important that the channel is hard to equalize.

关键词： joint equalization and decoding turbo-equalization optimal DFE Wiener filtering

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：