Code division multiple access communications: multiuser detection based on a recurrent neural network structure

Teich, Werner G.; Seidl, Mathis

doi:10.1109/isssta.1996.563450

Cited by 41 publications

(31 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The performance of the optimal detector based on MLSE can not be simulated due to its computational complexity (there are (2 1) 1683 2 2 M K + = possible sequences), thus the theoretical BPSK AWGN bound is depicted in the figures, which is expected to be close to the curve of optimal detector [9].It is given as the function of bit energy per noise variance ratio( In this paper we have proposed a novel multi-user detection scheme, which makes use of ITCNN optimization algorithm in MUD. The new method resulted in better performance than TCNN detector algorithms, namely 1..2dB gain in performance can be achieved, only 7..8 additional iteration is needed.…”

Section: Resultsmentioning

confidence: 99%

Sub-optimal multiuser detector using an improved transiently chaotic neural network

Jiang

2014

2014 10th International Conference on Natural Computation (ICNC)

View full text Add to dashboard Cite

This paper proposes a sub-optimal multiuser detector (MUD) algorithm for CDMA system based on an improved transiently chaotic neural network (ITCNN) which introduces a wavelet function into the activation function of the transiently chaotic neural network, and gives a concrete model of the MUD after appropriate transformations and mappings. The proposed neural network makes use of the wavelet and chaotic simulated annealing parameters of the recurrent neural network to control the network evolving behavior so that the network has richer and more flexible dynamics rather than conventional neural networks, so that it can be expected to have much powerful ability to search for globally optimal or sub-optimal solutions ,and can refrain from the serious local optimal problem of Hopfield-type neural networks. Simulation experiments have been performed to show the effectiveness and validation of the proposed method for MUD problem.

show abstract

Section: Resultsmentioning

confidence: 99%

Sub-optimal multiuser detector using an improved transiently chaotic neural network

Jiang

2014

2014 10th International Conference on Natural Computation (ICNC)

View full text Add to dashboard Cite

show abstract

“…The idea of the (recurrent neural network) RNN equalizer [2] is to estimate the interference and subtract it from the received symbol.…”

Section: Optimal Equalizationmentioning

confidence: 99%

“…The idea of this work is to improve the performance of single carrier frequency division multiple access (SC-FDMA), used in the LTE uplink [1]. SC-FDMA employs frequency domain equalization [1], which is compared with an iterative equalization in the time domain, using the recurrent neural network (RNN) equalizer [2]. In a third approach a combination of equalization and decoding for coded transmission, known as turbo equalization, is presented [3].…”

Section: Introductionmentioning

confidence: 99%

Features of equalization in LTE technology with MIMO and SC-FDMA

Abdourahaman

2015

EEJET

View full text Add to dashboard Cite

“…In this case VD with reasonable complexity and a performance as close as possible to the optimum must be applied. We use a VD which is based on soft-decision iterative interference cancellation [3], [7], [8]. This detector is very similar to the detector proposed by Vanhaverbeke et al [1].…”

Section: A Vector Detectionmentioning

confidence: 99%

Soft iterative interference cancellation with successive over relaxation for digital transmission schemes based on multiple sets of orthogonal spreading codes

Teich

Wallner

2012

2012 6th International Conference on Signal Processing and Communication Systems

View full text Add to dashboard Cite

Employing multiple sets of orthogonal spreading codes a bandwidth and power efficient digital transmission scheme can be realized. On each of the resulting subchannels antipodal transmission is used. Increasing the number of spreading codes, on the one hand, increases the data rate and thus the bandwidth efficiency of the transmission. On the other hand the interference between the subchannels is increased as well. This unavoidable interference resulting from non-orthogonal codes must be removed by an iterative vector detection algorithm (softdecision iterative interference cancellation). We show, that these iterative methods can be improved with respect to convergence and convergence speed by applying the method of successive over relaxation.Index Terms-Successive over relaxation, vector equalization, recurrent neural networks.

show abstract

Code division multiple access communications: multiuser detection based on a recurrent neural network structure

Cited by 41 publications

References 12 publications

Sub-optimal multiuser detector using an improved transiently chaotic neural network

Sub-optimal multiuser detector using an improved transiently chaotic neural network

Features of equalization in LTE technology with MIMO and SC-FDMA

Soft iterative interference cancellation with successive over relaxation for digital transmission schemes based on multiple sets of orthogonal spreading codes

Contact Info

Product

Resources

About