Multiuser Detection in SDMA–OFDM Wireless Communication System Using Complex Multilayer Perceptron Neural Network

The space division multiple access–orthogonal frequency division multiplexing (SDMA–OFDM) wireless system has become very popular owing high spectral efficiency and high load capability. The optimal maximum likelihood multiuser detection (MUD) technique suffers from high computational complexity. On the other hand the linear minimum mean square error (MMSE) MUD techniques yields poor performance and also fails to detect users in overload scenario, where the number of users are more than that of number of receiving antennas. By contrast, the differential evolution algorithm (DEA) aided minimum symbol error rate (MSER) MUD can sustain in overload scenario as it can directly minimizes probability of error rather than mean square error. However, all these classical techniques are still complex as these do channel estimation and multiuser detection sequentially. In this paper, complex multi layer perceptron (CMLP) neural network model is suggested for MUD in SDMA–OFDM system as it do both channel approximation and MUD simultaneously. Simulation results prove that the CMLP aided MUD performs better than the MMSE and MSER techniques in terms of enhanced bit error rate performance with low computational complexity.     

Minimum symbol error rate multiuser detection using an effective invasive weed optimization for MIMO/SDMA–OFDM system

Space division multiple access–orthogonal frequency division multiplexing system has become a potential wireless communication system by offering high spectral efficiency, performance and capacity. This article deals with minimum symbol error rate (MSER)‐based multiuser detection (MUD) technique for the space division multiple access–orthogonal frequency division multiplexing system using an efficient invasive weed optimization (IWO) algorithm. The IWO algorithm is used for finding optimal weights such that the probability of error is directly minimized rather than minimizing the mean square error. Because of this, the MSER MUD is able to detect users even in overload scenario, where the number of users is more than the number of receiving antennas, unlike several classical detection techniques. The IWO is inspired from the nature of invasive colonization of weeds and relatively simple compared with other optimization techniques. The bit error rate performance of the proposed IWO‐aided MSER MUD is found to be better than minimum means square error and differential evolution algorithm‐aided MSER MUDs. Simulation results show that the proposed IWO MSER achieves faster convergence and lower complexity compared with the differential evolution MSER MUD. Copyright © 2013 John Wiley & Sons, Ltd.     

Radial basis function-based node localization for unmanned aerial vehicle-assisted 5G wireless sensor networks

Neural Computing and Applications - Localization or positioning of wireless sensor nodes is an essential task for a wide range of applications in wireless sensor networks-based fifth generation...     

Neural network-based adaptive multiuser detection schemes in SDMA–OFDM system for wireless application

Neural network applications in adaptive multiuser detection (MUD) schemes are suggested here in the context of space division multiple access–orthogonal frequency division multiplexing system. In this paper, various neural network (NN) models like feed forward network (FFN), recurrent neural network (RNN) and radial basis function network (RBFN) are adopted for MUD. MUD using NN models outperforms other existing schemes like genetic algorithm--assisted minimum bit error rate (MBER) and minimum mean square error MUDs in terms of BER performance and convergence speed. Among these NN models, the FNN MUD performs efficiently as RNN in full load scenario, where the number of users is equal to number of receiving antennas. In overload scenario, where the number of users is more than the number of receiving antennas, the FNN MUD performs better than RNN MUD. Further, the RBFN MUD provides a significant enhancement in performance over FNN and RNN MUDs under both overload and full load scenarios because of its better classification ability due to Gaussian nonlinearity. Extensive simulation analysis considering Stanford University Interim channel models applied for fixed wireless applications shows improvement in convergence speed and BER performance of the proposed NN-based MUD algorithms.     

Neural network-based multiuser detection for SDMA–OFDM system over IEEE 802.11n indoor wireless local area network channel models

Space division multiple access – orthogonal frequency division multiplexing-based wireless communication has the potential to offer high-spectral efficiency, system performance and capacity. This article proposes an efficient blind multiuser detection (MUD) scheme using artificial neural network models such as the radial basis function. The proposed MUD technique is consistently outperforming the existing minimum mean square error and minimum bit error rate (MBER) MUDs with the performance close to the optimal maximum likelihood (ML) detector. Besides that, the computational complexity of the proposed one is comparatively lower than both the MBER and ML detectors. Further, it can also outperform MBER MUD in the overload scenario, where the number of users is more than that of the number of receiving antennas simulation-based study showing BER performance and complexity are carried out to prove the efficiency of the proposed techniques. This analysis is carried through the IEEE 802.11n standard channel models, which are designed for indoor wireless local area network applications of bandwidth up to 100?MHz at frequencies 2 and 5?GHz.     

Semianalytical Modeling of Concrete Beams Rehabilitated with Externally Prestressed Composites

This study attempts to develop a semianalytical model for the mechanical behavior of reinforced concrete (RC) beams rehabilitated with externally prestressed carbon fiber-reinforced polymers (CFRP) laminates. The main significance of this study is the model of the process of degradation of RC beams until failure and its recovery through externally prestressed CFRP. Experiments have been carried out to observe the load–deflection behavior of fresh RC beams until the load resistance of the beam is exhausted. The beams have been rehabilitated with external CFRP laminates with varying levels of prestress. The rehabilitated beams have been reloaded until failure. The load–deflection behavior of the fresh and rehabilitated beams has been compared. A model for the load–deflection behavior of the fresh and rehabilitated beam has been proposed. The main import of the model is that it incorporates the effect of confinement of concrete. The model shows very good agreement with the experimental results.     

Design of Large Scale MU-MIMO System with Joint Precoding and Detection Schemes for Beyond 5G Wireless Networks

The large scale multiuser multiple input multiple output (MU-MIMO) is one of the promising communication technology for 5G wireless networks as it offers reliability, high spectral efficiency and high throughput. The lattice reduction (LR) precoding based user level local likelihood ascent search (ULAS) detection scheme is proposed in this paper for efficient signal detection in large scale MU-MIMO system. The initial solution of ULAS algorithm is obtained from the LR precoding assisted zero forcing detector. The LR precoding transforms the non-orthogonal channel matrix into nearly orthogonal channel, which helps to mitigate inter antenna interference (IAI) exists at each user. The remaining multiuser interference (MUI) imposed to each user from undesired users is cancelled by the proposed ULAS multiuser detection scheme. Thus, the proposed LR precoding assisted ULAS mitigates both IAI and MUI unlike the classical detector, those try to moderate either IAI or MUI. By contrast, the proposed ULAS detector provides performance close to optimal maximum likelihood detector with just a fraction of its complexity.

     

Design of MC-CDMA receiver using radial basis function network to mitigate multiple access interference and nonlinear distortion

Multicarrier code division multiple access (MC-CDMA) is a novel wireless communication technology with high spectral efficiency and system performance. However, all multiple access techniques including MC-CDMA were most likely to have multiple access interference (MAI). So, this paper mainly aims at designing a suitable receiver for MC-CDMA system to mitigate such MAI. The classical receivers like maximal-ratio combining and minimum mean square error fail to cancel MAI when the MC-CDMA is subjected to nonlinear distortions, which may occur due to saturated power amplifiers or arbitrary channel conditions. Being highly nonlinear structures, the neural network (NN) receivers such as multilayer perceptron and radial basis function networks could be better alternative for such a case. The possibility NN receiver for a MC-CDMA system under different nonlinear conditions has been studied with respect to both performance and complexity analysis.

     

Design of near‐optimal local likelihood search‐based detection algorithm for coded large‐scale MU‐MIMO system

Massive multiuser multiple input multiple output (MU‐MIMO) system is aimed to improve throughput and spectral efficiency through a large number of antennas incorporated at the transmitter and/or receiver. However, the MU‐MIMO system usually suffers from interantenna interference (IAI) and multiuser interference (MUI). The IAI imposes due to closely spaced antennas at each user equipment (UE), and MUI is enforced when one user comes under the vicinity of another user in the same cellular network. Most of the previous literatures considered any one of these interferences. However, the present work proposes singular value decomposition (SVD) precoding‐assisted user‐level local likelihood ascent search (LLAS) algorithm to mitigate both IAI and MUI. In the uplink MU‐MIMO, the IAI is cancelled by SVD, and the residual MUI is mitigated by LLAS detection. The LLAS detection balances the trade‐off between the classical suboptimal likelihood ascent search (LAS) and optimal maximum likelihood (ML) detection techniques. The proposed LLAS performs local search among all 2M_T‐dimensional neighborhood vectors at each UE, where M_T represents number of transmitting antennas of each UE. Thus, its performance is near optimal, and its complexity is much lower than ML detector.