Adaptive Spatial Modulation MIMO Based on Machine Learning

Yang, Ping; Xiao, Yue; Xiao, Ming; Guan, Yong Liang; Li, Shaoqian; Wang, Xiang

doi:10.1109/jsac.2019.2929404

Cited by 80 publications

(53 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One extension of this work is to consider the impact of the propagation environment on the ML-assisted link adaptive system, such as the generalization capability of the trained classifier when different channel models are considered. Another extension of the work is to use other classification algorithms, which are able to attain a similar performance as the k-NN, but come with lower computational cost and are less demanding on memory storage [35], [54].…”

Section: Discussionmentioning

confidence: 99%

Machine Learning Assisted Adaptive Index Modulation for mmWave Communications

Liu

El‐Hajjar

et al. 2020

IEEE Open J. Commun. Soc.

View full text Add to dashboard Cite

In this paper, we propose an orthogonal frequency-division multiplexing system supported by the compressed sensing assisted index modulation, termed as (OFDM-CSIM), applied to millimeter-wave (mmWave) communications. In the OFDM-CSIM mmWave system, information is conveyed not only by the classic constellation symbols but also by the on/off status of subcarriers, where the size of constellation symbols and the number of active subcarriers can be beneficially configured for maximizing the system's throughput. We conceive a machine learning (ML) assisted adaptive OFDM-CSIM mmWave system, which simultaneously benefits from the OFDM with index modulation (IM), compressed sensing (CS) and the hybrid beamforming techniques. Specifically, a ML-assisted link adaptation scheme is designed based on the k-nearest neighbors (k-NN) algorithm with the objective to maximize the system's throughput. Our studies show that the proposed ML-assisted link adaptation is capable of providing higher throughput than the conventional threshold-based link adaptation when different antenna structures are considered. Furthermore, the achievable data rates of four types of antenna arrays, including uniform linear array (ULA), uniform rectangular planar array (URPA), uniform circle planar array (UCPA) and uniform cylindrical array (UCYA), are investigated and compared over mmWave channels. The simulation results show that the UCYA achieves the highest data rate among these antenna arrays.

show abstract

Section: Discussionmentioning

confidence: 99%

Machine Learning Assisted Adaptive Index Modulation for mmWave Communications

Liu

El‐Hajjar

et al. 2020

IEEE Open J. Commun. Soc.

View full text Add to dashboard Cite

show abstract

“…SFVG [10]. It can be seen that SFVG gives the best performance because it provides individual real and imaginary scalar values of the received signal and channel matrices.…”

Section: Detectormentioning

confidence: 98%

Block Deep Neural Network-Based Signal Detector for Generalized Spatial Modulation

et al. 2020

View full text Add to dashboard Cite

Generalized Spatial Modulation (GSM) is being considered for high capacity and energy-efficient networks of the future. However, signal detection due to inter channel interference among the active antennas is a challenge in GSM systems and is the focus of this letter. Specifically, we explore the feasibility of using deep neural networks (DNN) for signal detection in GSM. In particular, we propose a block DNN (B-DNN) based architecture, where the active antennas and their transmitted constellation symbols are detected by smaller sub-DNNs. After N-ordinary DNN detection, the Euclidean distance-based soft constellation algorithm is implemented. The proposed B-DNN detector achieves a BER performance that is superior to traditional block zero-forcing (B-ZF) and block minimum mean-squared error (B-MMSE) detection schemes and similar to that of classical maximum likelihood (ML) detector. Further, the proposed method requires less computation time and is more accurate than alternative conventional numerical methods.

show abstract

“…is sent into an OFDM modulator, and the output is a row of the transmit signal matrix S(t). The transmit signal S(t) goes through the multipath channel H(τ ,t) = [ĥ nr,nt (τ ,t)] [3] superimposed by the additive white Gaussian noise (AWGN), wherê h nr,nt (τ ,t) = [h (1) nr,nt (τ 1 ,t),h (2) nr,nt (τ…”

Section: A System Modelmentioning

confidence: 99%

An Experimental Investigation of Enhanced SM-OFDM Over Indoor Rician Multipath Channels

Jiang

Liu

Yang

et al. 2020

IEEE Trans. Veh. Technol.

Self Cite

View full text Add to dashboard Cite

In this letter, we investigate enhanced spatial modulation (ESM) aided orthogonal frequency division multiplexing (OFDM) systems. ESM extends the conventional SM by introducing a series of signal constellations. Existing research shows that ESM displays performance superiority over SM in flat-fading channels. For frequency-selective fading channels, we design a practical implementation of an ESM&SM aided OFDM hybrid system to characterize the bit error rate (BER) performance of ESM and conventional SM with an experimental wireless testbed. Form the experimental results, it is found that ESM achieves better BER performance than SM on frequency-selective channels, which are consistent with the Monte Carlo simulation results. Index Terms-Bit error rate (BER), enhanced spatial modulation (ESM), multiple-input multiple-output orthogonal frequency division multiplexing (MIMO-OFDM), wireless testbed. I. INTRODUCTION M ULTIPLE-INPUT multiple-output orthogonal frequency division multiplexing (MIMO-OFDM) [1] is a key enabling technique for modern high-rate communications. However, due to the use of multiple-antenna and multiplecarrier, current MIMO-OFDM suffers from several problems, such as the inter-channel interference (ICI), the inter-antenna interference (IAI), the need for multiple radio frequency (RF) chains [2], and the high peak-to-average power ratio (PAPR) of the transmitted signals. These problems result in extra complexity or power burden to MIMO-OFDM system design. Recently, spatial modulation-OFDM (SM-OFDM) has been proposed to address some of the above mentioned problems pertinent to MIMO-OFDM. The main idea of SM-OFDM is that at each channel use only one single transmit antenna (TA) activates its subcarrier for data transmission. The sparsity of the transmit vectors in frequency domain helps lower the PAPR, reduce the ICI, and allow a low-complexity receiver [2]-[4]. To date, some intensive studies have been conducted on SM-OFDM [5]-[7]. To be specific, [5] studied the average bit error rate (BER) performance of SM-OFDM with the socalled N-continuous (NC) precoder under perfect and imperfect channel estimations. [6] proposed a detection scheme for SM-OFDM which can effectively mitigate the effect of

show abstract

Adaptive Spatial Modulation MIMO Based on Machine Learning

Cited by 80 publications

References 42 publications

Machine Learning Assisted Adaptive Index Modulation for mmWave Communications

Machine Learning Assisted Adaptive Index Modulation for mmWave Communications

Block Deep Neural Network-Based Signal Detector for Generalized Spatial Modulation

An Experimental Investigation of Enhanced SM-OFDM Over Indoor Rician Multipath Channels

Contact Info

Product

Resources

About