Corpus ID: 235727494

Geometric Machine Learning for Channel Covariance Estimation in Vehicular Networks

  title={Geometric Machine Learning for Channel Covariance Estimation in Vehicular Networks},
  author={Imtiaz Nasim and Ahmed S. Ibrahim},
Learning the covariance matrices of spatiallycorrelated wireless channels, in millimeter-wave (mmWave) vehicular communication, can be utilized in designing environmentaware beamforming codebooks. Such channel covariance matrices can be represented on non-Euclidean Riemannian manifolds, thanks to their symmetric positive definite (SPD) characteristics. Consequently in this paper, we propose a Riemannian-Geometric machine learning (G-ML) approach for estimating the channel covariance matrices… Expand

Figures from this paper


Generative Adversarial Estimation of Channel Covariance in Vehicular Millimeter Wave Systems
A novel solution that exploits machine learning tools, namely conditional generative adversarial networks (GAN), is developed to learn these functions between the environment and the channel covariance matrices. Expand
Spatial Channel Covariance Estimation for the Hybrid MIMO Architecture: A Compressive Sensing-Based Approach
Two approaches to covariance estimation based on compressive sensing techniques are proposed, one is to apply a time-varying sensing matrix, and the other is to exploit the prior knowledge that the covariance matrix is Hermitian. Expand
Covariance Matrix Estimation in Massive MIMO
This work exploits common structure of the covariance matrices to derive methods for accurate covariance matrix estimation by the appropriate assignment of pilot sequences to the users in consecutive channel coherence intervals. Expand
Channel Covariance Matrix Estimation via Dimension Reduction for Hybrid MIMO MmWave Communication Systems
This paper forms the channel covariance estimation as a structured low-rank matrix sensing problem via Kronecker product expansion and uses a low-complexity algorithm to solve this problem. Expand
Covariance clustering on Riemannian manifolds for acoustic model compression
Experimental results show the effectiveness of the proposed novel clustering algorithm, reducing the acoustic model size nearly to the half without noticeable loss in recognition performance. Expand
Systematic Codebook Designs for Quantized Beamforming in Correlated MIMO Channels
This paper proposes a universal codebook design for correlated channels when channel statistical information is known at the transmitter that is robust to channel statistics and is implemented by maps that can rotate and scale spherical caps on the Grassmannian manifold. Expand
Learning Beam Codebooks with Neural Networks: Towards Environment-Aware mmWave MIMO
A neural network architecture is developed that accounts for the hardware constraints and learns beam codebooks that adapt to the surrounding environment and the user locations and leads to noticeable gains compared to classical codebook design approaches. Expand
Low-PAPR Precoding Design for Massive Multiuser MIMO Systems via Riemannian Manifold Optimization
  • Jung-Chieh Chen
  • Mathematics, Computer Science
  • IEEE Communications Letters
  • 2017
This work proposes the use of Riemannian manifold optimization (RMO) that can solve the CE precoding design problem and demonstrates that the proposed RMO-based solver achieves nearly the same performance of the conventional sequential gradient descent-basedsolver, but the complexity is considerably reduced. Expand
Flat Beam Design for Massive MIMO Systems via Riemannian Optimization
A novel algorithm to design beamformer with flat beampattern for massive multi-input-multi-output systems where the base station is equipped with large-scale uniform planar array (UPA). Expand
Joint Spatial Division and Multiplexing—The Large-Scale Array Regime
JSDM achieves significant savings both in the downlink training and in the CSIT uplink feedback, thus making the use of large antenna arrays at the base station potentially suitable also for frequency division duplexing systems, for which uplink/downlink channel reciprocity cannot be exploited. Expand