On the Latent Space of mmWave MIMO Channels for NLOS Identification in 5G-Advanced Systems

In mission-critical verticals such as automated driving, 5G-advanced networks must provide centimeter-level dynamic positioning along with ultra-reliable low-latency communication services. Massive Multiple-Input Multiple-Output (mMIMO) and millimeter waves (mmWave) are the key enablers, allowing high accuracy angle and delay estimation. Still, extracting such information from highly-dimensional Channel Impulse Responses (CIRs) results in a complex task, due to channel sparsity and intermittent blockage. In this paper we focus on non-line-of-sight (NLOS) identification from CIR data, proposing a Deep Autoencoding Kernel Density Model (DAKDM) to characterize the statistics of the channel latent features. We formulate the problem as a semi-supervised anomaly detection task in which only LOS samples, i.e., normal data, are adopted for training. DAKDM is a single-stage training model that takes as input the full CIR thanks to an AutoEncoder (AE) structure. The proposed method is able to learn the latent distribution by means of a Kernel Density Estimator (KDE) in combination with a deep learning likelihood network. We validate the proposed solution in a 5G Urban micro (UMi) vehicular scenario. Results show that the proposed model can significantly outperform conventional algorithms and obtain similar performances to variational Bayes algorithms at one tenth of the inference time.

Automated summary

This paper proposes a Deep Autoencoding Kernel Density Model (DAKDM) for non-line-of-sight (NLOS) identification from Channel Impulse Response (CIR) data. The proposed method learns the latent distribution using a Kernel Density Estimator (KDE) in combination with a deep learning likelihood network. It has been validated in a 5G Urban micro (UMi) vehicular scenario and shows better performance compared to conventional algorithms.