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

Abstract

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-lineof-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.

A feasibility study of 5G positioning with current cellular network deployment

“…The distinct and innovative features of PRSs include improved correlation properties with respect to any other 5G signal and improved hearability thanks to the concept of muting 7 . Thereby, such cellular communication standard has the most advanced design of the physical layer to specifically address positioning applications.The need for an accurate, reliable and secure cellular positioning has emerged in a number of 5G and beyond application verticals [8][9][10][11][12][13][14][15] , such as geolocation, geomarketing, augmented reality, asset monitoring, social media, and more 16 . Moreover, the information on the position of the User Equipment (UE) or network apparata is also strategic for location-aware communications, such as in device-to-device communications 17 , vehicular communications [18][19][20][21][22] , or in new paradigms of wireless communication using reconfigurable intelligent surfaces 23 .…”

“…The need for an accurate, reliable and secure cellular positioning has emerged in a number of 5G and beyond application verticals [8][9][10][11][12][13][14][15] , such as geolocation, geomarketing, augmented reality, asset monitoring, social media, and more 16 . Moreover, the information on the position of the User Equipment (UE) or network apparata is also strategic for location-aware communications, such as in device-to-device communications 17 , vehicular communications [18][19][20][21][22] , or in new paradigms of wireless communication using reconfigurable intelligent surfaces 23 .…”

Inter-Frame-Relationship Protected Signal: A New Design for Radio Frequency Fingerprint Authentication

“…Detection-based Detect the appearance of anomalous traffic [18][19][20][21][22][23] Prevention-based Detect the injected frame for discarding [24,25] The first type of solution is detection-based, which aims to detect the appearance of anomalous traffic. The basic idea is to utilize the well-defined relationship between different frames: once a forged frame is injected, the relationship is corrupted and, thus, can be detected.…”

“…However, the sequence number is easy to predict and forge by the attacker using soft wireless card or by techniques proposed in [ 20 ]; in addition, the sequence number is not available for control and management frames. Except for the sequence number, the relationships, including received signal strength [ 21 ], arrival time [ 22 ], and channel response [ 23 ], are also studied in previous research. Although these anomaly detection techniques can provide lightweight detection of traffic anomaly, they cannot guarantee normal communication when such attacks occur.…”