Artificial Intelligence and Dimensionality Reduction: Tools for Approaching Future Communications

Abstract

This article presents a novel application of the t-distributed Stochastic Neighbor Embedding (t-SNE) clustering algorithm to the telecommunication field. t-SNE is a dimensionality reduction algorithm that allows the visualization of large dataset into a 2D plot. We present the applicability of this algorithm in a communication channel dataset formed by several scenarios (anechoic, reverberation, indoor and outdoor), and by using six channel features. Applying this artificial intelligence (AI) technique, we are able to separate different environments into several clusters allowing a clear visualization of the scenarios. Throughout the article, it is proved that t-SNE has the ability to cluster into several subclasses, obtaining internal classifications within the scenarios themselves. t-SNE comparison with different dimensionality reduction techniques (PCA, Isomap) is also provided throughout the paper. Furthermore, post-processing techniques are used to modify communication scenarios, recreating a real communication scenario from measurements acquired in an anechoic chamber. The dimensionality reduction and classification by using t-SNE and Variational AutoEncoders show good performance distinguishing between the recreation and the real communication scenario. The combination of these two techniques opens up the possibility for new scenario recreations for future mobile communications. This work shows the potential of AI as a powerful tool for clustering, classification and generation of new 5G propagation scenarios.

Identifying Soccer Teams’ Styles of Play: A Scoping and Critical Review

“…It was concluded that using specific vectors, game styles could be identified based on each type of action. Finally, García-Aliaga, Marquina Nieto, Coterón, Rodríguez-González, Gil Ares, and Refoyo Román [ 60 ] employed the t-distributed Stochastic Neighbor Embedding (t-SNE) clustering algorithm, which can process large multivariate datasets and visualize them into a 2D plot [ 73 ]. Consequently, the various placements of the teams in the plots reflect the disparity between their playing styles.…”

Joint Direction-of-Arrival and Time-of-Arrival Estimation with Ultra-wideband Elliptical Arrays

“…In fact, new communication environments are materializing these days; namely, vehicleto-everything (V2X), ship-to-ship (S2S), high speed train-totrain or UAV-to-UAV [18]- [21]. Thus, a great deal of effort is being put into characterizing their most important parameters and key performance indicators, direction of arrival (DoA) and time of arrival (ToA) among them, with the aim of improving bandwidth, latency, data rate, power consumption and reliability in present and future communication systems [22]- [28].…”

Time-Gating Technique for Recreating Complex Scenarios in 5G Systems

“…Improving KPIs, and therefore the performance of wireless links, requires a proper characterization and knowledge of all channel parameters: direction of arrival (DoA), time of arrival (ToA), delay spread, path loss, and K factor, among others. With knowledge of the channel parameters, different scenarios can be effectively distinguished [3], even recreated and emulated through the use of post-processing techniques based on the creation/removal of reflections in the communication channel This work has been supported by grant TED2021-129938B-I00 funded by MCIN/AEI/10.13039/501100011033 and by the European Union NextGener-ationEU/PRTR. It has also been supported by grants PDC2022-133900-I00, PID2020-112545RB-C54 and TED2021-131699B-I00; and by Universidad de Granada through grant PPJIB2022-05; and in part by the Predoctoral Grant FPU19/01251 and FPU19/04085.…”