Keynote 01:Optimization Methods in Computational Intelligence for Joint Wireless Channel Parameter Estimation over Advanced Radio Interface Technologies

Abstract

Advanced Radio Interface Technologies (RITs) combine broadband signalling—hence multicarrier operation and richly multipath propagation—with multi-antenna transceivers. In these regimes, joint estimation of channel parameters (angles of arrival/departure, delays, Doppler/frequency offsets, gains/phases, etc.) becomes a central yet challenging inference problem. Objective or cost functions are often nonconvex, multimodal, and simulator-defined, with scarce gradients, tight pilot budgets, and low signal-to-noise ratios (SNRs). Therefore, among computational intelligence (CI) categories that encompass 1) neural networks and 2) fuzzy systems, the third or 3) population-based and bioinspired optimization (PBO/BO) methods – such as particle swarm optimization (PSO), differential evolution (DE), genetic algorithms (GA), grey wolf optimizer (GWO), and related swarms – have gained traction as global search engines that either directly minimize maximum-likelihood (ML) or mean-square error (MSE) criteria or act as robust initializers for hybrid pipelines. In this talk, first we integrate a disciplinary taxonomy relating artificial intelligence (AI), optimization, and Monte Carlo inference to place CI and PBO/BO within a broader computational context worth contemplating. Then we survey the current state of the art on CI optimization for wireless channel parameter estimation and analyze the strengths and weaknesses of each CI subcategory versus the others and against conventional estimation methods. We synthesize algorithmic patterns, objectives, accuracy, convergence/complexity trends, and empirical findings, etc., over advanced RITs, and we discuss most recent progress and open challenges