Modelling Large-Scale Signal Fading in Urban Environment Based on Fuzzy Inference System

Measurement and Prediction of Short-Range Path Loss between 27 and 40 GHz in University Campus Scenarios

“…Equations ( 10) and (11) provide the path to introduce the set of cluster centres in the Fuzzy model. Takagi-Sugeno-type rules were used, which have been shown to accurately represent complex behaviors with just a few rules.…”

“…More recently, non-traditional artificial intelligence techniques such as fuzzy clustering prediction [2], artificial neural networks [2]- [6], deep learning [7], [8] and machine learning [4], [9] have also been used to estimate the path loss in different environments. These models are also been used in angle-of-arrival estimation [10], large-scale signal fading modeling [11], and indoor localization [12].…”

Multi‐adaptive neuro‐fuzzy inference system modelling for prediction of band‐notched behaviour of slotted‐UWB antennas optimised using evolutionary algorithms

“…In addition, with a slight change even in a single geometrical parameter, the whole simulation process is to be repeated for getting a new solution. Thus, the obligation of having an instant solution for every minor change in the geometry is effectively resolved by using soft computing based models [12–32]. These models, once trained properly, give the instant answer for every minor change in the geometrical parameters.…”

“…Limitations of each of these techniques encouraged the combination and creation of new techniques by exploiting the advantages of the individual techniques. Neuro‐fuzzy model combining neural network with fuzzy set methods enhances the capacity and mitigates the disadvantages of each approach acting alone [23, 24]. Fuzzy logic parameters can be tuned using the learning capability of neural network for which the past experience and knowledge of the network directly generate rules from the original data.…”