Open AccessMultiple‐input–multiple‐output channel modelling using multi‐layer perceptron with finite impulse response and infinite impulse response synapses
Author(s) -
Sarma Kandarpa Kumar,
Mitra Abhijit
Publication year - 2013
Publication title -
iet communications
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.355
H-Index - 62
eISSN - 1751-8636
pISSN - 1751-8628
DOI - 10.1049/iet-com.2012.0635
Subject(s) - infinite impulse response , mimo , computer science , finite impulse response , perceptron , channel (broadcasting) , feed forward , multilayer perceptron , impulse response , artificial neural network , algorithm , control theory (sociology) , impulse (physics) , telecommunications , mathematics , artificial intelligence , digital filter , engineering , control engineering , bandwidth (computing) , mathematical analysis , physics , control (management) , quantum mechanics
Multiple‐input–multiple‐output (MIMO) wireless technology is a viable option likely to be able to meet the demands of the ever‐expanding mobile networks. For MIMO system, channel estimation is still a challenging area due to several difficulties. Soft‐computational approaches can be additions to the list of traditional methods of MIMO channel modelling primarily because these tools, for their ability to learn, are better placed to use channel side information for improved performance. One of the viable means of such innovative channel estimation is the use of the artificial neural network (ANN) in a feedforward format known as multi‐layer perceptron (MLP). But as these ANNs prove to be suitable for static and slowly varying cases, time‐varying MIMO channels are modelled using modified MLP with temporal attributes developed using finite impulse response (FIR) and infinite impulse response (IIR) blocks in place of the synaptic links. Six sub‐classes of each of the FIR‐MLP and the IIR‐MLP are formulated, which show better performance than the conventional MLP in modelling the MIMO channels.