A neural network approach to blind source separation;
Institution: | Anna University |
---|---|
Department: | A neural network approach to blind source separation |
Year: | 2015 |
Keywords: | blind source separation; information and communication engineering; neural network |
Record ID: | 1188447 |
Full text PDF: | http://shodhganga.inflibnet.ac.in/handle/10603/34347 |
This work has focused on development of an Adaptive Self newlineNormalized Radial Basis Function ASNRBF neural network and anUnsupervised Stochastic Gradient Descent learning Algorithm USGDA for newlineBlind Source Separation BSS problem BSS is one of the fundamental and newlinechallenging problems in Artificial Neural Networks ANN and SignalProcessing fields It is an emerging field of fundamental research with many newlinepotential applications and it has garnered much recent research andcommercial interest in the fields such as digital and wireless communications newlinesignal processing acoustics medicine etc The objective of blind sourceseparation is to separate unknown signals that have been mixed together the newlinedesired signals and the mixing matrix are not known and the only availabledata being the mixture signal Hyvarinen et al 2001 newline newline%%%Reference p.133-137