![]() Since the network expects real inputs, create a two column vector, where the first column is the real values of the received symbol and the second column is the imaginary values of the received symbol. ![]() Input a received symbol to the network and train it to estimate the exact LLR values. Set up a shallow neural network with one input layer, one hidden layer, and one output layer. 'UnitAveragePower',1, 'OutputType', 'approxllr', 'NoiseVariance',noiseVariance) 'UnitAveragePower',1, 'OutputType', 'llr', 'NoiseVariance',noiseVariance) ĪpproxLLR(:,snrIdx) = qamdemod(r,M,symOrder. ġi*(rand(numSymbols,1)*(maxImag-minImag)+minImag) ĮxactLLR(:,snrIdx) = qamdemod(r,M,symOrder. R = (rand(numSymbols,1)*(maxReal-minReal)+minReal) +. Const = qammod(0:15,M,symOrder, 'UnitAveragePower',1)
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |