We propose a joint source-channel-network coding scheme, based on compressivesensing principles, for wireless networks with AWGN channels (that may includemultiple access and broadcast), with sources exhibiting temporal and spatialdependencies. Our goal is to provide a reconstruction of sources within anallowed distortion level at each receiver. We perform joint source-channelcoding at each source by randomly projecting source values to a lowerdimensional space. We consider sources that satisfy the restricted eigenvalue(RE) condition as well as more general sources for which the randomness of thenetwork allows a mapping to lower dimensional spaces. Our approach relies onusing analog random linear network coding. The receiver uses compressivesensing decoders to reconstruct sources. Our key insight is the fact that,compressive sensing and analog network coding both preserve the sourcecharacteristics required for compressive sensing decoding.
展开▼
