Neural Approximations of Analog Joint Source-Channel Coding

An estimation setting is considered, where a number of sensors transmit their observations of a physical phenomenon, described by one or more random variables, to a sink over noisy communication channels. The goal is to minimize a quadratic distortion measure (Minimum Mean Square Error - MMSE) under a global power constraint on the sensors' transmissions. Linear MMSE encoders and decoders, parametrically optimized in encoders' gains, Shannon-Kotel'nikov mappings, and nonlinear parametric functional approximators (neural networks) are investigated and numerically compared, highlighting subtle differences in sensitivity and achievable performance.

[1]  Tor A. Ramstad,et al.  Shannon-kotel-nikov mappings in joint source-channel coding , 2009, IEEE Transactions on Communications.

[2]  S. Hyakin,et al.  Neural Networks: A Comprehensive Foundation , 1994 .

[3]  Luc Vandendorpe,et al.  Adaptive Power Allocation in Wireless Sensor Networks with Spatially Correlated Data and Analog Modulation: Perfect and Imperfect CSI , 2010, EURASIP J. Wirel. Commun. Netw..

[4]  Amir K. Khandani,et al.  Linear estimation of correlated data in wireless sensor networks with optimum power allocation and analog modulation , 2008, IEEE Transactions on Communications.

[5]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[6]  Kenneth Rose,et al.  Optimized Analog Mappings for Distributed Source-Channel Coding , 2010, 2010 Data Compression Conference.

[7]  Sae-Young Chung,et al.  On the construction of some capacity-approaching coding schemes , 2000 .

[8]  Mario Marchese,et al.  Non-linear coding and decoding strategies exploiting spatial correlation in wireless sensor networks , 2012, IET Commun..

[9]  Jason L. Speyer,et al.  Stochastic Processes, Estimation, and Control , 2008, Advances in design and control.

[10]  Kenneth Rose,et al.  Optimal mappings for joint source channel coding , 2010, 2010 IEEE Information Theory Workshop on Information Theory (ITW 2010, Cairo).

[11]  Sethu Vijayakumar,et al.  Proc. 13th Int. Conf. on Artificial Intelligence and Statistics (AISTATS 2010), JMLR: W&CP 9:677-684, Chia Laguna, Sardinia, Italy (2010). , 2010 .

[12]  P.A. Floor,et al.  Dimension Reducing Mappings in Joint Source-Channel Coding , 2006, Proceedings of the 7th Nordic Signal Processing Symposium - NORSIG 2006.

[13]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.

[14]  Alejandro Ribeiro,et al.  Bandwidth-constrained distributed estimation for wireless sensor networks-part II: unknown probability density function , 2006, IEEE Transactions on Signal Processing.

[15]  C. Tellambura,et al.  Linear estimation of correlated data in wireless sensor networks with optimum power allocation and analog modulation , 2008 .

[16]  M. Vetterli,et al.  Sensing reality and communicating bits: a dangerous liaison , 2006, IEEE Signal Processing Magazine.

[17]  Yichuan Hu,et al.  Analog Joint Source-Channel Coding Using Non-Linear Curves and MMSE Decoding , 2011, IEEE Transactions on Communications.

[18]  M. Sanguineti,et al.  Approximating Networks and Extended Ritz Method for the Solution of Functional Optimization Problems , 2002 .

[19]  Andrea J. Goldsmith,et al.  Linear Coherent Decentralized Estimation , 2006, IEEE Transactions on Signal Processing.