Neural Network Detection of Data Sequences in Communication Systems

We consider detection based on deep learning, and show it is possible to train detectors that perform well without any knowledge of the underlying channel models. Moreover, when the channel model is known, we demonstrate that it is possible to train detectors that do not require channel state information (CSI). In particular, a technique we call a sliding bidirectional recurrent neural network (SBRNN) is proposed for detection where, after training, the detector estimates the data in real time as the signal stream arrives at the receiver. We evaluate this algorithm, as well as other neural network (NN) architectures, using the Poisson channel model, which is applicable to both optical and molecular communication systems. In addition, we also evaluate the performance of this detection method applied to data sent over a molecular communication platform, where the channel model is difficult to model analytically. We show that SBRNN is computationally efficient, and can perform detection under various channel conditions without knowing the underlying channel model. We also demonstrate that the bit error rate performance of the proposed SBRNN detector is better than that of a Viterbi detector with imperfect CSI as well as that of other NN detectors that have been previously proposed. Finally, we show that the SBRNN can perform well in rapidly changing channels, where the coherence time is on the order of a single symbol duration.

[1]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[2]  V.W.S. Chan,et al.  Principles of Digital Communication and Coding , 1979 .

[3]  Brian M. Sadler,et al.  Modeling of non-line-of-sight ultraviolet scattering channels for communication , 2009, IEEE J. Sel. Areas Commun..

[4]  N. Hayasaka,et al.  Channel modeling of nondirected wireless infrared indoor diffuse link , 2007 .

[5]  Jürgen Schmidhuber,et al.  Framewise phoneme classification with bidirectional LSTM and other neural network architectures , 2005, Neural Networks.

[6]  J. Collins,et al.  Synthetic biology devices for in vitro and in vivo diagnostics , 2015, Proceedings of the National Academy of Sciences.

[7]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[8]  Yair Be'ery,et al.  Learning to decode linear codes using deep learning , 2016, 2016 54th Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[9]  Vahid Jamali,et al.  Channel Estimation for Diffusive Molecular Communications , 2016, IEEE Transactions on Communications.

[10]  Kuldip K. Paliwal,et al.  Bidirectional recurrent neural networks , 1997, IEEE Trans. Signal Process..

[11]  Özgür B. Akan,et al.  Body area nanonetworks with molecular communications in nanomedicine , 2012, IEEE Communications Magazine.

[12]  Cong Shen,et al.  An Iterative BP-CNN Architecture for Channel Decoding , 2017, IEEE Journal of Selected Topics in Signal Processing.

[13]  Andrea J. Goldsmith,et al.  Machine learning based channel modeling for molecular MIMO communications , 2017, 2017 IEEE 18th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC).

[14]  Chong Wang,et al.  Deep Speech 2 : End-to-End Speech Recognition in English and Mandarin , 2015, ICML.

[15]  Urbashi Mitra,et al.  Capacity of Diffusion-Based Molecular Communication Networks Over LTI-Poisson Channels , 2014, IEEE Transactions on Molecular, Biological and Multi-Scale Communications.

[16]  Chen Gong,et al.  Channel Estimation and Signal Detection for Optical Wireless Scattering Communication With Inter-Symbol Interference , 2015, IEEE Transactions on Wireless Communications.

[17]  Raviraj S. Adve,et al.  Molecular Communication in Fluid Media: The Additive Inverse Gaussian Noise Channel , 2010, IEEE Transactions on Information Theory.

[18]  David Burshtein,et al.  Deep Learning Methods for Improved Decoding of Linear Codes , 2017, IEEE Journal of Selected Topics in Signal Processing.

[19]  Jeff Hasty,et al.  Programmable probiotics for detection of cancer in urine , 2015, Science Translational Medicine.

[20]  Stephan ten Brink,et al.  Scaling Deep Learning-Based Decoding of Polar Codes via Partitioning , 2017, GLOBECOM 2017 - 2017 IEEE Global Communications Conference.

[21]  Timothy J. O'Shea,et al.  An Introduction to Machine Learning Communications Systems , 2017, ArXiv.

[22]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[23]  Necmi Taspinar,et al.  Multiuser detection with neural network and PIC in CDMA systems for AWGN and Rayleigh fading asynchronous channels , 2007, Wirel. Pers. Commun..

[24]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[25]  Juan José Murillo-Fuentes,et al.  Gaussian Processes for Multiuser Detection in CDMA receivers , 2005, NIPS.

[26]  Ami Wiesel,et al.  Deep MIMO detection , 2017, 2017 IEEE 18th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC).

[27]  Ian F. Akyildiz,et al.  Nanonetworks: A new communication paradigm , 2008, Comput. Networks.

[28]  Bernd-Peter Paris,et al.  Neural networks for multiuser detection in code-division multiple-access communications , 1992, IEEE Trans. Commun..

[29]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[30]  Zabih Ghassemlooy,et al.  Optical Wireless Communications: System and Channel Modelling with MATLAB® , 2012 .

[31]  Jr. G. Forney,et al.  Viterbi Algorithm , 1973, Encyclopedia of Machine Learning.

[32]  Ah Chung Tsoi,et al.  Face recognition: a convolutional neural-network approach , 1997, IEEE Trans. Neural Networks.

[33]  Urbashi Mitra,et al.  Neural network techniques for adaptive multiuser demodulation , 1994, IEEE J. Sel. Areas Commun..

[34]  Bartosz A. Grzybowski,et al.  Chemistry in motion : reaction-diffusion systems for micro- and nanotechnology , 2009 .

[35]  Andrea J. Goldsmith,et al.  A molecular communication system using acids, bases and hydrogen ions , 2015, 2016 IEEE 17th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC).

[36]  Navdeep Jaitly,et al.  Towards End-To-End Speech Recognition with Recurrent Neural Networks , 2014, ICML.

[37]  Andrew W. Eckford,et al.  Molecular MIMO: From Theory to Prototype , 2016, IEEE Journal on Selected Areas in Communications.

[38]  Jun Chen,et al.  Capacity-Achieving Distributions for the Discrete-Time Poisson Channel—Part I: General Properties and Numerical Techniques , 2014, IEEE Transactions on Communications.

[39]  Kiran Karra,et al.  Learning approximate neural estimators for wireless channel state information , 2017, 2017 IEEE 27th International Workshop on Machine Learning for Signal Processing (MLSP).

[40]  Jakob Hoydis,et al.  An Introduction to Deep Learning for the Physical Layer , 2017, IEEE Transactions on Cognitive Communications and Networking.

[41]  Arun K. Majumdar,et al.  Reconstruction of probability density function of intensity fluctuations relevant to free-space laser communications through atmospheric turbulence , 2007, SPIE Optical Engineering + Applications.

[42]  Vahid Jamali,et al.  SCW codes for optimal CSI-free detection in diffusive molecular communications , 2017, 2017 IEEE International Symposium on Information Theory (ISIT).

[43]  L. Debnath.  Nonlinear Partial Differential Equations for Scientists and Engineers , 1997 .

[44]  Andrew W. Eckford,et al.  Tabletop Molecular Communication: Text Messages through Chemical Signals , 2013, PloS one.

[45]  Andrea J. Goldsmith,et al.  Capacity of molecular channels with imperfect particle-intensity modulation and detection , 2017, 2017 IEEE International Symposium on Information Theory (ISIT).

[46]  S. Shamai,et al.  Capacity of a pulse amplitude modulated direct detection photon channel , 1990 .

[47]  Andrea J. Goldsmith,et al.  Non-Coherent Detection for Diffusive Molecular Communications , 2017, ArXiv.

[48]  Mohamed Ibnkahla,et al.  Applications of neural networks to digital communications - a survey , 2000, Signal Process..

[49]  Tatsuya Suda,et al.  Molecular communication for health care applications , 2006, Fourth Annual IEEE International Conference on Pervasive Computing and Communications Workshops (PERCOMW'06).

[50]  Christopher A. Voigt,et al.  Environmentally controlled invasion of cancer cells by engineered bacteria. , 2006, Journal of molecular biology.

[51]  Tara N. Sainath,et al.  Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups , 2012, IEEE Signal Processing Magazine.

[52]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[53]  Milica Stojanovic,et al.  Underwater acoustic communication channels: Propagation models and statistical characterization , 2009, IEEE Communications Magazine.

[54]  Du Limin,et al.  Efficient Viterbi beam search algorithm using dynamic pruning , 2004, Proceedings 7th International Conference on Signal Processing, 2004. Proceedings. ICSP '04. 2004..

[55]  Stephan ten Brink,et al.  Deep Learning Based Communication Over the Air , 2017, IEEE Journal of Selected Topics in Signal Processing.

[56]  Andrea J. Goldsmith,et al.  A Novel Experimental Platform for In-Vessel Multi-Chemical Molecular Communications , 2017, GLOBECOM 2017 - 2017 IEEE Global Communications Conference.

[57]  Erik Dahlman,et al.  4G: LTE/LTE-Advanced for Mobile Broadband , 2011 .

[58]  Kiran Karra,et al.  Learning to communicate: Channel auto-encoders, domain specific regularizers, and attention , 2016, 2016 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT).

[59]  Andrew W. Eckford,et al.  A Comprehensive Survey of Recent Advancements in Molecular Communication , 2014, IEEE Communications Surveys & Tutorials.

[60]  Jürgen Schmidhuber,et al.  Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks , 2006, ICML.

[61]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[62]  Robert Schober,et al.  Optimal Receiver Design for Diffusive Molecular Communication With Flow and Additive Noise , 2013, IEEE Transactions on NanoBioscience.

[63]  Yair Be'ery,et al.  RNN Decoding of Linear Block Codes , 2017, ArXiv.

[64]  Zhen Li,et al.  Protein Secondary Structure Prediction Using Cascaded Convolutional and Recurrent Neural Networks , 2016, IJCAI.