Ann Assisted Turbo Coding for Use With Ofdm

ANN ASSISTED TURBO CODING FOR USE WITH OFDM SIGNAL IN WIRELESS CHANNEL

SUBMITTED BY ANNARAO.V.PATIL

UNDER THE GUIDENCE OF DR. SIDDARAMA.R. PATIL

INTRODUCTIONThe performance of the OFDM system can

improved by channel coding techniques.

The disadvantage of channel coding technique is design complexity.

The system design can be simplified by the use of soft computing methods like artificial neural network.

Here we basically deals with using ANN for turbo coding

What is ANN

Ann is nothing but artificial neural network

It is inspired by biological neural network

It is basically know for its massive parallelism

There Are Basically Ten Billion Of Neurons In Human Brain.

Sixty Trillions Of Inter connetion.

Practically Such Massive Connection Is Not Possible.

Depending On The Application We Go For Smaller Connectivity.

BIOLOGICAL NEURAL NETWORK

ARTIFICIAL NEURAL NETORK

LITERATURE SURVEY1943 McCulloch and Pitts proposed the McCulloch-Pitts neuron

model

1958 Rosenblatt introduced the simple single layer networks now called Perceptrons.

1969 Minsky and Papert’s book Perceptrons demonstrated the limitation of single layer perceptrons.

1986 The Back-Propagation learning algorithm for Multi-Layer Perceptrons was rediscovered and the whole field took off again.

1989: Tsividis: Neural Network on a chip

LITERATURE SURVEYA comparative performance analysis of OFDM using

matlab simulation with M-PSK and M-QAM mapping by J.N. PATEL and U.D dalal, 2007

.TTCM-OFDM over dispersive fading channels, by L.

Piazzo and L.Hanzo,2000.

Turbo TCM Coded OFDM Systems for Non- Gaussian Channels, by Y. Wang and L. Wei,2006.

“Neural Network Decoding of Turbo Codes”, R. Annauth and H.C.S. Rughooputh, 1999,

PROBLEM DEFINATIONFrom the extensive literature survey it is observed

that, there is a lot of scope and requirement to reduce the design complexity

Ann assisted coding approach is not found in the literature which reduce the design complexity

“Design and analysis of ANN assisted turbo coding for use with OFDM signal in wireless channel”

OBJECTIVE BASED ON LITERATURE SURVEYTo study and implement ANN assisted turbo

coding for use with OFDM signal in wireless channel

To reduce the design complexity, increase the performance in term of BER and to reduce the time of operation

METHADOLOGY

TURBO ENCODER

TURBO DECODER

CROSS ENTROPYCross entropy is a measure of the distance

between two distribution

ARTIFICIAL NEURAL NETWORKASSISTING TURBO CODEINGDEDNFEDN

TRAINING DEDN

REFERENCE[1] J.N. Patel and U.D Dalal: "A Comparative Performance Analysis of

OFDM Using MATLAB Simulation with M-PSK and M-QAM Mapping," in Proceedings of International Conference on Computational Intelligence and Multimedia Applications, 2007, vol.4, pp.406-410, Dec.2007

[2] L Piazzo and L Hanzo; "TTCM-OFDM over dispersive fading channels," in Proceedings of 51st IEEE Vehicular Technology Conference VTC 2000, vol.1, no., pp.66-70,2000

[3] Y. Wang and L. Wei; , "Turbo TCM Coded OFDM Systems for Non-Gaussian Channels," in Proceedings of IEEE International Symposium on ,Information Theory, 2006, vol., no., pp.1389-1393, July 2006

[4] T. S.Rappaport; “ Wireless Communications-Principles and Practice,”2nd Edition, PHI,2002

[5] R. Annauth and H.C.S. Rughooputh; “Neural Network Decoding of Turbo Codes”, in Proceedings of IEEE International Joint Conference on Neural Networks, 1999, vol 5,pp 3336-3341.,1999

[6] demonstration of artificial neural network in matlab by Robyn Ball and Philippe Tissot Division of Nearhsore Research, Texas A&M University – Corpus Christi,2006.

[7] Learning in Multi-Layer Perceptrons, Back-Propagation by DR .John A. Bullinaria, 2004

THANK YOU