A Dish Parallel BP for Traffic Flow Forecasting

Reducing training time for artificial neural network (ANN) when training large samples is an active area of research. CThe back propagation (BP) is wildly used in Short-term Traffic Flow Forecasting Cwhich requires the training set size be much larger than the network size.C In order to improve training speed, Data parallelism is a good idea. A novel data parallel BP based on dish network is proposed in this paper. CTheoretical and experimental evidence prove that tChe dish data parallel BP reduce the communication cost compared with the traditional one. CCMeanwhile, by using the real traffic flow data of DaLian city, experiments show that this dish data parallel BPC improves the training speed and enhances speed-up radio.

[1]  Chao Han,et al.  A review of some main models for traffic flow forecasting , 2003, Proceedings of the 2003 IEEE International Conference on Intelligent Transportation Systems.

[2]  Mihir Bellare,et al.  Forward-Security in Private-Key Cryptography , 2003, CT-RSA.

[3]  Paul Feldman,et al.  A practical scheme for non-interactive verifiable secret sharing , 1987, 28th Annual Symposium on Foundations of Computer Science (sfcs 1987).

[4]  Jun Wang,et al.  A discrete-time recurrent neural network for shortest-path routing , 2000, IEEE Trans. Autom. Control..

[5]  Leonid Reyzin,et al.  A New Forward-Secure Digital Signature Scheme , 2000, ASIACRYPT.

[6]  Paul Kang-Hoh Phua,et al.  Parallel nonlinear optimization techniques for training neural networks , 2003, IEEE Trans. Neural Networks.

[7]  Mihir Bellare,et al.  A Forward-Secure Digital Signature Scheme , 1999, CRYPTO.

[8]  Torben P. Pedersen.  Distributed Provers with Applications to Undeniable Signatures , 1991, EUROCRYPT.

[9]  Chanathip Namprempre,et al.  Forward-Secure Threshold Signature Schemes , 2001, CT-RSA.

[10]  E. M. Anagnostakis,et al.  Short-term load forecasting based on artificial neural networks parallel implementation , 2002 .

[11]  Li Yuanxiang,et al.  Parallel training algorithm of BP neural networks , 2000, Proceedings of the 3rd World Congress on Intelligent Control and Automation (Cat. No.00EX393).

[12]  Adi Shamir,et al.  How to share a secret , 1979, CACM.

[13]  Leonid Reyzin,et al.  Forward-Secure Signatures with Fast Key Update , 2002, SCN.