Real-time cloud computing for web-based searching system of pattern recognition

For cross-platform real-time systems, cloud computing technology is an innovative application of pattern recognition method. This study is the use of associative memory of the way to do the work of pattern recognition; this system is real-time client-server type network pattern recognition system. Remote user can operate through the browser to draw the shape or character of industrial components, and recognition system to the database through Internet search. Cloud storage server contains a database of pattern samples. In the training period, the user can specify any of the pattern to what in real-time. Patterns are recorded in the cloud server database. In the recall period, an innovative database matching methods have been proposed. This method can effectively solve the problem of RNN a false state of the database than on the technology to overcome the problem of capacity constraints RNN. In this new approach, CWBPR system partition database in the cloud server, a pattern record set, and then figure out they were separate sections for each value of W and θ. CWBPR system to deal with each of the last segment of the pattern recognition work. Pattern recognition technology for the network, the paper has two simulation experiments are clearly discussed. The first experiment identified a number of characters; the second experiment is the pattern recognition of industrial components. Finally, the paper also put forward innovative pattern recognition method to the traditional text input search method comparison.

[1]  Robert P. W. Duin,et al.  Superlearning and neural network magic , 1994, Pattern Recognit. Lett..

[2]  Ricardo Azevedo,et al.  User Provided Cloud Computing , 2010, 2010 10th IEEE/ACM International Conference on Cluster, Cloud and Grid Computing.

[3]  Dennis Gannon,et al.  The Client and the Cloud: Democratizing Research Computing , 2011, IEEE Internet Computing.

[4]  Sungyoung Lee,et al.  Adoption issues for cloud computing , 2009, iiWAS.

[5]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[6]  Z. Tan,et al.  PATTERN RECOGNITION WITH STOCHASTIC RESONANCE IN A GENERIC NEURAL NETWORK , 2000 .

[7]  R. Lippmann,et al.  An introduction to computing with neural nets , 1987, IEEE ASSP Magazine.

[8]  Martin Hasler,et al.  Recursive neural networks for associative memory , 1990, Wiley-interscience series in systems and optimization.

[9]  W. A. Little,et al.  Analytic study of the memory storage capacity of a neural network , 1978 .

[10]  Jinwen Ma.  A Neural Network Approach to Real-Time Pattern Recognition , 2001, Int. J. Pattern Recognit. Artif. Intell..

[11]  Giles,et al.  Searching the world wide Web , 1998, Science.

[12]  Subhash Kak.  Better Web Searches and Prediction with Instantaneously Trained Neural Networks , 1999 .

[13]  Yue Sun,et al.  Cloud Computing Based Internet Data Center , 2009, CloudCom.

[14]  Youry Khmelevsky,et al.  Cloud computing infrastructure prototype for university education and research , 2010, WCCCE.

[15]  Roelof K. Brouwer.  An integer recurrent artificial neural network for classifying feature vectors , 1999, ESANN.

[16]  Roelof K. Brouwer.  A Fuzzy Recurrent Artificial Neural Network (FRANN) for Pattern Classification , 2000, Int. J. Uncertain. Fuzziness Knowl. Based Syst..

[17]  J. Hopfield,et al.  Computing with neural circuits: a model. , 1986, Science.

[18]  Hugh Garraway.  Parallel Computer Architecture: A Hardware/Software Approach , 1999, IEEE Concurrency.

[19]  John J. Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities , 1999 .

[20]  Robert P. W. Duin,et al.  The effective capacity of multilayer feedforward network classifiers , 1994, Proceedings of the 12th IAPR International Conference on Pattern Recognition, Vol. 3 - Conference C: Signal Processing (Cat. No.94CH3440-5).

[21]  C. Lee Giles,et al.  Searching the Web: general and scientific information access , 1999, First IEEE/POPOV Workshop on Internet Technologies and Services. Proceedings (Cat. No.99EX391).

[22]  Kwok-wai Joseph Lee,et al.  Information retrieval on the world wide web , 2001 .

[23]  Sameer Singh,et al.  A Long Memory Pattern Modelling and Recognition System for Financial Time-Series Forecasting , 1999, Pattern Analysis & Applications.

[24]  Daniel J. Amit,et al.  Modeling brain function: the world of attractor neural networks, 1st Edition , 1989 .

[25]  Hongjun Lu,et al.  Integrating database and World Wide Web technologies , 2004, World Wide Web.