Multi-wheel graph neuron: a distributed associative memory for structured P2P networks
Pages 147 - 154
Abstract
The significant growing amount of shared files in distributed and serverless P2P networks has impacted heavily on content management and retrieval field. In this paper, we propose an associative memory network with intention to provide efficient pattern recognition within P2P networks. An efficient pattern recognition algorithm which works within distributed and dynamic nature of P2P network would be beneficial for better content handling and distribution. Our approach, which is called multi-wheel Graph Neuron (mWGN), is a variant of Graph Neuron (GN)-based algorithm built on top of Chord overlay network. GN algorithm is an associative memory designed for wireless sensor environment. mWGN is a restructured design from Hierarchical Graph Neuron (HGN), preserving its single cycle learning, lightweight and accuracy feature while requiring fewer number of nodes. Result from the experiment shows the proposed approach is highly accurate and the fault tolerance of Chord protocol provides stability for the proposed approach.
References
[1]
S. N. Srihari, S. H. Cha, and S. Lee, "Establishing handwriting individuality using pattern recognition techniques." Proc. ICDAR'2001, pp. 1195--1204, Seattle, Sept. 2001.
[2]
T. Liang, and Y. Pi, "On Spam Detection Based on Cognitive Pattern Recognition." Proc. International Conference on Computational Intelligence and Security Workshops, pp. 136--139, Heilongjiang, China, Dec. 2007.
[3]
B. Mosbah, "Speech Recognition for Disabilities People Information and Communication Technologies." Proc. ICTTA '06, pp. 864--869, Damascus, Syria, April 2006.
[4]
A. I. Khan, M. Baqer, and Z. A. Baig, "Implementing a graph neuron array for pattern recognition within unstructured wireless sensor networks," Lecture Notes in Computer Science, Springer-Verlag, pp. 208--217, 2006.
[5]
A. Ahmadi, Y. Shirakawa, A. Abedin et al., "An LSI hardware design for online character recognition using ssociative memory." Proc. 48th IEEE International Midwest Symposium on Circuits and Systems, pp. 464--467, Cincinnati, Ohio, August 2005.
[6]
B. B. Nasution, and A. I. Khan, "A Hierarchical Graph Neuron Scheme for Real-Time Pattern Recognition," IEEE Transactions on Neural Networks, vol. 19, no. 2, pp. 212--229, Feb 2008.
[7]
J. J. Hopfield, "Neural networks and physical systems with emergent collective computational properties." Proceedings of the National Academy of Sciences, 79, pp. 2554--2558.
[8]
P. Picton, Neural Networks, 2nd ed., New York: Palgrave, 2000.
[9]
B. Kosko, "Bidirectional associative memories," IEEE Transactions on Systems, Man and Cybernetics, Part B, vol. 17, pp. 59--68, 2006.
[10]
G. X. Ritter, P. Sussner, and J. L. Diaz-de-Leon, "Morphological associative memories," IEEE Trans. Neural Netw., vol. 9, no. 2, pp. 281--292, March 1998.
[11]
W. Lipo, "Multi-associative neural networks and their application to learning and retrieving complex spatio temporal sequences," IEEE Trans. Syst., Man, Cybern. B, Cybern, vol. 29, no. 1, pp. 73--83, Feb 1999.
[12]
C. Y. Liou, and S. K. Yuan, "Error tolerant associative memory," Biological Cybernetics, vol. 81, pp. 331--342, 1999.
[13]
S. Chartier, and M. Noukadoum, "A sequential dynamic heteroassociation memory for multistep pattern recognition and one to many association," IEEE Trans. Neural Netw., vol. 17, no. 1, pp. 59--68, 2006.
[14]
B. Murdock, "A theory for the storage and retrieval of item and associative information," Psychological Review, vol. 89, pp. 17, 1982.
[15]
R. Perfetti, and E. Ricci, "Recurrent Correlation Associative Memory," IEEE Transactions on Neural Networks, vol. 19, no. 2, pp. 333--345, Feb 2008.
[16]
H. C. Choi, and S. Y. Oh, "Efficient Human-like Memory Management based on Walsh-based Associative Memory for Real-time Pattern Recognition." Proc. IJCNN'06, Vancouver, Canada, pp. 3657--3663, July 2006.
[17]
A. I. Khan, "A peer-to-peer associative memory for intelligent information systems." Proc. 13th Australasian Conference on Information Systems, Vol. 1, pp. 317--326, Melbourne, Australia, Dec. 2002.
[18]
J. L. Gross, and J. Yellen, Graph Theory and its applications: CRC Press, 1998.
[19]
A. H. M. Amin, and A. I. Khan, "Single-Cycle Image Recognition Using an Adaptive Granularity Associative Memory Network." Proc. Australasian Conference on Artificial Intelligence 2008, pp. 386--392, Auckland, New Zealand, Dec. 2008.
[20]
I. Stoica, R. Morris, D. Karger et al., "Chord: A scalable peer-to-peer lookup protocol for internet applications," IEEE/ACM Transactions on Networking, vol. 22, no. 1, pp. 12, Jan 2004.
[21]
E. K. Lua, J. Crowcroft, R. S. M. Pias et al., "A Survey and Comparison of Peer-to-Peer Overlay Network Schemes," IEEE Communications Surveys & Tutorials, vol. 7, no. 2, pp. 21, 2004.
Index Terms
- Multi-wheel graph neuron: a distributed associative memory for structured P2P networks
Recommendations
A Wheel Graph Structured Associative Memory for Single-Cycle Pattern Recognition within P2P Networks
WAINA '10: Proceedings of the 2010 IEEE 24th International Conference on Advanced Information Networking and Applications WorkshopsA novel and efficient associative-memory-based pattern recognition scheme within P2P networks is proposed and implemented. The proposed scheme, known as the multi-wheel Graph Neuron, is adapted from Graph Neuron-based algorithms which are single-cycle, ...
Building small worlds in unstructured P2P networks using a multiagent Bayesian inference mechanism
AAMAS '07: Proceedings of the 6th international joint conference on Autonomous agents and multiagent systemsOver the past few years, peer-to-peer(p2p) unstructured networks have emerged as an attractive paradigm for enabling online interactions between a large number of users in a decentralized manner. However, the decentralized nature of unstructured p2p ...
Measurements of topological characteristics for Peer-to-Peer systems
The popularity of Peer-to-Peer (P2P) file sharing applications such as Gnutella, Kazaa and eDonkey has created a considerable amount of research interest in P2P architectures. In order to evaluate a P2P network properly, we must take into account the ...
Comments
Information & Contributors
Information
Published In
December 2009
763 pages
ISBN:9781605586601
DOI:10.1145/1806338
- General Chair:
- Gabriele Kotsis,
- Program Chairs:
- David Taniar,
- Eric Pardede
Copyright © 2009 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]
Sponsors
- Johannes Kepler University
In-Cooperation
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 14 December 2009
Check for updates
Author Tags
Qualifiers
- Research-article
Conference
iiWAS '09
Sponsor:
iiWAS '09: 11th International Conference on Information Integration and Web-based Applications & Services
December 14 - 16, 2009
Kuala Lumpur, Malaysia
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 96Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 05 Mar 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in