Research on Abnormal Data Processing Method in Intelligent Data Adapter Based on Bayesian Network

Ping Hao; Bin Li Lu

doi:10.4028/www.scientific.net/AMR.765-767.1190

Paper Titles

The Study of Logistics Distribution Routing Optimization Problem Based on B2C E-Commerce
p.1173

Research on the Customized Color Mapping Technology of Reservoir 3D Display
p.1177

Unified Traceability Information System of Logistics Pallet Based on the Internet of Things
p.1181

A Semantic Parsing Model Applied into Search Engine
p.1186

Research on Abnormal Data Processing Method in Intelligent Data Adapter Based on Bayesian Network
p.1190

A Global Optimization Approach for Solving the D.C. Multiplicative Programming Problem
p.1196

Generating High-Quality Random Numbers by Next Nearest-Neighbor Cellular Automata
p.1200

User Behavior Analysis Based on Gn Interface of GPRS Network
p.1205

Geographical Information Services Classification Based on FCA - A Case Study in Vector Spatial Statistic Analysis
p.1210

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 765-767Research on Abnormal Data Processing Method in...

Research on Abnormal Data Processing Method in Intelligent Data Adapter Based on Bayesian Network

Abstract:

This paper put forward a bayesian network junction tree reasoning and rule reasoning hybrid algorithm to solve the adaptation problem in Public Data Center of heterogeneous system, based on the research in intelligent data processing method. Using adapters dynamic data monitoring function, first, pick out all abnormal data. then, apply the hybrid algorithm on the abnormal data. finally, recover the abnormal data and report abnormal processing result. This method has been applied to many domestic universitiess intelligent data exchange system in the Public Data Center. Through practice, this algorithm can effectively improve the reliability and integrity in heterogeneous data exchange system, and obtained good application effect.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 765-767)

Pages:

1190-1195

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.765-767.1190

Citation:

Cite this paper

Online since:

September 2013

Authors:

Ping Hao, Bin Li Lu

Keywords:

Bayesian Network (BN), Data Mining (DM), Heterogeneous Data Processing, Junction Tree Reasoning, Probability Inference

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] PEAR. J. Probabilistic Reasoning in Intelligent Systems; Networks of Plausibale Inference[M]. San Francisco; Morgan Kaufmann, 1988; 62-65.

Google Scholar

[2] HUANG C, DARWICHE A. Inference in Bayesian Networks; a Procedural Guide[J]. International Journal of Approximate Reasoning, 1994(11); 1-158.

Google Scholar

[3] Murphy K P. A variational approximation for bayesian networks with discrete and Continuous Latent Variables[EB/OL]. htpp: /www. berkeley. edu/ - murphy/publ. 2005-05-14.

Google Scholar

[4] Kjaerulff U, Hugin D. A computational system for dynamic time-sliced Bayesian networks [J]. International Journal of Forecasting, Special Issue on Probability Forcasting, 1994, 19(10); 1-3.

Google Scholar

[5] Gregory F Cooper, Edward Hemkovits. A Bayesian method for the induction of probability networks from data[J]. Machine Learning(S0885 - 6125). 1992, 9(4); 309-347.

Google Scholar

[6] Philippe Galinier, Michel Habib, Christophe Paul. Chordal graphs and ther clique graphs [EB/OL]. http: /citeseer. nj. ncc. com/galinier95chordal. html (2003).

Google Scholar

[7] B. Boerlage, Link Strengths in Bayesian networks, Master's thesis, Dept of Computer Science, U. of British Columbia (1995).

Google Scholar

[8] Kevin Patrick Murphy et. al, The Bayes Net Toolbox for Matlab, http: /www. ai. mit. edu/~murphyk/Software/BNT/bnt. html.

Google Scholar