The Optimal Detection and Analysis for High-Degree Camouflaged Incursion Features Based on Improved BP Neural Network

Hong Li Lu

doi:10.4028/www.scientific.net/AMR.846-847.1538

Paper Titles

RFID Mutual Authentication Protocol Based on Chaos Key
p.1519

Research on Hash-Based Low-Cost RFID Security Authentication Protocol
p.1524

Design and Realization of Efficient USB Data Transmission System Based on VB
p.1531

The Application of Computers in PACS System Regionalization
p.1534

The Optimal Detection and Analysis for High-Degree Camouflaged Incursion Features Based on Improved BP Neural Network
p.1538

Monitoring System Design for Ships Network
p.1542

Emergency Simulation Exercise System Research Based on the Dynamic Information Repository
p.1546

Building Intelligent Parking Lot Based on RFID and Cloud Computing Technology
p.1550

Database Design on English Learning Resources Website Based on Oracle
p.1554

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 846-847The Optimal Detection and Analysis for High-Degree...

The Optimal Detection and Analysis for High-Degree Camouflaged Incursion Features Based on Improved BP Neural Network

Abstract:

In order to effectively increase the incursion features detection accuracy with high-degree camouflage in the network, this paper proposes a high-degree camouflaged incursion features detection algorithm based on BP neural network. This paper utilizes distributed components to collect and analyze the incursion data features with high-degree camouflage, and designs an incursion features detection proxy module based on BP neural network. This paper takes the protocol platform developed by some company in Zhengzhou city as an example to detect the incursion of malicious information and presents the detailed diagnose methods and procedures in which the accuracy can reach up to 93.7%.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 846-847)

Pages:

1538-1541

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.846-847.1538

Citation:

Cite this paper

Online since:

November 2013

Authors:

Hong Li Lu*

Keywords:

BP Neural Network (BPNN), Incursion Features Detection, Mobile Agent

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] Guoqing Li, Bin Zhang, Shuhong Li, Wei Fang Rong Sun, The Study of Crew Physical and Psychological Evaluation Model and Sports Intervention Method, IJACT, Vol. 5, No. 1, p.20 ~ 28, (2013).

Google Scholar

[2] Desheng Liu, Keqi Wang, Flow Meter online Compensation Based on Neural Network Algorithm, IJACT, Vol. 5, No. 1, p.297 ~ 303, (2013).

Google Scholar

[3] Limin Luo, zhen Zhou, Based on the network security intrusion characteristics testing technology research, [J]Bulletin of Science and Technology, 2012, 28(4): 114-117.

Google Scholar

[4] Yu Zhou, Chuan Zhang, Xiaoming Zhou, Study on EEG Password Based on Brain Friend Mode, IJACT, Vol. 5, No. 1, p.733 ~ 741, (2013).

Google Scholar

[5] Haijun Xiao, Fan Hong, Zhaoli Zhang, Junguo Liao. Invasion characteristics of classification and support vector machine (SVM) based on fusion detection research, , [J] Computer Emulation, 2008, 25(4): 130-132.

Google Scholar

[6] Defan Zhou, Jingang Jiang, Chunling Luo, Yao Chen, Multi-Objective Flexible Job-Shop Scheduling Method Study Based on The Integration Algorithm of GA-BP, JDCTA, Vol. 7, No. 2, p.109 ~ 116, (2013).

DOI: 10.4156/jdcta.vol7.issue2.12

Google Scholar