Research on the Detection Method of the Malicious Attacks on Campus Network

2014 ◽  
Vol 644-650 ◽  
pp. 3291-3294
Author(s):  
Jing Lei Wang
Keyword(s):  
Support Vector Machine ◽  
Detection Method ◽  
Attack Detection ◽  
Support Vector ◽  
Detection Accuracy ◽  
Campus Network ◽  
Malicious Attacks ◽  
Accuracy Rate ◽  
Malicious Attack ◽  
Conventional Manner

The problem of malicious attacks detection on campus network is studied to improve the accuracy of detection. When detecting malicious attacks on campus network, a conventional manner is usually conducted in malicious attack detection of campus network. If a malicious signature is mutated into a new feature, the conventional detection method cannot recognize the new malicious signature, resulting in a relative low detection accuracy rate of malicious attacks. To avoid these problems, in this paper, the malicious attacks detection method for campus network based on support vector machine algorithm is proposed. The plane of support vector machine classification is constructed, to complete the malicious attacks detection of campus network. Experiments show that this approach can improve the accuracy rate of the malicious attack detection, and achieve satisfactory results.

Eye Detection Using Color, Haar Features, and Efficient Support Vector Machine

2012 ◽  
pp. 286-309
Author(s):  
Shuo Chen ◽  
Chengjun Liu
Keyword(s):  
Support Vector Machine ◽  
Face Recognition ◽  
Detection Method ◽  
Support Vector ◽  
Grand Challenge ◽  
Detection Accuracy ◽  
Eye Detection ◽  
Color Information ◽  
Haar Features ◽  
Improved Performance

Eye detection is an important initial step in an automatic face recognition system. Though numerous eye detection methods have been proposed, many problems still exist, especially in the detection accuracy and efficiency under challenging image conditions. The authors present a novel eye detection method using color information, Haar features, and a new efficient Support Vector Machine (eSVM) in this chapter . In particular, this eye detection method consists of two stages: the eye candidate selection and validation. The selection stage picks up eye candidates over an image through color information, while the validation stage applies 2D Haar wavelet and the eSVM to detect the center of the eye among these candidates. The eSVM is defined on fewer support vectors than the standard SVM, which can achieve faster detection speed and higher or comparable detection accuracy. Experiments on Face Recognition Grand Challenge (FRGC) database show the improved performance over existing methods on both efficiency and accuracy.

scholarly journals Establishment of Relational Model of Congenital Heart Disease Markers and GO Functional Analysis of the Association between Its Serum Markers and Susceptibility Genes

2016 ◽  
Vol 2016 ◽  
pp. 1-14 ◽  
Author(s):  
Min Liu ◽  
Luosha Zhao ◽  
Jiaying Yuan
Keyword(s):  
Support Vector Machine ◽  
Congenital Heart Disease ◽  
Heart Disease ◽  
Congenital Heart ◽  
Susceptibility Genes ◽  
Serum Markers ◽  
Relational Model ◽  
Support Vector ◽  
Detection Accuracy ◽  
Accuracy Rate

Purpose. The purpose of present study was to construct the best screening model of congenital heart disease serum markers and to provide reference for further prevention and treatment of the disease.Methods. Documents from 2006 to 2014 were collected and meta-analysis was used for screening susceptibility genes and serum markers closely related to the diagnosis of congenital heart disease. Data of serum markers were extracted from 80 congenital heart disease patients and 80 healthy controls, respectively, and then logistic regression analysis and support vector machine were utilized to establish prediction models of serum markers and Gene Ontology (GO) functional annotation.Results. Results showed that NKX2.5, GATA4, and FOG2 were susceptibility genes of congenital heart disease. CRP, BNP, and cTnI were risk factors of congenital heart disease (p<0.05); cTnI, hs-CRP, BNP, and Lp(a) were significantly close to congenital heart disease (p<0.01). ROC curve indicated that the accuracy rate of Lp(a) and cTnI, Lp(a) and BNP, and BNP and cTnI joint prediction was 93.4%, 87.1%, and 97.2%, respectively. But the detection accuracy rate of the markers’ relational model established by support vector machine was only 85%. GO analysis suggested that NKX2.5, GATA4, and FOG2 were functionally related to Lp(a) and BNP.Conclusions. The combined markers model of BNP and cTnI had the highest accuracy rate, providing a theoretical basis for the diagnosis of congenital heart disease.

Damage Identification for Simply-Supported Bridge Based on SVM Optimized by PSO (PSO-SVM)

2011 ◽  
Vol 80-81 ◽  
pp. 490-494 ◽  
Author(s):  
Han Bing Liu ◽  
Yu Bo Jiao ◽  
Ya Feng Gong ◽  
Hai Peng Bi ◽  
Yan Yi Sun
Keyword(s):  
Support Vector Machine ◽  
Classification Accuracy ◽  
Damage Identification ◽  
Fitness Function ◽  
Support Vector ◽  
Detection Accuracy ◽  
Damage Localization ◽  
Swarm Optimization ◽  
Simply Supported ◽  
Beam Bridge

A support vector machine (SVM) optimized by particle swarm optimization (PSO)-based damage identification method is proposed in this paper. The classification accuracy of the damage localization and the detection accuracy of severity are used as the fitness function, respectively. The best and can be obtained through velocity and position updating of PSO. A simply supported beam bridge with five girders is provided as numerical example, damage cases with single and multiple suspicious damage elements are established to verify the feasibility of the proposed method. Numerical results indicate that the SVM optimized by PSO method can effectively identify the damage locations and severity.

scholarly journals Combustible Gas Classification Modeling using Support Vector Machine and Pairing Plot Scheme

Sensors ◽  
2019 ◽  
Vol 19 (22) ◽  
pp. 5018 ◽  
Author(s):  
Kyu-Won Jang ◽  
Jong-Hyeok Choi ◽  
Ji-Hoon Jeon ◽  
Hyun-Seok Kim
Keyword(s):  
Support Vector Machine ◽  
Gas Sensors ◽  
Learning Algorithm ◽  
Support Vector ◽  
Detection Accuracy ◽  
Minimum Concentration ◽  
Industrial Sites ◽  
Combustible Gas ◽  
Proposed Model ◽  
Combustible Gases

Combustible gases, such as CH4 and CO, directly or indirectly affect the human body. Thus, leakage detection of combustible gases is essential for various industrial sites and daily life. Many types of gas sensors are used to identify these combustible gases, but since gas sensors generally have low selectivity among gases, coupling issues often arise which adversely affect gas detection accuracy. To solve this problem, we built a decoupling algorithm with different gas sensors using a machine learning algorithm. Commercially available semiconductor sensors were employed to detect CH4 and CO, and then support vector machine (SVM) applied as a supervised learning algorithm for gas classification. We also introduced a pairing plot scheme to more effectively classify gas type. The proposed model classified CH4 and CO gases 100% correctly at all levels above the minimum concentration the gas sensors could detect. Consequently, SVM with pairing plot is a memory efficient and promising method for more accurate gas classification.

scholarly journals Infrared–ultrasonic sensor fusion for support vector machine–based fall detection

2018 ◽  
Vol 29 (9) ◽  
pp. 2027-2039 ◽  
Author(s):  
Zhangjie Chen ◽  
Ya Wang
Keyword(s):  
Support Vector Machine ◽  
Sensor Fusion ◽  
Learning Algorithm ◽  
Fall Detection ◽  
Ultrasonic Sensor ◽  
Support Vector ◽  
Detection Accuracy ◽  
Data Recording ◽  
Fusion Algorithm ◽  
Average Accuracy

This article presents an infrared–ultrasonic sensor fusion approach for support vector machine–based fall detection, often required by elderly healthcare. Its detection algorithms and performance evaluation are detailed. The location, size, and temperature profile of the user can be estimated based on a novel sensory fusion algorithm. Different feature sets of the support vector machine–based machine learning algorithm are analyzed and their impact on fall detection accuracy is evaluated and compared empirically. Experiments study three non-fall activities, standing, sitting, and stooping, and two fall actions, forward falling and sideway falling, to simulate daily activities of the elderly. Fall detection accuracy studies are performed based on discretely and continuously (closer to reality) recorded experimental data, respectively. For the discrete data recording, an average accuracy of 92.2% is achieved when the stand-alone Grid-EYE is used and the accuracy is increased to 96.7% when sensor fusion is used. For the continuous data recording (180 training sets, 60 test sets at each distance), an average accuracy less than 70.0% is achieved when the stand-alone Grid-EYE is used and the accuracy is increased to around 90.3% after sensor fusion. New features will be explored in the next step to further increase detection accuracy.

Sign in / Sign up

Export Citation Format

Share Document