To use SVM to detect DDoS precisely, the features vector that can distinguish normal stream from attack stream is required. According to the characters of DDoS, a group of relative values features (RLT features) are proposed. For indicating the existence and intensity of DDoS attack simultaneously, multi-class SVM (MCSVM) is introduced to DDoS detection. As shown in the emulation experiments, our method can detect various DDoS attacks effectively and indicate the attack intensity. The detection result is better than other present detection measures. Because RLT features include more attack information than the detection measures using single attack character, a better detection result is available.
{"title":"DDoS Attack Detection Based on RLT Features","authors":"Tu Xu, Dake He, Yu Luo","doi":"10.1109/CIS.2007.56","DOIUrl":"https://doi.org/10.1109/CIS.2007.56","url":null,"abstract":"To use SVM to detect DDoS precisely, the features vector that can distinguish normal stream from attack stream is required. According to the characters of DDoS, a group of relative values features (RLT features) are proposed. For indicating the existence and intensity of DDoS attack simultaneously, multi-class SVM (MCSVM) is introduced to DDoS detection. As shown in the emulation experiments, our method can detect various DDoS attacks effectively and indicate the attack intensity. The detection result is better than other present detection measures. Because RLT features include more attack information than the detection measures using single attack character, a better detection result is available.","PeriodicalId":127238,"journal":{"name":"2007 International Conference on Computational Intelligence and Security (CIS 2007)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129076506","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Support Vector Machines (SVMs) have become one of the most popular methods in Machine Learning during the last few years, but its performance mainly depends on the selection of optimal parameters which is very complex. In this study, the SCEM-UA algorithm developed by Vrugt is employed for parameters selection of Support Vector Regression (SVR). The SCEM-UA algorithm, which operates by merging the strengths of the Metropolis algorithm, controlled random search, competitive evolution, and complex shuffling, can avoid the tendency of falling into local minima. The proposed method was tested on a complicated nonlinearly runoff forecasting. The results illustrated that SCEM-UA algorithm can successfully identify the optimal parameters of SVR than grid search method, and can achieve an accurate prediction. Keywords: Support Vector Machines; Optimization; SCEM-UA; Time series; Forecasting
{"title":"Parameters Selection for SVR Based on the SCEM-UA Algorithm and its Application on Monthly Runoff Prediction","authors":"Liu Ji, W. Bende","doi":"10.1109/CIS.2007.29","DOIUrl":"https://doi.org/10.1109/CIS.2007.29","url":null,"abstract":"Support Vector Machines (SVMs) have become one of the most popular methods in Machine Learning during the last few years, but its performance mainly depends on the selection of optimal parameters which is very complex. In this study, the SCEM-UA algorithm developed by Vrugt is employed for parameters selection of Support Vector Regression (SVR). The SCEM-UA algorithm, which operates by merging the strengths of the Metropolis algorithm, controlled random search, competitive evolution, and complex shuffling, can avoid the tendency of falling into local minima. The proposed method was tested on a complicated nonlinearly runoff forecasting. The results illustrated that SCEM-UA algorithm can successfully identify the optimal parameters of SVR than grid search method, and can achieve an accurate prediction. Keywords: Support Vector Machines; Optimization; SCEM-UA; Time series; Forecasting","PeriodicalId":127238,"journal":{"name":"2007 International Conference on Computational Intelligence and Security (CIS 2007)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121691100","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Lejun Zhang, Lin Guo, Wu Yang, Wei Wang, Yongtian Yang
This paper presents an efficient survivability hierarchy analysis method for networked information system. In the hierarchical model, the top level is the survivability of system; the second is the survivability of essential service; the third is the survivability of atomic module; the lowest one is vulnerability. With the help of attack graph, the survivability (3R+A) is quantified according the records of the Qos before and after attack. Key words: survivability, hierarchical model
{"title":"An Efficient Survivability Hierarchy Analysis Model for Networked Information System","authors":"Lejun Zhang, Lin Guo, Wu Yang, Wei Wang, Yongtian Yang","doi":"10.1109/CIS.2007.110","DOIUrl":"https://doi.org/10.1109/CIS.2007.110","url":null,"abstract":"This paper presents an efficient survivability hierarchy analysis method for networked information system. In the hierarchical model, the top level is the survivability of system; the second is the survivability of essential service; the third is the survivability of atomic module; the lowest one is vulnerability. With the help of attack graph, the survivability (3R+A) is quantified according the records of the Qos before and after attack. Key words: survivability, hierarchical model","PeriodicalId":127238,"journal":{"name":"2007 International Conference on Computational Intelligence and Security (CIS 2007)","volume":"112 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127970044","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Wei Jiang, Hongli Zhang, Zhihong Tian, Xin-fang Song
This paper presents a game-theoretic method for analyzing the active defense of computer networks. We regard the interactions between an attacker and the defender as a two-player, non-cooperative, zero-sum, finite game and formulate an attack-defense game (ADG) model for the game. An optimal active defense strategy decision (OADSD) algorithm is developed using the ADG and cost-sensitive model. Optimal defense strategies with minimizing costs are used to defend the attack and harden the network in advance. Finally, experiments show that our ADG model and the OADSD algorithm are effective in reducing the overall cost of defense systems and defend attacks that may occur in the future.
{"title":"A Game Theoretic Method for Decision and Analysis of the Optimal Active Defense Strategy","authors":"Wei Jiang, Hongli Zhang, Zhihong Tian, Xin-fang Song","doi":"10.1109/CIS.2007.31","DOIUrl":"https://doi.org/10.1109/CIS.2007.31","url":null,"abstract":"This paper presents a game-theoretic method for analyzing the active defense of computer networks. We regard the interactions between an attacker and the defender as a two-player, non-cooperative, zero-sum, finite game and formulate an attack-defense game (ADG) model for the game. An optimal active defense strategy decision (OADSD) algorithm is developed using the ADG and cost-sensitive model. Optimal defense strategies with minimizing costs are used to defend the attack and harden the network in advance. Finally, experiments show that our ADG model and the OADSD algorithm are effective in reducing the overall cost of defense systems and defend attacks that may occur in the future.","PeriodicalId":127238,"journal":{"name":"2007 International Conference on Computational Intelligence and Security (CIS 2007)","volume":"111 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115883533","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In the paper, we discuss the relationship between the membership function of the fuzzy control system and the wavelet basis function. We prove that a wavelet mother function can be described by a membership function of the fuzzy control system and a membership function of the fuzzy control system can also be described by a simple wavelet mother function. The one-to-one corresponding relationship between the membership function of the fuzzy control system and the wavelet basis function is verified. Thus the essence of the fuzzy reasoning and fuzzy control is revealed. This paper presents a new approach to applying wavelet analysis to fuzzy system identification, fuzzy control and fuzzy data analysis, etc.
{"title":"Fuzzy Control System Based on Wavelet Analysis","authors":"Rui Wang, Zhao-ming Lei, Hexu Sun, Yi Zheng","doi":"10.1109/CIS.2007.86","DOIUrl":"https://doi.org/10.1109/CIS.2007.86","url":null,"abstract":"In the paper, we discuss the relationship between the membership function of the fuzzy control system and the wavelet basis function. We prove that a wavelet mother function can be described by a membership function of the fuzzy control system and a membership function of the fuzzy control system can also be described by a simple wavelet mother function. The one-to-one corresponding relationship between the membership function of the fuzzy control system and the wavelet basis function is verified. Thus the essence of the fuzzy reasoning and fuzzy control is revealed. This paper presents a new approach to applying wavelet analysis to fuzzy system identification, fuzzy control and fuzzy data analysis, etc.","PeriodicalId":127238,"journal":{"name":"2007 International Conference on Computational Intelligence and Security (CIS 2007)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132213216","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In order to recognize and track all of the heads exactly in top view images, a novel approach of 3D feature extraction of heads based on target region matching is presented. The main idea starts from the disparity of head region, which is generally extracted in global dense disparity image obtained by block matching method. Deferent from the block matching, the correspondence searching in target region matching is not done in the regions around every pixel in image but in the candidate head regions extracted in advance by monocular image processing. As the number of candidate head regions is far less than the resolution of image, the computational complexity and time consume can be largely reduced. After the disparity of candidate head regions are obtained, the 3D features of head, including the height feature and the perspective feature, can be extracted to largely improve the accuracy of head recognition.
{"title":"3D Feature Extraction of Head based on Target Region Matching","authors":"Haibin Yu, Jilin Liu, Jingbiao Liu","doi":"10.1109/CIS.2007.87","DOIUrl":"https://doi.org/10.1109/CIS.2007.87","url":null,"abstract":"In order to recognize and track all of the heads exactly in top view images, a novel approach of 3D feature extraction of heads based on target region matching is presented. The main idea starts from the disparity of head region, which is generally extracted in global dense disparity image obtained by block matching method. Deferent from the block matching, the correspondence searching in target region matching is not done in the regions around every pixel in image but in the candidate head regions extracted in advance by monocular image processing. As the number of candidate head regions is far less than the resolution of image, the computational complexity and time consume can be largely reduced. After the disparity of candidate head regions are obtained, the 3D features of head, including the height feature and the perspective feature, can be extracted to largely improve the accuracy of head recognition.","PeriodicalId":127238,"journal":{"name":"2007 International Conference on Computational Intelligence and Security (CIS 2007)","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131781662","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Improved Variable Precision Rough Set (VPRS) is proposed to extract the significant decision rules from a Student Information Table (SIT) in the distance learning environment. Moreover, two approaches are proposed. The first approach, VPRS based on Bayesian Confirmation Measures (BCM) is presented in order to handle totally ambiguous and enhance the precision of Rough set, and to deal with multi decision classes. The second approach, the VPRS parameters are refined, especially with multi decision classes. These concepts have been demonstrated by an example. The simulated result gives good accuracy and precise information with few computational steps.
{"title":"Improved Variable Precision Rough Set Model and its Application to Distance Learning","authors":"A. Abbas, Juan Liu, S. O. Mahdi","doi":"10.1109/CIS.2007.41","DOIUrl":"https://doi.org/10.1109/CIS.2007.41","url":null,"abstract":"Improved Variable Precision Rough Set (VPRS) is proposed to extract the significant decision rules from a Student Information Table (SIT) in the distance learning environment. Moreover, two approaches are proposed. The first approach, VPRS based on Bayesian Confirmation Measures (BCM) is presented in order to handle totally ambiguous and enhance the precision of Rough set, and to deal with multi decision classes. The second approach, the VPRS parameters are refined, especially with multi decision classes. These concepts have been demonstrated by an example. The simulated result gives good accuracy and precise information with few computational steps.","PeriodicalId":127238,"journal":{"name":"2007 International Conference on Computational Intelligence and Security (CIS 2007)","volume":"304 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132975569","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
JongSeon Lim, Kyung-Soo Joo, KyungSoo Kim, Mun-Young Choi
With the recent expansion of e-commerce, B2B has surfaced as an area of substantial interest to the corporate world. B2B refers to economic transactions created among businesses through various networks, including the Internet. Currently, XML documents are partially used in e-commerce for exchanging information among businesses, and the core corporate systems are expected to be based on XML as web service becomes more prevalent. In turn, many companies are becoming competitively involved in developing XML DBMS. Conventional XML DBMS studies use XML DTD to express the XML document structure. Since XML DTD defines simple format expressions, there are numerous difficulties in defining the XML document structure. In order to overcome such issues, this paper proposes an automatic conversion mechanism and algorithm for the relational database schema using the XML schema, which as been selected as the W3C standard, in order to store XML data in the relational database generally used in data content storage based on the XML schema. Furthermore, a module will be develop for converting the XML schema design based on this approach into a relational database schema. This should allow efficient management of the XML data through the relational database.
{"title":"Design of Automatic Database Schema Generator Based on XML Schema","authors":"JongSeon Lim, Kyung-Soo Joo, KyungSoo Kim, Mun-Young Choi","doi":"10.1109/CIS.2007.222","DOIUrl":"https://doi.org/10.1109/CIS.2007.222","url":null,"abstract":"With the recent expansion of e-commerce, B2B has surfaced as an area of substantial interest to the corporate world. B2B refers to economic transactions created among businesses through various networks, including the Internet. Currently, XML documents are partially used in e-commerce for exchanging information among businesses, and the core corporate systems are expected to be based on XML as web service becomes more prevalent. In turn, many companies are becoming competitively involved in developing XML DBMS. Conventional XML DBMS studies use XML DTD to express the XML document structure. Since XML DTD defines simple format expressions, there are numerous difficulties in defining the XML document structure. In order to overcome such issues, this paper proposes an automatic conversion mechanism and algorithm for the relational database schema using the XML schema, which as been selected as the W3C standard, in order to store XML data in the relational database generally used in data content storage based on the XML schema. Furthermore, a module will be develop for converting the XML schema design based on this approach into a relational database schema. This should allow efficient management of the XML data through the relational database.","PeriodicalId":127238,"journal":{"name":"2007 International Conference on Computational Intelligence and Security (CIS 2007)","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127582076","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A multilayer recurrent fuzzy neural network (MRFNN) is proposed for dynamic system modeling in this paper. The proposed MRFNN has six layers combined with T-S fuzzy model. The recurrent structures are formed by local feedback connections in the membership layer and the rule layer. With these feedbacks, the fuzzy sets are time-varying and the temporal problem of dynamic system can be solved well. The parameters of MRFNN are learned by modified chaotic search (CS) and least square estimation (LSE) simultaneously, where CS is for tuning the premise parameters and LSE is for updating the consequent coefficients accordingly. Simulation results of chaos system identification show the proposed approach is effective for dynamic system modeling with high accuracy. And then the proposed approach is applied to a batch reactor modeling.
{"title":"Dynamic System Modeling with Multilayer Recurrent Fuzzy Neural Network","authors":"He Liu, Dao-huo Huang, L. Jia","doi":"10.1109/CIS.2007.34","DOIUrl":"https://doi.org/10.1109/CIS.2007.34","url":null,"abstract":"A multilayer recurrent fuzzy neural network (MRFNN) is proposed for dynamic system modeling in this paper. The proposed MRFNN has six layers combined with T-S fuzzy model. The recurrent structures are formed by local feedback connections in the membership layer and the rule layer. With these feedbacks, the fuzzy sets are time-varying and the temporal problem of dynamic system can be solved well. The parameters of MRFNN are learned by modified chaotic search (CS) and least square estimation (LSE) simultaneously, where CS is for tuning the premise parameters and LSE is for updating the consequent coefficients accordingly. Simulation results of chaos system identification show the proposed approach is effective for dynamic system modeling with high accuracy. And then the proposed approach is applied to a batch reactor modeling.","PeriodicalId":127238,"journal":{"name":"2007 International Conference on Computational Intelligence and Security (CIS 2007)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115449504","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The neural network was conducted based on the Takagi-Sugeno fuzzy systems. Predictions of the biogas production rate, volatile fatty acid and CH4 for the UASB reactor were made using fuzzy neural network based on database collected from the anaerobic system shocked by the Chloroform and 2, 4-dinitrophenol loading. The correlation coefficients of observed and simulated values were above 0.940 for the training set, and above 0.860 for testing set. The results showed that fuzzy neural network can perfectly predict the performance of UASB shocked by the toxic loading, and has greatly adaptability to the variations of the anaerobic treatment system .
{"title":"Simulation of T-S Fuzzy Neural Network to UASB Reactor Shocked by Toxic Loading","authors":"Gang Cao, Mingyu Li, Cehui Mo","doi":"10.1109/CIS.2007.27","DOIUrl":"https://doi.org/10.1109/CIS.2007.27","url":null,"abstract":"The neural network was conducted based on the Takagi-Sugeno fuzzy systems. Predictions of the biogas production rate, volatile fatty acid and CH4 for the UASB reactor were made using fuzzy neural network based on database collected from the anaerobic system shocked by the Chloroform and 2, 4-dinitrophenol loading. The correlation coefficients of observed and simulated values were above 0.940 for the training set, and above 0.860 for testing set. The results showed that fuzzy neural network can perfectly predict the performance of UASB shocked by the toxic loading, and has greatly adaptability to the variations of the anaerobic treatment system .","PeriodicalId":127238,"journal":{"name":"2007 International Conference on Computational Intelligence and Security (CIS 2007)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116430558","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：