The paper develops radial basis function neural networks (RBFNN) applications in the traffic signs recognition. Firstly traffic signs are detected by using their color and shape informations. Then genetic algorithm (GA), which has a powerful global exploration capability, is applied to train RBFNN to obtain appropriate structures and parameters according to given objective functions. In order to improve recognition speed and accuracy, traffic signs are classified into three categories by special color and shape information. Three RBFNNs are designed for the three categories. Before fed into networks, the sign images are transformed into binary images and their features are optimized by linear discriminate analysis (LDA). The training set imitating possible sign transformations in real road conditions, is created to train and test the nets. The experimental results show the feasibility and validity of the proposed algorithm.
{"title":"Traffic Signs Detection and Recognition by Improved RBFNN","authors":"Yangping Wang, Jianwu Dang, Zhengping Zhu","doi":"10.1109/CIS.2007.223","DOIUrl":"https://doi.org/10.1109/CIS.2007.223","url":null,"abstract":"The paper develops radial basis function neural networks (RBFNN) applications in the traffic signs recognition. Firstly traffic signs are detected by using their color and shape informations. Then genetic algorithm (GA), which has a powerful global exploration capability, is applied to train RBFNN to obtain appropriate structures and parameters according to given objective functions. In order to improve recognition speed and accuracy, traffic signs are classified into three categories by special color and shape information. Three RBFNNs are designed for the three categories. Before fed into networks, the sign images are transformed into binary images and their features are optimized by linear discriminate analysis (LDA). The training set imitating possible sign transformations in real road conditions, is created to train and test the nets. The experimental results show the feasibility and validity of the proposed algorithm.","PeriodicalId":127238,"journal":{"name":"2007 International Conference on Computational Intelligence and Security (CIS 2007)","volume":"25 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":"123365582","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 signature database of intrusion detection system is usually built by the short sequences of system call. The real-time efficiency and accuracy of intrusion detection is greatly influenced by the scale of signature database and the approach of intrusion data analysis. In this paper, a typical set method is provided to compress the normal signature database. Using the data set of UNM CERT sendmail for testing, the feasibility of typical set method is validated, and a proper rate of typical set for intrusion detection is proposed. Meanwhile, the LSM (Linux Security Modules) framework is presented to hook system calls and other audit data from operation system to build intrusion detection system signature database and identify intrusion activity. A system service process oriented detection idea is also introduced to make the intrusion detection more pertinent and accurate. Abnormal detection experiments results show good performance of our intrusion detection method.
{"title":"A Typical Set Method of Intrusion Detection Technology Base on Computer Audit Data","authors":"Du Xuetao, Ji Chunfu, Fu Yubing","doi":"10.1109/CIS.2007.75","DOIUrl":"https://doi.org/10.1109/CIS.2007.75","url":null,"abstract":"The signature database of intrusion detection system is usually built by the short sequences of system call. The real-time efficiency and accuracy of intrusion detection is greatly influenced by the scale of signature database and the approach of intrusion data analysis. In this paper, a typical set method is provided to compress the normal signature database. Using the data set of UNM CERT sendmail for testing, the feasibility of typical set method is validated, and a proper rate of typical set for intrusion detection is proposed. Meanwhile, the LSM (Linux Security Modules) framework is presented to hook system calls and other audit data from operation system to build intrusion detection system signature database and identify intrusion activity. A system service process oriented detection idea is also introduced to make the intrusion detection more pertinent and accurate. Abnormal detection experiments results show good performance of our intrusion detection method.","PeriodicalId":127238,"journal":{"name":"2007 International Conference on Computational Intelligence and Security (CIS 2007)","volume":"42 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":"126516248","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 this paper, first we proposed a method of attribute reduction based on rough set under fuzzy equivalent relation. We computed the similarity of cases with the fuzzy equivalent relation, reduced the attributes by the same fuzzy equivalent partitions based on rough set, and then gave a method of computing the weights of the attributes. Comparing with the traditional method of attribute reduction based on rough set, more information of the primary data is held, and more accuracy of the attribute reduction is enhanced by our method.
{"title":"A Study on the Method of Attribute Reduction Based on Rough Set under Fuzzy Equivalent Relation","authors":"Guorui Jiang, G. Zang","doi":"10.1109/CIS.2007.151","DOIUrl":"https://doi.org/10.1109/CIS.2007.151","url":null,"abstract":"In this paper, first we proposed a method of attribute reduction based on rough set under fuzzy equivalent relation. We computed the similarity of cases with the fuzzy equivalent relation, reduced the attributes by the same fuzzy equivalent partitions based on rough set, and then gave a method of computing the weights of the attributes. Comparing with the traditional method of attribute reduction based on rough set, more information of the primary data is held, and more accuracy of the attribute reduction is enhanced by our method.","PeriodicalId":127238,"journal":{"name":"2007 International Conference on Computational Intelligence and Security (CIS 2007)","volume":"87 14 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":"126296152","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 new physically based model for the shape modification of B-spline curve with geometric constraints is presented. The deformation energy of the B-spline curve is minimized based on finite element method, while geometric constraints can be imposed to control the modified shape. By changing the external force, different methods of modification can be obtained. The method based on least square, which results from applying no force, is local and simpler, but the modified shape seems less smooth. While the method based on global deformation, which is more complicated by adding synthetic spring force, can give more natural and smooth results.
{"title":"Shape Modification of B-Spline Curve with Geometric Constraints","authors":"Siyuan Cheng, Xiangwei Zhang, Kelun Tang","doi":"10.1109/CIS.2007.43","DOIUrl":"https://doi.org/10.1109/CIS.2007.43","url":null,"abstract":"A new physically based model for the shape modification of B-spline curve with geometric constraints is presented. The deformation energy of the B-spline curve is minimized based on finite element method, while geometric constraints can be imposed to control the modified shape. By changing the external force, different methods of modification can be obtained. The method based on least square, which results from applying no force, is local and simpler, but the modified shape seems less smooth. While the method based on global deformation, which is more complicated by adding synthetic spring force, can give more natural and smooth results.","PeriodicalId":127238,"journal":{"name":"2007 International Conference on Computational Intelligence and Security (CIS 2007)","volume":"10 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":"122229049","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 this paper, we present a new class of two-stage min- imum risk distribution games model based on credibility theory and two-stage fuzzy optimization method. Then we first introduce approximation approach to dealing with the approximation of the distribution games problem. After that, a hybrid algorithm, which combines approximation approach, neural network (NN) and particle warm opti- mizer (PSO), is designed to solve the distribution games problem, and a numerical example is given to show the fea- sibility of the hybrid algorithm.
{"title":"Fuzzy Distribution Games with Minimum Risk Criteria","authors":"Bin Sun, Yian-Kui Liu","doi":"10.1109/CIS.2007.131","DOIUrl":"https://doi.org/10.1109/CIS.2007.131","url":null,"abstract":"In this paper, we present a new class of two-stage min- imum risk distribution games model based on credibility theory and two-stage fuzzy optimization method. Then we first introduce approximation approach to dealing with the approximation of the distribution games problem. After that, a hybrid algorithm, which combines approximation approach, neural network (NN) and particle warm opti- mizer (PSO), is designed to solve the distribution games problem, and a numerical example is given to show the fea- sibility of the hybrid algorithm.","PeriodicalId":127238,"journal":{"name":"2007 International Conference on Computational Intelligence and Security (CIS 2007)","volume":"32 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":"115959673","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}
Traditional unsupervised change detection algorithms based on simple MRF model assume that subimages applied to extracting features are homogeneous, but that is not always true and causes low accuracy. Based on the fields correlation Markov random field (CMRF) model, an adaptive algorithm is proposed in this paper. The labeling is obtained through solving a MAP (Maximum a posterior) problem by ICM (Iteration Condition Model). Features of each pixel are exacted by using only the pixels currently labeled as the same pattern. With the adapted features, the new labeling is obtained. The satisfied experimental confirm the effectiveness of proposed techniques. Although the proposed method has been presented in the specific context of the analysis of multitemporal remote-sensing images, it could be used in any change detection application requiring the technique based on the difference image
传统的基于简单MRF模型的无监督变化检测算法假设用于提取特征的子图像是均匀的，但这并不总是正确的，并且导致准确率低。基于场相关马尔可夫随机场(CMRF)模型，提出了一种自适应算法。通过ICM(迭代条件模型)求解MAP (Maximum a posterior problem)问题获得标记。每个像素的特征仅通过使用当前标记为相同模式的像素来确定。利用适应的特征，得到新的标记。实验结果验证了所提方法的有效性。虽然所提出的方法是在多时相遥感图像分析的具体背景下提出的，但它可以用于任何需要基于差分图像技术的变化检测应用
{"title":"An Improved MRF Based Unsupervised Change Detection Method","authors":"Yuan Qi, Zhao Rong-Chun","doi":"10.1109/CIS.2007.100","DOIUrl":"https://doi.org/10.1109/CIS.2007.100","url":null,"abstract":"Traditional unsupervised change detection algorithms based on simple MRF model assume that subimages applied to extracting features are homogeneous, but that is not always true and causes low accuracy. Based on the fields correlation Markov random field (CMRF) model, an adaptive algorithm is proposed in this paper. The labeling is obtained through solving a MAP (Maximum a posterior) problem by ICM (Iteration Condition Model). Features of each pixel are exacted by using only the pixels currently labeled as the same pattern. With the adapted features, the new labeling is obtained. The satisfied experimental confirm the effectiveness of proposed techniques. Although the proposed method has been presented in the specific context of the analysis of multitemporal remote-sensing images, it could be used in any change detection application requiring the technique based on the difference image","PeriodicalId":127238,"journal":{"name":"2007 International Conference on Computational Intelligence and Security (CIS 2007)","volume":"45 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":"124992221","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 dynamic counterpropagation network based on the forward only counterpropagation network (CPN) is applied to face detection in this paper. The network, called the dynamic supervised forward-propagation network (DSFPN) trains using a supervised algorithm and can grow dynamically during training allowing subclasses in the training data to be learnt. The network is trained using the categorized wavelet coefficients of the image as features of the image. The results suggests a 98% correct detection rate can be achieved with 4% false positives by increasing network complexity.
{"title":"Face Detection from Greyscale Images Using Details from Categorized Wavelet Coefficients as Features for a Dynamic Counterpropagation Network","authors":"L. Yeong, L. Ang, K. Seng","doi":"10.1109/CIS.2007.230","DOIUrl":"https://doi.org/10.1109/CIS.2007.230","url":null,"abstract":"A dynamic counterpropagation network based on the forward only counterpropagation network (CPN) is applied to face detection in this paper. The network, called the dynamic supervised forward-propagation network (DSFPN) trains using a supervised algorithm and can grow dynamically during training allowing subclasses in the training data to be learnt. The network is trained using the categorized wavelet coefficients of the image as features of the image. The results suggests a 98% correct detection rate can be achieved with 4% false positives by increasing network complexity.","PeriodicalId":127238,"journal":{"name":"2007 International Conference on Computational Intelligence and Security (CIS 2007)","volume":"42 11 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":"127663096","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 this study a new combination of nonlinear backstepping scheme with fuzzy system is presented for controlling a rotary inverted pendulum system to achieve better performance in nonlinear controller approach. This study uses two different fuzzy systems: off-line and on-line to consider different concept. The purpose of this study is to design a stabilizing controller that balances the inverted pendulum in the up-right position.
{"title":"The Off-Line and On-Line Fuzzy Backstepping Controllers for Rotary Inverted Pendulum System","authors":"M. Rahmanian, M. A. Shoorehdeli, M. Teshnehlab","doi":"10.1109/CIS.2007.217","DOIUrl":"https://doi.org/10.1109/CIS.2007.217","url":null,"abstract":"In this study a new combination of nonlinear backstepping scheme with fuzzy system is presented for controlling a rotary inverted pendulum system to achieve better performance in nonlinear controller approach. This study uses two different fuzzy systems: off-line and on-line to consider different concept. The purpose of this study is to design a stabilizing controller that balances the inverted pendulum in the up-right position.","PeriodicalId":127238,"journal":{"name":"2007 International Conference on Computational Intelligence and Security (CIS 2007)","volume":"31 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":"133420583","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}
{"title":"Reinforcing Business Leaders' Role in Striving for Information Security","authors":"J. Anttila","doi":"10.1109/CIS.2007.176","DOIUrl":"https://doi.org/10.1109/CIS.2007.176","url":null,"abstract":"","PeriodicalId":127238,"journal":{"name":"2007 International Conference on Computational Intelligence and Security (CIS 2007)","volume":"87 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":"134544584","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}
Based on the characteristics of optimal operation of cascaded hydropower stations, a mathematic model about the multistage optimization is established. In order to improve the capability of the traditional algorithm in optimal operation of cascaded reservoirs, Niche Genetic Algorithm (NGA) is suggested. This method could avoid the situation of GA convergence at a much earlier stage. The validity of improvement algorithm is testified by the solution of three classic functions. Finally it is successfully applied to the cascaded hydropower stations of the Qing River. The results show that NGA has not only better optimization capability, but also better accuracy. It is a superior non-linear optimal method which could locally search the global solution with greater probability.
{"title":"An Improved Genetic Algorithm for Optimal Operation of Cascaded Reservoirs","authors":"Na Li, Ya-dong Mei","doi":"10.1109/CIS.2007.50","DOIUrl":"https://doi.org/10.1109/CIS.2007.50","url":null,"abstract":"Based on the characteristics of optimal operation of cascaded hydropower stations, a mathematic model about the multistage optimization is established. In order to improve the capability of the traditional algorithm in optimal operation of cascaded reservoirs, Niche Genetic Algorithm (NGA) is suggested. This method could avoid the situation of GA convergence at a much earlier stage. The validity of improvement algorithm is testified by the solution of three classic functions. Finally it is successfully applied to the cascaded hydropower stations of the Qing River. The results show that NGA has not only better optimization capability, but also better accuracy. It is a superior non-linear optimal method which could locally search the global solution with greater probability.","PeriodicalId":127238,"journal":{"name":"2007 International Conference on Computational Intelligence and Security (CIS 2007)","volume":"52 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":"124715543","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：