The mobile robot Simultaneous Localization and Mapping (SLAM) in unknown environments has been considered to be an important and fundamental problem in the mobile robotics research domain. Nowadays most methods for SLAM are focused on probabilistic Bayesian estimation, this paper propose an Unscented Kalman Filter (UKF) Assistant-Proposal Distribution (UKF-APD) particle algorithm,compute the Euclidean distance of particle approximate distribution to the UKF-APD, and take it as an adaptive particle-resampling criterion, the proposed algorithm can avoid particles’ impoverishment and deviation to the real robot posterior distribution. Experimental results demonstrate the effectiveness of the proposed algorithm.
{"title":"An Adaptive UKF-Based Particle Filter for Mobile Robot SLAM","authors":"Xianzhong Chen","doi":"10.1109/JCAI.2009.115","DOIUrl":"https://doi.org/10.1109/JCAI.2009.115","url":null,"abstract":"The mobile robot Simultaneous Localization and Mapping (SLAM) in unknown environments has been considered to be an important and fundamental problem in the mobile robotics research domain. Nowadays most methods for SLAM are focused on probabilistic Bayesian estimation, this paper propose an Unscented Kalman Filter (UKF) Assistant-Proposal Distribution (UKF-APD) particle algorithm,compute the Euclidean distance of particle approximate distribution to the UKF-APD, and take it as an adaptive particle-resampling criterion, the proposed algorithm can avoid particles’ impoverishment and deviation to the real robot posterior distribution. Experimental results demonstrate the effectiveness of the proposed algorithm.","PeriodicalId":154425,"journal":{"name":"2009 International Joint Conference on Artificial Intelligence","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123614444","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, a novel fuzzy particle swarm optimization(NFPSO), in which inertia weight as well as the learning coefficient can be adaptively adjusted according to the control information translated from the fuzzy logic controller (FLC) during the search process, is presented by introducing a two-input and two-output FLC into the canonical particle swarm optimization (CPSO). The effectiveness of NFPSO proposed in this paper is demonstrated by applying it to three benchmark functions obtained from the literature. The simulation results show that NFPSO outperforms CPSO and other fuzzy PSO versions.
{"title":"Fuzzy Particle Swarm Optimization Algorithm","authors":"Dong-ping Tian, N. Li","doi":"10.1109/JCAI.2009.50","DOIUrl":"https://doi.org/10.1109/JCAI.2009.50","url":null,"abstract":"In this paper, a novel fuzzy particle swarm optimization(NFPSO), in which inertia weight as well as the learning coefficient can be adaptively adjusted according to the control information translated from the fuzzy logic controller (FLC) during the search process, is presented by introducing a two-input and two-output FLC into the canonical particle swarm optimization (CPSO). The effectiveness of NFPSO proposed in this paper is demonstrated by applying it to three benchmark functions obtained from the literature. The simulation results show that NFPSO outperforms CPSO and other fuzzy PSO versions.","PeriodicalId":154425,"journal":{"name":"2009 International Joint Conference on Artificial Intelligence","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122652853","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}
Image representation is an important issue in computer graphics, computer vision, robotics, image processing and pattern recognition. In this paper, we proposed an improved color image representation method by using the direct non-symmetry and anti-packing model with triangles and rectangles (DNAMTR). Also, we propose an algorithm of the DNAMTR for color images and analyze the total data amount of the algorithm. By comparing the representation algorithm of the DNAMTR with those of the latest direct non-symmetry and anti-packing model (DNAM) and the popular linear quadtree, the experimental results presented in this paper show that the former can greatly reduce the numbers of subpatterns or nodes and simultaneously save the data storage much more effectively than the latter.
{"title":"An Improved Color Image Representation Method by Using Direct Non-symmetry and Anti-packing Model with Triangles and Rectangles","authors":"Shaohong Fang, Chuanbo Chen, Yunping Zheng","doi":"10.1109/JCAI.2009.38","DOIUrl":"https://doi.org/10.1109/JCAI.2009.38","url":null,"abstract":"Image representation is an important issue in computer graphics, computer vision, robotics, image processing and pattern recognition. In this paper, we proposed an improved color image representation method by using the direct non-symmetry and anti-packing model with triangles and rectangles (DNAMTR). Also, we propose an algorithm of the DNAMTR for color images and analyze the total data amount of the algorithm. By comparing the representation algorithm of the DNAMTR with those of the latest direct non-symmetry and anti-packing model (DNAM) and the popular linear quadtree, the experimental results presented in this paper show that the former can greatly reduce the numbers of subpatterns or nodes and simultaneously save the data storage much more effectively than the latter.","PeriodicalId":154425,"journal":{"name":"2009 International Joint Conference on Artificial Intelligence","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125186549","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}
Considering that freeway mainline has not only high speed but also the ability to store large amount of vehicles, this research proposed a new approach for controlling both freeway on-ramp and mainline. Based on local ramp metering strategy ALINEA, this approach controls both on-ramp vehicles and mainline shoulder lane vehicles according to real-time traffic condition of the ramp and mainline so that to make good use of vehicle store capacity of mainline and at the same time reduce freeway travel time and ramp queue. Using simulation and comparison, the feasibility and effectiveness of this approach was proved.
{"title":"An Approach of Controlling Both Freeway On-ramp and Mainline","authors":"Nan Jiang, Shoupeng Tang","doi":"10.1109/JCAI.2009.40","DOIUrl":"https://doi.org/10.1109/JCAI.2009.40","url":null,"abstract":"Considering that freeway mainline has not only high speed but also the ability to store large amount of vehicles, this research proposed a new approach for controlling both freeway on-ramp and mainline. Based on local ramp metering strategy ALINEA, this approach controls both on-ramp vehicles and mainline shoulder lane vehicles according to real-time traffic condition of the ramp and mainline so that to make good use of vehicle store capacity of mainline and at the same time reduce freeway travel time and ramp queue. Using simulation and comparison, the feasibility and effectiveness of this approach was proved.","PeriodicalId":154425,"journal":{"name":"2009 International Joint Conference on Artificial Intelligence","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126044823","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}
Analyzed the necessity of the integration on the management information system based on Agent according to the globalization. Introduced how to construct the system and the steps in detail. At last shows briefly the technique that support the system.
{"title":"The Construction of the Dynamic Management Information System Based on Agent","authors":"Zhenzhong Ge, Hongli Wang","doi":"10.1109/JCAI.2009.191","DOIUrl":"https://doi.org/10.1109/JCAI.2009.191","url":null,"abstract":"Analyzed the necessity of the integration on the management information system based on Agent according to the globalization. Introduced how to construct the system and the steps in detail. At last shows briefly the technique that support the system.","PeriodicalId":154425,"journal":{"name":"2009 International Joint Conference on Artificial Intelligence","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129849589","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 propose a real-time forest fire detection algorithm using artificial neural networks based on dynamic characteristics of fire regions segmented from video images. Fire region is obtained from image with the help of threshold values in HSV color space. Area, roundness and contour are computed for fire regions from each 5 continuous frames. The average and mean square deviation of them are used as dynamic characteristics, and taken as input of the artificial neural network. The trained BP network can help identify forest fire, even distinguish it from moving car or flying flag with red color. Experimental results of our method prove its value in forest fire surveillance.
{"title":"Image Based Forest Fire Detection Using Dynamic Characteristics with Artificial Neural Networks","authors":"Dengyi Zhang, Shizhong Han, Jianhui Zhao, Zhong Zhang, Chengzhang Qu, Youwang Ke, Xiang Chen","doi":"10.1109/JCAI.2009.79","DOIUrl":"https://doi.org/10.1109/JCAI.2009.79","url":null,"abstract":"In this paper, we propose a real-time forest fire detection algorithm using artificial neural networks based on dynamic characteristics of fire regions segmented from video images. Fire region is obtained from image with the help of threshold values in HSV color space. Area, roundness and contour are computed for fire regions from each 5 continuous frames. The average and mean square deviation of them are used as dynamic characteristics, and taken as input of the artificial neural network. The trained BP network can help identify forest fire, even distinguish it from moving car or flying flag with red color. Experimental results of our method prove its value in forest fire surveillance.","PeriodicalId":154425,"journal":{"name":"2009 International Joint Conference on Artificial Intelligence","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130135376","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 novel gene regulatory network model via the fuzzy logic is proposed. Fuzzy logic can effectively model gene regulation and interaction to accurately reflect the underlying biology. By judging genes expression level on the fuzzy rule, Fuzzy Boolean network (FBN) makes it possible to handle simultaneously the randomness and fuzziness of biological phenomena
{"title":"Fuzzy Logical on Boolean Networks as Model of Gene Regulatory Networks","authors":"Honglin Xu, Shitong Wang","doi":"10.1109/JCAI.2009.78","DOIUrl":"https://doi.org/10.1109/JCAI.2009.78","url":null,"abstract":"A novel gene regulatory network model via the fuzzy logic is proposed. Fuzzy logic can effectively model gene regulation and interaction to accurately reflect the underlying biology. By judging genes expression level on the fuzzy rule, Fuzzy Boolean network (FBN) makes it possible to handle simultaneously the randomness and fuzziness of biological phenomena","PeriodicalId":154425,"journal":{"name":"2009 International Joint Conference on Artificial Intelligence","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128395045","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}
Grid technology is a research hotspot nowadays. To apply grid technology to education resources management will maximize integration of existing education resources. Education resources can be managed effectively by using distributional management thought, which can change current status of the disorder about education resources management. In this paper, resource classification standard in LOM is taken as partition standard of grid community; grid community model based on education resources is constructed as the framework of education resources management according to the characteristics of grid management architecture; construction of grid community and internal structure of community are also discussed according to the characteristics of grid community.
{"title":"A Study on Management Model of Grid Community Based on Education Resource","authors":"Yan Ma, Juhua Zhang, Qin Yang, Yuhui Qiu","doi":"10.1109/JCAI.2009.132","DOIUrl":"https://doi.org/10.1109/JCAI.2009.132","url":null,"abstract":"Grid technology is a research hotspot nowadays. To apply grid technology to education resources management will maximize integration of existing education resources. Education resources can be managed effectively by using distributional management thought, which can change current status of the disorder about education resources management. In this paper, resource classification standard in LOM is taken as partition standard of grid community; grid community model based on education resources is constructed as the framework of education resources management according to the characteristics of grid management architecture; construction of grid community and internal structure of community are also discussed according to the characteristics of grid community.","PeriodicalId":154425,"journal":{"name":"2009 International Joint Conference on Artificial Intelligence","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124623866","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, a filled function approach for constrained global optimization (FFACGO) is proposed. It is a combination of the idea of filled function method in unconstrained global optimization with the concept of penalty function in constrained optimization.Moreover, this FFACGO can be easily actualized with a process that aims at successively finding better optimizer. The performance of the FFACGO in numerical experiments for several testing functions is quite satisfactory and shows its efficiency
{"title":"A FFACGO for Constrained Global Optimization","authors":"Wei-xiang Wang, Y. Shang","doi":"10.1109/JCAI.2009.176","DOIUrl":"https://doi.org/10.1109/JCAI.2009.176","url":null,"abstract":"In this paper, a filled function approach for constrained global optimization (FFACGO) is proposed. It is a combination of the idea of filled function method in unconstrained global optimization with the concept of penalty function in constrained optimization.Moreover, this FFACGO can be easily actualized with a process that aims at successively finding better optimizer. The performance of the FFACGO in numerical experiments for several testing functions is quite satisfactory and shows its efficiency","PeriodicalId":154425,"journal":{"name":"2009 International Joint Conference on Artificial Intelligence","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131141553","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}
During last few years, a number of kernel-based online algorithms have been developed that have shown better performance on a number of tasks. A well designed online algorithm needs less computation to reach the same test accuracy as the corresponding batch algorithm. In this paper, we devise an online training algorithm for L2-SVM. Our work is motivated by HULLER, an online algorithm proposed by A. Bordes and L. Bottou. The proposed algorithm implements two speedups with respect to HULLER, first it chooses an old example for removal based on sound computation instead of random selection; second it uses more effective update rule. Experiments on benchmark data sets show the merits of our method.
{"title":"Online Nearest Point Algorithm for L2-SVM","authors":"Guosheng Wang","doi":"10.1109/JCAI.2009.186","DOIUrl":"https://doi.org/10.1109/JCAI.2009.186","url":null,"abstract":"During last few years, a number of kernel-based online algorithms have been developed that have shown better performance on a number of tasks. A well designed online algorithm needs less computation to reach the same test accuracy as the corresponding batch algorithm. In this paper, we devise an online training algorithm for L2-SVM. Our work is motivated by HULLER, an online algorithm proposed by A. Bordes and L. Bottou. The proposed algorithm implements two speedups with respect to HULLER, first it chooses an old example for removal based on sound computation instead of random selection; second it uses more effective update rule. Experiments on benchmark data sets show the merits of our method.","PeriodicalId":154425,"journal":{"name":"2009 International Joint Conference on Artificial Intelligence","volume":"337 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115982426","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：