A detection algorithm of moving objects which is robust and effective is proposed for the problem of the chaos and variety scenes. The background model based color quickly is build during the nonrestraint learning. According to the background of the chaos, it updates the model. However, shadow is also detected as moving object because of the same characters between them, so the algorithm of shadow removal based on its characteristic of chroma, lightness and crossover entropy was presented too. Finally, the algorithm was simulated in real-time and experimental effect, and achieved better results.
{"title":"Research of Moving Object Detection Algorithm Based on Non-restraint Learning and Shadow Removal Algorithm","authors":"Jiyuan Zhang, Xue Bai","doi":"10.1109/WGEC.2009.75","DOIUrl":"https://doi.org/10.1109/WGEC.2009.75","url":null,"abstract":"A detection algorithm of moving objects which is robust and effective is proposed for the problem of the chaos and variety scenes. The background model based color quickly is build during the nonrestraint learning. According to the background of the chaos, it updates the model. However, shadow is also detected as moving object because of the same characters between them, so the algorithm of shadow removal based on its characteristic of chroma, lightness and crossover entropy was presented too. Finally, the algorithm was simulated in real-time and experimental effect, and achieved better results.","PeriodicalId":277950,"journal":{"name":"2009 Third International Conference on Genetic and Evolutionary Computing","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116710907","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 view of the high operation cost of Gini index for SLIQ algorithm while searching the optimal split scheme, and from the objective distribution of data, the thesis introduces the concept of Density of Data Distribution. The new SLIQ algorithm, improved on the base of Gini index, is adopted in synthetic evaluation. The results in the example demonstrate that the number of the Gini index is reduced greatly after the improvement of SLIQ algorithm while searching the optimal split scheme. The cost of sorting and the optimal split point is also cut down. So the size of decision tree is simplified. Thus the evaluating objectives are classified, and the evaluating results are arranged in order and then the ordering and classified synthetic evaluation is realized.
{"title":"Improvement of SLIQ Algorithm and its Application in Evaluation","authors":"Huacheng Zhang, Xie Wu","doi":"10.1109/WGEC.2009.89","DOIUrl":"https://doi.org/10.1109/WGEC.2009.89","url":null,"abstract":"In view of the high operation cost of Gini index for SLIQ algorithm while searching the optimal split scheme, and from the objective distribution of data, the thesis introduces the concept of Density of Data Distribution. The new SLIQ algorithm, improved on the base of Gini index, is adopted in synthetic evaluation. The results in the example demonstrate that the number of the Gini index is reduced greatly after the improvement of SLIQ algorithm while searching the optimal split scheme. The cost of sorting and the optimal split point is also cut down. So the size of decision tree is simplified. Thus the evaluating objectives are classified, and the evaluating results are arranged in order and then the ordering and classified synthetic evaluation is realized.","PeriodicalId":277950,"journal":{"name":"2009 Third International Conference on Genetic and Evolutionary Computing","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116955769","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}
Negative selection mechanism in virus detection model is improved by optimizing the configuration of variable radius detector in this paper. The radius of the detector is configured automatically, and the contradiction between the number of detectors and its detection range is resolved. The immune system has better adaptability and dynamic in this paper.
{"title":"An Immune System Algorithm Based on Variable Detection Radius of the Negative Selection Mechanism","authors":"Hua Jiang, WenLing Mo, Jing Qin","doi":"10.1109/WGEC.2009.119","DOIUrl":"https://doi.org/10.1109/WGEC.2009.119","url":null,"abstract":"Negative selection mechanism in virus detection model is improved by optimizing the configuration of variable radius detector in this paper. The radius of the detector is configured automatically, and the contradiction between the number of detectors and its detection range is resolved. The immune system has better adaptability and dynamic in this paper.","PeriodicalId":277950,"journal":{"name":"2009 Third International Conference on Genetic and Evolutionary Computing","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125944361","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}
High speed collecting and managing system of spot welding signal can achieve the A/D conversion and data collection. The data of welding current, electrode voltage as well as welding cycle has been collected. Subsequently, they were processed with data acquisition and memory module, wavelet filtering of digit signal module, U-I curves and energy analyzing module, respectively. Based on the collections of welding current and electrode voltage, a criterion splash occurrence and the defective of loose weld by U-I curves change and acreage were proposed. The results prove that the criterion can decipher the welding splash and defective of loose weld accurately.
{"title":"Analysis of Welding Defects in Spot Welding Process U-I Curves","authors":"Ru-xiong Li, Xiao-chun Lei, P. Zhou","doi":"10.1109/WGEC.2009.110","DOIUrl":"https://doi.org/10.1109/WGEC.2009.110","url":null,"abstract":"High speed collecting and managing system of spot welding signal can achieve the A/D conversion and data collection. The data of welding current, electrode voltage as well as welding cycle has been collected. Subsequently, they were processed with data acquisition and memory module, wavelet filtering of digit signal module, U-I curves and energy analyzing module, respectively. Based on the collections of welding current and electrode voltage, a criterion splash occurrence and the defective of loose weld by U-I curves change and acreage were proposed. The results prove that the criterion can decipher the welding splash and defective of loose weld accurately.","PeriodicalId":277950,"journal":{"name":"2009 Third International Conference on Genetic and Evolutionary Computing","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125285665","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}
X. Wang, Lingzhong Zhao, Congwen Zeng, Junyan Qian, T. Gu
Declarative methods for planning problems admit highly efficient and understandable problem description. Mechanical Assembly Sequence Planning (MASP) is a kind of planning problem that is difficult and of great importance in industrial production. This paper proposes a novel Answer Set Programming (ASP) based declarative solution to MASP. Given a CAD model of an assembly, all assembly knowledge and necessary constraints can be produced automatically. With the answer set solver DLV all assembly sequences could be generated. And thanks to the declarativeness of the method the representation efficiency and time efficiency of the method can be improved separately.
{"title":"An ASP Based Solution to Mechanical Assembly Sequence Planning","authors":"X. Wang, Lingzhong Zhao, Congwen Zeng, Junyan Qian, T. Gu","doi":"10.1109/WGEC.2009.158","DOIUrl":"https://doi.org/10.1109/WGEC.2009.158","url":null,"abstract":"Declarative methods for planning problems admit highly efficient and understandable problem description. Mechanical Assembly Sequence Planning (MASP) is a kind of planning problem that is difficult and of great importance in industrial production. This paper proposes a novel Answer Set Programming (ASP) based declarative solution to MASP. Given a CAD model of an assembly, all assembly knowledge and necessary constraints can be produced automatically. With the answer set solver DLV all assembly sequences could be generated. And thanks to the declarativeness of the method the representation efficiency and time efficiency of the method can be improved separately.","PeriodicalId":277950,"journal":{"name":"2009 Third International Conference on Genetic and Evolutionary Computing","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125314476","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}
With the development of the embedded technology, the Zigbee communication protocol is used in more and more application systems. In this paper we proposed a scheme to realize the intellectualized management system of garage in the community. In the scheme, we combined the embedded technology with the Zigbee wireless communication technology, utilized the license plate recognition system to recognize the vehicle in and out the community automatically, used the Zigbee module to control the community's gating intelligently and established a wireless communication network based on the Zigbee and used the Zigbee radio transmission technology to locate and monitor the community vehicles wirelessly. Practice result shows that the system can be managed automatically and saves the labor cost greatly and costs low with high reliability and extendibility and strong usability and broad application prospect.
{"title":"Design and Implementation on the Intelligent Management System of Garage in the Community Based on Zigbee","authors":"Lei Wu, Ming Zhao","doi":"10.1109/WGEC.2009.32","DOIUrl":"https://doi.org/10.1109/WGEC.2009.32","url":null,"abstract":"With the development of the embedded technology, the Zigbee communication protocol is used in more and more application systems. In this paper we proposed a scheme to realize the intellectualized management system of garage in the community. In the scheme, we combined the embedded technology with the Zigbee wireless communication technology, utilized the license plate recognition system to recognize the vehicle in and out the community automatically, used the Zigbee module to control the community's gating intelligently and established a wireless communication network based on the Zigbee and used the Zigbee radio transmission technology to locate and monitor the community vehicles wirelessly. Practice result shows that the system can be managed automatically and saves the labor cost greatly and costs low with high reliability and extendibility and strong usability and broad application prospect.","PeriodicalId":277950,"journal":{"name":"2009 Third International Conference on Genetic and Evolutionary Computing","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116015215","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 steer-by-wire system, with which the conventional mechanical linkage between the steering wheel and the front wheel is removed, is suited to active steering control, to improve vehicle stability, dynamics and maneuverability, as well as to autonomous steering control to assist the driver. Conventional controller for steer-by-wire system is designed with general feedback control method. However, driver can not exactly feel reaction torque generated from tire. This paper adopts the method of integral partition PID Control. Computer models were developed under the environment of MATLAB/SIMULNK and the Integral Partition PID Control scheme of steer-by-wire control was presented too. Return-to-center of steering wheel and steering of the front wheel were simulated and analyzed. The simulation results illustrate that steer-by-wire controller with Integral Partition PID Control is better in dynamic characteristics than the conventional PID controller in the return-to-center of steering wheel and stabilization time.
{"title":"Research of Automotive Steer-by-Wire Control Based on Integral Partition PID Control","authors":"Xiuwei Fu, Li Fu, Feng Kong","doi":"10.1109/WGEC.2009.21","DOIUrl":"https://doi.org/10.1109/WGEC.2009.21","url":null,"abstract":"The steer-by-wire system, with which the conventional mechanical linkage between the steering wheel and the front wheel is removed, is suited to active steering control, to improve vehicle stability, dynamics and maneuverability, as well as to autonomous steering control to assist the driver. Conventional controller for steer-by-wire system is designed with general feedback control method. However, driver can not exactly feel reaction torque generated from tire. This paper adopts the method of integral partition PID Control. Computer models were developed under the environment of MATLAB/SIMULNK and the Integral Partition PID Control scheme of steer-by-wire control was presented too. Return-to-center of steering wheel and steering of the front wheel were simulated and analyzed. The simulation results illustrate that steer-by-wire controller with Integral Partition PID Control is better in dynamic characteristics than the conventional PID controller in the return-to-center of steering wheel and stabilization time.","PeriodicalId":277950,"journal":{"name":"2009 Third International Conference on Genetic and Evolutionary Computing","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122745785","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 constructed the response surface mold through the neural network, elaborated the concept and mathematics description of the response surface. Through a real example, we solved the coupling relationship during multidisciplinary as well as the synthesis coordination of many disciplines with multidisciplinary design based on the response surface. We completed the data exchanging and coordinating during each sub-discipline through the response surface of neural network and approached the optimal solution. The research indicates that the response face mold constructed with neural network can reduce the analysis time and enhance the precision to a great extent and help us seek for better design finally.
{"title":"Research on Multidisciplinary Design Optimization Based Response Surface Technology of Artificial Neural Network","authors":"Hanyun Wen, Jie Hu","doi":"10.1109/WGEC.2009.28","DOIUrl":"https://doi.org/10.1109/WGEC.2009.28","url":null,"abstract":"In the paper, we constructed the response surface mold through the neural network, elaborated the concept and mathematics description of the response surface. Through a real example, we solved the coupling relationship during multidisciplinary as well as the synthesis coordination of many disciplines with multidisciplinary design based on the response surface. We completed the data exchanging and coordinating during each sub-discipline through the response surface of neural network and approached the optimal solution. The research indicates that the response face mold constructed with neural network can reduce the analysis time and enhance the precision to a great extent and help us seek for better design finally.","PeriodicalId":277950,"journal":{"name":"2009 Third International Conference on Genetic and Evolutionary Computing","volume":"217 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114598968","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}
Many current mining tasks analyze data in environments with distributed computing nodes. Classification in such scenario needs to perform local mining task in each data site and then integrate local classifiers to a global model of the data. However, integration strategy can influence the performance and complexity of the final model. In this paper, based on the formalization of combining multiple classifiers by stacking in Distributed Data Mining, a new strategy to from meta-level training set is proposed, which can describe the vote made by each base-level classifiers. The experiment results show that our method achieve better performance for those datasets with highly skewed class distribution.
{"title":"Combining Distributed Classifies by Stacking","authors":"Yanyan Wei, Taoshen Li, Zhihui Ge","doi":"10.1109/WGEC.2009.146","DOIUrl":"https://doi.org/10.1109/WGEC.2009.146","url":null,"abstract":"Many current mining tasks analyze data in environments with distributed computing nodes. Classification in such scenario needs to perform local mining task in each data site and then integrate local classifiers to a global model of the data. However, integration strategy can influence the performance and complexity of the final model. In this paper, based on the formalization of combining multiple classifiers by stacking in Distributed Data Mining, a new strategy to from meta-level training set is proposed, which can describe the vote made by each base-level classifiers. The experiment results show that our method achieve better performance for those datasets with highly skewed class distribution.","PeriodicalId":277950,"journal":{"name":"2009 Third International Conference on Genetic and Evolutionary Computing","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122110632","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 selection of fuzzy control rule is one of the keys in fuzzy controller’s design. The article introduces particle swarm optimization (PSO) algorithms optimizing fuzzy control rule in details, and applies the optimized rule to design fuzzy controller. The result of simulation shows that applying PSO to optimize fuzzy control rule is feasible and effective. It enlarges the application scope of PSO algorithms and provides a new way to design fuzzy controller.
{"title":"The Optimizing of Fuzzy Control Rule Based on Particle Swarm Optimization Algorithms","authors":"Sun Wei, Mingming Liu, Yongbao Song","doi":"10.1109/WGEC.2009.186","DOIUrl":"https://doi.org/10.1109/WGEC.2009.186","url":null,"abstract":"The selection of fuzzy control rule is one of the keys in fuzzy controller’s design. The article introduces particle swarm optimization (PSO) algorithms optimizing fuzzy control rule in details, and applies the optimized rule to design fuzzy controller. The result of simulation shows that applying PSO to optimize fuzzy control rule is feasible and effective. It enlarges the application scope of PSO algorithms and provides a new way to design fuzzy controller.","PeriodicalId":277950,"journal":{"name":"2009 Third International Conference on Genetic and Evolutionary Computing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129621486","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：