{"title":"Parallel robots pose accuracy compensation using artificial neural networks","authors":"Dayong Yu, D. Cong, Jun-wei Han","doi":"10.1109/ICMA.2008.4798850","DOIUrl":"https://doi.org/10.1109/ICMA.2008.4798850","url":null,"abstract":"Parallel robots pose accuracy compensation approach using artificial neural networks has been developed. In this method, an artificial neural network is used with conventional inverse kinematics computation module in parallel. A backpropagation neural network is designed and implemented to learn parallel robot kinematics model error. The trained neural network can be used to performed online pose accuracy compensation in task. Simulation and experimental results for a parallel robot are presented to show the effectiveness of the compensation method based on neural networks.","PeriodicalId":280101,"journal":{"name":"2005 International Conference on Machine Learning and Cybernetics","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129559708","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":"Fuzzy modeling method based on data mining","authors":"Xiu-Quan Chen, Yong-Fu Wang, Xiaojia Huang","doi":"10.1109/WCICA.2008.4593779","DOIUrl":"https://doi.org/10.1109/WCICA.2008.4593779","url":null,"abstract":"Aiming at WM method lacking of completeness and robustness, which was presented by Lixin Wang, fuzzy system is set up by data mining in this paper. Rules base and fuzzy system produced by data mining can ergodic all the fuzzy subspace, which insures the completeness of rules base. Otherwise, rules produced by data mining are elected out in the whole sample data, but WM method is a result only from a certain datum. So, data mining has better robustness and simulation results show its validity.","PeriodicalId":280101,"journal":{"name":"2005 International Conference on Machine Learning and Cybernetics","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124610850","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":"Eigenstructure assignment for linear systems with constrained output via state feedback - a parametric approach","authors":"Y. Xue, G. Duan","doi":"10.1109/CHICC.2006.280537","DOIUrl":"https://doi.org/10.1109/CHICC.2006.280537","url":null,"abstract":"A parametric approach for eigenstructure assignment for linear systems with constrained output via state feedback is proposed. The condition for positive invariance is derived. Based on the parametric solution to a Sylvester matrix equation, parameterizations of all the state feedback control matrices and the closed-loop eigenvector matrices are established. The partial eigenstructure assignment is a case of the proposed approach. The parametric method offers all the design degrees of freedom, which can be utilized to achieve certain desired properties and performances in the design of control systems. A numerical example shows the effect of the proposed approach.","PeriodicalId":280101,"journal":{"name":"2005 International Conference on Machine Learning and Cybernetics","volume":"187 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121057652","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":"Intuitionistic fuzzy filter of lattice implication algebras","authors":"Haiming Li, Jian-Ming Gong, Zheng Pei, Xiaoping Qiu","doi":"10.1109/ICMLC.2005.1527945","DOIUrl":"https://doi.org/10.1109/ICMLC.2005.1527945","url":null,"abstract":"In the paper, the concept of intuitionistic fuzzy filter in lattice implication algebras is introduced, and its properties are discussed. The relation between intuitionistic fuzzy filter and intuitionistic fuzzy lattice filter is shown, the equivalent conditions of intuitionistic fuzzy filter are obtained, these lay a theory foundation for more applying intuitionistic fuzzy filter in lattice implication algebras.","PeriodicalId":280101,"journal":{"name":"2005 International Conference on Machine Learning and Cybernetics","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115113490","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":"Fuzzy multiple reference models adaptive control and simulation study","authors":"Z. Ji, Rongjia Zhu, Yan-Xia Shen","doi":"10.1109/ICMLC.2005.1527410","DOIUrl":"https://doi.org/10.1109/ICMLC.2005.1527410","url":null,"abstract":"A new method of fuzzy multiple reference models adaptive control (FMRMAC) for dealing with significant and unpredictable system parameter variations is presented. In this method, different suitable reference models are chosen by fuzzy rules when changes occurred to the model parameters. A successful application to the speed servo system of dynamic model of brushless DC motor (BLDCM) shows this method works well with high dynamic performance under the condition of command speed change and load torque disturbance.","PeriodicalId":280101,"journal":{"name":"2005 International Conference on Machine Learning and Cybernetics","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115134012","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":"Dynamic economic load dispatch using hybrid genetic algorithm and the method of fuzzy number ranking","authors":"Guo-Li Zhang, Haiyan Lu, Geng-yin Li, Guangquan Zhang","doi":"10.1109/ICMLC.2005.1527359","DOIUrl":"https://doi.org/10.1109/ICMLC.2005.1527359","url":null,"abstract":"This paper proposes a new economic load dispatch model that considers cost coefficients with uncertainties and the constraints of ramp rate. The uncertainties are represented by fuzzy numbers, and the model is known as fuzzy dynamic economic load dispatch model (FDELD). A novel hybrid genetic algorithm with quasi-simplex techniques is proposed to handle the FDELD problem. The algorithm creates offspring by using generic operation and quasi-simplex techniques in parallel. The quasi-simplex techniques consider two potential optimal search directions in generating prospective offspring. One direction is the worst-opposite direction, which is used in the conventional simplex techniques, and the other is the best-forward direction, which is a ray from the centroid of a polyhedron whose vertexes are all the points but the best one towards the best point of the simplex. In addition, in order to reserve more fuzzy information, the fuzzy number ranking method is used to optimize the cost function, avoiding the lost some useful information by getting /spl lambda/-level set. The experimental study shows that FDELD is more practical model; the algorithm and techniques proposed are very efficient to solve FDELD problem.","PeriodicalId":280101,"journal":{"name":"2005 International Conference on Machine Learning and Cybernetics","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114643012","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":"Load forecasting model of power system based on Lyapunov index","authors":"Zhan-Hui Lu, Zhijun Zhu, Jing-Quan Li","doi":"10.1109/ICMLC.2005.1527783","DOIUrl":"https://doi.org/10.1109/ICMLC.2005.1527783","url":null,"abstract":"By analyzing the non-linear chaos characteristic of the power load time sequence, this paper sets up a mathematic model, figures out the max Lyapunov index of the time sequence, identifies the chaos characteristic of the system and develops a load forecasting software to draw a graph of predicted value and actual value. The example indicates that the forecasting model using the Lyapunov index has higher predicting precision.","PeriodicalId":280101,"journal":{"name":"2005 International Conference on Machine Learning and Cybernetics","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116782360","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":"A new weighted support vector machine with GA-based parameter selection","authors":"Shuang Liu, Chuanying Jia, Heng Ma","doi":"10.1109/ICMLC.2005.1527703","DOIUrl":"https://doi.org/10.1109/ICMLC.2005.1527703","url":null,"abstract":"When training sets with uneven class sizes are used, the classification error based on C-support vector machine is undesirably biased towards the class with smaller training set. When training with multi-duplicated samples, C-SVM depends on each sample leading to more time for training. A new weighted support vector machine algorithm is proposed based on the analysis of the cause of such problems, which compensates for the unfavorable impact caused by the uneven class sizes and makes the decision speed faster. To obtain a good generalization performance, genetic algorithm is used to tune the regularization parameter and parameter of the kernel function when training the model. Experiments show that the proposed approach can control the misclassification error rates of classes and deal with multi-duplicate samples with good generalization performance.","PeriodicalId":280101,"journal":{"name":"2005 International Conference on Machine Learning and Cybernetics","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121346147","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":"Research on the Problem of Vehicle Loadind Based on Effective Space Model","authors":"Peng Zhao, Yong Wang, Qian Zhang, Xiutai Yang","doi":"10.1109/ICMLC.2005.1526968","DOIUrl":"https://doi.org/10.1109/ICMLC.2005.1526968","url":null,"abstract":"In the integrated model, which is composed of the vehicle fill problem, VFP for short, and the vehicle scheduling problem, VSP for short, according to their interrelationship and interrestriction, the solution of VFP takes the key role to ensure the whole solutions of the model are high efficient and feasible. By researching on the problem of vehicle loading based on effective space, a method has been put forward for this kind of problems, and it has been proved that this method is valuable in practice.","PeriodicalId":280101,"journal":{"name":"2005 International Conference on Machine Learning and Cybernetics","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121346825","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":"A new method of information extraction from PDF files","authors":"Fang Yuan, Bo Lu","doi":"10.1109/ICMLC.2005.1527225","DOIUrl":"https://doi.org/10.1109/ICMLC.2005.1527225","url":null,"abstract":"With the rapid increase of the PDF files in Internet, how to manage and search PDF files efficiently and quickly has become an urgent problem to be solved. The most important step of solving this problem is to extract information from the PDF files. This paper presents a new method for extracting information from PDF files. It first parses PDF files to get text and format information and injects tags into text information to transform it into semi-structured text, and finally, one pattern match algorithm based on tree model is applied to obtain the solution. A further experiment proved this method was effective.","PeriodicalId":280101,"journal":{"name":"2005 International Conference on Machine Learning and Cybernetics","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127201572","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}