Pub Date : 2012-07-15DOI: 10.1109/ICMLC.2012.6358949
Jingjing Cao, S. Kwong, Ran Wang, Ke Li
Extreme Learning Machine (ELM) has become popular for solving classification problem due to its fast speed. However, the system of ELM may be unreliable since its performance often relies on random input hidden node parameters. The techniques of combining multiple classifiers are widely adopted to improve both reliability and accuracy of a single classifier. Thus, this paper presents a minimum square error (MSE) based weighted voting method to optimize the linear combination of multiple ELMs. The experimental results over ten VCI data sets show better classification performance than the original ELM and the voting based ELM classifiers.
{"title":"A weighted voting method using minimum square error based on Extreme Learning Machine","authors":"Jingjing Cao, S. Kwong, Ran Wang, Ke Li","doi":"10.1109/ICMLC.2012.6358949","DOIUrl":"https://doi.org/10.1109/ICMLC.2012.6358949","url":null,"abstract":"Extreme Learning Machine (ELM) has become popular for solving classification problem due to its fast speed. However, the system of ELM may be unreliable since its performance often relies on random input hidden node parameters. The techniques of combining multiple classifiers are widely adopted to improve both reliability and accuracy of a single classifier. Thus, this paper presents a minimum square error (MSE) based weighted voting method to optimize the linear combination of multiple ELMs. The experimental results over ten VCI data sets show better classification performance than the original ELM and the voting based ELM classifiers.","PeriodicalId":128006,"journal":{"name":"2012 International Conference on Machine Learning and Cybernetics","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132362096","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}
Pub Date : 2012-07-15DOI: 10.1109/ICMLC.2012.6358944
Guoyou Shi, Shuang Liu
Generalization performance of support vector machines depends on optimal selection of parameter values. But training the best parameters for C-Support Vector Machines (C-SVM) classifier with RBF kernel is time-consuming. We can hardly finish training process for large data sets with traditional methods. Multithreading as a widespread programming and execution model allows multiple threads to exist within the context of a single process, which has been widely applied in data processing and analyzing. In this paper, we studied how to adopt genetic algorithm and multithreading model to complete optimal model selection of C-SVM classifier with RBF kernel. This new approach not only chooses global parameters, but also saves training time based on parallel computing process. Experimental results show the efficiency and feasibility of new approach.
{"title":"Model selection of RBF kernel for C-SVM based on genetic algorithm and multithreading","authors":"Guoyou Shi, Shuang Liu","doi":"10.1109/ICMLC.2012.6358944","DOIUrl":"https://doi.org/10.1109/ICMLC.2012.6358944","url":null,"abstract":"Generalization performance of support vector machines depends on optimal selection of parameter values. But training the best parameters for C-Support Vector Machines (C-SVM) classifier with RBF kernel is time-consuming. We can hardly finish training process for large data sets with traditional methods. Multithreading as a widespread programming and execution model allows multiple threads to exist within the context of a single process, which has been widely applied in data processing and analyzing. In this paper, we studied how to adopt genetic algorithm and multithreading model to complete optimal model selection of C-SVM classifier with RBF kernel. This new approach not only chooses global parameters, but also saves training time based on parallel computing process. Experimental results show the efficiency and feasibility of new approach.","PeriodicalId":128006,"journal":{"name":"2012 International Conference on Machine Learning and Cybernetics","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130035302","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}
Pub Date : 2012-07-15DOI: 10.1109/ICMLC.2012.6359606
Chung-Wei Chiu, Chih-Feng Hu, Chi Kuang
The hierarchical sliding mode control (HSMC) has been proposed to achieve the position control of a spherical robot driven by Omni wheels. The two-direction movement can be accomplished by the cross type arrangement of driving wheels. Based on the two-layer architecture of HSMC and the Lyapunov stability theorem, the equivalent control of each subsystem is deduced, and then the total control law is derived. The original state dependent switching scheme of the HSMC will cause the failure of position control. So it has been modified as a positive constant without any switching to achieve the position control.
{"title":"Hierarchical sliding mode control of a spherical robot driven by Omni wheels","authors":"Chung-Wei Chiu, Chih-Feng Hu, Chi Kuang","doi":"10.1109/ICMLC.2012.6359606","DOIUrl":"https://doi.org/10.1109/ICMLC.2012.6359606","url":null,"abstract":"The hierarchical sliding mode control (HSMC) has been proposed to achieve the position control of a spherical robot driven by Omni wheels. The two-direction movement can be accomplished by the cross type arrangement of driving wheels. Based on the two-layer architecture of HSMC and the Lyapunov stability theorem, the equivalent control of each subsystem is deduced, and then the total control law is derived. The original state dependent switching scheme of the HSMC will cause the failure of position control. So it has been modified as a positive constant without any switching to achieve the position control.","PeriodicalId":128006,"journal":{"name":"2012 International Conference on Machine Learning and Cybernetics","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134045048","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}
Pub Date : 2012-07-15DOI: 10.1109/ICMLC.2012.6358979
Zhongwen Li, Cheng-Bin Wu, Yi Xie, Zheng-Wei Jing
The weak security capability of RFID systems has greatly hindered the development of RFID applications in the Internet of things. EPC C1G2 has many security risks, such as the plain-text transmission of tag information, the easily compromised passwords, and the shortage of tag authentication. Some studies on designing security protocols for RFID tags either do not conform to EPC C1G1 or suffer from security flaws. After analyzing the existing security protocols, this paper designs a secure access control protocol of RFID tags. The analysis results have showed that the proposed protocol meet the security requirements of RFID systems based on EPC C1G2.
{"title":"A secure access control protocol of RFID tags based on EPC C1G2","authors":"Zhongwen Li, Cheng-Bin Wu, Yi Xie, Zheng-Wei Jing","doi":"10.1109/ICMLC.2012.6358979","DOIUrl":"https://doi.org/10.1109/ICMLC.2012.6358979","url":null,"abstract":"The weak security capability of RFID systems has greatly hindered the development of RFID applications in the Internet of things. EPC C1G2 has many security risks, such as the plain-text transmission of tag information, the easily compromised passwords, and the shortage of tag authentication. Some studies on designing security protocols for RFID tags either do not conform to EPC C1G1 or suffer from security flaws. After analyzing the existing security protocols, this paper designs a secure access control protocol of RFID tags. The analysis results have showed that the proposed protocol meet the security requirements of RFID systems based on EPC C1G2.","PeriodicalId":128006,"journal":{"name":"2012 International Conference on Machine Learning and Cybernetics","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131488864","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}
Pub Date : 2012-07-15DOI: 10.1109/ICMLC.2012.6359674
K. Tseng, Y. Shiao
This research is mainly investigating into the power variations between non-regenerative braking power mode and the regenerative braking power mode of the Electrical Multiple Units (EMU) which are used in Taipei Rapid Transit Systems (TRTS) Nangang, Banqiao and Tucheng lines. It also aims to find the optimal usage of the regenerative braking power, not only providing a reasonable planning of the substation capacity for construction at the initial stage in order to avoid possible waste on investment, but also effectively reducing loadings of the electric power facilities and the related power expenditure at the stage of operation. Moreover, it is expected that other metro authorities in our country will therefore pay more attention to the EMU's regenerative power utilization, and eventually apply it to the planning and design of the EMU regenerative power for all the railway systems.
{"title":"The analysis of regenerative breaking power for Taipei Rapid Transit Systems Electrical Multiple Units","authors":"K. Tseng, Y. Shiao","doi":"10.1109/ICMLC.2012.6359674","DOIUrl":"https://doi.org/10.1109/ICMLC.2012.6359674","url":null,"abstract":"This research is mainly investigating into the power variations between non-regenerative braking power mode and the regenerative braking power mode of the Electrical Multiple Units (EMU) which are used in Taipei Rapid Transit Systems (TRTS) Nangang, Banqiao and Tucheng lines. It also aims to find the optimal usage of the regenerative braking power, not only providing a reasonable planning of the substation capacity for construction at the initial stage in order to avoid possible waste on investment, but also effectively reducing loadings of the electric power facilities and the related power expenditure at the stage of operation. Moreover, it is expected that other metro authorities in our country will therefore pay more attention to the EMU's regenerative power utilization, and eventually apply it to the planning and design of the EMU regenerative power for all the railway systems.","PeriodicalId":128006,"journal":{"name":"2012 International Conference on Machine Learning and Cybernetics","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130872475","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}
Pub Date : 2012-07-15DOI: 10.1109/ICMLC.2012.6359460
Luzheng Bi, Junxing Shang, G. Gan
Computational models of driving behavior developed in a cognitive architecture can provide better scientific understanding of driving, simulate driving behavior, quantitatively predict possible interference of in-vehicle tasks, and thus help develop human factors guidelines and tools for in-vehicle systems design. Driver lane changing is a common activity in driving. Therefore, modeling driver lane changing control with a cognitive architecture should be an important component of cognitive models of driving behavior. In this paper, we develop a computational model of driver lane changing control with the Queuing Network-Model Human Processor (QN-MHP) cognitive architecture based on neuroscience and psychological findings. The simulation and experimental results from lane changing on straight and curved roads show that this model can perform the control process of lane changing well and the model's control process is consistent with that of drivers.
{"title":"Modeling driver lane changing control with the queuing network-model human processor","authors":"Luzheng Bi, Junxing Shang, G. Gan","doi":"10.1109/ICMLC.2012.6359460","DOIUrl":"https://doi.org/10.1109/ICMLC.2012.6359460","url":null,"abstract":"Computational models of driving behavior developed in a cognitive architecture can provide better scientific understanding of driving, simulate driving behavior, quantitatively predict possible interference of in-vehicle tasks, and thus help develop human factors guidelines and tools for in-vehicle systems design. Driver lane changing is a common activity in driving. Therefore, modeling driver lane changing control with a cognitive architecture should be an important component of cognitive models of driving behavior. In this paper, we develop a computational model of driver lane changing control with the Queuing Network-Model Human Processor (QN-MHP) cognitive architecture based on neuroscience and psychological findings. The simulation and experimental results from lane changing on straight and curved roads show that this model can perform the control process of lane changing well and the model's control process is consistent with that of drivers.","PeriodicalId":128006,"journal":{"name":"2012 International Conference on Machine Learning and Cybernetics","volume":"31 12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131004246","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}
As a source of electricity production, the level of automation in thermal power units is increasing higher and higher due to the construction of smart power grids. The units in grids should be working in automatic generation control and primary frequency. The optimal control has changed to a hot spot in the industry. A new method for optimal control which is used by an external optimization controller is proposed in this paper. The method is different from the traditional method, and it is not limited to the capability of distributed control system which is used in the field. By using the high-performance external optimization controller, the complex control logic and advanced control algorithms (model predictive control) can be achieved in optimal control. Using this method in the control of circulating fluidized bed boiler in field, we show that the boiler can be controlled efficiently. So this method can improve the control level of the units, and this method is not designed for one unit, it can be used widely in thermal power units.
{"title":"External optimization controller in optimal control of thermal power units","authors":"Yue Zhang, Hong-Bing Xu, Meng-Jiao Liu, Weiyang Chen","doi":"10.1109/ICMLC.2012.6359462","DOIUrl":"https://doi.org/10.1109/ICMLC.2012.6359462","url":null,"abstract":"As a source of electricity production, the level of automation in thermal power units is increasing higher and higher due to the construction of smart power grids. The units in grids should be working in automatic generation control and primary frequency. The optimal control has changed to a hot spot in the industry. A new method for optimal control which is used by an external optimization controller is proposed in this paper. The method is different from the traditional method, and it is not limited to the capability of distributed control system which is used in the field. By using the high-performance external optimization controller, the complex control logic and advanced control algorithms (model predictive control) can be achieved in optimal control. Using this method in the control of circulating fluidized bed boiler in field, we show that the boiler can be controlled efficiently. So this method can improve the control level of the units, and this method is not designed for one unit, it can be used widely in thermal power units.","PeriodicalId":128006,"journal":{"name":"2012 International Conference on Machine Learning and Cybernetics","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131187342","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}
Pub Date : 2012-07-15DOI: 10.1109/ICMLC.2012.6358937
Zhi-Qian Huang, Wing W. Y. Ng
The Localized Generalization Error Model (L-GEM) provides a practical framework for evaluating generalization capability of a learning machine , e.g. neural network. The Q value of the L-GEM controls the coverage of unseen samples under evaluation. Owing to the nonlinear and real unknown relationship of unseen samples and their generalization error, different Q values yield different L-GEM values. In this paper, we adopt an evolutionary procedure based on genetic programming and artificial datasets to estimate functional relationship between Q values and statistics of training samples. In this first empirical study, a simple training samples generated from two two-dimensional Gaussian distribution is adopted. Resulting formulae provide hints to select optimal Q value for given classification problems.
{"title":"Empirical estimation of functional relationships between Q value of the L-GEM and training data using genetic programming","authors":"Zhi-Qian Huang, Wing W. Y. Ng","doi":"10.1109/ICMLC.2012.6358937","DOIUrl":"https://doi.org/10.1109/ICMLC.2012.6358937","url":null,"abstract":"The Localized Generalization Error Model (L-GEM) provides a practical framework for evaluating generalization capability of a learning machine , e.g. neural network. The Q value of the L-GEM controls the coverage of unseen samples under evaluation. Owing to the nonlinear and real unknown relationship of unseen samples and their generalization error, different Q values yield different L-GEM values. In this paper, we adopt an evolutionary procedure based on genetic programming and artificial datasets to estimate functional relationship between Q values and statistics of training samples. In this first empirical study, a simple training samples generated from two two-dimensional Gaussian distribution is adopted. Resulting formulae provide hints to select optimal Q value for given classification problems.","PeriodicalId":128006,"journal":{"name":"2012 International Conference on Machine Learning and Cybernetics","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133497198","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}
This paper proposes to distinguish between overlapped speech and single-speaker speech using fractal dimension feature. It is found that the degree of chaos in single-speaker speech frames is lower than that in overlapped speech frames, which indicates that the fractal dimension can be used as a feature to distinguish overlapped speech from single-speaker speech. We carried out experiments for evaluating the effectiveness of fractal dimension. Experimental results show that combining traditional features with fractal dimension feature achieves the highest discrimination rate of 81.0%.
{"title":"Fractal dimension feature for distinguishing between overlapped speech and single-speaker speech","authors":"Wei Li, Qianhua He, Yanxiong Li, Xueyuan Zhang, Xiaohui Feng","doi":"10.1109/ICMLC.2012.6358902","DOIUrl":"https://doi.org/10.1109/ICMLC.2012.6358902","url":null,"abstract":"This paper proposes to distinguish between overlapped speech and single-speaker speech using fractal dimension feature. It is found that the degree of chaos in single-speaker speech frames is lower than that in overlapped speech frames, which indicates that the fractal dimension can be used as a feature to distinguish overlapped speech from single-speaker speech. We carried out experiments for evaluating the effectiveness of fractal dimension. Experimental results show that combining traditional features with fractal dimension feature achieves the highest discrimination rate of 81.0%.","PeriodicalId":128006,"journal":{"name":"2012 International Conference on Machine Learning and Cybernetics","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133823918","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}
Pub Date : 2012-07-15DOI: 10.1109/ICMLC.2012.6359511
S. A. Jayasuriya, Alan Wee-Chung Liew
In brain image analysis, the automatic identification of symmetry plane has various applications. This paper presents a new method that uses the concept of fractal dimension as a quantitative measure for identifying symmetry plane in three-dimensional (3D) brain magnetic resonance (MR) images. The method was tested on various 3D MRI datasets. Robust and accurate results were obtained in our experiments.
{"title":"Fractal dimension as a symmetry measure in 3D brain MRI analysis","authors":"S. A. Jayasuriya, Alan Wee-Chung Liew","doi":"10.1109/ICMLC.2012.6359511","DOIUrl":"https://doi.org/10.1109/ICMLC.2012.6359511","url":null,"abstract":"In brain image analysis, the automatic identification of symmetry plane has various applications. This paper presents a new method that uses the concept of fractal dimension as a quantitative measure for identifying symmetry plane in three-dimensional (3D) brain magnetic resonance (MR) images. The method was tested on various 3D MRI datasets. Robust and accurate results were obtained in our experiments.","PeriodicalId":128006,"journal":{"name":"2012 International Conference on Machine Learning and Cybernetics","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115353482","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：