Pub Date : 2011-01-01DOI: 10.1109/TSMCC.2011.2107552
H. Ö. Ünver
{"title":"System Architectures Enabling Reconfigurable Laboratory-Automation Systems","authors":"H. Ö. Ünver","doi":"10.1109/TSMCC.2011.2107552","DOIUrl":"https://doi.org/10.1109/TSMCC.2011.2107552","url":null,"abstract":"","PeriodicalId":55005,"journal":{"name":"IEEE Transactions on Systems Man and Cybernetics Part C-Applications and Re","volume":"71 1","pages":"909-922"},"PeriodicalIF":0.0,"publicationDate":"2011-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72969760","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 : 2009-07-01DOI: 10.1109/TSMCC.2009.2020789
Howard Li, Simon X. Yang, M. Seto
Recently, a coordinated hybrid agent (CHA) framework was proposed for the control of multiagent systems (MASs). It was demonstrated that an intelligent planner can be designed for the CHA framework to automatically generate desired actions for multiple robots in an MAS. However, in previous studies, only static obstacles in the workspace were considered. In this paper, a neural-network-based approach is proposed for a multirobot system with moving obstacles. A biologically inspired neural-network-based intelligent planner is designed for the coordination of MASs. A landscape of the neural activities for all neurons of a CHA agent contains information about the agent's local goal and moving obstacles. The proposed approach is able to plan the paths for multiple robots while avoiding moving obstacles. The proposed approach is simulated using both Matlab and Vortex. The Vortex module executes control commands from the control system module, and provides the outputs describing the vehicle state and terrain information, which are, in turn, used in the control module to produce the control commands. Simulation results show that the developed intelligent planner of the CHA framework can control a large complex system so that coordination among agents can be achieved.
{"title":"Neural-Network-Based Path Planning for a Multirobot System With Moving Obstacles","authors":"Howard Li, Simon X. Yang, M. Seto","doi":"10.1109/TSMCC.2009.2020789","DOIUrl":"https://doi.org/10.1109/TSMCC.2009.2020789","url":null,"abstract":"Recently, a coordinated hybrid agent (CHA) framework was proposed for the control of multiagent systems (MASs). It was demonstrated that an intelligent planner can be designed for the CHA framework to automatically generate desired actions for multiple robots in an MAS. However, in previous studies, only static obstacles in the workspace were considered. In this paper, a neural-network-based approach is proposed for a multirobot system with moving obstacles. A biologically inspired neural-network-based intelligent planner is designed for the coordination of MASs. A landscape of the neural activities for all neurons of a CHA agent contains information about the agent's local goal and moving obstacles. The proposed approach is able to plan the paths for multiple robots while avoiding moving obstacles. The proposed approach is simulated using both Matlab and Vortex. The Vortex module executes control commands from the control system module, and provides the outputs describing the vehicle state and terrain information, which are, in turn, used in the control module to produce the control commands. Simulation results show that the developed intelligent planner of the CHA framework can control a large complex system so that coordination among agents can be achieved.","PeriodicalId":55005,"journal":{"name":"IEEE Transactions on Systems Man and Cybernetics Part C-Applications and Re","volume":"22 19 1","pages":"410-419"},"PeriodicalIF":0.0,"publicationDate":"2009-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77828505","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 : 2009-03-01DOI: 10.1109/TSMCC.2008.2007246
Zhiwu Li, Sen Zhu, Mengchu Zhou
Petri nets are a popular mathematical tool to investigate the deadlock problems in resource allocation systems. As an important problem solution paradigm in computer science, the divide-and-conquer strategy is used in this paper to investigate the deadlock prevention for flexible manufacturing systems (FMSs) that are modeled with Petri nets. Based on the concept of resource circuits, a plant net model is divided into an idle subnet, an autonomous subnet, and a number of small but independent subnets, called toparchies, from the viewpoint of deadlock control. A liveness-enforcing supervisor, called toparch, is designed for each toparchy. If a particular separation condition holds in a plant net model, the computational complexity of toparches is significantly reduced. This research shows that the resultant net, called monarch, by composing the toparches derived for the toparchies can serve as a liveness-enforcing Petri net supervisor for the whole plant model. FMS examples are given to illustrate the proposed method.
{"title":"A Divide-and-Conquer Strategy to Deadlock Prevention in Flexible Manufacturing Systems","authors":"Zhiwu Li, Sen Zhu, Mengchu Zhou","doi":"10.1109/TSMCC.2008.2007246","DOIUrl":"https://doi.org/10.1109/TSMCC.2008.2007246","url":null,"abstract":"Petri nets are a popular mathematical tool to investigate the deadlock problems in resource allocation systems. As an important problem solution paradigm in computer science, the divide-and-conquer strategy is used in this paper to investigate the deadlock prevention for flexible manufacturing systems (FMSs) that are modeled with Petri nets. Based on the concept of resource circuits, a plant net model is divided into an idle subnet, an autonomous subnet, and a number of small but independent subnets, called toparchies, from the viewpoint of deadlock control. A liveness-enforcing supervisor, called toparch, is designed for each toparchy. If a particular separation condition holds in a plant net model, the computational complexity of toparches is significantly reduced. This research shows that the resultant net, called monarch, by composing the toparches derived for the toparchies can serve as a liveness-enforcing Petri net supervisor for the whole plant model. FMS examples are given to illustrate the proposed method.","PeriodicalId":55005,"journal":{"name":"IEEE Transactions on Systems Man and Cybernetics Part C-Applications and Re","volume":"1 1","pages":"156-169"},"PeriodicalIF":0.0,"publicationDate":"2009-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90293212","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 : 2008-11-01DOI: 10.1109/TSMCC.2008.2001570
Vivek Kanhangad, Ajay Kumar, David Zhang
We note that there are some discrepancies in the results reported in the previous titled paper. Our experiments indicate that the authors have considered only a subset of all possible fusion rules, contradicting the statement that all possible rules have been considered. Moreover, the authors state that only monotonic rules can be optimal, and therefore, all other rules can be ignored. However, our experimental results examining all possible rules demonstrate that a nonmonotonic rule can also be an optimum fusion rule.
{"title":"Comments on \"An Adaptive Multimodal Biometric Management Algorithm\"","authors":"Vivek Kanhangad, Ajay Kumar, David Zhang","doi":"10.1109/TSMCC.2008.2001570","DOIUrl":"https://doi.org/10.1109/TSMCC.2008.2001570","url":null,"abstract":"We note that there are some discrepancies in the results reported in the previous titled paper. Our experiments indicate that the authors have considered only a subset of all possible fusion rules, contradicting the statement that all possible rules have been considered. Moreover, the authors state that only monotonic rules can be optimal, and therefore, all other rules can be ignored. However, our experimental results examining all possible rules demonstrate that a nonmonotonic rule can also be an optimum fusion rule.","PeriodicalId":55005,"journal":{"name":"IEEE Transactions on Systems Man and Cybernetics Part C-Applications and Re","volume":"55 1","pages":"841-843"},"PeriodicalIF":0.0,"publicationDate":"2008-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80418678","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 : 2008-01-01DOI: 10.1109/TSMCC.2007.906053
Z. Wang, X. Liu
The six papers in this special section are devoted to intelligent computation and bioinformatics.
本专题的六篇论文是关于智能计算和生物信息学的。
{"title":"Guest Editorial Foreword to the Special Issue on Intelligent Computation for Bioinformatics","authors":"Z. Wang, X. Liu","doi":"10.1109/TSMCC.2007.906053","DOIUrl":"https://doi.org/10.1109/TSMCC.2007.906053","url":null,"abstract":"The six papers in this special section are devoted to intelligent computation and bioinformatics.","PeriodicalId":55005,"journal":{"name":"IEEE Transactions on Systems Man and Cybernetics Part C-Applications and Re","volume":"1 1","pages":"1-2"},"PeriodicalIF":0.0,"publicationDate":"2008-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89753437","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 : 2007-07-01DOI: 10.1109/TSMCC.2007.897325
M. Jeng, Mengchu Zhou
The six papers and one correspondence in this special section focus on the engineering applications of Petri nets.
本专题的六篇论文和一篇通信着重于Petri网的工程应用。
{"title":"Guest Editorial Special Issue on Engineering Applications of Petri Nets","authors":"M. Jeng, Mengchu Zhou","doi":"10.1109/TSMCC.2007.897325","DOIUrl":"https://doi.org/10.1109/TSMCC.2007.897325","url":null,"abstract":"The six papers and one correspondence in this special section focus on the engineering applications of Petri nets.","PeriodicalId":55005,"journal":{"name":"IEEE Transactions on Systems Man and Cybernetics Part C-Applications and Re","volume":"51 1","pages":"442-443"},"PeriodicalIF":0.0,"publicationDate":"2007-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85757546","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 : 2007-03-01DOI: 10.1109/TSMCC.2006.887015
Feiyue Wang, Derong Liu, Simon X. Yang, Li Li
The eight papers in this special issue focus on networking, sensing, and control for networked control systems (NCS). The papers, which are briefly summarized, examine the architectures, algorithms and applications of NCS.
{"title":"Guest Editorial: Networking, Sensing, and Control for Networked Control Systems: Architectures, Algorithms, and Applications","authors":"Feiyue Wang, Derong Liu, Simon X. Yang, Li Li","doi":"10.1109/TSMCC.2006.887015","DOIUrl":"https://doi.org/10.1109/TSMCC.2006.887015","url":null,"abstract":"The eight papers in this special issue focus on networking, sensing, and control for networked control systems (NCS). The papers, which are briefly summarized, examine the architectures, algorithms and applications of NCS.","PeriodicalId":55005,"journal":{"name":"IEEE Transactions on Systems Man and Cybernetics Part C-Applications and Re","volume":"47 1","pages":"157-159"},"PeriodicalIF":0.0,"publicationDate":"2007-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86709015","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 : 2005-11-01DOI: 10.1109/TSMCC.2004.843208
Fei-Yue Wang
Extrinsic calibration or coordinate frame calibration of multiple cameras is a critical step for conducting three-dimensional measurement effectively from visual images. Based on the concept of relative world coordinate system, an efficient method for calibrating the coordinate frames for multiple cameras has been developed in this paper. Its basic idea is to compute the transformation matrices between cameras from their individual transformation matrices to a relative world coordinate system such that its absolute coordinate information is not required and methods for single camera calibration can be utilized. A solution procedure that separates rotational parameters from translation parameters of transformation matrices has been developed where the rotational parameters are obtained first by solving a set of nonlinear equations involving two Euler angular parameters, while the translational parameters are then calculated analytically. In addition, equations for calculating the depth information and matching lines in general cases have been presented. Finally, a detailed numerical investigation regarding the error and sensitivity analysis of the proposed calibration algorithms has been performed extensively.
{"title":"An efficient coordinate frame calibration method for 3-D measurement by multiple camera systems","authors":"Fei-Yue Wang","doi":"10.1109/TSMCC.2004.843208","DOIUrl":"https://doi.org/10.1109/TSMCC.2004.843208","url":null,"abstract":"Extrinsic calibration or coordinate frame calibration of multiple cameras is a critical step for conducting three-dimensional measurement effectively from visual images. Based on the concept of relative world coordinate system, an efficient method for calibrating the coordinate frames for multiple cameras has been developed in this paper. Its basic idea is to compute the transformation matrices between cameras from their individual transformation matrices to a relative world coordinate system such that its absolute coordinate information is not required and methods for single camera calibration can be utilized. A solution procedure that separates rotational parameters from translation parameters of transformation matrices has been developed where the rotational parameters are obtained first by solving a set of nonlinear equations involving two Euler angular parameters, while the translational parameters are then calculated analytically. In addition, equations for calculating the depth information and matching lines in general cases have been presented. Finally, a detailed numerical investigation regarding the error and sensitivity analysis of the proposed calibration algorithms has been performed extensively.","PeriodicalId":55005,"journal":{"name":"IEEE Transactions on Systems Man and Cybernetics Part C-Applications and Re","volume":"7 1","pages":"453-464"},"PeriodicalIF":0.0,"publicationDate":"2005-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80619392","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 : 2005-08-01DOI: 10.1109/TSMCC.2005.848155
Bin Fang, Yuanyan Tang
Sparse data problems are prominent in applications of offline signature verification. By using a small number of training samples, the class statistics estimation errors may be significant, resulting in worsened verification performance. In this paper, we propose two methods to improve the statistics estimation. The first approach employs an elastic distortion model to artificially generate additional training samples for pairs of genuine signatures. These additional samples, together with original genuine samples, are used to compute statistic parameters for a Mahalanobis distance threshold classifier. The other approach is to adopt regularization techniques to overcome the problem of inverting an ill-conditioned sample covariance matrix due to insufficient training samples. A ridge-like estimator is modeled to add some constant values for diagonal elements of the sample covariance matrix. Experimental results showed that both methods were able to improve verification accuracy when they were incorporated with a set of peripheral features. Effectiveness of the methods was validated by quantity analysis.
{"title":"Improved class statistics estimation for sparse data problems in offline signature verification","authors":"Bin Fang, Yuanyan Tang","doi":"10.1109/TSMCC.2005.848155","DOIUrl":"https://doi.org/10.1109/TSMCC.2005.848155","url":null,"abstract":"Sparse data problems are prominent in applications of offline signature verification. By using a small number of training samples, the class statistics estimation errors may be significant, resulting in worsened verification performance. In this paper, we propose two methods to improve the statistics estimation. The first approach employs an elastic distortion model to artificially generate additional training samples for pairs of genuine signatures. These additional samples, together with original genuine samples, are used to compute statistic parameters for a Mahalanobis distance threshold classifier. The other approach is to adopt regularization techniques to overcome the problem of inverting an ill-conditioned sample covariance matrix due to insufficient training samples. A ridge-like estimator is modeled to add some constant values for diagonal elements of the sample covariance matrix. Experimental results showed that both methods were able to improve verification accuracy when they were incorporated with a set of peripheral features. Effectiveness of the methods was validated by quantity analysis.","PeriodicalId":55005,"journal":{"name":"IEEE Transactions on Systems Man and Cybernetics Part C-Applications and Re","volume":"58 1","pages":"276-286"},"PeriodicalIF":0.0,"publicationDate":"2005-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86777232","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 : 2005-08-01DOI: 10.1109/TSMCC.2005.848171
Xiaogang Wang, Xiaoou Tang
In video surveillance, the faces of interest are often of small size. Image resolution is an important factor affecting face recognition by human and computer. In this paper, we propose a new face hallucination method using eigentransformation. Different from most of the proposed methods based on probabilistic models, this method views hallucination as a transformation between different image styles. We use Principal Component Analysis (PCA) to fit the input face image as a linear combination of the low-resolution face images in the training set. The high-resolution image is rendered by replacing the low-resolution training images with high-resolution ones, while retaining the same combination coefficients. Experiments show that the hallucinated face images are not only very helpful for recognition by humans, but also make the automatic recognition procedure easier, since they emphasize the face difference by adding more high-frequency details.
{"title":"Hallucinating face by eigentransformation","authors":"Xiaogang Wang, Xiaoou Tang","doi":"10.1109/TSMCC.2005.848171","DOIUrl":"https://doi.org/10.1109/TSMCC.2005.848171","url":null,"abstract":"In video surveillance, the faces of interest are often of small size. Image resolution is an important factor affecting face recognition by human and computer. In this paper, we propose a new face hallucination method using eigentransformation. Different from most of the proposed methods based on probabilistic models, this method views hallucination as a transformation between different image styles. We use Principal Component Analysis (PCA) to fit the input face image as a linear combination of the low-resolution face images in the training set. The high-resolution image is rendered by replacing the low-resolution training images with high-resolution ones, while retaining the same combination coefficients. Experiments show that the hallucinated face images are not only very helpful for recognition by humans, but also make the automatic recognition procedure easier, since they emphasize the face difference by adding more high-frequency details.","PeriodicalId":55005,"journal":{"name":"IEEE Transactions on Systems Man and Cybernetics Part C-Applications and Re","volume":"29 1","pages":"425-434"},"PeriodicalIF":0.0,"publicationDate":"2005-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87749583","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：