In this paper the application of Fuzzy Cognitive Map (FCM) in controlling a process problem and its use in modelling Supervisory Manufacturing Systems is presented. The description, construction and the mathematical m...
详细信息
In this paper the application of Fuzzy Cognitive Map (FCM) in controlling a process problem and its use in modelling Supervisory Manufacturing Systems is presented. The description, construction and the mathematical model of Fuzzy Cognitive Map are examined. Then, a chemical process is modelled with FCM and its behaviour is simulated and the application of Fuzzy Cognitive Maps in the mode ling of the Supervisor of Manufacturing Systems is discussed.
This paper introduces the concept of cross-positivity for vector fields and explores ramifications of cross-positivity relative to solutions of ordinary differential equations. The motivation is to understand the dyna...
详细信息
Patients with sustained ventricular tachycardia and ventricular fibrillation have a potential for sudden death. After myocardial infarction the chance to get sustained ventricular tachycardia or ventricular fibrillati...
详细信息
Patients with sustained ventricular tachycardia and ventricular fibrillation have a potential for sudden death. After myocardial infarction the chance to get sustained ventricular tachycardia or ventricular fibrillation increases, thus reduction in number of sudden death requires advanced predictive procedures. In this study, frequency domain feature extraction, clustering and classification models are combined for providing an integrated system for the sustained ventricular arrythmias. The radial basis function network and the fuzzy c-means algorithm for training clustering and classification were investigated. These techniques do not have limitation of the previous classical procedures. The value of sensitivity and specificity, on the data was used here, for the RBFN were found to be 92.3% and 71.4%, respectively, also the value of sensitivity and specificity for the PCM were found to be 84.6% and 71.4%, respectively.
The main objective of the research project reported in this paper is to design an assistive device that will help patients with eye-implant to have natural eye movement. The patients lose their eye for various reasons...
详细信息
The main objective of the research project reported in this paper is to design an assistive device that will help patients with eye-implant to have natural eye movement. The patients lose their eye for various reasons. The loss of an eye can be solved by the ocular implant. The artificial eye can be made like a real eye cosmetically. But the problem is that it is static and does not have the natural movement of an eye. We design an ocular assistive system to enable the artificial eye have the natural movement of a real eye. This paper starts with the literature review of the eye movement detection methods and followed by the description of the experimental system we designed and constructed. The paper is concluded with further considerations.
We present the results of an empirical study in which we evaluated cost-sensitive learning algorithms on a rooftop detection task, which is one level of processing in a building detection system. Specifically, we inve...
详细信息
We present the results of an empirical study in which we evaluated cost-sensitive learning algorithms on a rooftop detection task, which is one level of processing in a building detection system. Specifically, we investigated how well machine learning methods generalized to unseen images that differed in location and in aspect. For the purpose of comparison, we included in our evaluation a handcrafted linear classifier, which is the selection heuristic currently used in the building detection system. ROC analysis showed that, when generalizing to unseen images that differed in location and aspect, a naive Bayesian classifier outperformed nearest neighbor and the handcrafted solution.
This article presents and compares two neural network-based approaches to global self-localization (GSL) for autonomous mobile robots using: (1) a Kohonen neural network, and (2) a region-feature neural network (RFNN)...
作者:
Peter GroumposBary IlyasovLarisa IsmagilovaRoza ValeevaUniversity of Patras
Department of Electrical and Computer Engineering Laboratory for Automation & Robotics GR-265 00 Rion Greece Fax: +30 61 997 309 Ufa State Aviation Technical University Department of Technical Cybernetics 12 K.Marx Street Ufa 450000 Russia Fax: (347-2) 22-29-18 Ufa State Aviation Technical University
Department of Technical Cybernetics 12 K.Marx Street Ufa 450000 Russia Fax: (347-2) 22-29-18
The problem of production control as of a complex dynamic object is under discussion. There are elaborated and studied intelligent control algorithms using modelling results of system functioning dynamics which testif...
详细信息
The problem of production control as of a complex dynamic object is under discussion. There are elaborated and studied intelligent control algorithms using modelling results of system functioning dynamics which testify to uncertainty of environment. The proposed procedure of information exchange allows to unit effectively the dynamic and intelligent algorithms as well as man participation in decision making.
In this paper, we derive tracking control laws for non-minimum phase nonlinear systems with both fast and slow, possibly unstable, zero dynamics. The fast zero dynamics arise from a perturbation of a nominal system. T...
详细信息
In this paper, we derive tracking control laws for non-minimum phase nonlinear systems with both fast and slow, possibly unstable, zero dynamics. The fast zero dynamics arise from a perturbation of a nominal system. These fast zeros can be problematic in that they may be in the right half plane and may cause large magnitude tracking control inputs. In this paper, we combine the ideas from some recent work of Hunt, Meyer and Su with that of Devasia, Chen and Paden on an asymptotic tracking procedure for non-minimum phase nonlinear systems. We give (somewhat subtle) conditions under which the tracking control input is bounded as the magnitude of the perturbation of the nominal system becomes zero. Explicit bounds on the control inputs are calculated for both SISO and MIMO systems using some interesting non-standard singular perturbation techniques. The method is applied to a suite of examples, including the simplified planar dynamics of VTOL and CTOL aircraft.
This paper investigates the application of conventional and neural adaptive control schemes to Gas Metal Are (GMA) welding. The goal is to produce welds of high quality and strength. This can be achieved through prope...
详细信息
This paper investigates the application of conventional and neural adaptive control schemes to Gas Metal Are (GMA) welding. The goal is to produce welds of high quality and strength. This can be achieved through proper on-line control of the geometrical and thermal characteristics of the process. The welding process is variant in time and strongly nonlinear, and is subject to many defects due to improper regulation of parameters like arc voltage and current, or travel speed of the torch. Adaptive control is thus naturally a very good candidate for the regulation of the geometrical and thermal characteristics of the welding process. Here four adaptive control techniques are reviewed and tested, namely: model reference adaptive control (MRAC), pseudogradient adaptive control (PAC), multivariable self-tuning adaptive control (STC), and neural adaptive control (NAC). Extensive numerical results are provided, together with a discussion of the relative merits and limitations of the above techniques.
作者:
Tzafestas, SGProkopiou, PAIntelligent
Robotics and Automation Laboratory Computer Science Division Department of Electrical and Computer Engineering National Technical University of Athens Zografou Campus 15773 Athens Greece
The response of a previously proposed teleoperator system, which was not based on the traditional notion of telepresence but on an original form of kinesthetic feedback, is tested under modeling errors of up to 50%. T...
详细信息
The response of a previously proposed teleoperator system, which was not based on the traditional notion of telepresence but on an original form of kinesthetic feedback, is tested under modeling errors of up to 50%. The original system is enhanced by replacing the previous controller of each robot with a sliding mode robust one. A two-stage approach is employed: a desired trajectory is first generated and then tracked by the controller. The difficulties incurred for the man/machine cooperation are discussed. This extension of the original teleoperator architecture is tested through simulations and compared with a twin system based on neural controllers, presented elsewhere. (C) 1997 Elsevier Science Ltd.
暂无评论