This paper presents a new method for computing the discriminant vectors of the Foley–Sammon optimal set. First, an equivalent criterion is presented to replace the Fisher criterion; then, the problem of computing the...
详细信息
This paper presents a new method for computing the discriminant vectors of the Foley–Sammon optimal set. First, an equivalent criterion is presented to replace the Fisher criterion; then, the problem of computing the discriminant vectors in R n is transformed into the maximum problem in a subspace. Several theorems relating to the method are also presented. Experimental results show that the present method is superior to the positive pseudoinverse method, and the perturbation method in terms of correct classification rate.
The authors consider the analysis of stochastic Petri net models with generally distributed transition firing times. A so-called hybrid state analysis method is developed. The basic idea is to make the extended state,...
详细信息
The authors consider the analysis of stochastic Petri net models with generally distributed transition firing times. A so-called hybrid state analysis method is developed. The basic idea is to make the extended state, i.e., the hybrid state, which is composed of a marking and the enabling times of enabled transitions under the marking, propagate as a Markov process by the inclusion of supplementary variables. The recursive equation of hybrid state density functions is given.< >
The authors consider a fuzzy controller that processes fuzzy information. They discuss the model of the fuzzy controller, with fuzzy inputs for error and change in error, using a max-min neural network. A new learning...
详细信息
The authors consider a fuzzy controller that processes fuzzy information. They discuss the model of the fuzzy controller, with fuzzy inputs for error and change in error, using a max-min neural network. A new learning algorithm, a modified delta rule, is derived. The generalization property of the neural net can be used to find a controller output for new fuzzy values of error and change in error. An example is presented showing the applicability of the fuzzy neural controller.< >
Applications of three types of fuzzy neural networks are presented: crisp signals used to evaluate fuzzy weights; fuzzy signals combined with fuzzy weights; and fuzzy signals transformed by a fuzzy neuron (no weights)...
详细信息
Applications of three types of fuzzy neural networks are presented: crisp signals used to evaluate fuzzy weights; fuzzy signals combined with fuzzy weights; and fuzzy signals transformed by a fuzzy neuron (no weights). The applications are drawn from the fuzzy controller, system identification, and fuzzy expert systems. In all cases a learning algorithm is proposed. In each case, a brief review is presented of the model of the fuzzy neuron, together with a detailed discussion of the application of the neural network built up of these fuzzy neurons.< >
It is proven that any continuous, layered, feedforward neural net can be approximated to any degree of accuracy by a (discrete) fuzzy expert system, and that any continuous, discrete, fuzzy expert system with one bloc...
详细信息
It is proven that any continuous, layered, feedforward neural net can be approximated to any degree of accuracy by a (discrete) fuzzy expert system, and that any continuous, discrete, fuzzy expert system with one block of rules may be approximated to any degree of accuracy by a three layered, feedforward neural net. The second result may be generalized to multiple blocks of rules by considering total (discrete) input and total (discrete) output from the fuzzy expert system. It is concluded that fuzzy expert systems and neural nets can both approximate functions (mappings, systems).< >
The direct fuzzification of a standard layered feedforward neural network where the signals and weights are fuzzy sets is discussed. A fuzzified delta rule is presented for learning. Three applications are given, incl...
详细信息
The direct fuzzification of a standard layered feedforward neural network where the signals and weights are fuzzy sets is discussed. A fuzzified delta rule is presented for learning. Three applications are given, including modeling a fuzzy expert system; performing fuzzy hierarchical analysis based on data from a group of experts; and modeling a fuzzy system. Further applications depend on proving that this fuzzy neural network can approximate a continuous fuzzy function to any degree of accuracy on a compact set.< >
The authors describe a rule-based fuzzy expert system using a method of approximate reasoning to evaluate the rules when given new data. It is argued that any fuzzy expert system using one block of rules can be approx...
详细信息
The authors describe a rule-based fuzzy expert system using a method of approximate reasoning to evaluate the rules when given new data. It is argued that any fuzzy expert system using one block of rules can be approximated. The theory is generalized to networks of neural nets and fuzzy expert systems using multiple interconnected blocks of rules. The authors demonstrate how the neural net is trained, and how the rules in the fuzzy expert system are written. An example illustrating these ideas is presented.< >
The fault recognition is a constructional problem involved in the plane inter-pretation of seismic *** paper presents a fault recognition expert system(FRES)built on blackboard model and introduces its technical chara...
详细信息
The fault recognition is a constructional problem involved in the plane inter-pretation of seismic *** paper presents a fault recognition expert system(FRES)built on blackboard model and introduces its technical characteristics such as rea-soning about control,focusing by step,integration of human inteUigcnce and machine in-telligence.
This paper proposes a methodology of combining eigenstructure assignment, feedforward gain with sliding mode control technique to realize an enhanced robust pitch pointing flight control system. This control system ca...
详细信息
This paper proposes a methodology of combining eigenstructure assignment, feedforward gain with sliding mode control technique to realize an enhanced robust pitch pointing flight control system. This control system can track step input commands without error and it turns out to be consistently robust against parameter variations and external disturbances. The design methodology is illustrated by application to an AFTI/F-16 aircraft.
A general state-space model of a two-dimensional linear multivariable discrete system was introduced by Kurek [1]. This model includes the 2-D models of Attasi [2], Roesser [3], and Fornasini and Marchesini [4]. In th...
详细信息
A general state-space model of a two-dimensional linear multivariable discrete system was introduced by Kurek [1]. This model includes the 2-D models of Attasi [2], Roesser [3], and Fornasini and Marchesini [4]. In this paper, a novel approach for computing the transfer function, the characteristic polynomial, and the adjoint matrix of the Kurek model is given. The procedure involves representation of the system characteristic equation in a matrix polynomial.
暂无评论