A recurrent neural network with a self-organizing structure based on the dynamic analysis of a task is presented in this paper. The stability of the recurrent neural network is guaranteed by design. A dynamic analysis method to sequence the subsystems of the recurrent neural network according to the fitness between the subsystems and the target system is developed. The network is trained with t...

A recurrent neural network with a self-organizing structure based on the dynamic analysis of a task is presented in this paper. The stability of the recurrent neural network is guaranteed by design. A dynamic analysis method to sequence the subsystems of the recurrent neural network according to the fitness between the subsystems and the target system is developed. The network is trained with t...

In order to analyze the evolvement trend of the network threat and to explore the self-perception and control problem of the security situation, the dynamic wavelet neural network model is integrated into the model design, and a kind of network security situation awareness based on the optimized dynamic wavelet neural network is put forward, so as to enhance the interaction and cognitive abilit...

We examine the dynamic formation and stochastic evolution of networks connecting individuals. The payoff to an individual from an economic or social activity depends on the network of connections among individuals. Over time individuals form and sever links connecting themselves to other individuals based on the improvement that the resulting network offers them relative to the current network....

In this paper, we focus on the optimization of the Rete algorithm on aspects of memory consumption and time-consuming in matching process. Facing the problem of requirement of limited memory and quick response from users in the rule pattern matching process of dynamic evolution of software system,on the basis of the classic Rete algorithm and from the perspective of the complexity of algorithm ...

in this paper, a novel neuro-fuzzy based method combined with a feature selection technique is proposed for online dynamic voltage stability status prediction of power system. this technique uses synchronized phasors measured by phasor measurement units (pmus) in a wide-area measurement system. in order to minimize the number of neuro-fuzzy inputs, training time and complication of neuro-fuzzy ...

background: understanding customers has become an urgent topic for increasing competitiveness. the purpopse of  the study was to develop a qualitative dynamic attribute value model which provides insight into the customers' value for healthcare institute managers by conducting the initial open-ended questionnaire survey to select participants purposefully. methods: a total number of 427 questio...

This paper proposes an original generic hierarchical framework in order to facilitate the modeling stage of complex autonomous robotics mission planning problems with action uncertainties. Such stochastic planning problems can be modeled as Markov Decision Processes [5]. This work is motivated by a real application to autonomous search and rescue rotorcraft within the ReSSAC project at ONERA. A...