Catálogo de publicaciones - libros

The high performance cryptographic chip is the core unit of the network information safety equipments. This paper proposes the design approach of the AES cryptographic system based on reconfigurable hardware, develops the method of key-sequence generation with the genetic algorithm that realizes different cipher key in every encryption round. The system has been implemented on Virtex-E FPGA. The result proves that the new design technology is feasible, and the security level of the AES is improved.

Compared with traditional Back Propagation (BP) neural network, the advantages of fuzzy neural network in fault diagnosis are analyzed. A new diagnosis method based on genetic algorithm (GA) and fuzzy Radial Basis Function (RBF) neural network is presented for complicated machinery system. Fuzzy membership functions are obtained by using RBF neural network, and then genetic algorithm is applied to train fuzzy RBF neural network. The trained fuzzy RBF neural network is used for fault diagnosis of ship main power system. Diagnostic results indicate that the method is of good generalization performance and expansibility. It can significantly improve the diagnostic precision.

A low-cost infrared and Neuro-Fuzzy-based approach for identification and classification of road markings is presented in this paper. The main task of the designed prototype, implemented at the University of La Laguna, is to collect information by a set of infrared sensors and to process it in an intelligent mode. As an example, it should inform the driver about the different signs and elements it is driving on, complementing other well-known and widely used security devices. For the identification and classification stages, a Neuro-Fuzzy approach has been chosen; given it is a good option in order to get fuzzy rules and memberships functions in an automatic way.

In this paper we introduce negation into Logical Markov Decision Processes, which is a model of Relational Reinforcement Learning. In the new model nLMDP the abstract state space can be constructed in a simple way, so that a good property of complementarity holds. Prototype action is also introduced into the model. A distinct feature of the model is that applicable abstract actions can be obtained automatically with valid substitutions. Given a complementary abstract state space and a set of prototype actions, a model-free Θ-learing method is implemented for evaluating the state-action-substitution value funcion.

A new two-stage optimization model for mobile agent routing in the wireless sensor network is presented as a integer linear programming problem based on the virtual connection topology sub graph. In the model, the solution is presented by two subpaths instead of the closed path which is usually applied in many path search methods to keep balance between computation cost and accuracy. A hybrid technique of genetic algorithm (GA) integrated with discrete particle swarm optimization (PSO), GAPSO is designed to solve the problem. Simulation experiments with different sizes and distributions of nodes show the effectiveness of the new model and GAPSO algorithm.

Stochastic Shortest Path problems (SSPs), a subclass of Markov Decision Problems (MDPs), can be efficiently dealt with VI, PI, RTDP, LAO* and so on. However, in many practical problems the estimation of the probabilities is far from accurate. In this paper, we present uncertain transition probabilities as close real intervals. Also, we describe a general algorithm, called gLAO*, that can solve uncertain MDPs efficiently. We demonstrate that Buffet and Aberdeen’s approach, searching for the best policy under the worst model, is a special case of our approaches. Experiments show that gLAO* inherits excellent performance of LAO* for solving uncertain MDPs.

We present a new local obstacle avoidance approach for mobile robots in partially known environments on the basis of the curvature-velocity method (CVM), the lane-curvature method (LCM) and the beam-curvature method (BCM). Not only does this method inherit the advantages from both BCM and LCM, but also it combines the prediction model of collision with BCM perfectly so that the so-called prediction based BCM (PBCM) comes into being and can be used to avoid moving obstacles in dynamic environments.

Management software is required to be adaptive and scalable since the managed objects become more and more dynamic and complex. In this paper, we introduce cognitive concepts to deal with the complexity in developing management software, and an interactive intelligent agency framework, called iSMAcy (intelligent System Management Agency), is developed as an integrated solution to realize adaptive system management. The cognitive concepts are applied at two levels. At micro level, the intentional agent kernel of functional agent use mental states such as beliefs, goals and intentions to realize integration of goal-directed behavior with situated reactive action. At macro level, high-level cognitive semantics such as goals, requests and commitments are interchanged among agents. An example of applying iSMAcy system on a simulated network management environment is described, and the efficiency of the intentional agent kernel is analyzed to ensure the reactivity of iSMAcy system.

The purpose of this paper is to investigate the use of hybrid intelligent control to aircraft automatic landing system. Current flight control law is adopted in the intelligent controller design. Tracking performance and adaptive capability are demonstrated through software simulations. Two control schemes that use neural network controller and neural controller with particle swarm optimization are used to improve the performance of conventional automatic landing system. Control gains are selected by particle swarm optimization. Hardware implementation of this intelligent controller is performed by DSP with VisSim platform. The proposed intelligent controllers can successfully expand the controllable environment in severe wind disturbances.

In this paper we first give a new method of time series model to forecast GDP of China. The method proposed here aims to emphasis the importance of the impact of STEP-Affair on the GDP forecasting. The superiority of the method to ARMA model is illustrated in an example presented accordingly. Then in the system of whole economic when the GDP forecasted above is given, how can we allocate the limited resources to make the economical behavior relative efficient. We use data envelopment analysis to show how to determine input interval. Each input among the input interval as well as the given output constitute an efficient decision making unit (DMU). For decision makers the techniques are very important in decision making, especially in macroeconomic policies making in China.