NP hard problems have appeared in many areas. In this article, it is discussed how to solve this kind of problems using artificial neural network— Hopfield/Tank model, especially the Travelling Salesman Problem (TSP...NP hard problems have appeared in many areas. In this article, it is discussed how to solve this kind of problems using artificial neural network— Hopfield/Tank model, especially the Travelling Salesman Problem (TSP). At first, a stability analysis shows the conditions of the model to converge to the vertices of the hypercube and its relation with the parameters. And then, a HT model for solving TSP is formulated. Some theorems are given to analyze the influence of parameter D on the three subspaces of the connection matrix in which D is set to zero. Based on these analyses, a dynamic analysis of the model is given and a set of parameters′ rules are established. It is indicated that, if the parameters are selected according to these rules, the final solutions are optimal or near optimal. However, the initial noise would have some influences on the final solutions. According to these theories, a 'damping' optimal method is proposed which can not only guarantee the final solutions are high quality, but also weaken the influence of the initial noise. On the other hand, many kinds of modified HT models are summarized and a more simple and effective model is given. Compared with some traditional and modern methods for solving TSP, the performance of our method is very good. Linking with the practice, some applications are exploited. Our method has also been used for programming the posts route of some city in China. Finally, a theoretical analysis is given for com munication network routing problem using HT model. Liu Rong Born in October 1966. He received the Engineering Ph.D in Beijing University Posts and Telecommunications in April 1994.展开更多
Now, the problem of modeling MPEG 1 video traffic still needs studying further. Based on the analysis of statistical characteristics of this kind of traffic, this paper presents a new traffic model. Simulation result...Now, the problem of modeling MPEG 1 video traffic still needs studying further. Based on the analysis of statistical characteristics of this kind of traffic, this paper presents a new traffic model. Simulation results show that the proposed model can reflect the statistical characteristics of the real MPEG 1 video traffic well.展开更多
In packet switched communication networks, traffic between any source destination (SD) pair is expected to be transmitted over multiple paths. In this paper, we focus on the problem how to optimally distribute the l...In packet switched communication networks, traffic between any source destination (SD) pair is expected to be transmitted over multiple paths. In this paper, we focus on the problem how to optimally distribute the load on a set of paths so that the overall network performance is maximized. This problem is first formulated as a nonlinear programming problem and then we propose a neural network (NN) to solve it. The NN architecture is discussed in detail. At last, we verify the effectiveness of our approach by applying it to a specific network model. The experimental results demonstrate that our method can yield optimal solutions with good stability.展开更多
So far, the problem of the harmonic retrieval with quadratic phase coupling in mixed noises has not been resolved well. For this reason, this paper, based on the third , forth order cumulants and Hilbert transform, ...So far, the problem of the harmonic retrieval with quadratic phase coupling in mixed noises has not been resolved well. For this reason, this paper, based on the third , forth order cumulants and Hilbert transform, proposes a new method named HBTFCH SVD TLS.The method can realize harmonic retrieval in mixed noises even when the harmonic signal includes the components of quadratic phase coupling.Simulation results show the effectiveness of the method.展开更多
文摘NP hard problems have appeared in many areas. In this article, it is discussed how to solve this kind of problems using artificial neural network— Hopfield/Tank model, especially the Travelling Salesman Problem (TSP). At first, a stability analysis shows the conditions of the model to converge to the vertices of the hypercube and its relation with the parameters. And then, a HT model for solving TSP is formulated. Some theorems are given to analyze the influence of parameter D on the three subspaces of the connection matrix in which D is set to zero. Based on these analyses, a dynamic analysis of the model is given and a set of parameters′ rules are established. It is indicated that, if the parameters are selected according to these rules, the final solutions are optimal or near optimal. However, the initial noise would have some influences on the final solutions. According to these theories, a 'damping' optimal method is proposed which can not only guarantee the final solutions are high quality, but also weaken the influence of the initial noise. On the other hand, many kinds of modified HT models are summarized and a more simple and effective model is given. Compared with some traditional and modern methods for solving TSP, the performance of our method is very good. Linking with the practice, some applications are exploited. Our method has also been used for programming the posts route of some city in China. Finally, a theoretical analysis is given for com munication network routing problem using HT model. Liu Rong Born in October 1966. He received the Engineering Ph.D in Beijing University Posts and Telecommunications in April 1994.
文摘Now, the problem of modeling MPEG 1 video traffic still needs studying further. Based on the analysis of statistical characteristics of this kind of traffic, this paper presents a new traffic model. Simulation results show that the proposed model can reflect the statistical characteristics of the real MPEG 1 video traffic well.
文摘In packet switched communication networks, traffic between any source destination (SD) pair is expected to be transmitted over multiple paths. In this paper, we focus on the problem how to optimally distribute the load on a set of paths so that the overall network performance is maximized. This problem is first formulated as a nonlinear programming problem and then we propose a neural network (NN) to solve it. The NN architecture is discussed in detail. At last, we verify the effectiveness of our approach by applying it to a specific network model. The experimental results demonstrate that our method can yield optimal solutions with good stability.
文摘So far, the problem of the harmonic retrieval with quadratic phase coupling in mixed noises has not been resolved well. For this reason, this paper, based on the third , forth order cumulants and Hilbert transform, proposes a new method named HBTFCH SVD TLS.The method can realize harmonic retrieval in mixed noises even when the harmonic signal includes the components of quadratic phase coupling.Simulation results show the effectiveness of the method.
