Mandan Liu

Learn More
This paper presents a cultural algorithm (CA) based on multilayer belief spaces that selects the best belief space from the multilayer belief spaces to guide the search of population space. The selected best belief space exploits knowledge extracted during the search to improve the performance of an evolutionary algorithm. We integrate cultural algorithm(More)
During optimize the weights of Elman recurrent neural networks by genetic algorithm, if use simple genetic algorithm, two problems appear: constringency too early and the speed of search too slow in the anaphase. Aim at these problems, an improved Niche genetic algorithm is presented in this paper. Simulation results show that this algorithm can achieve(More)
Clustering techniques have emerged as a popular choice for achieving energy efficiency and scalable performance in large scale sensor networks. In order to achieve efficient use of energy networks that extend the network time, increase the amount of data transfer, this study and reference in many previous proposed clustering algorithms, this paper(More)
In order to balance the energy consumption of the wireless sensor network(W SN), this paper studies the traditional routing protocol HEED, and proposed an inter-cluster multi-hop routing protocol NHEED (A New kind of multi-hop routing protocol based on HEED). To process the isolate node product by HEED, the NHEED use a method add the isolate node to nearest(More)
In this contribution, a Bayes Ying-Yang(BYY) harmony based approach for on-line signature verification is presented. In the proposed method, a simple but effective Gaussian Mixture Models(GMMs) is used to represent for each user's signature model based on the prior information collected. Different from the early works, in this paper, we use the Bayes Ying(More)
In this paper, an emerging artificial neural network is proposed and researched. The differential of exciting intensity of each neuron is mutually feedback to each other in the network. Hence the overall network turns out to be a high-order nonlinear system. Besides, the iterative equations are derived by discretizing the state equations. In this way, the(More)
Effective monitoring and early warning for cracking severity are directly related to the ethylene production stability and the overall economic benefits. Elman neural network is used to establish the early warning model of cracking severity, and an improved Cultural Differential Evolution algorithm(ICDE) is proposed to training the model. This hybrid(More)
A new improved Elman neural network, OAIF-Elman(output-add-input feedback Elman) network is presented based on the Elman neural network in this paper. The new Elman network is endowed with state-feedback and output-feedback by an additional output-context layer, which is added to the former input to get a new input of network. It is applied for setting up(More)