摘要：
Variable selection has been extensively studied in linear regression and classification models. Most of these models assume that the input variables are noise free, the response variables are corrupted by Gaussian noise. In this paper, we discuss the variable selection problem assuming that both input variables and response variables are corrupted by Gaussian noise. We analyze the prediction error when augment one related noise variable. We show that the prediction error always decrease when more variable were employed for prediction when the joint distribution of variables are known. Based on this analysis, in sense of mean square error, the optimal variable selection can be obtained. We found that the results is very different from the matching pursuit algorithm(MP), which is widely used in variable selection problems.
期刊：
Applied Mechanics and Materials,2014年530-531:15-18 ISSN：1662-7482
作者机构：
[Gao, Lu] School of Electrical and Electronic Engineering, Wuhan Polytechnic University, Wuhan, China;[Li, Zhong Min] School of Information Engineering, Nanchang Hangkong University, Nanchang, China
会议名称：
2014 International Conference on Sensors Instrument and Information Technology, ICSIIT 2014
摘要：
In the applications based on Wireless Sensor Networks (WSNs) , localization is one of the most fundamental and important technologies if the accurate location information cant be determined, these application cant be accomplished. Then main idea in localization algorithms is that every unknown node in WSN can localize itself by position information from the landmarks or other nodes. in the last years localization is still a hot field and some new algorithms are proposed. In this paper, the localization algorithms are classified on the basis of the way to get position information, and a simple analysis is present. the paper are ended by discussing some open issues.
摘要：
Particle swarm optimization (PSO) is a new intelligent search technique, which is inspired by swarm intelligence. Although PSO has shown good performance in many benchmark optimization problems, it suffers from premature convergence in solving complex multimodal problems. In this paper, we propose a novel PSO algorithm, called PSO with a simulated binary crossover operator (SCPSO), to improve the performance of PSO. Experimental results on several benchmark problems show that SCPSO achieves better performance than standard PSO.
期刊：
Solid State Communications,2014年185:30-34 ISSN：0038-1098
通讯作者：
Huang, H. L.
作者机构：
[Huang, H. L.; Wu, Y. Y.; Sun, Z. Y.] Wuhan Polytech Univ, Sch Elect & Elect Engn, Wuhan 430000, Peoples R China.;[Wang, B.] ENN Grp Co Ltd, Langfang 065001, Hebei, Peoples R China.
通讯机构：
[Huang, H. L.] W;Wuhan Polytech Univ, Sch Elect & Elect Engn, Wuhan 430000, Peoples R China.
关键词：
A. Two-dimensional spin model;D. Bell inequality;D. Nonlocality;D. Phase transition
摘要：
In this paper, we use the Bell inequality to study the bipartite correlation in an exactly soluble two-dimensional Ising-Heisenberg spin system. The Bell inequality can detect not only the quantum phase transition, but also the thermal phase transitions, or the system. The property or bipartite correlation in the system is also analyzed. In the quantum anti-ferromagnetic phase, the Bell inequality is violated thus nonlocality is present. It is interesting that the nonlocality is enhanced by thermal fluctuation, and similar results have not been observed in anti-ferromagnetic phases. In the ferromagnetic phase, the quantum correlation turns out to be very novel, which cannot be captured by entanglement or nonlocality. (C) 2014 Elsevier Ltd. All rights reserved.
期刊：
Applied Mechanics and Materials,2014年543-547:164-167 ISSN：1660-9336
作者机构：
[Yu, Nan Hui] School of Mechanical Engineering, Wuhan Polytechnic University, Wuhan, 430023, China;[Fan, Ji Jun] School of Electrical and Electronic Engineering, Wuhan Polytechnic University, Wuhan, 430023, China
会议名称：
International Conference on Vehicle and Mechanical Engineering and Information Technology, VMEIT 2014
会议时间：
19 February 2014 through 20 February 2014
关键词：
Finite Element Method (FEM);Press Cage;Screw Press;Stress Analysis
摘要：
Microstructure evolution and size effect of a two-dimensional barium titanate lattice sqaure have been studied using phase-field simulation. Based on the Landau phenomenological model, we calculated the microstructure evolution of the tetragonal and orthorhombic ferroelectric BaTiO3 started from a single domain with various lattice sizes. A direction-dependent hysteresis loop can be quantitatively described. The results show that both the phase transition with temperature and polarization switching under an external electric field are accompanied by multidomain and multiphase production in a large single-domain lattice, but synchronous changes in polarization in small lattice; As the grain size decreases, the orthorhombic -> tetragonal phase-transition temperature increased, while the tetragonal -> cubic, cubic -> tetragonal, and tetragonal -> orthorhombic phase-transition temperatures decrease. An interesting conclusion is that it shows triple hysteresis loops along the [11]-direction when the lattice size decreases to a certain size. The simulations of microstructure evolutions not only produce a good domain-switching process under various electric fields, but also provide a comprehensive microstructure evolution in the vicinity of the phase-transition points. The physics underlying the continuous evolution of microstructure with electric field and temperature is discussed. (C) 2014 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim
