高氧化态（Ⅱ─Ⅳ）三核金属簇合物构型的人工神经网络判别方法

本文运用一典型的人工神经网络模型─“反向传播”模型，对高氧化态（Ⅱ─Ⅳ）三核金属簇合物的构型分布进行了分析，得到了较好的分类、预报结果为化合物结构分析提供了新的工具。     

Improving signal prediction performance of neural networks through multiresolution learning approach.

In this paper, we extend the original work on multiresolution learning for neural networks, and present new developments on the multiresolution learning paradigm. The contributions of this paper include: (1) proposing a new concept and method of adjustable neural activation functions in multiresolution learning to improve neural network learning efficacy and generalization performance for signal predictions; (2) providing new insightful explanations for the multiresolution learning paradigm from a multiresolution optimization perspective; (3) exploring underlying ideas why the multiresolution learning scheme associated with adjustable activation functions would be more appropriate for the multiresolution learning paradigm; and (4) providing rigorous validations to evaluate the multiresolution learning paradigm with adjustable activation functions and comparing it with the schemes of multiresolution learning with fixed activation functions and traditional learning. This paper presents systematically new analytical and experimental results on the multiresolution learning approach for training an individual neural network model, demonstrates our integral solution on neural network learning efficacy, and illustrates the significant improvements on neural networks' generalization performance and robustness for nonlinear signal predictions.     

Synthesis of TiO<Subscript>2</Subscript> Hybrid Molecular Imprinted Polymer for Ethofumesate Linked by Silane Coupling Agent

TiO₂ hybrid molecular imprinted polymer (MIP) for ethofumesate using methacrylic acid (MAA) as the functional monomer and silane coupling agent 3-(trimethoxysilyl) propylmethacrylate (KH570) as organic–inorganic connective bridge was synthesized via photo-excitation method. Hydrogen bond was proved to act between MAA and ethofumesate for pre- and post-polymerization binding properties as testified by UV spectrometric method. KH570 modified TiO₂ nanoparticles were prepared via sonochemical reaction, which can accelerate hydrolysis, increase collision chance for the reactive system and improve the dispersion of the nanoparticles. Scanning electron microscope (SEM), transmission electron microscope (TEM), binding and the adsorption kinetics experiments as well as thermogravimetric analysis (TGA) were employed for characterization. The results indicated that the hybrid MIP revealed a larger surface area and more ordered imprinting cavities with improved thermal stability compared to organic-only MIP. Furthermore, faster adsorption kinetics and enhancive adsorption capacity were achieved, which made it promising in chemical sensor applications.     

One-to-Many and Many-to-One Optical Chaos Communications Using Semiconductor Lasers

A theoretical construction of one-to-many (OTM) and many-to-one (MTO) chaos synchronization communications using semiconductor lasers is presented. One center laser provides strong injections (strong link) to other side lasers, and the side lasers also provide weak injections (weak link) to the center one. Simulation results show that the side lasers synchronize with the center laser through injection-locking. In addition, messages transmitted via the strong links or the weak links experience strong chaos pass filtering, enabling us to realize OTM and MTO communications.     

Evolving artificial neural network ensembles

Using a coordinated group of simple solvers to tackle a complex problem is not an entirely new idea. Its root could be traced back hundreds of years ago when ancient Chinese suggested a team approach to problem solving. For a long time, engineers have used the divide-and-conquer strategy to decompose a complex problem into simpler sub-problems and then solve them by a group of solvers. However, knowing the best way to divide a complex problem into simpler ones relies heavily on the available domain knowledge. It is often a manual process by an experienced engineer. There have been few automatic divide-and-conquer methods reported in the literature. Fortunately, evolutionary computation provides some of the interesting avenues to automatic divide-and-conquer methods. An in-depth study of such methods reveals that there is a deep underlying connection between evolutionary computation and ANN ensembles. Ideas in one area can be usefully transferred into another in producing effective algorithms. For example, using speciation to create and maintain diversity had inspired the development of negative correlation learning for ANN ensembles, and an in-depth study of diversity in ensembles. This paper will review some of the recent work in evolutionary approaches to designing ANN ensembles.     

Prognostic factors of early sequelae and fatal outcome of Japanese encephalitis

A clinical case control study to identify prognostic factors present at hospital admission associated with early sequelae and fatal outcome of acute Japanese encephalitis (JE) was carried out in Gusi county, Henan Province, central China from June to September 1991. A total of 70 patients with laboratory-confirmed acute JE were studied, of whom 3 cases died and 33 cases had neurological or psychiatric sequelae at the end of three months follow-up. The results showed that acute JE at younger age, with higher body temperature, high white cell count in CSF, and deep coma present at hospital admission were markers for unfavorable outcomes (sequelae or fatal). A history of the vaccination was not correlated with the early sequelae and fatal outcome of the disease. The paper suggests that early diagnosis and treatment and universal JE vaccination for all susceptible populations are keys for decreasing incidence of sequelae and fatal outcome of acute JE.     

伺服元件的生产应用及发展趋势

本文概括地介绍了我国自70年代以来伺服元件的生产发展状况、元件的性能特点和应用情况，并分析了今后发展的趋势。