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.     

Single-longitudinal-mode fiber ring laser employing an equivalent phase-shifted fiber Bragg grating

A novel single-longitudinal-mode (SLM) fiber ring laser that incorporates an equivalent phase-shifted fiber Bragg grating acting as an ultra-narrow bandpass filter in the laser cavity is proposed. The equivalent phase-shifted fiber Bragg grating has an ultra-narrow transmission bandwidth which ensures an SLM lasing. Stable SLM operation without mode hopping is demonstrated.     

常用小水电工程地面控制测量方法

测量工作在小水电工程建设中起着重要的作用。小水电工程按其布置的方式分为堤坝式、引水式和混合式三种。堤坝式电站的测量工作比较简单,而引水式和混合式电站是高水头式,这类电站传统的地面控制测量方法是建立小三角网,但目前由于GPS和全站仪的全面普及,传统的小三角网控制已完全被GPS测量或与EDM导线结合的方法所代替。文章着重介绍引水式或混合式高水头小水电工程的地面控制测量。     

Time dependent crystal-smectic transformation in perylene-containing polyimides

The crystalline conformations of perylene polyimides (PPIs), with alkyl spacers varying in length from C₃ to C₁₂ are discussed. Although modeling of single chains would suggest the possibility that those with odd number of CH₂ groups adopt a flat helical shape, X-ray diffraction suggests that the chains with odd and even spacers have the same conformation, due to the necessity to pack the perylene units. Upon annealing, the UV-vis absorption maximum red-shifts by about 10 nm, indicating enhanced π-stacking between the perylenes. Several changes in the spectra are seen with an increase in annealing time, at a given temperature. With an increase in annealing time, X-ray diffraction patterns show changes in the number of reflections, indicative of a crystal to mesogenic transition. The time required for this transition increases with a decrease in the spacer length, and annealing temperature, suggesting that the dynamics of this transition is very slow.     

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.     

Behaviors of concrete-filled steel tubular members subjected to combined loading

The present study is an investigation on the behaviors of concrete-filled thin-walled steel tubular members subjected to combined loading, such as compression and torsion, bending and torsion, compression, bending and torsion. ABAQUS software is used in this paper for the finite element analysis (FEA). A comparison of results calculated using this modeling shows generally good agreement with test results. The FEA modeling is then used to investigate the influence of important parameters that determine the ultimate strength of the composite members under combined loading, such as compression and torsion, bending and torsion, compression, bending and torsion. The parametric studies provide information for the development of formulae for calculating the ultimate strength of the composite members subjected to combined loading.     

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.     

基于DSP的电力数据采集平台的设计与研究

介绍了一种用于电力系统的数据采集系统.该系统采用数字信号处理器(DSP)和复杂可编程逻辑器件(CPLD)作为核心芯片,给出了主要部分的电路及其原理、功能,系统中使用CPLD实现基本逻辑,使系统有足够的冗余和灵活性,具有可靠性高、可升级等优点.