Classification of the cardiotocogram data for anticipation of fetal risks using machine learning techniques

The aim of the research is evaluating the classification performances of eight different machine-learning methods on the antepartum cardiotocography (CTG) data. The classification is necessary to predict newborn health, especially for the critical cases. Cardiotocography is used for assisting the obstetricians’ to obtain detailed information during the pregnancy as a technique of measuring fetal well-being, essentially in pregnant women having potential complications. The obstetricians describe CTG shortly as a continuous electronic record of the baby's heart rate took from the mother's abdomen. The acquired information is necessary to visualize unhealthiness of the embryo and gives an opportunity for early intervention prior to happening a permanent impairment to the embryo. The aim of the machine learning methods is by using attributes of data obtained from the uterine contraction (UC) and fetal heart rate (FHR) signals to classify as pathological or normal. The dataset contains 1831 instances with 21 attributes, examined by applying the methods. In the paper, the highest accuracy displayed as 99.2%.     

Cartesian grid methods using radial basis functions for solving Poisson, Helmholtz, and diffusion–convection equations

Four methods that solve the Poisson, Helmholtz, and diffusion–convection problems on Cartesian grid by collocation with radial basis functions are presented. Each problem is split into a problem with an inhomogeneous equation and homogeneous boundary conditions, and a problem with a homogeneous equation and inhomogeneous boundary conditions. The former problem is solved by collocation with multiquadrics, whereas the latter problem is solved by collocation with either multiquadrics or fundamental solutions. It is found that methods that make use of fundamental solutions for collocation yield more accurate solutions that are less sensitive to the shape parameter of multiquadrics and node arrangement. Additional collocation appears to improve the quality of solutions.     

电力变压器动稳定破坏的分析和对策

对大型电力变压器绕组在变压器发生外部短路时所受的辐向力和轴向力进行了分析和计算，比较了国内外不同的计算方法和得出的不同结果。     

Neural Computation of the MoM Matrix Elements for Planar Configurations

In this paper a new artificial neural network (ANN) based model for the calculation of the method of moments (MoM) matrix elements is presented. Training sets that characterize the matrix elements are first constructed. These sets are then utilized to effectively train two radial basis function (RBF) neural networks to accurately estimate all the elements of the MoM matrix for any mesh used. The potential of the proposed approach is demonstrated in the case of a narrow microstrip line. The current distribution on the microstrip line produced by the trained RBF networks agrees very well with the exact distribution. In addition, the proposed ANN model is much faster than the conventional MoM procedure.     

Use of radial forces for fault detection in tapping

A model-based method for fault detection in tapping based on torque and radial forces is proposed. The method allows the identification of faults typical of a tapping operation including axial misalignment, tap runout, tooth breakage both singly and together. The validation experiments have been run on aluminum 356 workpieces for different combinations of process faults. Results have shown that the model predictions are in good agreement with the experimental radial force and torque signals under various fault conditions.     

一种在Kalman滤波中引入径向速度测量的新方法

研究在距离和径向速度测量噪声统计相关的情形下把径向速度测量引入Kalman滤波的新方法。分析了径向速度测量噪声与位置测量更新后状态滤波误差的统计相关性,根据Gauss-Markov定理导出了对应于径向速度测量的滤波方程由此而得到一种序贯滤波算法。两个不同的蒙特卡罗仿真表明,通过采用这一新算法引人径向速度测量,不仅可以大大提高状态估计的精度,而且其估计性能和计算效率优于传统的EKF。     

A simplified expression for the hard-sphere dimer fluid radial distribution function

Recently, in our laboratory a closed form expression for the correlation function of the hard-sphere dimer fluid obtained from Wertheims multidensity Ornstein-Zernike integral equation theory with Percus-Yevick approximation was presented by Kim et al. [2001]. However, it is difficult to apply its expression to perturbation theory and vapor-liquid equilibria calculations, since it is of very complex form. In this work, we present a simplified expression for the first shell of the radial distribution function (RDF) of the hard-sphere dimer fluid using a series expansion of the analytical expression. The expansion is carried out in terms of both the packing fraction and the radial distance. Expressions are also obtained for the coordination number and its first and second derivatives as functions of radial distance and packing fraction. These expressions, which are useful in perturbation theory, are simpler to use than those obtained from the starting equation, while giving good agreement with the original expression results. Then we present an simplified equation of state for the square-well dimer fluid of variable well width (λ) based on Barker-Henderson perturbation theory using its expression for the radial distribution function of the hard-sphere dimer fluid, and test its expression with NVT and Gibbs ensemble Monte Carlo simulation data [Kim et al., 2001].     

Specific interactions in blends containing Chitosan and functionalized polymers. Molecular dynamics simulations

Chitosan (CS)/poly(vinyl alcohol) (PVA) and Chitosan/poly(2-hydroxyethyl methacrylate) (P2HEM) blends have been studied through molecular dynamic simulations. In a previous work it was found miscibility between these polymers and it was attributed to hydrogen bonding formation. However, the experimental information obtained was not enough to know which of the interacting groups of Chitosan, i.e. -CH₂OH or -NH₂, are responsible of the interaction. Therefore, we have performed molecular dynamics simulation runs of 1 ns in order to calculate radial distribution functions (RDF) for the groups tentatively involved in the interaction. The results are correlated with our previous experimental data. This way, we have obtained a more precise conclusive information about the interactions involved as function of the blends composition. For low compositions of PVA and P2HEM the interaction is predominantly with the hydroxymethyl groups of CS while as the composition of PVA and P2HEM increases, the interaction with the amine groups increases.     

Nonlinear adaptive algorithms for equalisation in mobile satellite communications

This paper considers the equalisation problem in Quadrature Phase-Shift Keying (QPSK) modulated signals which have been distorted by the passage through a transmission channel. The channel is modelled as a Rician fading channel to simulate the behaviour of the transmission channel in the mobile satellite context. The equalisation is treated as the generalisation of the channel behaviour, and some algorithms with the structure of an artificial neural network using the Multilayer Perceptron, Volterra Series and Radial Basis Function are described. Results for the BER performance of typical transversal equalisers, with Square-Root Kalman adaptation algorithm, and algorithms with artificial neural network structure are also reported and evaluated. Improved performance is exhibited by the artificial neural network approaches.