一个普通话文语转换系统中的韵律模型

韵律模型是文语转换系统中的重要组成部分,对合成语音的自然度起着至关重要的作用。结合人工神经网络和单元选择算法,将它们分别应用于韵律模型中时长和基频曲线的生成,其中时长模型采用三层的反向传播网络,而基频模型则采用一种基于最小距离和的单元选择算法。     

UPS电源的选择与使用

随着计算机和网络的快速发展和广泛应用,UPS市场已进入了一个成熟阶段。如何选择与使用UPS已经成为用户最关心的问题。本文主要介绍了UPS的种类和作用,指出了用户选用、维护UPS应注意的一些问题。     

变频调速系统中电动机和变频器选择及问题分析

本文分析了选用标准笼形电动机的容量计算方法、问题分析和选用变频器的型式、容量、注意事项。     

基于模糊粗糙集信息熵的蚁群特征选择方法

目前针对高维数据特征选择提出的启发式算法多数容易陷入局部最优,无法对整个特征空间进行有效搜索。为了提高对特征域的并行搜索能力,基于模糊粗糙集的信息熵原理,对蚁群模型的搜索策略、信息素更新和状态转移规则等进行了改进,提出蚁群特征选择方法。经UCI数据实验验证,该算法比传统的特征选择算法具有更好的选择效果,是有效的。     

Design of data feature-driven 1D/2D convolutional neural networks classifier for recycling black plastic wastes through laser spectroscopy

In this study, two types of convolutional neural network (CNN) classifiers are designed to handle the problem of classifying black plastic wastes. In particular, the black plastic wastes have the property of absorbing laser light coming from spectrometer. Therefore, the classification of black plastic wastes remains still a challenging problem compared to classifying other colored plastic wastes using existing spectroscopy (i.e., NIR). When it comes the classification problem of black plastic wastes, effective classification techniques by the laser spectroscopy of Fourier Transform-Infrared Radiation (FT-IR) with Attenuated Total Reflectance (ATR) and Raman to analyze the classification problem of black plastic wastes are introduced. Due to the strong ability of extracting spatial features and remarkable performance in image classification, 1D and 2D CNN through data features are designed as classifiers. The technique of chemical peak points selection is considered to reduce data redundancy. Furthermore, through the selection of data features based on the extracted 1D data with peak points is introduced. Experimental results demonstrate that 2DCNN classifier designed with the help of 2D data feature selection as well as 1DCNN classifier shows the best performance compared with other reported methods for classifying black plastic wastes.     

Solving cold-standby reliability redundancy allocation problems using a new swarm intelligence algorithm

A powerful new hybrid algorithm based on Simplified Swarm Optimization (SSO), Elite Selection and Boundary Search (BS), called the SEB, is proposed for solving the cold-standby reliability redundancy allocation problem (RRAP). The RRAP is a famous mixed-integer nonlinear programming problem in system design that requires that the reliability objective be set to satisfy the resource consumption constraint. In order to balance the exploration and exploitation abilities, the proposed SEB implements a new SSO to update the solutions, an elite selection is performed to select the solutions for subsequent iterations, and the new BS improves the best solution. The performance of the proposed SEB is evaluated by comparing the results with those obtained using existing algorithms and three RRAP benchmark problems taken from the literature.     

基于Chernoff上界的多类问题特征选择优化迭代算法

本文提出正态分布条件下面向不同分布的多类问题基于Chernoff上界的特征选择优化迭代算法.该算法由两重迭代组成首先在设定的原始空间和特征空间Chernoff参数s条件下,通过解矩阵方程的迭代算法求得变换矩阵的最优解;然后,在变换矩阵确定的特征空间中搜索最佳的参数s使错误概率上界最小;最后采用折半法修正设定的Chernoff参数s及其迭代步长.通过分析和实例可见基于Chernoff上界特征选择是面向不同分布的多类问题的最佳特征选择方法.     

图像压缩算法性能的测试与分析工具

本文研究了图像压缩算法性能的评价方法,提出了图像压缩算法性能的测试算法,包括横向比较测试和纵向分解测试,并在此基础上设计并实现了压缩算法性能的测试与分析工具。该工具能够测试和分析压缩算法的性能,并自动生成各种分析图表,为用户提供了方便,具有较大的实用价值。为了提高评价的效率、准确性和全面性,文中提出了测试图像的选择方法和测试结果的分析方法,具有一定的理论意义。     

Web信息抽取系统的设计

为了获取分散Web页面中隐含信息,设计了Web信息抽取系统。该系统首先使用一种改进的HITS主题精选算法进行信息采集;然后对Web页面的HTML结构进行文档的数据预处理;最后,基于DOM树的XPath绝对路径生成算法来获取被标注结点的XPath表达式,并使用XPath语言结合XSLT技术来编写抽取规则,从而得到结构化的数据库或XML文件,实现了Web信息的定位和抽取。通过一个购物网站的抽取实验证明,该系统的抽取效果良好,可以实现相似Web页面的批量抽取。     

改进的智能优化在多用户检测中的应用

针对概率克隆选择微粒群算法（PCSPSO）在解决离散优化问题时效果不佳的缺点进行改进,将改进后的算法（IPCSPSO）应用于多用户检测,提出基于改进的概率克隆选择微粒群算法的多用户检测器（IPCSPSO-MUD）。IPCSPSO在由二次更新后的记忆集和原种群构成的临时种群中寻找全局最优解,进一步扩大搜索范围;以抗体生存期望值为标准更新种群,保证抗体多样性。仿真结果表明,所提出的多用户检测器在误码率性能、收敛速度、抗远近效应能力和系统容量等方面均有显著提高。