A Constrained Line Search Optimization Method for Discriminative Training of HMMs

In this paper, we propose a novel optimization algorithm called constrained line search (CLS) for discriminative training (DT) of Gaussian mixture continuous density hidden Markov model (CDHMM) in speech recognition. The CLS method is formulated under a general framework for optimizing any discriminative objective functions including maximum mutual information (MMI), minimum classification error (MCE), minimum phone error (MPE)/minimum word error (MWE), etc. In this method, discriminative training of HMM is first cast as a constrained optimization problem, where Kullback-Leibler divergence (KLD) between models is explicitly imposed as a constraint during optimization. Based upon the idea of line search, we show that a simple formula of HMM parameters can be found by constraining the KLD between HMM of two successive iterations in an quadratic form. The proposed CLS method can be applied to optimize all model parameters in Gaussian mixture CDHMMs, including means, covariances, and mixture weights. We have investigated the proposed CLS approach on several benchmark speech recognition databases, including TIDIGITS, Resource Management (RM), and Switchboard. Experimental results show that the new CLS optimization method consistently outperforms the conventional EBW method in both recognition performance and convergence behavior.     

A model reference robust control with application to a flight control system design

In this paper, a new model reference robust control scheme for plants with relative degree greater than one is proposed for the purpose of coping with the “explosion of complexity” problem in control law design. The key of the scheme is that we use a first‐order filter to link each subsystem, so that the derivative of some nonlinear functions can be avoided. As a result, the final control law can be greatly simplified. The application of this scheme to a flight control system shows that both the tracking performance and the control effort can be improved significantly in comparison with earlier research. Copyright © 2008 John Wiley and Sons Asia Pte Ltd and Chinese Automatic Control Society     

图像匹配技术在套印误差自动检测中的应用

准确检测套印偏差是印刷机自动套印系统中最为关键的技术;针对印刷色标图案的特点,提出了一种新的基于图像匹配的套印误差检测方法,通过相关匹配处理获取各单色色标的位置,并巧妙利用色标圆线的直径确定了系统的标称分辨率,进而计算出各色组问纵向和横向的套印误差;文中详细给出了算法原理和实验结果;相对于经典的边缘检测方法,图像匹配技术充分利用了色标图案的整体信息;实验结果表明,该方法对像素灰度的变化和系统噪声具有鲁棒性,检测精度高。     

USB在阵列声波测井数据采集中的应用

提出了一种基于通用串行总线(USB)的阵列声波测井数据采集系统,该采集系统的构成模块包括模拟信号处理、高速数据采集子系统、采集控制器、串行数据和控制接口以及主机接口等;以CPLD担当数据采集控制器,采集深度、速率等参数可根据实际需要动态设置,从驱动程序初始化和卸载、设备启动、设备控制和数据读写等方面详细分析了用于数据采集系统的USB驱动程序设计,基于14位ADC的采集电路实测信噪比不小于65dB;该采集系统可用于井下阵列声波测井仪调试,以及实验室声波换能器性能测试。     

基于P89V51的两轴稳定平台控制器设计

船在海上航行时会随着海浪不停的晃动,船载天线跟随船体晃动则会产生通讯中断,因此采取船载两轴稳定平台来实现天线与船体晃动的隔离,保证船载天线间的通讯质量;文中两轴稳定平台系统采用双闭环控制和积分分离PID控制器实现;文章阐述了船载稳定平台控制系统的工作原理,设计了一款基于P89V51微处理器的两轴稳定平台控制器,并给出了控制器硬件电路的设计原理图;最后按功能实现对软件模块进行了划分和介绍;通过摇摆台模拟试验,该两轴稳定平台控制系统运行可靠,动态精度较高,能确保船载天线之间的正常通讯。     

基于信息融合的管道泄漏检测与定位技术应用研究

基于目前已经在石油输送管道中应用的SCADA系统将信息融合技术应用于管道泄漏检测与定位系统中;该方法应用管道泄漏时的多种特征信号,采用最优加权融合算法将多元信息综合处理,扩展了时间和空间上的检测范围,提高了泄漏检测系统的灵敏度和可靠性;在实验室用水泵和不锈钢管道组成的水循环系统进行了模拟实验,通过对比验证了信息融合检漏方法比单一检漏方法具有明显的优越性。     

基于μC/OS—Ⅱ的回流焊炉的任务研究

主要对回流焊的温度控制系统设计中的嵌入式操作系统μC/OS-Ⅱ的任务进行研究;首先对回流焊硬件系统进行简单介绍,并对主要的硬件器件和电路做了说明,接着分析μC/OS-Ⅱ任务块的基本原理,然后阐述了任务管理的调度,最后着重讨论了针对回流焊的μC/OS-Ⅱ实时操作系统的任务划分以及三个任务之间的通讯实现;实际运行结果表明该软件系统稳定性好,可靠性高,人机界面友好,维护简单。     

小型飞行器综合测试系统方案设计

针对小型飞行器系统各部件在研制和生产中的测试要求,提出了小型飞行器综合测试系统的方案设计;方案设计中详细介绍了系统组成,并对方案中涉及的航空电子分系统、发动机分系统、无线电数据链分系统的测试内容及测试方法进行了分析说明;根据测试方法和测试内容,给出了综合测试系统的硬件设计原理和软件设计流程;运用该设计方案进行了综合测试设备发动机分系统测试的研制工作,并投入试运行,结果表明该方案设计合理可行,可推广应用于该领域或其它领域的测控系统的研制中。     

基于GML地理空间数据表达的研究

地理空间的表达是地理数据组织、存储、运算、分析的基础.阐述地理标记语言GML的特点,提出基于Web环境下地理空间数据表达的三层体系结构,总结GML技术对地理空间数据表达的作用和意义.     

Three-dimensional face recognition in the presence of facial expressions: an annotated deformable model approach

In this paper, we present the computational tools and a hardware prototype for 3D face recognition. Full automation is provided through the use of advanced multistage alignment algorithms, resilience to facial expressions by employing a deformable model framework, and invariance to 3D capture devices through suitable preprocessing steps. In addition, scalability in both time and space is achieved by converting 3D facial scans into compact metadata. We present our results on the largest known, and now publicly available, face recognition grand challenge 3D facial database consisting of several thousand scans. To the best of our knowledge, this is the highest performance reported on the FRGC v2 database for the 3D modality