Shape "break-and-repair" strategy and its application to automated medical image segmentation

In three-dimensional medical imaging, segmentation of specific anatomy structure is often a preprocessing step for computer-aided detection/diagnosis (CAD) purposes, and its performance has a significant impact on diagnosis of diseases as well as objective quantitative assessment of therapeutic efficacy. However, the existence of various diseases, image noise or artifacts, and individual anatomical variety generally impose a challenge for accurate segmentation of specific structures. To address these problems, a shape analysis strategy termed "break-and-repair" is presented in this study to facilitate automated medical image segmentation. Similar to surface approximation using a limited number of control points, the basic idea is to remove problematic regions and then estimate a smooth and complete surface shape by representing the remaining regions with high fidelity as an implicit function. The innovation of this shape analysis strategy is the capability of solving challenging medical image segmentation problems in a unified framework, regardless of the variability of anatomical structures in question. In our implementation, principal curvature analysis is used to identify and remove the problematic regions and radial basis function (RBF) based implicit surface fitting is used to achieve a closed (or complete) surface boundary. The feasibility and performance of this strategy are demonstrated by applying it to automated segmentation of two completely different anatomical structures depicted on CT examinations, namely human lungs and pulmonary nodules. Our quantitative experiments on a large number of clinical CT examinations collected from different sources demonstrate the accuracy, robustness, and generality of the shape "break-and-repair" strategy in medical image segmentation.     

基于局部人脸图像的ICA人脸识别方法

提出了一种基于局部人脸图像独立分量分析的特征提取方法.该方法将人脸图像分成若干个相等的部分,将分成的局部人脸图像矩阵作为训练样本,并先后从水平方向,垂直方向提取训练样本的独立分量.相较于传统的独立分量分析(ICA)方法,该方法具有如下优点:有效解决了传统ICA在进行特征抽取过程中的高维小样本问题;将局部人脸图像作为训练样本,这不仅增加了训练样本数,而且有利于提取人脸局部特征;依次从训练样本的水平方向、垂直方向提取训练样本特征,使得提取的特征不仅维数更小,而且能更有效地反映样本的局部信息.以上优点使得提出的算法较传统方法在人脸识别方面更稳定,识别率更高,在Yale人脸库和AR人脸库上验证了该算法的有效性.     

.NET环境下MFC框架应用的包装集成技术研究

为有效解决.NET应用中对MFC遗留应用系统的快速集成问题,并尽量重用已有系统,研究了.NET环境下MFC应用系统的包装集成技术,提出了用混合DLL方式来对MFC应用进行大粒度封装的方案.在此基础上开发了一个包装器中间件,对该中间件的体系结构进行了分析,叙述了中间件主要组成部分的关键实现技术,然后给出了一个实例.实践结果表明,该技术是行之有效的,能够满足许多应用系统的需求,提高开发效率.     

基于DDS的低通滤波器设计与仿真

分析了几种经典滤波器特性,重点研究了DDS系统中低通滤波器的设计方法。根据DDS的结构特点和输出杂散频谱特性,结合滤波器技术指标使用了归一化法完成了一个九阶椭圆函数低通滤波器的设计,使其通带截至频率为120MHz、通带内最大衰减为0.2dB、在135MHz处阻带内最小衰减为66dB。通过Multisim10对其进行仿真后可以得出,使用此种方法设计的低通滤波器过渡带陡峭、幅频特性仿真良好,并且能够很好地满足预期的技术指标。     

基于TMS320C6722的高速铁路轨道信号发送与接收模拟系统

介绍一套高速铁路轨道信号模拟系统,讨论了系统的硬件和软件设计方法。系统以TMS320C6722浮点DSP为数据处理核心,ARM协处理器为控制核心,能够模拟自主开发的、适合中国高速铁路的改进型数字编码和正交化FSK轨道信号的发送和解调过程。     

有时态本体模型及其管理原型系统

为使本体能够方便地表达、处理与时间相关的信息,将有效时间概念引入本体模型,介绍有时态本体模型定义及相关定理,在此基础上,实现有时态本体管理原型系统,并将该原型系统应用于存在时态冲突的信息集成系统中进行实验。实验结果证明了将本体用有效时间进行扩展,从而形成有时态本体模型,并对其进行存储管理的必要性,同时也显示了该原型系统对时态查询的支持能力。     

Analysis and application of Bio-Inspired Multi-Net Security Model

With the rapid development of network technologies and deteriorating of network environment, traditional single-net security system cannot satisfy the security requirement. The excellent security performance of biological systems impels the bio-inspired network security theory to be a hot research area currently. Based on Bio-inspired Multidimensional Network Security Model we have put forward, we have advanced Bio-inspired Multi-Net Security system by implementing the functional distribution of different subnets of different transient states in Multi-Net Paralleling structure. Firstly, parameter estimation and modified algorithms of Hidden Markov Model are introduced to construct the mathematical mode of B-MNS; secondly, the integrated performance of our modified B-MNS has been tested and its simulation has been carried out. So the feasibility, validity and high efficiency of our model have been demonstrated theoretically, and practically.     

Linking denotational semantics with operational semantics for web services

Web Services have become more and more important in these years, and BPEL4WS (BPEL) is a de facto standard for the web service composition and orchestration. It contains several distinct features, including the scope-based compensation and fault handling mechanism. The denotational semantics and operational semantics have been explored for BPEL. The two semantic models should be consistent. This paper considers the linking of these two semantics. Our approach is to derive the denotational semantics from operational semantics for BPEL, which aims for the consistency of the two models. Moreover, the derivation can be applied in exploring the program equivalence easily, especially for parallel programs.     

HMM在自然语言处理领域中的应用研究

隐马尔可夫模型（HMM）是一种强大的统计学机器学习技术,该模型已经成功地应用于连续语音识别、在线手写识别,在生物学信息中也得到了广泛的应用。由于该模型的强大的学习能力,在自然语言处理领域逐渐得到了应用。对隐马尔可夫模型在词性标注、命名实体识别、信息抽取应用中的关键问题进行了分析。着重分析了在信息抽取时使用隐马尔可夫模型的重点和难点问题,期望让更多的研究人员进一步认识和了解HMM。最后分析了隐马尔可夫模型在应用中的不足之处和改进研究。     

J2ME移动远程控制应用的研究

讨论采用J2ME技术实现移动远程控制应用的方法.方法在手机端采用MIDP里的HttpConnection接口技术,PC端采用Servlet技术,并实现了手机对PC机的远程控制.方法可运用于智能居家、家电信息化等,推动物联网发展普及.