中文文本信息过滤技术研究

随着互联网信息数量的急剧增加,文本信息过滤技术越来越受到重视。本文首先介绍了文本信息过滤技术的发展历史和研究现状,阐述了中文文本过滤的特点和要求。重点分析了中文文本过滤技术的关键技术和评价标准。     

基于灰度变换的沥青混合料图像增强及分割实现

数字图像技术是提取和描述沥青混合料细观结构的有效途径,可以通过图像增强、图像分割实现集料和其他组分的分离。通过灰度变换方法调整图像的动态灰度范围,便于进行后续的图像分割处理。结合Matlab软件实现图像的灰度变换增强,同时采用代数运算、除噪滤波进行处理,实现了混合料图像的分割处理及边界识别。     

Transportation mode detection – an in-depth review of applicability and reliability

The wide adoption of location-enabled devices, together with the acceptance of services that leverage (personal) data as payment, allows scientists to push through some of the previous barriers imposed by data insufficiency, ethics and privacy skepticism. The research problems whose study require hard-to-obtain data (e.g. transportation mode detection, service contextualisation, etc.) have now become more accessible to scientists because of the availability of data collecting outlets. One such problem is the detection of a user's transportation mode. Different fields have approached the problem of transportation mode detection with different aims: Location-Based Services (LBS) is a field that focuses on understanding the transportation mode in real-time, Transportation Science is a field that focuses on measuring the daily travel patterns of individuals or groups of individuals, and Human Geography is a field that focuses on enriching a trajectory by adding domain-specific semantics. While different fields providing solutions to the same problem could be viewed as a positive outcome, it is difficult to compare these solutions because the reported performance indicators depend on the type of approach and its aim (e.g. the real-time availability of LBS requires the performance to be computed on each classified location). The contributions of this paper are three fold. First, the paper reviews the critical aspects desired by each research field when providing solutions to the transportation mode detection problem. Second, it proposes three dimensions that separate three branches of science based on their main interest. Finally, it identifies important gaps in research and future directions, that is, proposing: widely accepted error measures meaningful for all disciplines, methods robust to new data sets and a benchmark data set for performance validation.     

基于目标监督的先验形状level set模型分割心脏MR图像

提出一种基于目标监督的先验形状level set模型分割心脏MR图像的方法。该方法先根据目标灰度的特征生成特征图像,使得特征图像目标区域灰度趋于一致,再在特征图像的基础上利用先验形状信息的水平集模型对目标进行分割。实验结果表明,该方法能够有效地分割心脏MRI图像。     

面向智能生产线的船舶曲面分段通用胎架设计

基于自适应电磁式支撑头、数显式三向调节支柱和模块化轨道运输等关键技术,设计一种新型的船舶曲面分段通用胎架,并对模型样品进行试制。一直以来,船厂广泛使用支柱式胎架,普遍存在滑移、支点变形和制作效率不高等问题。研究成果可为解决上述问题提供参考,并为未来船舶曲面分段智能生产线的胎架研制提供设计思路。     

基于离散水平集方法的Chan-Vese模型

采用离散形式的水平集函数代替传统的符号距离函数,提出基于离散水平集方法的Chan-Vese模型。采用变分方法得到水平集函数演化的梯度降方程,对得到的演化方程进行半隐式离散求解和数值算例验证,并与传统的符号距离函数方法进行对比,以验证离散水平集方法在图像分割中的优势。实验结果表明,基于离散水平集方法的Chan-Vese模型分割速度和精度比用符号距离函数实现的Chan-Vese模型有明显提高。     

Network-Wide Traffic State Observation and Analysis Method Using Pseudo-Color Map

A novel algorithm is proposed in this paper to meet the demand of urban traffic control and management for network-wide traffic states observation and analysis. Urban traffic network is mapped to a pseudo-color image with pixels corresponding to grids. The colors of the pixels represent the corresponding grids' states values so that this pseudo-color image vividly represents the macroscopic traffic state. The Otsu algorithm is used to find the congested regions automatically. The evolutionary patterns of traffic state are determined by calculating and analyzing the optical flow field of consecutive pseudo-color images. A case study of Beijing macroscopic traffic state observation and analysis is also presented to show the effectiveness of the proposed method.     

车牌自动识别系统设计与实现

车牌自动识别分为图像预处理、车牌定位、字符分割、字符识别四步。利用形态学变换对图像进行滤波聚类,HOUGH变换对车牌图像进行水平校正,BP神经网络的方法进行字符识别,最后基于DELPHI7．0环境下设计开发了车牌自动识别系统。     

Performance measures and data requirements for congestion management systems

Many metropolitan areas have started programs to monitor the performance of their transportation network and to develop systems to measure and manage congestion. This paper presents a review of issues, procedures, and examples of application of geographic information system (GIS) technology to the development of congestion management systems (CMSs). The paper examines transportation network performance measures and discusses the benefit of using travel time as a robust, easy to understand performance measure. The paper addresses data needs and examines the use of global positioning system (GPS) technology for the collection of travel time and speed data. The paper also describes GIS platforms and sample user interfaces to process the data collected in the field, data attribute requirements and database schemas, and examples of application of GIS technology for the production of maps and tabular reports.     

Grouping travelers on the basis of their different car and transit levels of use

Market segmentation studies in travel behavior research are ordinarily based on socioeconomic characteristics and personality traits. This study explores the usefulness of a different approach, where the actual overall mobility levels across different ground transportation modes, along with desired changes in the use of cars and transit, are used as clustering variables. Using a given mode can in fact influence the personal representation of that mode, which in turn has been proven to be a key element in transport behaviours. We form such multimodality-based clusters from two field studies, one involving employees of the French transportation research institute INRETS and the other a representative sample of residents of the US San Francisco Bay Area. We find that strong users of a given mode would like to bring more balance to their “modal consumptions” by decreasing the use of this mode more than the average, and increasing the use of the alternative mode. However, concerning ground transport travel budgets, the desire to travel more (or less) overall seems less strongly related to the composition of the modal balance. The US dataset shows also a greater latent demand for travel than the French one. Socioeconomic characteristics of the clusters could not explain the patterns that were found, confirming the importance of taking into account multimodality issues in travel behavior research. Some policy implications from these findings are finally reported.