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。     

A constraint programming model with time uncertainty for cooperative flight departures

The lack of a proper integration of strategic Air Traffic Management decision support tools with tactical Air Traffic Control interventions usually generates a negative impact on the Reference Business Trajectory adherence, and in consequence affects the potential of the Trajectory-Based Operations framework. In this paper, a new mechanism relaying on Reference Business Trajectories as a source of data to reduce the amount of Air Traffic Controller interventions at the tactical level while preserving Air Traffic Flow Management planned operations is presented. Artificial Intelligence can enable Constraint Programming as it is a powerful paradigm for solving complex, combinatorial search problems. The proposed methodology takes advantage of Constraint Programming and fosters adherence of Airspace User’s trajectory preferences by identifying tight interdependencies between trajectories and introducing a new mechanism to improve the aircraft separation at concurrence events considering time uncertainty. The underlying philosophy is to capitalize present degrees of freedom between layered Air Traffic Management planning tools, when sequencing departures at the airports by considering the benefits of small time stamp changes in the assigned Calculated Take-Off Time departures and to enhance Trajectory-Based Operations concepts.     

Enhanced delay propagation tree model with Bayesian Network for modelling flight delay propagation

An enhanced Delay Propagation Tree model with Bayesian Network (DPT-BN) is developed to model multi-flight delay propagation and delay interdependencies. Using a set of real airline data, results show that flights have non-homogeneous delay propagation effects. The DPT-BN model is used to infer posterior delay profiles with different delay and scheduling scenarios. The major contribution of the DPT-BN model is to demonstrate how the modelling of non-independent and identically distributed delay profiles is more realistic for the observed delay propagation mechanism, and how robust airline scheduling methodologies can benefit from this probability-based delay model.     

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。