Daily activity pattern recognition by using support vector machines with multiple classes

The focus of this paper is to learn the daily activity engagement patterns of travelers using Support Vector Machines (SVMs), a modeling approach that is widely used in Artificial intelligence and Machine Learning. It is postulated that an individual’s choice of activities depends not only on socio-demographic characteristics but also on previous activities of individual on the same day. In the paper, Markov Chain models are used to study the sequential choice of activities. The dependencies among activity type, activity sequence and socio-demographic data are captured by employing hidden Markov models. In order to learn model parameters, we use sequential multinomial logit models (MNL) and multiclass Support Vector Machines (K-SVM) with two different dependency structures. In the first dependency structure, it is assumed that type of activity at time ‘t’ depends on the last previous activity and socio-demographic data, whereas in the second structure we assume that activity selection at time ‘t’ depends on all of the individual’s previous activity types on the same day and socio-demographic characteristics. The models are applied to data drawn from a set of California households and a comparison of the accuracy of estimation of activity types and their sequence in the agenda, indicates the superiority of K-SVM models over MNL. Additionally, we show that accuracy in estimating activity patterns increases using different sets of explanatory variables or tuning parameters of the kernel function in K-SVM.     

新的汽车牌照识别系统及其成像技术

介绍了一种高性能的汽车牌照识别系统及其成像技术。系统采用了新的成像控制和闪光灯补光技术，使其成像特别适合牌照区域分割和字符识别，成像质量完全不受实际应用环境中强烈的光线变化的影响，从而达到较高的全天候识别率和实际应用的要求。给出了系统在全天候条件下的成像效果和牌照识别效果．结果显示系统可在全天候条件下获得高质量的图像。     

基于网格量化和区间均值的动态目标识别

动态目标识别中，当摄像机和目标之间相对距离变化时，对于同一目标的多尺度序列图像。虽然目标区域图像大小和清晰度不同，但整体结构分布具有相似性和一致性。根据这一特点，提出基于目标区域网格量化的方法。在目标区域上形成采样网格，通过相对量化提取结构特征矩阵。对于同一目标序列图像中的每一个目标区域，其结构特征矩阵基本不变。结构特征矩阵反映象素分布的自相关性质。进一步，对由干扰引起的灰度值结构分布误差，采用网格区间均值的方法加以解决。目标区域网格量化是对相邻采样点的差值进行量化匹配。区间均值是对少数相邻采样点的进一步匹配。实例表明，本文的方法运算速度快、可靠性高，达到了实用目的。     

接触网系统各部件内部应力概率分布规律

采用有限元并结合改进算法的径向基神经网络RBF,判别接触网系统各部件内部应力的随机分布规律。以兰新线武嘉段接触网腕臂为算例,把安装角度、冰负载、承力索覆冰风负载、接触线覆冰风负载等参量作为基本变量,按各变量的分布规律随机地产生50组样本数据,通过有限元计算出每一组参数对应的内部最大应力,依据随机抽样规律抽取40组,按经验分布计算出对应的应力分布函数值。利用RBF进行模式识别得到应力符合威布尔分布,并用回归分析计算出正态分布、指数分布、威布尔分布、对数正态分布二个变量的相关系数。从相关系数和拟合图可以看出,应力符合威布尔分布最好,服从指数分布的可能性最小,RBF识别的结果与回归分析的结果是一致的。     

浅谈铁路平面曲线的施工放样测量

根据线路中线的特点，介绍了线路平面缓和曲线和线路中线在曲线地段侧移的计算和处理方法。重点论述了曲线平移的计算公式推导，并提出了一种新计算方法。     

辊锻模具设计的理论及试验研究

通过对辊锻模具与锻件的啮合运动分析，推导出由锻件轮廓方程确定模具型槽方程的理论公式，并通过试验对该公式进行了验证。     

虹膜识别技术的应用与发展

虹膜识别技术是一种生物特征识别技术,本文在分析其研究现状、识别流程的基础上,简单的介绍了虹膜图像的采集、虹膜定位、归一化与增强、虹膜编码、比较与判决等主要内容。     

һ�����͵��˶�Ŀ��ʶ��������㷨�о�

提出了一种应用于智能交通监控系统的运动目标识别和跟踪方法。针对帧间差分提取运动目标的缺陷与不足,提出了一种基于冗余小波变换的运动目标识别算法,即直接在冗余小波变换域提取运动区域,从而检测出运动目标。对于检测出来的运动目标,本文对mean-shift算法进行了改进,采用自适应mean-shift算法,对目标进行跟踪。实验结果表明,本文提出的算法可以有效地提取运动目标,即使目标与背景具有较高的相似度,也可以较准确的提取出前景运动信息,效果要好于传统的帧差法;跟踪目标准确度高,不受目标大小变化的影响。本算法具较高的实用价值和应用前景。     

Urban travel time reliability at different traffic conditions

The decision making of travelers for route choice and departure time choice depends on the expected travel time and its reliability. A common understanding of reliability is that it is related to several statistical properties of the travel time distribution, especially to the standard deviation of the travel time and also to the skewness. For an important corridor in Changsha (P.R. China) the travel time reliability has been evaluated and a linear model is proposed for the relationship between travel time, standard deviation, skewness, and some other traffic characteristics. Statistical analysis is done for both simulation data from a delay distribution model and for real life data from automated number plate recognition (ANPR) cameras. ANPR data give unbiased travel time data, which is more representative than probe vehicles. The relationship between the mean travel time and its standard deviation is verified with an analytical model for travel time distributions as well as with the ANPR travel times. Average travel time and the standard deviation are linearly correlated for single links as well as corridors. Other influence factors are related to skewness and travel time standard deviations, such as vehicle density and degree of saturation. Skewness appears to be less well to explain from traffic characteristics than the standard deviation is.     

一种被动声纳目标识别数据融合方法的研究

文章首先对目标噪声信号采用五种不同的方法提取特征矢量,然后采用基于自适应遗传BP算法的神经网络分别对五种特征矢量并发地进行分类,再采用遗传算法对分类器组合过程中的多参数进行优化,最后由五种分类结果最优组合产生最终的分类结果。实验结果表明该系统具有很好的分类效果。