一种基于贝叶斯特征的视频图像人脸检测

提出了一种基于仿射运动模型和贝叶斯理论的视频图像人脸检测方法.建立仿射运动模型进行运动估计,提取运动对象区域;对训练图像提取人脸与非人脸的统计特征,利用贝叶斯准则建立概率模型;根据贝叶斯分类器和支持向量机分类器将图像特征分为人脸类与非人脸类,从而检测出视频运动图像中的人脸区域.     

Bus arrival time prediction at bus stop with multiple routes

Provision of accurate bus arrival information is vital to passengers for reducing their anxieties and waiting times at bus stop. This paper proposes models to predict bus arrival times at the same bus stop but with different routes. In the proposed models, bus running times of multiple routes are used for predicting the bus arrival time of each of these bus routes. Several methods, which include support vector machine (SVM), artificial neural network (ANN), k nearest neighbours algorithm (k-NN) and linear regression (LR), are adopted for the bus arrival time prediction. Observation surveys are conducted to collect bus running and arrival time data for validation of the proposed models. The results show that the proposed models are more accurate than the models based on the bus running times of single route. Moreover, it is found that the SVM model performs the best among the four proposed models for predicting the bus arrival times at bus stop with multiple routes.     

连拱隧道先行洞室支护体系施工力学性态研究

结合连拱隧道工程实践,对隧道施工中先行洞室支护体系应力进行相关监测,分析不同开挖工序下应力变化规律。研究结果表明:先行洞室上台阶及仰拱开挖引起了支护应力较大变化及重分布,为支护稳定的控制点;隧道开挖对支护应力的纵向影响距离大致为隧道跨度的2倍,约为20～25 m;开挖效应消失后,左右拱圈45°处应力的时间效应较其它位置要明显;封闭支护结构是改善结构受力的有效途径,应及时施作仰拱和形成封闭环。该研究结论可为类似条件下连拱隧道设计施工和现场监测提供借鉴与参考。     

高速公路挖方边坡优化设计智能方法与应用

文章针对高速公路挖方边坡设计的特点和要求,结合依托工程实例,阐述了基于支持向量机和粒子群算法的智能方法在高速公路挖方边坡优化设计中的具体应用,为高速公路挖方边坡优化设计提供参考。     

基于支持向量机的沥青路面使用性能评价

路面使用性能决定了路面维修养护的方法。但沥青路面使用性能4个指标：PCI、SSI、SRI和IRI中路面状况指数检测困难。支持向量机是具有严格统计学习理论的新型学习方法。它对解决小样本非线性等问题具特有的优势。基于支持向量机理论,分析沥青路面使用性能4个指标间的关系,建立了SSI、SRI、IRI实测数据对PCI的预测模型,获得了令人满意的预估效果。结果表明,支持向量机是沥青路面性能评估的简单有效的方法。     

Application of the support vector machine and heuristic k-shortest path algorithm to determine the most eco-friendly path with a travel time constraint

This study aims to determine an eco-friendly path that results in minimum CO₂ emissions while satisfying a specified budget for travel time. First, an aggregated CO₂ emission model for light-duty cars is developed in a link-based level using a support vector machine. Second, a heuristic k-shortest path algorithm is proposed to solve the constrained shortest path problem. Finally, the CO₂ emission model and the proposed eco-routing model are validated in a real-world network. Specifically, the benefit of the trade-off between CO₂ emission reduction and the travel time budget is discussed by carrying out sensitivity analysis on a network-wide scale. A greater spare time budget may enable the eco-routing to search for the most eco-friendly path with higher probability. Compared to the original routes selected by travelers, the eco-friendly routes can save an average of 11% of CO₂ emissions for the trip OD pairs with a straight distance between 6 km and 9 km when the travel time budget is set to 10% above the least travel time. The CO₂ emission can also be reduced to some degree for other OD pairs by using eco-routing. Furthermore, the impact of market penetration of eco-routing users is quantified on the potential benefit for the environment and travel-time saving.     

基于支持向量机的汽车爪极发电机高效电磁建模分析

在对爪极发电机电磁特性进行严格电磁仿真的基础上,基于支持向量机非参数回归建模技术建立面向计算机辅助设计的快速准确模型。通过仿真和统计检验表明,所建立的模型准确可行,并且是高效的。     

基于SVM的桥梁状态监测方法

随着交通领域的迅速发展,保障桥梁安全、降低维护费用成为普遍关注的问题。以振动分析为基础、广泛借助信息技术的理论和方法,进行桥梁状态监测成为当前的研究热点。考虑到的桥梁损伤样本很难获得、个体差异使得损伤数据难以共享的实际问题,本文将桥梁状态监测归结为异常监测问题,引入基于SVM的一类学习算法从长期监测数据中获取正常状态的模式,实现异常状态的精确报警。文中采用香港汀九桥400小时实测数据,验证了这种方法的实际效果。     

基于虚拟支撑力的隧道合理支护时机探讨分析

以连云港北固山隧道为工程背景,利用有限元分析软件,分析了隧道开挖后在不同荷载释放系数下施加支护的作用效果；同时,结合超前注浆加固机理,对施作超前支护与不施作超前支护两种工况在不同支护时机下施作初期支护的围岩及支护结构的力学特征进行了对比分析,并根据两种工况下支护时机对隧道开挖后围岩及支护结构力学特征的影响,初步确定了较理想的初期支护时机.     

一种新的支持向量回归算法及其在集装箱吞吐量预测中的应用

支持向量机是基于统计学习理论框架下的一种新的通用机器学习方法,是一种处理非线性分类和非线性回归的有效方法。由于具有完备的理论基础和出色的学习性能,该技术已成为当前国际机器学习界的研究热点,能较好地对应解决小样本、高维数、非线性和局部极小点等实际问题。近来,SVR方法被引入求解回归和预测问题,并在各领域中得到广泛的应用。文章提出了一种新的基于单参数的Lagrangian支持向量回归算法,并将该算法应用在集装箱吞吐量预测中。估算结果证明了这种改进的支持向量回归算法在集装箱吞吐量预测中的有效性和实用性。