基于最小二乘支持向量机的车型识别算法研究

以感应线圈车辆检测器检测数据为分析基础,给出了基于Bayes理论的感应曲线自适应特征提取流程和方法,对选取的12个统计特征指标进行提取和优选。选择了曲线宽度、最大值、波峰数量、最小波谷值和波谷比组成车型识别模型的特征输入向量,不仅降低了输入向量的维数,缩短了最小二乘支持向量机的训练时间,同时也可加快车型识别的分类速度,增强特征值的分类辨别能力,提高车型分类的可靠性。在提出的基于最小二乘支持向量机的车型识别算法中,采用了修剪算法,加快了计算速度,同时保持了良好的回归性能。通过实例分析证明:基于最小二乘支持向量机的车型识别算法可提高自学习能力和识别准确率。     

决策树剪枝方法的比较

为在决策树剪枝中正确选择剪枝方法，基于理论分析和算例详细地比较了当前主要的4种剪枝方法的计算复杂性、剪枝方式、误差估计和理论基础．与PEP相比，MEP产生的树精度较小且树较大；REP是最简单的剪枝方法之一，但需要独立剪枝集；在同样精度情况下，CCP比REP产生的树小．如果训练数据集丰富，可以选择REP，如果训练数据集较少且剪枝精度要求较高，则可以选用PEP．     

青草背长江大桥主缆缠丝初拉力的修正分析

文章阐述了悬索桥主缆缠丝拉力的变化过程和主缆缠丝预加力的计算方法,并结合重庆涪陵青草背长江大桥主桥工程实例,在原设计缠丝初始导入力的基础上通过分析计算与比较,对该桥主缆缠丝的原设计初拉力进行了修正,为类似工程项目提供参考。     

Pruning and ranking the Pareto optimal set,application for the dynamic multi‐objective network design problem

Solving the multi‐objective network design problem (MONDP) resorts to a Pareto optimal set. This set can provide additional information like trade‐offs between objectives for the decision making process, which is not available if the compensation principle would be chosen in advance. However, the Pareto optimal set of solutions can become large, especially if the objectives are mainly opposed. As a consequence, the Pareto optimal set may become difficult to analyze and to comprehend. In this case, pruning and ranking becomes attractive to reduce the Pareto optimal set and to rank the solutions to assist the decision maker. Because the method used, may influence the eventual decisions taken, it is important to choose a method that corresponds best with the underlying decision process and is in accordance with the qualities of the data used. We provided a review of some methods to prune and rank the Pareto optimal set to illustrate the advantages and disadvantages of these methods. The methods are applied using the outcome of solving the dynamic MONDP in which minimizing externalities of traffic are the objectives, and dynamic traffic management measures are the decision variables. For this, we solved the dynamic MONDP for a realistic network of the city Almelo in the Netherlands using the non‐dominated sorting genetic algorithm II. For ranking, we propose to use a fuzzy outranking method that can take uncertainties regarding the data quality and the perception of decision makers into account; and for pruning, a method that explicitly reckons with significant trade‐offs has been identified as the more suitable method to assist the decision making process. Copyright © 2012 John Wiley & Sons, Ltd.     

旋转避障式打草割灌机的研究与应用

介绍了高速公路绿化养护中,如何实现打草割灌机械化作业的方式,及旋转避障式打草割灌机的研究和应用.