基于随机森林结合前向序列选择算法的铁路隧道防水板检测数据关键影响因素识别北大核心

针对参数特征复杂度高的铁路产品,提出了一种基于随机森林(RF)结合前向序列选择(SFS)算法的铁路产品检验检测数据关键影响因素识别方法,以辅助基于经验的识别方法。创新使用RF-SFS算法,将其应用于铁路隧道防水板检验检测数据关键影响因素的识别研究。根据多年铁路隧道防水板检测数据,建立RF模型,获得了影响铁路隧道防水板检测结果的特征关键性评分序列。随后,结合SFS方法得出关键性评分序列的阈值,将排名前6位的影响因素识别为关键特征,模型的预测能力达到99.98%。为验证关键特征识别方法的有效性,对比分析3种模型在使用不同特征子集时的预测能力。当仅选用关键特征时,3种模型的预测能力均达到最佳,加入冗余特征后模型的预测能力逐渐降低。     

公共自行车使用时空特性挖掘及租还需求预测

基于宁波市公共自行车刷卡数据、POI(Point of Interest)数据、气象和空气质量等数据，从数据驱动视角，深入挖掘公共自行车使用的时空特征及站点租还车需求预测。在时间上，采用KMeans算法，将站点聚为5类，探讨各类站点的时变需求规律及影响因素；在空间上，提出基于POI 数据的站点用地类型识别方法，将站点分为居住类、交通设施类、办公类和商业休闲类。构建以 15，30，60 min 为间隔，以租还车需求为目标变量的随机森林预测模型，并与常用的 BP (Back Propagation)神经网络、K最近邻方法进行比较。结果表明，随机森林模型的精度更高，适用性更强。以30 min为间隔的站点租还车需求预测精度最高，考虑站点土地利用类型后能有效提高模型的预测精度。本文结果可作为未来站点平衡调度的依据并推广应用于共享单车系统，为改善服务水平提供技术和理论支撑。     

港口物流园区建设风险分析与评估

根据港口物流园区建设的特点,分析其建设中存在的各类风险及风险因素,在此基础上建立了风险评估指标体系,并用模糊综合评估法对其风险水平进行了评估。     

Real-time trip purpose prediction using online location-based search and discovery services

The use of smartphone technology is increasingly considered a state-of-the-art practice in travel data collection. Researchers have investigated various methods to automatically predict trip characteristics based upon locational and other smartphone sensing data. Of the trip characteristics being studied, trip purpose prediction has received relatively less attention. This research develops trip purpose prediction models based upon online location-based search and discovery services (specifically, Google Places API) and a limited set of trip data that are usually available upon the completion of the trip. The models have the potential to be integrated with smartphone technology to produce real-time trip purpose prediction. We use a recent, large-scale travel behavior survey that is augmented by downloaded Google Places information on each trip destination to develop and validate the models. Two statistical and machine learning prediction approaches are used, including nested logit and random forest methods. Both sets of models show that Google Places information is a useful predictor of trip purpose in situations where activity- and person-related information is uncollectable, missing, or unreliable. Even when activity- and person-related information is available, incorporating Google Places information provides incremental improvements in trip purpose prediction.     

海堤内坡种植防护林的安全影响分析及尺度论证

海堤从外海堤脚至内侧护堤之间的滩涂围垦空间,既是陆地边缘,也是水的边缘。外侧可构建滨海景观,内侧结合随塘河形成亲水景观,具有得天独厚的优势。内侧平台的防护林及景观有机结合,可构建人们休闲旅游的"黄金绿带"。结合台州某海堤生态提升工程,提出海堤生态提升总体技术方案,重点对海堤内坡种植景观防护林对海堤安全的影响进行分析,明确种植平台高程、尺度布置等主要技术参数,为类似海堤生态改造工程提供参考。     

MapX在停车场可视化信息管理中的应用

MapX是一种功能强大的可编程ActiveX组件，能够与VB．Net等多种高级编程语言结合进行地理信息系统的二次开发。文章以VB．Net为开发工具，深入研究了MapX在停车场可视化管理中的具体应用，借助MapX开发了城市停车场可视化信息管理系统。该系统摆脱了停车场沉重繁琐的手工作业式传统管理模式，提高了停车场信息管理的效率。     

公园城市街道一体化设计理念的应用实践——以成都杉板桥路市政管线改造设计为例

以成都市公园城市街道一体化建设试点项目——杉板桥路(二环-中环)改造项目为工程背景，阐述了传统市政管线改造设计要点和公园城市街道一体化理念下市政管线改造设计要点。介绍了公园城市街道一体化设计理念在该项目中的应用实践。对改造项目进行了管线现状及需求分析和管线建设边界条件分析，详细介绍了市政管线改造采用缆线管廊、综合排管的创新设计方案。     

Physical–biological coupling in spore dispersal of kelp forest macroalgae

The physical–biological linkages controlling the dispersal of spores produced by macroalgae that reside in kelp forests are complicated and laced with feedbacks. Here we discuss the fundamental elements of these interactions. Biological considerations include spore swimming and sinking speeds, their periods of viability in the plankton, and the height of spore release above the seafloor, which together determine the durations over which spores can be swept by horizontal currents before they contact the seafloor. Morphologies and material properties of canopy forming kelps may also influence the drag exerted on passing waters by the kelps, the plants' ability to persist in the face of rapid flows, and thereby the degree to which impinging currents are redirected around, or slowed within, kelp forests. Macroalgal life histories, and the size of spore sources as controlled by the dimensions of kelp forests and the density and fecundity of individuals within them, influence effective dispersal distances as well. Physical considerations encompass the mean speed, direction, and timescales of variability of currents relative to spore suspension times, the interaction of surface gravity waves with currents in producing turbulence in the benthic boundary layer, wind-driven surface mixing, water stratification, and shoreline bathymetry and substratum roughness, all of which can affect the interplay of vertical and horizontal transport of macroalgal spores. Intricate within-forest processes may induce attenuation of current speeds and consequent reductions in seabed shear, along with simultaneous production of small-scale turbulence in kelp wakes. Slower mean currents and smaller eddy scales in turn may attenuate vertical mixing within forests, thus extending spore suspension times. Further complexities likely arise due to changes in the relative rates of horizontal and vertical dispersion, modifications to the overall profiles of vertical mixing, and the creation of fine-scale secondary flows around kelp individuals and substratum features. Under conditions of more rapid currents, submergence of the surface canopy and the establishment of skimming flows at the canopy–fluid interface may introduce additional coherent flow structures that alter rates of fluid exchange to and from the forest. Many of these coupled physical–biological processes are just beginning to be examined in a rigorous fashion in kelp forests, but their potential importance is clear.     

港口集装箱物流园区规模的研究

在提出港口物流园区研究现状的前提下,分析了港口集装箱物流园区的作用,对港口集装箱物流园区核心功能区划分进行了深入探讨,最后对港口物流园区规模的测算提出了模型和方法,并附以算例。     

基于车辆运行数据的疲劳驾驶状态检测

疲劳驾驶是导致交通事故的主要原因之一，及时检测疲劳驾驶，并提醒驾驶员集中注意力，对保证安全行车具有重要意义.本文基于CAN(Controller Area Network)总线采集的车辆运行状态数据，提取了18项与驾驶行为相关的特征，并采用随机森林算法对疲劳驾驶进行识别，结果表明整体的识别准确率为0.785，其中召回率为0.61，即61%的疲劳驾驶状态可被识别出来.实验表明，基于车辆运行状态的疲劳驾驶检测具有一定的效果，且与其他客观的疲劳驾驶检测方法(基于驾驶员生理指标和图像面部特征)相比，具有简单方便，不影响驾驶，且成本低的优势.