The intelligent use of finite element methods

The structural analysis based on application of numerical methods used in the solution of complex structural problems, when applied correctly, is a powerful tool leading to rational structural design of ships. This paper discusses the practicalities of its application and indicates that in order to achieve the stated objective, the following are essential pre-requisites: a) full understanding of the problem; b) ability to solve the problem using currently available methods; and c) ability to interpret the results of the analysis correctly. Whilst there is still a lot of discussion on whether the structural analysis represents a structural design or a structural verification tool, the view expressed in this paper is that the structural analysis should mainly be used in the latter context. This means that a sound engineering solution ought to be established in the first phase of the analysis and used as a basis. The final results will then only be used to perfect the structural detail and modify the areas where rapid stress gradients occur. Any other approach would invariably require repetitive, time consuming and costly iterations which under normal circumstances may prove to be counter-productive. This paper presents a few examples of practical application, the methodology of achieving the solution and the way of interpreting the results.     

铁路公益性客运范围界定混合决策模型

随着国家“基本公共服务均等化”规划的提出和铁路“政企分开”市场化改革的推进,铁路公益性与商业性服务之间的矛盾越发突出. 合理界定铁路公益性客运范围是缓解冲突,实现有效供给的前提. 本文结合定性与定量分析,构建了基于B-C-C三阶段决策流程和 PCFA-FCM降维聚类算法的铁路公益性客运范围界定混合决策模型.B-C-C三阶段决策模型以社会效益、经济状况和现实能力作为层进式判定条件,实现铁路公益性客运范围界定的顶层决策.PCFA-FCM降维聚类算法解决了决策流程实际运作中最难实现的社会效益(公益程度)量化分析问题,可以摆脱列车类型的约束,根据实际指标属性进行分类.     

一种改进K-means模型的城市轨道交通突发事件分级方法

针对城市轨道交通事件量化分级的难题,本文提出了一种改进的 K-means聚类的突发事件分级方法.首先,从事件类型、持续时间、影响程度等方面分析各种类型事件的特征规律,提取 8个关键特征量用于聚类分析;其次,应用主成分分析法提取 4个主成分变量并提出权重系数计算方法,实现特征向量降维;提出了基于密度扫描的初始聚类中心确定方法,并将改进的 K-means聚类算法应用于地铁突发事件的分级.案例结果表明,与原始 K-means聚类方法对比,应用本文提出的改进方法聚类效果更佳.研究成果已应用于北京地铁应急指挥系统,验证了本文方法的可行性.     

Automated classification based on video data at intersections with heavy pedestrian and bicycle traffic: Methodology and application

Pedestrians and cyclists are amongst the most vulnerable road users. Pedestrian and cyclist collisions involving motor-vehicles result in high injury and fatality rates for these two modes. Data for pedestrian and cyclist activity at intersections such as volumes, speeds, and space–time trajectories are essential in the field of transportation in general, and road safety in particular. However, automated data collection for these two road user types remains a challenge. Due to the constant change of orientation and appearance of pedestrians and cyclists, detecting and tracking them using video sensors is a difficult task. This is perhaps one of the main reasons why automated data collection methods are more advanced for motorized traffic. This paper presents a method based on Histogram of Oriented Gradients to extract features of an image box containing the tracked object and Support Vector Machine to classify moving objects in crowded traffic scenes. Moving objects are classified into three categories: pedestrians, cyclists, and motor vehicles. The proposed methodology is composed of three steps: (i) detecting and tracking each moving object in video data, (ii) classifying each object according to its appearance in each frame, and (iii) computing the probability of belonging to each class based on both object appearance and speed. For the last step, Bayes’ rule is used to fuse appearance and speed in order to predict the object class. Using video datasets collected in different intersections, the methodology was built and tested. The developed methodology achieved an overall classification accuracy of greater than 88%. However, the classification accuracy varies across modes and is highest for vehicles and lower for pedestrians and cyclists. The applicability of the proposed methodology is illustrated using a simple case study to analyze cyclist–vehicle conflicts at intersections with and without bicycle facilities.     

A robust approach for road users classification using the motion cues

Video monitoring of traffic is a common practice in major cities. The data generated by video monitoring has practical uses such as traffic analysis for city planning. However, the usefulness of video monitoring of traffic is limited unless there is also a reliable way to automatically classify road users. This paper presents an automated method of road users’ classification into vehicles, cyclists, and pedestrians by using their motion cues. In this method, the movement of road users was captured on sequences of video frames. The videos were analysed using a feature-based tracking system, which has returned the tracks of road users. The separate pieces of information gained from these tracks are hereafter called Classifiers. There are nineteen classifiers included in this method. The classifiers’ values were assessed and integrated into a fuzzy membership framework, which in turn required prior configurations to be available. This led to the final classification of road users. The performance of this method demonstrated promising results. An important contribution of this paper is the creation of a robust approach that can integrate different classifiers using fuzzy membership framework. The developed method also uses parametric classifiers, which do not depend on the specific geometry or traffic operation of the intersection. This is a key advantage because it enables transferability and improves the practicality and usefulness of the method.     

Soft Radial Basis Cellular Neural Network (SRB-CNN) based robust low-cost truck detection using a single presence detection sensor

This paper does present a comprehensive concept for a robust and reliable truck detection involving solely one single presence sensor (e.g. an inductive loop, but also any other presence sensor) at a signalized traffic junction. Hereby, two operations modes are distinguished: (a) during green traffic light phases, and (b) a much challenging case, during red traffic light phases. First, it is shown how difficult the underlying classification task is, this mainly due to strongly overlapped classes, which cannot be easily separated by simple hyper-planes. Then, a novel soft radial basis cellular neural/nonlinear network (SRB-CNN) based concept is developed, validated and extensively benchmarked with a selection of the best representatives of the current related state-of-the-art classification concepts (namely the following: support vector machines with radial basis function, artificial neural network, naive Bayes, and decision trees). For benchmarking purposes, all selected competing classifiers do use the same features and the superiority of the novel CNN based classifier is thereby underscored, as it strongly outperforms the other ones. This novel SRB-CNN based concept does satisfactorily fulfill the hard industrial requirements regarding robustness, low-cost, high processing speed, low memory consumption, and the capability to be deployed in low cost embedded systems.     

Vehicle classification from low-frequency GPS data with recurrent neural networks

The categorization of the type of vehicles on a road network is typically achieved using external sensors, like weight sensors, or from images captured by surveillance cameras. In this paper, we leverage the nowadays widespread adoption of Global Positioning System (GPS) trackers and investigate the use of sequences of GPS points to recognize the type of vehicle producing them (namely, small-duty, medium-duty and heavy-duty vehicles). The few works which already exploited GPS data for vehicle classification rely on hand-crafted features and traditional machine learning algorithms like Support Vector Machines. In this work, we study how performance can be improved by deploying deep learning methods, which are recently achieving state of the art results in the classification of signals from various domains. In particular, we propose an approach based on Long Short-Term Memory (LSTM) recurrent neural networks that are able to learn effective hierarchical and stateful representations for temporal sequences. We provide several insights on what the network learns when trained with GPS data and contextual information, and report experiments on a very large dataset of GPS tracks, where we show how the proposed model significantly improves upon state-of-the-art results.     

潜水器吊放系统设计

通过对船级社相关规范内容的深入分析研究,本文对潜水器吊放系统的设计要点进行梳理,帮助设计人员了解相关总体参数的选取与应用,形成一套完整的设计准则,为潜水器吊放系统的总体设计提供重要理论依据。     

自动化集装箱码头业务流程设计

针对目前自动化集装箱码头的设计中缺少业务流程的规范性和纲领性操作指引的问题,从自动化集装箱码头业务流程的基础框架、分类及层级设计原则、设计方法和步骤以及流程建模与验证等方面进行研究,并结合青岛港自动化集装箱码头进行业务流程设计。结果表明,使用本文方法设计的自动化集装箱码头业务流程能够提升决策和建设的效率,可为类似工程提供参考。