用改进的前向神经网络预测铁路货运量

对影响铁路货运量的因素进行了分析。根据影响铁路货运量的诸因素的特点，介绍了一种改进的前向神经网络预测方法，并建立了铁路货运量前向神经网络预测模型。算例表明，其预测精度高于常规预测方法。     

基于人工神经网络的柴油机故障诊断

故障诊断是计算机模式识别领域的一个活跃课题。文中提出了基于人工神经网络的柴油机故障诊断方法，设计了适合该诊断系统的BP网络结构，并给出了一种基于黄金分割法改进的BP算法，用来自适应调整网络学习速率。仿真结果表明：该算法具有很快的学习速度和较高的学习精度，完全适用于柴油机故障诊断系统。     

汽车防追尾碰撞数学模型研究

为了提高车辆在高速行驶状态下的主动安全性能,研究了处于追尾行驶状态的本车与前车的运动学特征;针对前车的不同运动状态分别推导出了跟车距离的计算模型并分析了模型中3个关键参数的随机性和动态性,对制动迟滞时间提出了基于模糊推理的确定方法,对本车制动减速度和前车的运动加速度提出了比较实用的动态测算公式;另外,研究了防追尾碰撞的控制与执行,建立了动态调整安全制动停车距离的神经网络模型,提出了基于危险裕度判别的安全控制方法。     

Who you are is how you travel: A framework for transportation mode detection using individual and environmental characteristics

With the increasing prevalence of geo-enabled mobile phone applications, researchers can collect mobility data at a relatively high spatial and temporal resolution. Such data, however, lack semantic information such as the interaction of individuals with the transportation modes available. On the other hand, traditional mobility surveys provide detailed snapshots of the relation between socio-demographic characteristics and choice of transportation modes. Transportation mode detection is currently approached using features such as speed, acceleration and direction either on their own or in combination with GIS data. Combining such information with socio-demographic characteristics of travellers has the potential of offering a richer modelling framework that could facilitate better transportation mode detection using variables such as age and disability. In this paper, we explore the possibility to include both elements of the environment and individual characteristics of travellers in the task of transportation mode detection. Using dynamic Bayesian Networks, we model the transition matrix to account for such auxiliary data by using an informative Dirichlet prior constructed using data from traditional mobility surveys. Results have shown that it is possible to achieve comparable accuracy with the most widely used classification algorithms while having a rich modelling framework, even in the case of sparse mobility data.     

Forecasting current and next trip purpose with social media data and Google Places

Trip purpose is crucial to travel behavior modeling and travel demand estimation for transportation planning and investment decisions. However, the spatial-temporal complexity of human activities makes the prediction of trip purpose a challenging problem. This research, an extension of work by Ermagun et al. (2017) and Meng et al. (2017), addresses the problem of predicting both current and next trip purposes with both Google Places and social media data. First, this paper implements a new approach to match points of interest (POIs) from the Google Places API with historical Twitter data. Therefore, the popularity of each POI can be obtained. Additionally, a Bayesian neural network (BNN) is employed to model the trip dependence on each individual’s daily trip chain and infer the trip purpose. Compared with traditional models, it is found that Google Places and Twitter information can greatly improve the overall accuracy of prediction for certain activities, including “EatOut”, “Personal”, “Recreation” and “Shopping”, but not for “Education” and “Transportation”. In addition, trip duration is found to be an important factor in inferring activity/trip purposes. Further, to address the computational challenge in the BNN, an elastic net is implemented for feature selection before the classification task. Our research can lead to three types of possible applications: activity-based travel demand modeling, survey labeling assistance, and online recommendations.     

A hybrid deep learning based traffic flow prediction method and its understanding

Deep neural networks (DNNs) have recently demonstrated the capability to predict traffic flow with big data. While existing DNN models can provide better performance than shallow models, it is still an open issue of making full use of spatial-temporal characteristics of the traffic flow to improve their performance. In addition, our understanding of them on traffic data remains limited. This paper proposes a DNN based traffic flow prediction model (DNN-BTF) to improve the prediction accuracy. The DNN-BTF model makes full use of weekly/daily periodicity and spatial-temporal characteristics of traffic flow. Inspired by recent work in machine learning, an attention based model was introduced that automatically learns to determine the importance of past traffic flow. The convolutional neural network was also used to mine the spatial features and the recurrent neural network to mine the temporal features of traffic flow. We also showed through visualization how DNN-BTF model understands traffic flow data and presents a challenge to conventional thinking about neural networks in the transportation field that neural networks is purely a “black-box” model. Data from open-access database PeMS was used to validate the proposed DNN-BTF model on a long-term horizon prediction task. Experimental results demonstrated that our method outperforms the state-of-the-art approaches.     

Impact assessment of extreme weather events on transport networks: A data-driven approach

The present paper presents a data-driven method for assessing the resilience of the European passenger transport network during extreme weather events. The method aims to fill in the gap of current research efforts regarding the quantification of impacts attributed to climate change and the identification of substitutability opportunities between transport modes in case of extreme weather events (EWE). The proposed method consists of three steps concerning the probability estimation of an EWE occurring within a transportation network, the assessment of its impacts and the passengers’ flow shift between various transport modes. A mathematical formulation for the proposed data-driven method is provided and applied in an indicative European small-scale network, in order to assess the impacts of EWE on modal choice. Results are expressed in passenger differentiated flows and the paper concludes with future research steps and directions.     

Controller design for gating traffic control in presence of time-delay in urban road networks

Recent studies demonstrated the efficiency of feedback-based gating control in mitigating congestion in urban networks by exploiting the notion of macroscopic or network fundamental diagram (MFD or NFD). The employed feedback regulator of proportional-integral (PI)-type targets an operating NFD point of maximum throughput to enhance the mobility in the urban road network during the peak period, under saturated traffic conditions. In previous studies, gating was applied directly at the border of the protected network (PN), i.e. the network part to be protected from over-saturation. In this work, the recently developed feedback-based gating concept is applied at junctions located further upstream of the PN. This induces a time-delay, which corresponds to the travel time needed for gated vehicles to approach the PN. The resulting extended feedback control problem can be also tackled by use of a PI-type regulator, albeit with different gain values compared to the case without time-delay. Detailed procedures regarding the appropriate design of related feedback regulators are provided. In addition, the developed feedback concept is shown to work properly with very long time-steps as well. A large part of the Chania, Greece, urban network, modelled in a microscopic simulation environment under realistic traffic conditions, is used as test-bed in this study. The reported results demonstrate a stable and efficient behaviour and improved mobility of the overall network in terms of mean speed and travel time.     

Achieving transport modal split targets at intermodal freight hubs using a model predictive approach

The increase of international freight commerce is creating pressure on the existing transport network. Cooperation between the different transport parties (e.g., terminal managers, forwarders and transport providers) is required to increase the network throughput using the same infrastructure. The intermodal hubs are locations where cargo is stored and can switch transport modality while approaching the final destination. Decisions regarding cargo assignment are based on cargo properties. Cargo properties can be fixed (e.g., destination, volume, weight) or time varying (remaining time until due time or goods expiration date). The intermodal hub manager, with access to certain cargo information, can promote cooperation with and among different transport providers that pick up and deliver cargo at the hub. In this paper, cargo evolution at intermodal hubs is modeled based on a mass balance, taking into account hub cargo inflows and outflows, plus an update of the remaining time until cargo due time. Using this model, written in a state-space representation, we propose a model predictive approach to address the Modal Split Aware – Cargo Assignment Problem (MSA–CAP). The MSA–CAP concerns the cargo assignment to the available transport capacity such that the final destination can be reached on time while taking into consideration the transport modality used. The model predictive approach can anticipate cargo peaks at the hub and assigns cargo in advance, following a push of cargo towards the final destination approach. Through the addition of a modal split constraint it is possible to guide the daily cargo assignment to achieve a transport modal split target over a defined period of time. Numerical experiments illustrate the validity of these statements.     

Modeling time-of-day car use behavior: A Bayesian network approach

In this research, a Bayesian network (BN) approach is proposed to model the car use behavior of drivers by time of day and to analyze its relationship with driver and car characteristics. The proposed BN model can be categorized as a tree-augmented naive (TAN) Bayesian network. A latent class variable is included in this model to describe the unobserved heterogeneity of drivers. Both the structure and the parameters are learned from the dataset, which is extracted from GPS data collected in Toyota City, Japan. Based on inferences and evidence sensitivity analysis using the estimated TAN model, the effects of each single observed characteristic on car use measures are tested and found to be significant. The features of each category of the latent class are also analyzed. By testing the effect of each car use measure on every other measure, it is found that the correlations between car use measures are significant and should be considered in modeling car use behavior.