A multi-pattern deep fusion model for short-term bus passenger flow forecasting

Short-term passenger flow forecasting is one of the crucial components in transportation systems with data support for transportation planning and management. For forecasting bus passenger flow, this paper proposes a multi-pattern deep fusion (MPDF) approach that is constructed by fusing deep belief networks (DBNs) corresponding to multiple patterns. The dataset of the short-term bus passenger flow is first segmented into different clusters by an affinity propagation algorithm. The passenger flow distribution of these clusters is subsequently analyzed for identifying different patterns. In each pattern, a DBN is developed as a deep representation for the passenger flow. The outputs of the DBNs are finally fused by chronological order rearrangement. Taking a bus line in Guangzhou city of China as an example, the present MPDF approach is modeled. Five approaches, non-parametric and parametric models, are applied to the same case for comparison. The results show that, the proposed model overwhelms all the peer methods in terms of mean absolute percentage error, root-mean-square error, and determination coefficient criteria. In addition, there exists significant difference between the addressed model and the comparison models. It is recommended from the present study that the deep learning technique incorporating the pattern analysis is promising in forecasting the short-term passenger flow.     

Predicting the passenger demand on bus services for mobile users

Public transport, especially the bus transport, can reduce the private car usage and fuel consumption, and alleviate traffic congestion. However, when traveling in buses, the travelers not only care about the waiting time, but also care about the crowdedness in the bus itself. Excessively overcrowded bus may drive away the anxious travelers and make them reluctant to take buses. So accurate, real-time and reliable passenger demand prediction becomes necessary, which can help determine the bus headway and help reduce the waiting time of passengers. Based on a large database from a real bus system, this paper aims to present a passenger demand prediction system for mobile users. The system includes a server-side bus information data stream processing and mining program and a client-side mobile application for Android smartphones. The server program continuously monitors for each bus stop the number of passengers waiting at the bus stop, the number of passengers that will pass the bus stop, as well as the traffic conditions in the area around the stop. It delivers real time bus and traffic information to mobile users via restful web services. The client-side location-based mobile application consumes these services to help mobile users make informed transportation choices. For example the availability of buses might be a deterrent when they are too crowded. However, there are three major challenges for predicting the passenger demands on bus services: inhomogeneous, seasonal bursty periods and periodicities. To overcome the challenges, we propose three predictive models and further take a data stream ensemble framework to predict the number of passengers. We develop a prototype system with different types of Android based mobile phones and comprehensively experiment over a 22-week period. The evaluation results suggest that the proposed system achieves outstanding prediction accuracy among 86,411 passenger demands on bus services, more than 78% of them are accurately forecasted.     

短时公交客流的弦不变量预测方法

短时公交客流预测是智能公交系统动态调度的基础.文中根据短时公交客流数据特性,提出基于弦理论的短时公交客流预测方法,模拟弦结构建立弦不变量客流预测模型(SI-PFPM),并采用遗传算法优化SI-PFPM中各参数.提出基于动态时间弯曲距离的仿射传播(AP)聚类算法,对短时公交客流时间序列进行聚类分析.利用SI-PFPM预测聚类子集数据,并分析预测残差,验证SI-PFPM可以预测短时公交客流的假设成立.最后将SI-PFPM的预测性能与现有方法进行对比分析,验证SI-PFPM对短时公交客流预测的有效性.     

公交网络中的乘客需求预测系统和方法

公共交通工具,尤其是公交车服务,可以减少私家车的使用和燃油消耗,缓解交通拥堵和环境污染状况。当乘坐公交车时,乘客不仅关心等车时间,更在乎公交车的拥挤程度,过度拥挤的公交车会导致乘客放弃乘坐。可见,准确、实时、可靠的乘客需求预测可以帮助公交公司决定合理的公交发车时间间隔,并且可以减少乘客的等车时间,这是人们急切需要的。基于实际公交系统的大量数据,提出一个面向移动用户的乘客需求预测系统。该系统包括服务器端的信息数据流处理和挖掘程序,以及客户端的移动应用程序。然而,公交网络中的乘客需求预测存在三大挑战:不均匀性、突发性和周期性。为了解决这些问题,提出了3种预测模型和1种基于滑动窗口的框架来预测乘客的数目。开发了一个原型系统,该系统可运行在多个版本的Android移动手机上,22个月的连续实验证明,该系统能够对公交网络中的864110项乘客需求进行精确预测,其准确度超过78%。     

A fast hybrid computer vision technique for real-time embedded bus passenger flow calculation through camera

Bus passenger flow calculation system is a critical part of the smart public transportation framework. Bus passenger flow information can help to make data statistics report of the passenger at a bus station which can be used by public transport operator to evaluate the quality of the transportation. Statistics report of crowded passengers in the bus station help managers to understand the bus transit operations, can provide the database for the intelligent transportation scheduling, help to provide more and better services for passengers, overall data statistics of passengers has important practical significance to improve public transport environment. This paper presents a passenger counting algorithm based on hybrid machine learning approach. In the first step, an advanced method is used to extract the Histogram of oriented gradients (HOG) feature of passenger’s heads. Classification of head features is done by using support vector machine (SVM) as a classifier for the liner model. Heads are detected successfully after performing all steps. In next step Kanade-Lucas-Tomasi (KLT) is used to reality head tracking, the multiple target tracking is achieved and the head motion trajectory of passenger target is captured stably. At last, the trajectory is analyzed and the automatic counting of bus passenger flow is realized. In the last step, the proposed algorithm is move to embedded system for practical implementation. In this paper, the algorithm intends to use ADSP-BF609 embedded platform for transplantation. The experimental results demonstrate that the statistical accuracy of the proposed algorithm is enhanced successfully; especially during the daytime with the good illustration, the effective counting of the passenger flow is achieved and the inward and outward passenger counting can be realized. In this paper three feature extraction models are used namely local binary patterns, histograms of oriented gradients and binarized statistical image in order to get accurate features. Furthermore, three common classification techniques including naïve bayes classifier, boosted tress and support vector machines are used for fine classification of extracted vectors obtained from different features extractors model. 94.50% accuracy is achieved when support vector machine (SVM) classifies the features extracted using Histogram of oriented gradients (HOG). SVM surpasses the accuracy obtained by Boosted tree namely 81.30% using Histogram of oriented gradients (HOG) features.

     

Mathematical model of moving collectives interaction: Public transport and passengers

In this paper, development of the model of collective interaction in the system “buses-passengers” represented in [1] is discussed. The point is that route busing depends on the travel time and alighting at bus stops; these times depend on boarding and passengers crowding at bus stops. In its turn, the number of passengers in the passenger compartment and at bus stops depends on the buses motion on the route.General equations and hypotheses describing the system behavior are formulated. A case of buses motion according to the schedule. Equations for deviations of system parameters from the values specified by the schedule are obtained and studied in the linear approximation.     

基于公共交通智能卡数据的可视化分析

针对现有公共交通数据的可视分析方法很难在不同空间粒度下对乘客时空分布、客流时空分布、区域间客流时序变化进行多任务分析的问题,设计实现了一个多视图融合的可视化分析系统。该系统结合城市公共交通的智能卡数据、车辆GPS数据、地铁和公交线路信息,利用出行链路模型和基于出行时空特征的回归模型完成了乘客起讫点（origin-destination,OD）推断;然后,设计了层次聚类的地图可视化方法,结合了融合方位信息的玫瑰图和动态对比堆叠折线流图来分析各区域间的客流时序特点、关联关系;最后,利用真实的深圳市公共交通数据的可视分析结果验证了系统的有效性。     

Detection of passenger flow on and off buses based on video images and YOLO algorithm

Bus passenger flow information is very important as a reference data for bus company line optimization, schedule scheduling basis, and passenger travel mode arrangement. With the development of image processing technology, it has become a current research trend to count passenger flow with the help of surveillance video of passengers getting on and off the bus. The specific research contents of this paper based on video image detection and statistics of passengers are as follows:(1) Collect head target image samples through a variety of ways, including 3960 positive head target samples and 4150 negative head target samples, which together constitute the head target feature database. (2) Established a head target detection model based on deep learning. First, the labeling of the head target training data set is completed. Then, after 15,000 iterations of model training, the YOLOv3 head target detection network model was obtained, with a recall rate of 92.12% and an accuracy rate of 89.71%. (3) A multi-target matching tracking algorithm based on the combination of Cam-shift and YOLOv3 is proposed. First, the Cam-shift algorithm is used to track the head target. Secondly, the head target tracking data and the YOLOv3 detection data are combined to solve the problem of drift during the tracking of the Cam-shift algorithm through the data association matching method based on the minimum distance, and then combined with the time constraint, a passenger location information judgment rule is proposed. Optimize the error and missed detection in the process of head target detection and tracking, and improve the reliability of passenger trajectory tracking. (4) A statistical algorithm for the detection of passengers getting on and off the bus is proposed. First, the trajectory of passengers in the bus boarding and disembarking area is analyzed, and a process for judging passengers’ boarding and boarding behavior is proposed. At the same time, a passenger position information judgment rule is proposed according to the different situations of whether there are new passengers or missing passengers, so as to optimize the problem of wrong detection and missing detection in the process of head target detection and tracking. (5) Finally, experiments are carried out in actual bus scenes and simulation scenes. The experiment proves that the statistical algorithm for the detection of passengers getting on and off the bus proposed in this paper has good detection, tracking and statistics effects in bus scenes and simulation scenes.

     

Towards proximity-based passenger sensing on public transport buses

While substantial research on intelligent transportation systems has focused on the development of novel wireless communication technologies and protocols, relatively little work has sought to fully exploit proximity-based wireless technologies that passengers actually carry with them today. This paper presents the real-world deployment of a system that exploits public transit bus passengers’ Bluetooth-capable devices to capture and reconstruct micro- and macro-passenger behavior. We present supporting evidence that approximately 12 % of passengers already carry Bluetooth-enabled devices and that the data collected on these passengers captures with almost 80 % accuracy the daily fluctuation of actual passengers flows. The paper makes three contributions in terms of understanding passenger behavior: We verify that the length of passenger trips is exponentially bounded, the frequency of passenger trips follows a power law distribution, and the microstructure of the network of passenger movements is polycentric.     

基于双指标带权线性规划的公交车调度模型研究

公交车辆调度系统的优化可以提高公交车辆的运营效率,缓解城市交通压力,改善交通环境.针对公交车辆调度的现状,首先引入了公交车载客率和乘客不满率两个指标,并为这两个指标建立了带权优化模型;然后求得每个时间段最佳公交车发车数量,获得最优解;最后通过带入最优解,求得封闭线路（有来回）的最少备车数.通过代入数据验证,所得解在允许误差范围内符合实际结果,因此模型准确可靠,且基于本模型算法实现的程序能够应用于公交车调度系统.     

单交叉口公交优先双系统模糊控制策略研究

公交系统能够显著地提高城市客运量,有效缓解日益增长的交通需求压力.交叉口公交优先是公交优先发展的一个重要措施,传统的交叉口控制方案将公交车辆与其他类型车辆同等对待,对于载客量较大的公交车辆是不公平的.以人均延误最小为目标,提出了一种单交叉口公交优先的双系统模糊控制模型,其相位模糊控制系统负责对相位方案进行优化,延时抉择模糊控制系统优化各相位的绿灯时间.仿真结果表明,相对于定时控制的公交优先机制,模型在正常交通流的情况下能够有效的减少人均延误.     

The seated bus passenger--a review

The paper describes the inter-relationship of anthropometry, rig studies and dynamic testing of aspects related to problems of the seated bus passenger. It seeks to draw together sub-sections of a very large study sponsored by the government through the Transport and Road Research Laboratory and undertaken by the Human Factors Group of Leyland Truck and Bus. It is relevant to all those designing passenger carrying transport systems.     

智能交通动态调度优化模型与评价方法

为了降低大城市市民出行成本,缓解公交企业运力压力,提出一种智能交通出行OD(Origin Destination,出行地和目的地)的公交调度优化算法,以公交出行OD客流预测和计划排班发车时间间隔为出发点,运用公交出行OD客流推导理论,构建智能交通出行OD的公交调度优化模型。通过获取个人OD数据,利用单条线路公交OD方法,实现全市公交OD矩阵推算。根据全市公交出行OD推算结果,求解公交调度模型,解决智能交通调度多目标规划和公交线网优化问题。通过仿真模拟试验,分析智能公交排班计划评价指标,计算车辆营运效率占比:自动排班仿真数据为79%,实际运营数据为73%;统计车辆高峰时段与全天营运车次占比:自动排班仿真数据为36.75%,实际运营数据为37.37%,满足智能公交计划排班评价指标的要求,实例证明模型和算法具有实用性和可靠性。     

Design of real-time fuzzy bus holding system for the mass rapid transit transfer system

In this research, we aim to design real-time fuzzy bus holding system (FBHS) for the mass rapid transit (MRT) transfer system with real-time information for a terminal station with in a metropolitan area. We employ fuzzy logic to develop a model for the MRT-bus system to achieve the following goals pertaining to bus holding strategies used: to reduce the bus waiting time, to reduce the passenger waiting time, and to reduce passenger traveling time. In order to enhance the performance of the MRT-bus transfer system, we develop several fuzzy rules in the transfer models that are different functions of the travel time taken by buses during different time periods, such as rush hours and off-peak hours. Real-time traffic information acquired by the intelligent transportation systems through global positioning systems is used as input data for the FBHS. A performance index function is derived and served as the performance measure to compare our system with real data. The experimental results show that the FBHS significantly reduces the overall passenger waiting time and improves the performance of the MRT-bus transfer system.     

Assigning buses to schedules in a metropolitan area

The problem of scheduling a fleet of buses to a given set of trips is encountered by large bus companies performing thousands of trips per day. The time-tables for those trips are planned separately and reflect the passengers demand for transportation. These time-tables are inputs for the bus scheduling procedures. The scheduling problem is difficult due to its size and due to many operational constraints which are imposed. A mathematical formulation of the problem is presented and an efficient algorithm is developed. This paper presents results and computational experience that were obtained from implementing the model in a large bus company.     

GCPSO优化混合核SVM的地铁车站客流预测

地铁中站点客流量为地铁运营调度部门提供实时调度管理依据。将径向基核函数与多项式核函数线性组合,构建了混合核支持向量回归机（SVM）预测模型。采用基于黄金分割的混沌粒子群（GCPSO）对混合核SVM的参数进行寻优,得到最佳的参数组合。利用该混合核SVM预测广州地铁3号线站点短期客流量。结果表明,GCPSO优化的混合核SVM预测模型对地铁站点的短期客流的预测精度高,预测数据和实测数据拟合良好,相对误差较小,明显优于SVM其他三种预测方法及Elman神经网络预测方法。     

基于小波包与长短时记忆融合的铁路旅客流量预测模型

短期铁路客运需求量的实时精准预测可以为实时调整客运服务结构提供依据.铁路旅客流量数据具有时变性、非线性和随机波动性等特点,传统的预测模型无法精准的预测短期内的客流量.本文提出一种基于小波包分解与长短时记忆融合的深度学习预测模型（WPA-LSTM）,首先用小波包分解将原始客运量时间序列分解重构成多个不同尺度的低频和高频序列,然后分别针对各个子序列进行LSTM模型训练和预测,最后将各子序列的预测值叠加作为WPA-LSTM模型的输出.采用某高铁367天的日旅客流量数据对模型进行实验验证,并与季节性模型和基于经验模态的长短时记忆融合模型进行对比,实验结果表明,WPA-LSTM模型可有效提高铁路旅客流量预测的精度.     

基于WiFi数据的地铁车站客流预警模型

为了降低地铁车站因客流增加或突发事件产生的客流安全风险,提出了基于WiFi探针检测数据的地铁车站客流预警模型。基于WiFi探针客流数据采集原理、数据属性特征和探针网络化布设方案,实现了对WiFi探针原始数据的预处理。同时建立了基于时间序列的地铁车站短时客流预测模型,并与线性回归模型进行了比较,通过计算地铁车站客流承载能力,构建了车站客流预警指标和分级预警模型。最后以上海地铁江苏路站为例进行模型验证,结果表明,基于WiFi探针技术的地铁车站客流检测和预测模型具备可行性和有效性,且预警模型对客流预警应用和研究有一定的参考意义。     

基于注意力机制和分时图卷积的公交客流预测

实际公交路网通常为复杂的非线性时变系统,难以有效构建线路间的时空间依赖关系.因此,文中提出基于注意力机制和分时图卷积的公交客流预测模型,提升公交客流量预测的准确性.首先通过长短期记忆网络提取历史数据中的时间特征,并利用通道注意力模块加权特征.再使用分时图卷积方法分析不同时段下公交线路间的空间依赖性,根据预测时段选择不同...     

基于Agent的快速公交系统仿真研究

针对目前公交系统仿真模型中存在的建模复杂、数据搜集困难等问题,构建了一个基于agent的快速公交系统仿真模型。将乘客、公交车、信号灯抽象为不同的agent,并引入车辆调度agent和站台管理agent,通过各agent之间的交互来仿真快速公交系统的运行。为了解决个别站点可能出现的"涌现"现象,模型中给出了一种基于动态调整的车辆调度算法,从而减少了乘客的等待时间。实验和分析表明,该模型建模简单,易于理解,不仅可以真实地模拟快速公交系统运行现象,而且对如何充分合理利用公交车资源有一定的借鉴作用。