A Combination Prediction Model for Short Term Travel Demand of Urban Taxi

This study proposes a prediction model considering external weather and holiday factors to address the issue of accurately predicting urban taxi travel demand caused by complex data and numerous influencing factors.The model integrates the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise(CEEMDAN)and Convolutional Long Short Term Memory Neural Network(ConvLSTM)to predict short-term taxi travel demand.The CEEMDAN decomposition method effectively decomposes time series data into a set of modal components,capturing sequence characteristics at different time scales and frequencies.Based on the sample entropy value of components,secondary processing of more complex sequence components after decomposition is employed to reduce the cumulative prediction error of component sequences and improve prediction efficiency.On this basis,considering the correlation between the spatiotemporal trends of short-term taxi traffic,a ConvLSTM neural network model with Long Short Term Memory(LSTM)time series processing ability and Convolutional Neural Networks(CNN)spatial feature processing ability is constructed to predict the travel demand for urban taxis.The combined prediction model is tested on a taxi travel demand dataset in a certain area of Beijing.The results show that the CEEMDAN-ConvLSTM prediction model outperforms the LSTM,Autoregressive Integrated Moving Average model(ARIMA),CNN,and ConvLSTM benchmark models in terms of Symmetric Mean Absolute Percentage Error(SMAPE),Root Mean Square Error(RMSE),Mean Absolute Error(MAE),and R2 metrics.Notably,the SMAPE metric exhibits a remarkable decline of 21.03%with the utilization of our proposed model.These results confirm that our study provides a highly accurate and valid model for taxi travel demand forecasting.

Impact of countdown signals on traffic safety and efficiency:a review and proposal

Countdown signals for motorized vehicles,which are intended to ensure safety on the road and regulate motor vehicle speed limits at road intersections,are still considered a relatively novel concept.These signals have been adopted by only a few countries,and the number of cities that use them is limited.This review aims to summarize the effects of countdown signals on traffic safety and efficiency and to determine the consistency and differences of existing research propositions on the matter.Based on the review,considerable research presents evidently different conclusions in the areas of driver red-light running and traffic safety.Particularly,some studies propose that countdown signals reinforce traffic safety,whereas others consider that such signals adversely affect traffic safety.Meanwhile,related literature provides varying conclusions on the aspect of traffic efficiency for vehicle headway.At present,the number of studies conducted regarding the driving behaviors of motorists toward countdown-signalized intersections is insufficient.Accordingly,such inadequate diversity in research causes difficulty in completely assessing the benefits and disadvantages of countdown signals.In this paper,an important future research direction on microcosmic driving psychological and physiological data combined with macro-driving behavior is proposed.

A synthetic differencein-differences model for the influence of CR Express on Chongqing's economy

Purpose-The China-Europe Railway Express(CR Express)in Chongqing has operated regularly and undergone large-scale development.Its impact on Chongqing's economic growth has become increasingly evident,necessitating further research in this field.Design/methodology/approach-This study employs the opening of CR Express as a quasi-natural experiment,designating Chongqing,which inaugurated the CR Express in 2011,as the treatment group.13 provinces and cities that had not yet opened the CR Express until 2017 were selected as the control group.Utilizing panel data from 14 provinces across China spanning from 2006 to 2017,the synthetic control method(SCM)is employed to synthetically construct Chongqing.To quantify the difference in economic development levels between Chongqing with the operation of the CR express and Chongqing without its operation.Key metrics such as gross domestic product(GDP),per capita GDP,total retail sales of consumer goods,import and export value and the proportions of the secondary and tertiary industries are employed to measure urban economic development capabilities.Chongqing is designated as the experimental group,and a double-difference model is constructed to regress the operation of the CR Express against economic development capabilities.Robustness tests are conducted to validate the analytical results.Findings-The results indicate that,compared to provinces without the operation of the CR Express,the initiation of the CR Express in Chongqing significantly enhances the economic development level of the city.The opening of the CR Express exhibits a pronounced positive impact on Chongqing's economic development,and these findings remain robust and effective even after parallel trend tests and placebo tests.Originalitylvalue-The study represents an expansion of the theoretical framework.In contrast to previous studies that relied on a single indicator such as GDP,this study selects six indicators from the dimensions of economy,trade and industry to measure regional economic development capabilities.Furthermore,employing the grey relational analysis method,the study screens these indicators,thereby providing a theoretical basis for the selection of indicators for measuring regional economic development capabilities.

Car-following strategy of intelligent connected vehicle using extended disturbance observer adjusted by reinforcement learning

Disturbance observer-based control method has achieved good results in the carfollowing scenario of intelligent and connected vehicle(ICV).However,the gain of conventional extended disturbance observer(EDO)-based control method is usually set manually rather than adjusted adaptively according to real time traffic conditions,thus declining the car-following performance.To solve this problem,a car-following strategy of ICV using EDO adjusted by reinforcement learning is proposed.Different from the conventional method,the gain of proposed strategy can be adjusted by reinforcement learning to improve its estimation accuracy.Since the“equivalent disturbance”can be compensated by EDO to a great extent,the disturbance rejection ability of the carfollowing method will be improved significantly.Both Lyapunov approach and numerical simulations are carried out to verify the effectiveness of the proposed method.

Reflection on methodology of the correlation between electromagnetic interference and safety in high-speed railway

Purpose – In the continuous development of high-speed railways, ensuring the safety of the operation controlsystem is crucial. Electromagnetic interference (EMI) faults in signaling equipment may cause transportationinterruptions, delays and even threaten the safety of train operations. Exploring the impact of disturbances onsignaling equipment and establishing evaluation methods for the correlation between EMI and safety isurgently needed.Design/methodology/approach – This paper elaborates on the necessity and significance of studying theimpact of EMI as an unavoidable and widespread risk factor in the external environment of high-speed railwayoperations and continuous development. The current status of research methods and achievements from theperspectives of standard systems, reliability analysis and safety assessment are examined layer by layer.Additionally, it provides prospects for innovative ideas for exploring the quantitative correlation between EMIand signaling safety.Findings – Despite certain innovative achievements in both domestic and international standard systems andrelated research for ensuring and evaluating railway signaling safety, there’s a lack of quantitative and strategic research on the degradation of safety performance in signaling equipment due to EMI. A quantitativecorrelation between EMI and safety has yet to be established. On this basis, this paper proposes considerationsfor research methods pertaining to the correlation between EMI and safety.Originality/value – This paper overviews a series of methods and outcomes derived from domestic andinternational studies regarding railway signaling safety, encompassing standard systems, reliability analysisand safety assessment. Recognizing the necessity for quantitatively describing and predicting the impact ofEMI on high-speed railway signaling safety, an innovative approach using risk assessment techniques as abridge to establish the correlation between EMI and signaling safety is proposed.

Probability Distribution of Ratio of China Aviation Network Edge Vertices Degree and Its Evolutionary Trace Based on Complex Network

In order to reveal the complex network characteristics and evolution principle of China aviation network, the probability distribution and evolution trace of ratio of China aviation network edge vertices degree were studied based on the statistics data of China civil aviation network in 1988, 1994, 2001, 2008 and 2015. According to the theory and method of complex network, the network system was constructed with the city where the airport was located as the network node and the route between cities as the edge of the network. Based on the statistical data, the ratio of edge vertices degree in China aviation network in 1988, 1994, 2001, 2008 and 2015 were calculated. Using the probability statistical analysis method and regression analysis approach, it was found that the ratio of edge vertices degree had linear probability distribution and the two parameters of the probability distribution had linear evolution trace.

Probability Distribution of Arithmetic Average of China Aviation Network Edge Vertices Nearest Neighbor Average Degree Value and Its Evolutionary Trace Based on Complex Network

In order to reveal the complex network characteristics and evolution principle of China aviation network,the probability distribution and evolution trace of arithmetic average of edge vertices nearest neighbor average degree values of China aviation network were studied based on the statistics data of China civil aviation network in 1988,1994,2001,2008 and 2015.According to the theory and method of complex network,the network system was constructed with the city where the airport was located as the network node and the route between cities as the edge of the network.Based on the statistical data,the arithmetic averages of edge vertices nearest neighbor average degree values of China aviation network in 1988,1994,2001,2008 and 2015 were calculated.Using the probability statistical analysis method,it was found that the arithmetic average of edge vertices nearest neighbor average degree values had the probability distribution of normal function and the position parameters and scale parameters of the probability distribution had linear evolution trace.

Evolution of Traffic Flow with Scale-Free Topology

We investigate the emergence of scale-free behaviour in a traffic system by using the NaSch model to simulate the evolution of traffic flow. A kind of evolution networks has been proposed, which is based on the evolution of the traffic flow. The network growth does not take into account preferential attachment, and the attachment of new node is independent of degree. The simulation results demonstrate that the output distribution of links is well described by a scale-free distribution.

The effect of ACC vehicles to mixed traffic flow consisting of manual and ACC vehicles

This paper studies the effect of adaptive cruise control （ACC） system on traffic flow by using simulations. The multiple headway and velocity difference （MHVD） model is used to depict the motion of ACC vehicles, and the simulation results are compared with the optimal velocity （OV） model which is used to depict the motion of manual vehicles. Compared the cases between the manual and the ACC vehicle flow, the fundamental diagram can be classified into four regions： I, II, III, IV. In low and high density the flux of the two models is the same; in region II the free flow region of the MHVD model is enlarged, and the flux of the MHVD model is larger than that of the OV model; in region III serious jams occur in the OV model while the ACC system suppresses the jams in the MHVD model and the traffic flow is in order, but the flux of the OV model is larger than that of the MHVD model. Similar phenomena also appeared in mixed traffic flow which consists of manual and ACC vehicles. The results indicate that ACC vehicles have significant effect on traffic flow. The improvement induced by ACC vehicles decreases with the increasing proportion of ACC vehicles.

Dynamics of Motorized Vehicle Flow under Mixed Traffic Circumstance

为了学习混合交通的动力学，流动由组成机械化并且非机械化的车辆，一个汽车追随者模型基于免费、小心的碰撞的原则，开车被建议。侧面的磨擦并且重叠开车被介绍描述在机械化车辆和非机械化的车辆之间的相互作用。由数字模拟，流动密度关系，时间空间的动力学，和速度进化详细被调查。结果显示非机械化的车辆在机械化车辆流动上有重要影响并且引起最大的流动在大约 13% 衰退。非机械化的车辆能减少机械化车辆速度和原因速度摆动当机械化车辆密度是低的时。而且，非机械化的车辆在震荡的速度上看重要抑制效果密度是否是中等的，高度，和如此的效果是机械化了车辆密度增加变弱。结果也强调为分开的必要性从非机械化的车辆机械化了车辆。

Road traffic states estimation algorithm based on matching of regional traffic attracters

To effectively solve the traffic data problems such as data invalidation in the process of the acquisition of road traffic states,a road traffic states estimation algorithm based on matching of the regional traffic attracters was proposed in this work.First of all,the road traffic running states were divided into several different modes.The concept of the regional traffic attracters of the target link was put forward for effective matching.Then,the reference sequences of characteristics of traffic running states with the contents of the target link's traffic running states and regional traffic attracters under different modes were established.In addition,the current and historical regional traffic attracters of the target link were matched through certain matching rules,and the historical traffic running states of the target link corresponding to the optimal matching were selected as the initial recovery data,which were processed with Kalman filter to obtain the final recovery data.Finally,some typical expressways in Beijing were adopted for the verification of this road traffic states estimation algorithm.The results prove that this traffic states estimation approach based on matching of the regional traffic attracters is feasible and can achieve a high accuracy.

Behaviours in a dynamical model of traffic assignment with elastic demand

This paper investigates the dynamical behaviour of network traffic flow. Assume that trip rates may be influenced by the level of service on the network and travellers are willing to take a faster route. A discrete dynamical model for the day-to-day adjustment process of route choice is presented. The model is then applied to a simple network for analysing the day-to-day behaviours of network flow. It finds that equilibrium is arrived if network flow consists of travellers not very sensitive to the differences of travel cost. Oscillations and chaos of network traffic flow are also found when travellers are sensitive to the travel cost and travel demand in a simple network.

Phase transition in evolution of traffic flow with scale-free property

This paper investigates the behaviour of traffic flow in traffic systems with a new model based on the NaSch model and cluster approximation of mean-field theory. The proposed model aims at constructing a mapping relationship between the microcosmic behaviour and the macroscopic property of traffic flow. Results demonstrate that scale-free phenomenon of the evolution network becomes obvious when the density value of traffic flow reaches at the critical point of phase transition from free flow to traffic congestion, and jamming is limited in this scale-free structure.

Cellular Automaton Models of Highway Traffic Flow Considering Lane-Control and Speed-Control

As two kinds of management modes of highway traffic control,lane-control,and speed-control produce different effect under different conditions.In this paper,traffic flow cellular automaton models for four-lane highway system with two opposing directions under the above two modes are established considering car and truck mixed running. Through computer numerical simulating,the fundamental diagrams with different parameters are obtained,and after the analysis of density-flux diagrams,the variation discipline of flux with traffic density under different control models is gained.The results indicate that,compared with lane-control,utilization ratio of road can be further improved with speed-control when the truck number increases.The research result is of great significance for reasonable providing theoretical guidance for highway traffic control.

Multi-fractal analysis of highway traffic data

The purpose of the present study is to investigate the presence of multi-fractal behaviours in the traffic time series not only by statistical approaches but also by geometrical approaches. The pointwisc Hǒlder exponent of a function is calculated by developing an algorithm for the numerical evaluation of HSlder exponent of time series. The traffic time series observed on the Beijing Yuquanying highway are analysed. The results from all these methods indicate that the traffic data exhibit the multi-fractal behaviour.

Model and algorithm of optimizing alternate traffic restriction scheme in urban traffic network

An optimization model and its solution algorithm for alternate traffic restriction(ATR) schemes were introduced in terms of both the restriction districts and the proportion of restricted automobiles. A bi-level programming model was proposed to model the ATR scheme optimization problem by aiming at consumer surplus maximization and overload flow minimization at the upper-level model. At the lower-level model, elastic demand, mode choice and multi-class user equilibrium assignment were synthetically optimized. A genetic algorithm involving prolonging codes was constructed, demonstrating high computing efficiency in that it dynamically includes newly-appearing overload links in the codes so as to reduce the subsequent searching range. Moreover,practical processing approaches were suggested, which may improve the operability of the model-based solutions.

Properties of train traffic flow in a moving block system

The development direction of railways is toward the improvement of capacity and service quality, where the service quality includes safety, schedule, high speed, and comfort. In light of the existing cellular automaton models, in this paper, we develop a model to analyze the mixed running processes of trains with maximal speeds of 500 km/h and 350 km/h respectively in the moving block system. In the proposed model, we establish some sound rules to control the running processes of a train, where the rules include the departure rules in the intermediate stations, the overtaking rules, and the conditions of speed limitation for a train stopping at a station or passing through a station. With the consideration of the mixed ratio and the distance between two adjacent stations, the properties of the train traffic flow （including capacity and average speed） are simulated. The numerical results show that the interactions among different trains will affect the capacity, and a proper increase of the spatial distance between two adjacent stations can enhance the capacity and the average speed under the moving block.

Analysis of the influence of occupation rate of public transit vehicles on mixing traffic flow in a two-lane system

Based on the existing classical cellular automaton model of traffic flow, a cellular automaton traffic model with different-maximum-speed vehicles mixed on a single lane is proposed, in which public transit and harbour-shaped bus stops are taken into consideration. Parameters such as length of cellular automaton, operation speed and random slow mechanism are re-demarcated. A harbour-shaped bus stop is set up and the vehicle changing lane regulation is changed. Through computer simulation, the influence of occupation rate of public transit vehicles on mixed traffic flow and traffic capacity is analysed. The results show that a public transport system can ease urban traffic congestion but creates new jams at the same time, and that the influence of occupation rate of public transit vehicles on traffic capacity is considerable. To develop urban traffic, attention should be paid to the occupation rate of public transit vehicles and traffic development in a haphazard way should be strictly avoided.

Screening and reconstruction of real-time traffic data

The quality of real time traffic information is of the great importance, therefore the factors having effect on traffic characteristics are analyzed in general, and the necessities of real time data processing are summarized. The identification and reconstruction of real time traffic data are analyzed using Kalman filter equation and statistical approach. Four methods for ITS (Intelligent transportation system) detector data screening in traffic management systems are discussed in detail. Meanwhile traffic data examinations are discussed with solutions formulated through analysis, and recommendations are made for information collection and data management in future.

Hierarchy property of traffic networks

The flourishing complex network theory has aroused increasing interest in studying the properties of real-world networks. Based on the traffic network of Chang-Zhu Tan urban agglomeration in central China, some basic network topological characteristics were computed with data collected from local traffic maps, which showed that the traffic networks were small-world networks with strong resilience against failure; more importantly, the investigations of as- sortativity coefficient and average nearestlneighbour degree implied the disassortativity of the traffic networks. Since traffic network hierarchy as an important basic property has been neither studied intensively nor proved quantitatively, the authors are inspired to analyse traffic network hierarchy with disassortativity and to finely characterize hierarchy in the traffic networks by using the n-degree-n-clustering coefficient relationship. Through numerical results and analyses an exciting conclusion is drawn that the traffic networks exhibit a significant hierarchy, that is, the traffic networks are proved to be hierarchically organized. The result provides important information and theoretical groundwork for optimal transport planning.