Search

Bus arrival time prediction not only provides convenience for passengers, but also helps to improve the efficiency of intelligent transportation system. Unfortunately, the low precision of bus-mounted GPS system, lack of real-time traffic information and poor performance of prediction model lead to low estimation accuracy - greatly influence bus service performance. Hence, in this paper, a GPS calibration method is put forward, while projection rules of specific road shapes are discussed. Moreover, two traffic factors, travel factor and dwelling factor, are defined to express real-time traffic state. Then, considering both historic data and real-time traffic condition, a hybrid dynamic BAT prediction factor, which achieves accuracy enhancement by taking into account traffic flow evaluation results and GPS position calibration, is defined. A LSTM training model is construct to realize BAT prediction. Experiment results demonstrate that our technique can provide a higher level of accuracy compared to methods based on traditional time-of-arrival techniques, especially in the accuracy of multi-stops BAT prediction.

With the development of the vehicular network, BusNet based service is of great interest to both bus companies and public users. But in this mode, due to the dynamic characteristics of the vehicle, how to effectively communicate has become a problem. In addition, considering the problem of jumping out of the local optimum, a new route optimization algorithm CSPSO (chaotic serial particle swarm optimization), is proposed. The comprehensive simulation results demonstrate that the proposed method can not only adapt to the dynamic changes of network topology, but also greatly reduce the possibility of falling into local optimum, and improve the communication performance significantly.

With the constant augmentation of V2X test requirements, vehicle test organizations urgently need to establish a series certification criterion. As a key factor affecting communication performance, channel features should be considered in the test procedure designed. In this paper, a 3D model is proposed to express the channel feature of the urban area, while the feature of scatter points is discussed. Field measurement data is employed to verify the effectiveness of the proposed model, which provides the theoretical basis for in-chamber V2V test scenarios setting. Experiment results show that the channel fading feature generating by the proposed model coincides with field measurement results.

The accuracy of travel time prediction is not only decided by the state of the current journey but also affected by that of the transfer journey. This paper focuses on the transit transfer problem of urban public transport and aims to improve the performance of multi-route bus travel time prediction. In this paper, two kinds of infect factors, which are macro infect factors and local infect factors, are defined. Then, a pre-processing approach is proposed to construct a travel chain, which is used to compensate the shortage of raw data set. Multi-route bus travel time is divided into four parts, which are travel time of the current driving segment (CDS), bus stop dwelling time module, stop-stop travel time, and transfer point waiting time. A parrel processing architecture, which includes four learning blocks, is designed to fulfill the prediction process of the above four time parts. The classic LSTM model is used to predict the CDS travel time and transfer point waiting time. An improved DA-RNN model, the MDARNN model, is proposed to predict the bus stop dwelling time module, stop-stop travel time. Moreover, a real-time traffic flow model is used to calibrate the prediction time of all four sub-models. Experiment results prove the validity of the proposed methods.

As an extended definition of Mobile Edge Computing, Multi-access Edge Computing provides service, such as computing and storage, not only to cellular network users, but also to other access networks users, such as connected vehicles. RSU (Roadside Unit), which serves as access point for connected vehicles, could provide MEC based services to road vehicles. However, the high mobility of vehicle will result in the frequent changes of network topology. Therefore, the service migration problem of mobile communication becomes a challenge. In this paper, a MSCN (Mobile Secondary Computing Node) based three-layer network framework is used as basis. Then Markov decision process is employed to express service migration problem, while corresponding optimal policy is given. A typical application, intersection control, is selected to study RSU deployment method and data flow interaction progress under MSCN framework. NS3 platform is used to fulfill the communication and application simulations. Simulation results show that application response latency of MSCN framework with service migration in high-density scenarios is significantly lower than that of MSCN framework without service migration, and prove the validity of proposed methods.

Intelligent connected vehicles exchange real-time driving information via wireless communication. To ensure corresponding application performance, field test is needed. Obviously, V2V communication performance is influenced by several factors, such as vehicle density, road factor, weather, etc., and bring great challenge for test scheme design, which is considered as a serious hinder of V2X market process. In this paper, a density-oriented test scheme is proposed. Both communication performance and run-time application performance tests are considered, and both software and hardware architectures are designed. Moreover, the interfaces and a control procedure are given. Then the test system is deployed in test field while tests are done to verify the effectiveness of proposed test scheme design.

The rapid development of intelligent vehicles brings new challenges to vehicle EMC design, which is benefited from test data-oriented troubleshooting. With the increase in electronic complexity, vehicle on-board system designers should confront with more and more EMC failure possibilities and are in need of effective EMC failure diagnosis approach. However, EMC fault diagnosis is difficult due to the distinguishing features of EMC test dataset, such as small sample, nonlinear, high dimensions, etc. Hence, in this paper, EMC reverse diagnostic model is proposed. Firstly, EMC feature extraction method is designed. Then SVM model is designed to realize EMC faults classification. Corresponding application effect is displayed. Experiment results show that proposed method could match the demand of EMC fault diagnosis for intelligent vehicles.

The vehicle density determines the frequency of information congestion and collision in VANETs, and affects the quality of communication. Cluster management of vehicle nodes can effectively improve communication efficiency of the network. A clustering framework based on changes in vehicle density and an improved k-means clustering algorithm based on vehicle movement characteristics are proposed in this paper. According to the change of vehicle density, nodes are dynamically clustered, in some cases MSCNs(Mobile Secondary Computing Node) are selected and virtual computing areas are divided. The simulation on NS3 shows that the proposed improved k-means-based adaptive clustering algorithm has strong stability and high communication efficiency.

With the rapid development of intelligent connected vehicles and VANET (vehicular ad-hoc network), many groups, both industrial and academic, have recognized that the shortage of scenario oriented vehicle-to-everything (V2X) testing specification seriously hinders the market process of V2X capable vehicles. It is well known that vehicle density and some other environmental factors severely influence V2X communication performance and corresponding application response performance. However, until now, there is no effective V2X communication scenarios-oriented test scheme available. Hence, in this paper, focusing on vehicle-to-vehicle (V2V) communication, a scenario-oriented V2V test scheme is proposed, while V2X communication impact factors are discussed. Then two test case catalogues-highway case and urban case, are defined. A field test system is designed, while the in-door prototype is used to fulfill the system verification test. NS-3 simulation process is used to verify the effectiveness of proposed test system. Experiment results show that test results coincide with NS-3 simulation results.

As one of the ad hoc networks, VANET (Vehicular Ad-hoc Network) also faces the conflict between user numbers and resource limits. Moreover, dynamic topology features and limited frequency resources bring a representative problem, which deadly influence VANET performance. In general, two factors influence the efficiency of resource allocation. The one is system structure, while the other is a resource allocation algorithm. In this paper, a hierarchical structure, which includes fixed control layer and mobile control layer, is designed to realize allocation control, while the graph coloring method is used to allocate frequency points. Simulation results show that the proposed method could improve network performance and allocate resources reasonably.

With the development of the vehicular network, BusNet based service is of great interest to both bus companies and public users. How to provide service and ensure service quality is considered as key points for the promotion of such kinds of applications. In this paper, a system architecture, which is designed based on Multi-access Edge Computing (MEC) architecture and software-defined network (SDN), is proposed. Moreover, considering the problem of the dynamicity of the network, a new routing path optimization algorithm, SPSO (serial particle swarm optimization), is proposed, while a dynamic weight matrix is used to improve routing performance. The comprehensive simulation results demonstrate that the proposed method can well adapt to the dynamic change of network topology, and improve communication performance significantly.

Protocol conformance test plays a necessary and important role in guaranteeing that Long Term Evolution-Vehicle to Everything (LTE-V2X) devices to meet the standards and achieve interoperability. Based on in-depth analyzing 3rd Generation Partnership Project (3GPP) release 14 and China LTE-V2X standards, in this paper, a LTE-V2X Conformance Testing Scheme is designed, while corresponding test process and message sets are defined. Test suite are designed according to message layer and network layer requirements. Finally, a test tool, VeTest, is proposed to realize conformance test. The work is significance for promoting the LTE-V2X standardization and interoperability.

The Digital Twin (DT) is one of the main concepts associated to the Industry 4.0 wave. This term is more and more used in industry and research initiatives. DT provides virtual representations of systems along their lifecycle, and should be used in autonomous driving test. In this paper, we have come out with using digital twin to test autonomous driving in a finite environment: based on the virtual simulation test environment of automatic driving, the test of real automatic driving vehicles for the virtual complex road scene can be realized by using the digital twin mapping.

Fatigued driving detection, which employs pattern recognition to discover the state of a driver’s fatigue, is considered a key technique to improve road safety. However, the widely used frontal face recognition systems have problems, such as low recognition accuracy, poor real-time ability, and highly complex algorithms. In this paper, a new color space modeling, which uses multi-threshold decision criteria, is used to enhance facial skin extraction performance, and a three-step strategy is designed to eliminate noise and other adverse effects. Experiments show that the proposed algorithm can extract side face contour lines effectively and provide a scientific basis for real-time tracking of fatigue.

This work addresses the task of road hazard state evaluation in traffic scenarios with MEC(multiple access edge computing) available information. Here we concentrate on inter-vehicle energy relationship, and devote to propose a prediction method, which could predict both regional overall hazard state and hazard distribution characteristics. A classical learning network, BP neutral network, is employed here for corresponding prediction process, while Ising model is used to explain road hazard state. The network training progress is discussed in detail. A validation data set is used to verify the effectiveness of proposed approach. Simulation results show that proposed method is able to make accuracy prediction of road hazard state. Resulting hazard values could be utilized to help driver avoid potential dangers and generate valid cruising trajectory.

With the concept of MEC (Multi-access Edge Computing) being put forward, RSU (Roadside Unit) is considered as a valid application provider, which not only executes transmission resource allocation and data processing related computing but also provides real-time applications to road vehicles. However, when fixed roadside nodes communicate with mobile vehicles, the high service migration rate could influence real-time feature of corresponding service. Moreover, vehicle density also affects service performance. Hence, in this paper, a new concept, MSCN (Mobile Secondary Computing Node), is defined, while a MSCN oriented infrastructure and MSCN selection mechanism are proposed. Then corresponding vehicle message dissemination mechanism is designed. A network simulator (NS-3.28) is employed to investigate the performance of the proposed architecture. The simulation results show that the proposed architecture significantly improves both communication performance and computing efficiency.

As the core technology of vehicle navigation system, path planning algorithm, which makes a great impact on the performance of navigation, has attracted substantial attention. However, the lack of predictive ability to traffic impedance leads to estimation error of road traffic. In addition, the geometry based link division method results in low computational efficiency. In this paper, a traffic impedance function, which considers historical accident factor, historical traffic factor, and real-time traffic factor, is proposed. Moreover, an accident hotspot oriented link division method is designed to reduce running time. Based on proposed impedance function, an improved A* algorithm is presented. The experimental results show that the proposed algorithm can improve path-searching efficiency, and show the ability to provide drivers with paths that are aware of real traffic condition and thus likely shorter travel time.

Fatigue driving is one of the most important causes of traffic accidents. Real-time fatigue driving detection and early warning is very important to reduce the number of traffic accidents, injuries, and deaths. Although traditional ECG (Electrocardiography) based methods can effectively identify fatigue state, they need a relatively long time period (in general 5 min) signal and can not be used to monitor fatigue state in real-time. In this paper, a short-time period ECG signals oriented method is proposed to improve detection real-time character. A pre-processing scheme is present to enhance the identifiably and frequency resolution of ECG signal. Meanwhile, a support vector machine (SVM) based fatigue detection model is given. Test results demonstrate that proposed method can effectively identify fatigue with only 5s interval ECG signal.

To improve safety on the urban roads, next-generation vehicles will be equipped with short-range communication technologies. However, the Basic Safety Messages (BSMs) is always transmitted by a contention based broadcasting mode, which lead to a high potential collision probability. In view of RSU, cluster based point coordination function is considered as an alternative. To improve communication performance and save the cost of RSU installation, in this paper, a public bus oriented contention-free mode is proposed. Mobile similarity is defined to construct road vehicle cluster. Bus node is used as a point coordinator to manage intra-cluster time slot allocation. NS-3 simulator is employed to investigate the performance of the proposed scheme. Simulation results show that the proposed scheme has strong stability and high communication efficiency for BSMs transmission.

On-road risk assessment is one of the important topics for intelligent vehicles research. Efficiency of risk assessment is affected by lack of on-road vehicles information, which should be solved by The Vehicular Ad-Hoc Network (VANET). In this paper, a regional vehicles hazard level estimation method, which employs Ising model to explain the inter-vehicles relationship, is proposed, an inter-vehicles relationship model is constructed, and corresponding parameters mapping relationship is studied. Then Ising model’s energy formula is used to illustrate regional hazard level. Moreover, based on the inter-vehicles relationship, we present an approach to build a regional threat distribution map, which indicates the passing threat of a certain ego-car. A series of experiments are done to examine the efficiency of the proposed method. Experiment results show that the proposed method can produce a reasonable danger evaluation for an ego-car.

With rapid development of intelligent connected vehicles and VANET (vehicular ad-hoc network), electromagnetic environment that vehicles are facing becomes more complex than ever. The popular multi-function on-board radio terminals include various wireless blocks, such as mobile phone, FM radio, Wi-Fi hotspot, GPS receiver and Bluetooth transceiver, etc. All these blocks are working in a circumstance full of radio energy. Both academic circles and professionals concern if the upcoming intelligent connected vehicle and the radio terminals on-board could withstand the increasingly complex electromagnetic environment, and keep a good performance under high power radiation. Unfortunately, until today, there is no commonly agreed specification for such kind of test. In this paper, the connected vehicles, together with the on-board radio terminal, are discussed to find out a solution for their EMC test, while immunity pre-test platform is designed and corresponding test schemes are presented.

Functional test is critical to the deployment of intelligent connected vehicle (ICV). Both industry and academia devote to create a testing framework, which could provide a reliable, quick, safe, low cost and reproducible method and accelerate the development of ICV. However, currently mainstream testing method, such as virtual test and on-road field test are sometimes difficult to satisfy the needs. In this paper, a semi-virtual test method, which employ semi anechoic chamber to construct operating environment of ICV, is proposed. Corresponding tests are done in semi-chamber of China Automotive Engineering Research Institute Co., Ltd (CAERI) to verify the effectiveness of proposed method. Test results show that proposed method is helpful for ICV function evaluation.

Building effective road hotspot analysis criterion can be very useful for improving road safety performance. The concept of composite performance index (CSPI), which is used to illustrate the risky level of the hotspot area, has become a popular practice in the field of road safety. However, CSPI focuses on hotspot area, which may cover a relatively large area, resulting in the failure of providing on-road driver warning message relating to hotspot inner characteristics. This study is to contribute to the ongoing research effort on hotspots evaluation. More specifically, based on Principal Component Analysis (PCA), a method for the hotspot cause factors analysis is proposed. Social factor and road factor are defined to express the internal factors, which lead to hotspot generation. Experiment results show that, the proposed two factors could reasonably explain the hotspot cause and could be considered as supplementary factors for hotspot risky level evaluation as well. Furthermore, this new method can be viewed as an intelligent decision support basis for on-road safety message generation.

Driving behavior optimization not only lowers the occurrence probability of the traffic accident and pollutant emissions, but also improves the energy efficiency level. Reasonable driving behavior evaluation and corresponding suggestion offer is the basis to optimize drivers driving behavior. Current studies indicate that corresponding data processing method deadly influence accuracy and rationality of driving behavior estimation results. However, due to the complexity of road environment, driving behavior estimation always faces the common difficulties of model establishment. In this paper, a new concept, critical zone, is defined to distinguish special driving areas. A typical critical zone, bus stop, is selected as modeling object area, while corresponding driving process — bus enters and leaves bus stop process — is selected to construct driving behavior model. Then, a good driving behavior parameters discovery method, which aims to provide real-time operation recommendations for bus stop accessing procedure, optimize driving technology, reduce fuel consumption and improve safety and comfort, is proposed. Bus data set is used to test effectiveness of proposed method. Test results demonstrate that the developed model and parameter discovery method are effective.

Road hotspots detection method is a key issue in the field of intelligent transportation research. Compared with normal hotspots caused by high traffic flow, abnormal hotspots, which are results of road accidents, perform an occurrence time random behavior and difficult to predict. In this paper, a region real-time congestion factor is constructed to realize road abnormal hotspots discovery. Based on taxi's GPS data of Hangzhou City, China, we analyze the relationship between proposed congestion factor and the real-time traffic data. Two accidental scenarios are built to verify the validity of the proposed method. The experiment results show that the proposed method performs well in real-time abnormal hotspot detection and analysis output could be useful in path planning and traffic management.

On-road large vehicles are always considered as potential danger, which could generate serious damage and strongly threaten road safety. Hence, large vehicle related accident forecasting becomes an important research topic in intelligence transportation area. In this paper, a large vehicle first clustering method (LVFC) is proposed to estimate the risk level of vehicle group. Composite performance index (CSPI), which is used to illustrate the risk level of hotspots area, has become a popular practice in the field of road safety. CSPI value is employed to illustrate environment condition of object road section. Combining CSPI with vehicle group's risk level, a comprehensive risk parameter is presented to represent real-time transportation condition, which illustrates the risk level of a road section with large vehicle group passing by. A vehicle following model is designed to simulate the generation of large vehicle first clusters and it's changing procedure, which provides justification for the proposed algorithm.

V2V transmission of Safety Warning Message (SWM) can provide warning before emergency occurs to avoid accident, and remind surrounding vehicles to avoid potential danger. There are two main problems that will affect the transmission performance of SWM, namely the high local flow and low efficiency caused by high probability of sub-health vehicles (SHV) and traditional single channel and flooding transmission mechanism. Therefore a novel channel allocation algorithm based on communication demand matrix has been proposed in this paper. A new parameter, communication demand relationship based on health evaluation results is defined and communication demand matrix (CDM) is constructed to measure the transmission demand between corresponding vehicles. Then intra-cluster channel allocation algorithm based on the CDM is studied to effectively allocate the channel resource and improve SWM dissemination performance. The simulation and experimental results show that the proposed mechanism has much higher ratio of fulfilled communication demand in the same time slots than flooding based on communication demand relationship (FD) methods in low, medium, and high vehicle density scenario. Beyond that, the proposed mechanism has better performance in receiving messages than FD and flooding.

During the last decade, the concept of cluster, has become a popular practice in the field of road safety, mainly for the identification of worst performing areas or time slots also known as hotspots. However, current clustering methods used to identify road accident hotspots suffer from various deficiencies at both theoretical and operational level, these include parameter sensitivity, identify difficultly on arbitrary shape, and cluster number's rationality. The objective of this study is to contribute to the ongoing research effort on hotspots identification. Employing the concept of natural neighbor, a new algorithm, named distance threshold based on natural nearest neighbor (DTH3N), is proposed in this paper, striving to minimize the aforementioned deficiencies of the current approaches. Experiment results show that, comparing with existing methods, proposed algorithm presents a better performance on cluster division. Furthermore, this new method can be viewed as an intelligent decision support basis for road safety performance evaluation, in order to prioritize interventions for road safety improvement.

Emergency warning message (EWM) transmission insurance is one of the most interesting topics for Vehicular Ad- Hoc Network (VANET) application. Clear channel assessment (CCA) threshold is deemed to be a key factor influencing EWM dissemination performance. Considering vehicle abnor- mal event hazard level and EWM's important level, a new parameter, EWM priority rank, is defined. Based on EWM priority, a new CCA threshold self-adjusting method is pro- posed in this paper. Moreover, according to the proposed CCA threshold selection method, an EWM dissemination algorithm is designed. A series of experiments on the sensor network testbed are done to evaluate the impact of proposed method on EWM dissemination. The experimental results show that an appropriate CCA threshold is benefit to improving global dissemination successful rate and shortening packet delivery delay. I. INTRODUCTION

Emergency warning message (EWM) transmission insurance is one of the most interesting topics for Vehicular Cyber-physical System (V-CPS) application. A relatively low transmission requirement should improve EWM's real-time delivery, and however, decrease reliability of packet delivery by its corresponding burst converge-cast, especially under the multi-hop condition. In this paper, a clear channel assessment (CCA) threshold selection method is proposed to ensure both real-time and reliability for EWM transmission. A series of experiments under several scenarios on the sensor network testbed evaluate its effectiveness. The experimental results show that the threshold adjusting method has a positive effect on the delivery rate. With an appropriately diminishing clear channel assessment threshold related to the packet hops, the global dissemination successful rate can be up to 73.5%, and more than 90% of the 1-hop nodes can receive the correct packet. These findings provide a practicable method to improve the dissemination performance.

The high peak-to-average power ratio (PAR) in Orthogonal Frequency Division Multiplexing (OFDM) modulation systems can significantly reduce power efficiency and performance. This paper examines the problem of reducing the peak-to-average power ratio (PAPR) occurring in OFDM systems based on IEEE 802.11a. A low complexity PAPR reduction algorithm is proposed. A revised ACE-POCS method is put forward and the simulation results for its performance are given. Proposed algorithm used revised ACE-POCS as the preferred method to reduce PAPR while clipping is used as last resort. System simulation based on OFDM shows that proposed algorithm can reduce system PAPR efficiently with low calculation complexity at the cost of Bit-Error-Ratio (BER) performance degradation slightly.

This paper examines the problem of reducing the peak-to-average power ratio (PAPR) occurring in non-contiguous OFDM (NC-OFDM) systems proposed for cognitive radio. The PAPR analysis for NC-OFDM is unlike that of contiguous OFDM and so mitigation schemes must be modified. We propose an algorithm that combines phase adjustment, interleaving and power back-off in a way that is tailored for NC-OFDM. The proposed algorithm exploits the agility of cognitive radio technology to rapidly choose and employ the appropriate PAPR reduction approach from a set of possibilities to achieve a significant decrease PAPR to a setting threshold. The simulation results show that the proposed algorithm achieves a large decrease in PAPR, and calculation complexity is low.