Xuting Duan

A Bayesian Compressive Sensing Vehicular Location Method Based on Three-Dimensional Radio Frequency

In vehicular ad hoc networks (VANETs) safety applications, vehicular position is fundamental information to achieve collision avoidance and fleet management. Now, position information is comprehensively provided by global positioning system (GPS). However, in the dense urban, due to multipath effect and signal occlusion, GPS-based positioning method potentially fails to provide accurate position information. For this reason, an assistant approach has been presented in this paper by using three-dimensional radio frequency, such as time of arrival (TOA) and direction of arrival (DOA). With the goal of providing an efficient and reliable estimation of vehicular position in general traffic scenarios, we propose a hybrid TOA/DOA positioning method based on Bayesian compressive sensing (BCS), which benefits from the realization of vehicle-to-roadside wireless interaction with the dedicated short range communication. The effectiveness of the proposed approach is proved through extensive experiments in several scenarios where different signal configurations and the noise conditions are taken into account. Moreover, some comparative experiments are also performed to confirm the strength of our proposed approach.

A V2X communication system and its performance evaluation test bed

IEEE 802.11p is the new standard for vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communication using 5.9GHz frequency band, which is widely employed to enable intelligent transportation systems (ITS) and cooperative vehicle infrastructure systems (CVIS). In this paper, we design and implement a testing platform of 802.11p-based dedicated short rang communications (DSRC), including a V2X communication system and a performance evaluation system. On the platform, the comprehensive performance of the prototype communication system can be tested and analyzed in terms of quality of services (QoS) metrics such as communication range, throughput, packet loss rate, delay and jitter. Extensive actual experiments have been conducted to validate the practical function of our developed platform as well as to demonstrate the efficiency of the 802.11p-based DSRC system.

A DSRC-Based Vehicular Positioning Enhancement Using a Distributed Multiple-Model Kalman Filter

Some inherent shortcomings of the global positioning systems (GPSs), such as limited accuracy and availability, limit the positioning performance of a vehicular location system in urban harsh environments. This motivates the development of cooperative positioning (CP) methods based on emerging vehicle-to-anything communications. In this paper, we present a framework of vehicular positioning enhancement based on dedicated short range communications (DSRC). An interactive multiple model is first used to track the distributed manners of both the vehicle acceleration variations and the switching of the covariances of DSRC physical measurements such as the Doppler frequency shift and the received signal strength indicator, with which a novel CP enhancement method is presented to improve the distributed estimation performance by sharing the motion states and the physical measurements among local vehicles through vehicular DSRC. We have also presented an analysis on the positioning performance, and a closed-formed lower bound, named the modified square position error bound (mSPEB), is derived for bounding the positioning estimation performance of CP systems. Simulation results have been supplemented to compare our proposed method with the stand-alone GPS implementation in terms of the root-mean-square error (RMSE), showing that the obtained positioning enhancement can improve comprehensive positioning performance by the percentage varying between about 35% and about 72% under different traffic intensities and the connected vehicle penetrations. More importantly, the RMSE achieved by our method is shown remarkably closed to the root of the theoretical mSPEB.

A Vehicular Positioning Enhancement with Connected Vehicle Assistance

In this paper, we consider the problem of vehicular positioning enhancement with emerging connected vehicles (CV) technologies. In order to actually describe the scenario, the Interacting Multiple Model (IMM) filter is used for depicting varies of observation models. A CV-enhanced IMM filtering approach is proposed to locate a vehicle by data fusion from both coarse GPS data and the Doppler frequency shifts (DFS) measured from dedicated short-range communications (DSRC) radio signals. Simulation results state the effectiveness of the proposed approach.

A Distributed Position-Based Protocol for Emergency Messages Broadcasting in Vehicular Ad Hoc Networks

Vehicular ad hoc networks (VANETs) can help reduce traffic accidents through broadcasting emergency messages among vehicles in advance. However, it is a great challenge to timely deliver the emergency messages to the right vehicles which are interested in them. Some protocols require to collect nearby real-time information before broadcasting a message, which may result in an increased delivery latency. In this paper, we proposed an improved position-based protocol to disseminate emergency messages among a large scale vehicle networks. Specifically, defined by the proposed protocol, messages are only broadcasted along their regions of interest, and a rebroadcast of a message depends on the information including in the message it has received. The simulation results demonstrate that the proposed protocol can reduce unnecessary rebroadcasts considerably, and the collisions of broadcast can be effectively mitigated.

The Cooperative Vehicle Infrastructure System Based on Machine Vision

The information acquisition is a key procedure of cooperative vehicle-infrastructure system (CVIS). With the advancement of computer image processing technology, more and more researchers use image recognition as the source of information acquisition. On this background, the authors develop a CVIS based on machine vision, including vehicular subsystem, the roadside subsystem and the parking lot subsystem. The system uses improved Canny algorithm to detect road channelization, HOG+SVM method to detect pedestrian and Haar+Adaboost method to detect vehicle. The experiment result shows that the detection accuracy and real-time of system is relatively high. In addition, the test also prove that the system is significant in driving assistance.

Swarm Intelligence Inspired Adaptive Traffic Control for Traffic Networks

The internet of Vehicles (IoV) technologies have boosted diverse applications related to Intelligent Transportation System (ITS) and Traffic Information Systems (TIS), which have significant potential to advance management of complex and large-scale traffic networks. With the goal of adaptive coordination of a traffic network to achieve high network-wide traffic efficiency, this paper develops a bio-inspired adaptive traffic signal control for real-time traffic flow operations. This adaptive control model is proposed based on swarm intelligence, inspired from particle swarm optimization. It treats each signalized traffic intersection as a particle and the whole traffic network as the particle swarm, then optimizes the global traffic efficiency in a distributed and on-line fashion. Our simulation results show that the proposed algorithm can achieve the performance improvement in terms of the queuing length and traffic flow allocation.

An Intrusion Detection System Based on Machine Learning for CAN-Bus

The CAN-Bus is currently the most widely used vehicle bus network technology, but it is designed for needs of vehicle control system, having massive data and lacking of information security mechanisms and means. The Intrusion Detection System (IDS) based on machine learning is an efficient active information security defense method and suitable for massive data processing. We use a machine learning algorithm—Gradient Boosting Decision Tree (GBDT) in IDS for CAN-Bus and propose a new feature based on entropy as the feature construction of GBDT algorithm. In detection performance, the IDS based on GBDT has a high True Positive (TP) rate and a low False Positive (FP) rate.

REFF: REliable and Fast Forwarding in Vehicular Ad-hoc Network.

Vehicular Ad-Hoc Network (VANET) has emerged as an increasingly dominant technology for future connected vehicle and vehicular networks, where the focus of the development of VANET lies in the standardization of message transmission and dissemination via multi-hop broadcasting. However, the current communication protocols concerning VANET face many challenges, including data flooding and collision, transmission delay and other problems. Most of the challenges are closely related to next-hop selection. Therefore, this paper proposes a new routing protocol named REliable and Fast Forwarding (REFF) to optimize the selection of nodes in VANET. In this protocol, node filtering and node evaluation are two main steps. Distance between previous node and candidate node, relative velocity between previous node and candidate nodes, included angle between direction of target node’s velocity and candidate node’s velocity and transmission power of candidate node are adopted as indexes to help select a specific node as the next hop using Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS). By using this technique, the number of candidates as next-hop is largely reduced, avoiding the data flooding and resulting transmission relay. In addition, simulations based on experiments are done to verify the feasibility. The results show that message achieves a faster and more reliable transmission using REFF.

Modeling and Simulation on Cooperative Movement of Vehicle Group Based on the Behavior of Fish

Fatigue driving might affect the traffic safety when the vehicles are on the cruising state in highway. Trying to solve this problem, this paper uses the movement pattern of the fish to the vehicles fleet, and develops a model of vehicle group with realistic restrictions based on the existed fish algorithms, the mobile behavioral model and cluster behavior model, and then demonstrates the feasibility of applying the fish behavior to the cooperative movement of vehicle groups through analyzing the trajectory, velocity and spacing of vehicles.