English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

According to the nonlinear and non-Gaussian characteristics of the traffic flow, we propose a SMC based traffic flow congestion event reconstruction framework based on traffic flow signals. The simulation states can get close to the real scene continuously along with the data assimilation model assimilates the real-time traffic signals constantly. The congestion event in real scene can be estimated based on the simulation data. Thus, we can estimate the congestion in different particles and finally reconstruct the congestion event. This framework can evaluate the current roads’ states based on the reconstruction results, and then the range and the start position of the congestion can be determined. Related experimental results are presented and analyzed. Introduction The rapid developments of static and dynamic sensors on real road network make it possible to get real-time traffic signals which can reflect the critical nature of traffic flow. In 2002, Martin Treiber and Dirk Helbing presented an adaptive smoothing algorithm which could get the vehicles’ density, the vehicles’ average speed quickly and accurately based on fixed sensors [1]. In 2007 Herrera and Bayen introduced many methods to acquire the vehicles’ density based on mobile sensors [2]. Obviously, the rational use of real-time traffic signals is the key to improve the accuracy of traffic flow event reconstruction. Event reconstruction has been widely used in various application domains, including digital investigation [3], digital filtering [4], power systems [5] and microscopic particles [6]. Traditionally, regression, inversion, and optimization are widely used although they have limitations for complex event reconstruction systems. Therefore, many researchers seek other approaches to the solutions. The initial method of Markov Chain Monte Carlo stochastic methodology and the improved methods of SMC methods were adopted to the dynamic data driven event reconstruction for atmospheric releases by Kosovic et al. (2007) [7]. In traffic flow systems, a short-term network traffic prediction method was proposed by Zhang and Huang in [8]. They use particle filter method and the ACD model to deal with the complex traffic signals. Bi Chang and Fan in [9] propose a particle filter based approach to estimate freeway traffic state, through the experiment which used the freeway link between the west of Peace Bridge and the west of San Yuan Bridge of the third ring in Beijing, they proved PF have an encouraging estimation performance. SMC based Traffic Flow Event Reconstruction Traffic Signal Collection using sliding window. Normally, the traffic signals at one time cannot represent the traffic flow appropriately due to the traffic data is changeable and has the feature of mobility. Here we introduce the thought of sliding window to cache and update the traffic signals fleetly, and increase the stability of the sensor data as well as keeping its real-time characteristic. The sliding window is formalized in equation (1). WT and Length are the total and current size of the International Industrial Informatics and Computer Engineering Conference (IIICEC 2015) © 2015. The authors Published by Atlantis Press 1771 sliding window respectively, Tail is a pointer that points to the location of a new arrival data, f is the data update rule. QueueW= T (1) Based on the thought of sliding window, we put forward the traffic signals management model in Fig. 1. The “Traffic Sensors” contains N sensors spread in the real road which can monitor M types of traffic signals. We can collect the sensor data and set up M*N sliding windows using “Sliding Window Generator”. “Sliding Window Manager” provides certain real-time data to “Assimilation Model” by dealing with the traffic signals stored in sliding windows.

Traffic Flow Signal based Traffic Event Reconstruction using Sequential Monte Carlo Methods