Real-time Traffic Jam Detection and Congestion Reduction Using Streaming Graph Analytics

With the growth of large cities, it becomes necessary to overcome several challenges related to infrastructure. In this context, urban mobility, including transportation systems, is a key topic. It is known that more efficient traffic management makes cities more efficient as a whole, improving the quality of life of their residents and tourists. A common problem that arises concerns traffic jams, encompassing their detection and management. With proper traffic jam detection, it is possible to implement traffic management methods to prevent long-term occurrences or even notify drivers to avoid specific locations. Some traffic jam detection solutions use sensors spread across cities, while others are based on sensors in drivers' smartphones. These approaches have limitations related mainly to the information reliability or to the cost and complexity of implementation. In this work, we propose an approach using Machine Learning techniques applied to public data of transportation systems to detect urban traffic jams. The proposed approach is evaluated using the publicly available GPS data from the buses of the Rio de Janeiro/Brazil transportation system and traffic jam events posted on Twitter by the Rio de Janeiro City Hall.

On ride-pooling and traffic congestion

In densely populated cities, severe vehicle congestion is an obstacle due to the massive increase of vehicles and bottleneck of roads. Traffic congestion brings severe economic and environmental hazards. Although it is hard to eliminate, it can be mitigated by finding the occurrence of the congestion well in advance to initiate appropriate control measures. Accurately estimating traffic speed, travel time, and other external factors is mandatory for forecasting congestion levels in a dynamic road network. In recent years, sensor-based traffic detection technologies have evolved to achieve accuracy and safety in intelligent transportation systems (ITS). However, some of them need more reliability, have weak usage in different visibility conditions, are hard to set, and have a high cost. Alternatively, modern navigation systems are developed to find the fastest, alternative routes, travel times, and congestion levels for a given source to destination. These systems use Global Positioning Systems (GPS) data to provide the routing information. Due to inaccurate/ inadequate GPS data samples, sometimes these systems may give misleading information. This work presents Long-Range Wide Area Network (LoRaWAN) architecture to overcome the abovementioned limitations. In our proposed case study, we have used the Dragino LoRaWAn Gps sensor (IN865), air quality sensor (MQ135), temperature and humidity sensor (SHT31), and other sensors to extract direct and indirect factors that influence traffic congestion. Haversine formula and hyper-heuristic-based Encoder-Decoder using Gated Recurrent Units with attention mechanism (ED-GRUAT) are used to estimate the segment-based distance, speed, vehicle travel times, and congestion levels. Our case study helps to calculate accurate traffic speed, travel times, and congestion levels.

A prerequisite for any monetary estimation of economic losses arising from traffic congestion is a reliable estimate of the value of travel time. Although the available evidence from abroad reveals significant differences in the values of individual components of time travel, specific valuations of travel time are rather rare in the Czech Republic. The aim of this paper is to expand the data base in the Czech Republic by presenting selected estimates of the travel time components for Czech drivers and passengers. Specifically, we elaborate on the value of travel time and time spent in congestion for medium-long domestic routes (represented by the Prague-Brno route). The results of our valuation study (N = 602) show that the value of travel time spent in congestion is almost twice as high as the value of travel time in free-flow traffic and suggest that the reduction of congestion and of the variation in travel time in general will bring significant economic benefits compared to shortening travel time in free-flow traffic. This evidence confirms the importance of distinguishing between different components of travel time when assessing the benefits of transport infrastructures. Importantly, our estimates of the value of travel time are much lower than those officially endorsed by Czech Ministry of Transport (MoT) for analysing benefits of new transport infrastructure.

The delay in transporting essential goods is primarily attributed to widespread traffic congestion globally. This issue not only results in significant time and fuel wastage but also poses a considerable challenge in efficiently disseminating traffic information and managing road conditions for authorities. Addressing these challenges, vehicular ad hoc networks (VANETs) have emerged as a crucial component of the cognitive intelligent transportation system (C-ITS). To tackle this issue effectively, vehicle-to-vehicle (V2V) communication plays a crucial role in fostering cooperation and optimizing route management within transportation networks. This paper proposes an innovative congestion detection system that integrates the fuzzy k-means (FKM) clustering technique with the fuzzy analytical hierarchy process (FAHP). Utilizing the simulation of urban mobility (SUMO) simulator, a detailed transport network is modeled where vehicle parameters indicative of congestion are collected, integrated using sensor fusion, and analyzed. These parameters are processed using FKM clustering and a mathematical mean algorithm to identify key congestion indicators. Subsequently, FAHP prioritizes these collected parameters, pinpointing congestion hotspots within specific routes. By incorporating cognitive intelligence, the system continuously refines congestion detection and response strategies, enhancing traffic flow efficiency and enabling proactive congestion avoidance. This approach promises a more effective congestion detection methodology with minimal installation costs. Moreover, it can be effortlessly integrated into vehicles to facilitate congestion avoidance strategies, thereby enhancing overall traffic flow efficiency and mitigating the negative impacts of traffic congestion on transportation networks globally.

The traffic congestion frequently occurs in urban transportations. In order to alleviate the traffic congestion, the vehicle information and communication system (VICS) has been developed. However, since each vehicle can obtain global information on traffic congestion using VICS, all vehicles in the congested areas tend to move to non-congested areas. As a result, the non-congested areas become congested areas. To avoid such the oscillation between the congested and non-congested areas, this paper proposes a novel method based on the vehicle ad hoc network (VANET) for alleviating traffic congestion in urban transportations. In the proposed method, since each vehicle independently collects local information on traffic congestion using VANET, traffic can be distributed from congested areas to non-congested areas. Through simulation experiments, this paper shows that the proposed method provides faster velocity and shorter trip time than VICS in the environments that traffic varies temporally and spatially, which occur in urban transportations.

Research on campus traffic congestion detection using BP neural network and Markov model

This article discusses the simulation and evaluation of a traffic congestion detection system which combines inter-vehicular communications, fixed roadside infrastructure and infrastructure-to-infrastructure connectivity and big data. The system discussed in this article permits drivers to identify traffic congestion and change their routes accordingly, thus reducing the total emissions of CO2 and decreasing travel time. This system monitors, processes and stores large amounts of data, which can detect traffic congestion in a precise way by means of a series of algorithms that reduces localized vehicular emission by rerouting vehicles. To simulate and evaluate the proposed system, a big data cluster was developed based on Cassandra, which was used in tandem with the OMNeT++ discreet event network simulator, coupled with the SUMO (Simulation of Urban MObility) traffic simulator and the Veins vehicular network framework. The results validate the efficiency of the traffic detection system and its positive impact in detecting, reporting and rerouting traffic when traffic events occur.

Modern networks generate a massive amount of traffic data streams. Analyzing this data is essential for various purposes, such as network resources management and cyber-security analysis. There is an urgent need for data analytic methods that can perform network data processing in an online manner based on the arrival of new data. Online machine learning (OL) techniques promise to support such type of data analytics. In this paper, we investigate and compare the OL techniques that facilitate data stream analytics in the networking domain. We also investigate the importance of traffic data analytics and highlight the advantages of online learning in this regard, as well as the challenges associated with OL-based network traffic stream analysis, e.g., concept drift and the imbalanced classes. We review the data stream processing tools and frameworks that can be used to process such data online or on-the-fly along with their pros and cons, and their integrability with de facto data processing frameworks. To explore the performance of OL techniques, we conduct an empirical evaluation on the performance of different ensemble- and tree-based algorithms for network traffic classification. Finally, the open issues and the future directions in analyzing traffic data streams are presented. This technical study presents valuable insights and outlook for the network research community when dealing with the requirements and purposes of online data streams analytics and learning in the networking domain.

Recent evidence suggests hospitals fail to meet guideline specified time to percutaneous coronary intervention (PCI) for a proportion of ST elevation myocardial infarction (STEMI) presentations. Implicit in achieving this time is the rapid assembly of crucial catheter laboratory staff. As a proof-of-concept, we set out to create regional maps that graphically show the impact of traffic congestion and distance to destination on staff recall travel times for STEMI, thereby producing a resource that could be used by staff to improve reperfusion time for STEMI. Travel times for staff recalled to one inner and one outer metropolitan hospital at midnight, 6 p.m., and 7 a.m. were estimated using Google Maps Application Programming Interface. Computer modeling predictions were overlaid on metropolitan maps showing color coded staff recall travel times for STEMI, occurring within non-peak and peak hour traffic congestion times. Inner metropolitan hospital staff recall travel times were more affected by traffic congestion compared with outer metropolitan times, and the latter was more affected by distance. The estimated mean travel times to hospital during peak hour were greater than midnight travel times by 13.4 min to the inner and 6.0 min to the outer metropolitan hospital at 6 p.m. (p < 0.001). At 7 a.m., the mean difference was 9.5 min to the inner and 3.6 min to the outer metropolitan hospital (p < 0.001). Only 45% of inner metropolitan staff were predicted to arrive within 30 min at 6 p.m. compared with 100% at midnight (p < 0.001), and 56% of outer metropolitan staff at 6 p.m. (p = 0.021). Our results show that integration of map software with traffic congestion data, distance to destination and travel time can predict optimal residence of staff when on-call for PCI.

Due to random nature of traffic and unpredictability of human behaviors, one of challenging problems in transportation engineering is traffic congestion which has a direct impact on the economy and environment with the increase in traveling time, fuel consumption and emissions. One of approaches to reduce traffic congestions is the advance Route Guidance Systems (RGSs) which can propose alternative optimal routes for vehicles, which are in or will be entering congested roads or areas. Advanced RGSs, usually employ real-time and predicted traffic information of the roads to find the best possible route for vehicles in a way that total traffic congestions will be reduced. In this paper, The ReFOCUS+, a dynamic semi-distributed, multi-layer, and Fog-Cloud based advance route guidance system architecture has been introduced. The ReFOCUS+ architecture, employ Road Side Units (RSUs), to calculate different traffic-related factors such as current and predicted road congestions, area congestions, traveling time, etc. Then, the ReFOCUS+ uses traffic factors to proposes a novel method to detect congested roads in an area and, apply re-routing to vehicles to ease the traffic congestion within each area using a multi-metric fitness function, called Road Weight Measurement (RWM). To evaluate the performance of ReFOCUS+, a new open-source Python-based program has been developed which is able to connect to SUMO traffic simulator and control the simulation. The simulation results demonstrate that ReFOCUS+ outperforms existing solutions and improve traveling time, fuel consumption and gas emissions. <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">11</sup> The developed program and software in this paper available at https://www.github.com/hamednoori/ReFOCUS+

Methods of treatment (case reports)

SNSJam: Road traffic analysis and prediction by fusing data from multiple social networks

Novel Use of Integrated Map Software and Traffic Congestion Data Affecting Staff Travel Time to PCI for STEMI

In this paper, we study how traffic congestion affects bond yields in urban areas of the United States (U.S.). While the adverse effects of congestion — such as increased stress and reduced economic activity — have been well documented, this is the first study that investigates its impact on the municipal bond market. Collecting the annual traffic data from the Urban Mobility Reports that were published by the Texas A&amp;M Transportation Institute, we examine municipal bonds and find that areas with high traffic congestion exhibit significantly higher bond yields. A one standard deviation increase in traffic congestion corresponds to a 12.8 basis-point increase in overall bond yields. Furthermore, we treat the COVID-19 pandemic as a shock that reduced traffic congestion due to public safety precautions. We find that areas experiencing greater reductions in congestion see a greater decrease in bond yields. These findings have implications for infrastructure governance. In particular, our findings imply that the management of infrastructure and implementation of policies which are aimed at reducing traffic congestion may also offer capital market benefits.