Light Traffic Conditions Research Articles

Interpretable machine learning for evaluating risk factors of freeway crash severity

Machine learning (ML) models are widely employed for crash severity modelling, yet their interpretability remains underexplored. Interpretation is crucial for comprehending ML results and aiding informed decision-making. This study aims to implement an interpretable ML to visualize the impacts of factors on crash severity using 5 years of freeways data from Iran. Methods including classification and regression trees (CART), K-nearest neighbours (KNNs), random forest (RF), artificial neural network (ANN) and support vector machines (SVM) were applied, with RF demonstrating superior accuracy, recall, F1-score and ROC. The accumulated local effects (ALE) were utilized for interpretation. Findings suggest that light traffic conditions ( volume / capacity < 0.5 ) with critical values around 0.05 or 0.38, and higher proportion of large trucks and buses, particularly at 10% and 4%, are associated with severe crashes. Additionally, speeds exceeding 90 km/h, drivers younger than 30 years, rollover crashes, collisions with fixed objects and barriers, nighttime driving and driver fatigue elevate the likelihood of severe crashes.

Road Survey by using Total Station and Design of Flexible Pavement

Abstract: In the current scenario the growth of a nation is totally depends upon the road infrastructure and connectivity of that nation. So, at the same time it’s equally important to construct sustainable and environment friendly roads in the country. This study compares the applications of novel surveying technologies for road surface mapping by total Stations and design of flexible pavement by using IIT pave. This project is on GIFT college Gate to Khordha - Chandaka Road. This is the road that connect our college and it is around 300 m stretch. In particular, a Leica TCRP 1203 instruments was used for surveying. This study deals with issues of road surveying under light traffic condition, the safety of surveyors, work methodology, optimization of surveying time, traffic volume study during 8.00-9.00am and 3.30-4.30pm. The aspects of data processing, assessment, traffic analysis, flexible pavement design as per IRC:37-2018 are also handled. Possible reasons for detected discrepancies between different approaches are discussed in detail. The methods in question both allow the accurate determination of paving material volumes that should be milled off the upper layer of the road surface and the volume of the filling material required to achieve a smooth road surface. However, this study evaluates the use of conventional surveying methods such as total station surveying in road surface mapping and design of flexible pavement (code IRC: 37) as well as the material evaluation. Now-a-days, handling the waste from different industry is a challenge. So, this study also evaluates the sustainability of waste material to construct the flexible pavement inside the college campus. Software used IIT pave, AutoCAD, Staad Pro

Enhancing energy efficiency of IEEE 802.15.4- based industrial wireless sensor networks

The IEEE 802.15.4 standard protocol has been widely used in many industrial wireless sensor networks (IWSN), due to its low energy, optimal data rate and relative long-distance characteristics. The protocol operation, however, should be optimized to maximize efficiency and minimize interference between wireless sensor network (WSN) nodes. The protocol supports two media access modes: carrier sense multiple access (CSMA) and time division multiple access (TDMA). In this paper, we use the enhancing energy efficiency of wireless sensor networks (EEE-WSN) protocol that alternates between these two modes. The objective is to accommodate for traffic load and to produce better efficiency. EEE-WSN utilizes CSMA in the case of having lightweight traffic, which is normally the case when having normal and non-critical events in the area of interest (AoI). It switches operation in case of heavy traffic load conditions, which often happen when a critical event is detected. Furthermore, a modified selective activation (SA) technique is used to minimize the energy consumption and to reduce the interference between redundant nodes. The protocol has been implemented using Qualnet simulator and its performance has been evaluated for different simulation time, packet rate ratios, and sent packets. The simulation results showed that the EEE-WSN outperformed the IEEE 802.15.4 while operated in either CSMA or TDMA by decreasing the energy consumption by around 1%. The amount of energy saving is exponentially increasing as a function of the simulation time. The EEE-WSN has lower end-to-end delay by 0.4, 0.1 s under light traffic conditions when compared with IEEE 802.15.4- TDMA, and IEEE 802.15.4-CSMA modes, respectively. At heavy traffic conditions, the EEE- WSN has similar end-to-end delay to IEEE 802.15.4- TDMA, and less end-to-end delay values by 0.3 s when compared to IEEE 802.15.4- CSMA. Although IEEE 802.15.4- TDAM has lower packet loss values by 5% when compared to EEE-WSN under light traffic conditions and similar loss at heavy traffic conditions, EEE-WSN still has lower packet loss values by 5% and 25% when compared to IEEE 802.15. 4- CSMA, under light and heavy traffic conditions, respectively.

Deep Deconvolution for Traffic Analysis With Distributed Acoustic Sensing Data

Distributed Acoustic Sensing (DAS) is a novel vibration sensing technology that can be employed to detect vehicles and to analyse traffic flows using existing telecommunication cables. DAS therefore has great potential in future “smart city” developments, such as real-time traffic incident detection. Though previous studies have considered vehicle detection under relatively light traffic conditions, in order for DAS to be a feasible technology in real-world scenarios, detection algorithms need to also perform robustly under a wide range of traffic conditions. In this study we investigate the potential of roadside DAS for the simultaneous detection and characterisation of the velocity of individual vehicles. To improve the temporal resolution and detection accuracy, we propose a self-supervised Deep Learning approach that deconvolves the characteristic car impulse response from the DAS data, which we refer to as a Deconvolution Auto-Encoder (DAE). We show that deconvolution of the DAS data with our DAE leads to better temporal resolution and detection performance than the original (non-deconvolved) data. We subsequently apply our DAE to a 24-hour traffic cycle, demonstrating the feasibility of our proposed method to process large volumes of DAS data, potentially in near-real time.

Dynamic resource scheduling for real-time group broadcasting in 6G cellular vehicular networks

Vehicle-to-Vehicle (V2V) messaging is an indispensable component of connected autonomous vehicle systems. The 3rd Generation Partnership Project (3GPP) is designed to support V2V communication without any infrastructure using sensing-based Semi-Persistent Scheduling (SPS) in order to avoid resource collisions for Cooperative Awareness Messages (CAMs) transmission. However, the legacy system suffers from significant collisions in a traffic congestion environment and resource waste in light traffic conditions. To address these problems, in this paper we propose a novel dynamic resource scheduling algorithm for real-time group broadcasting, inspired by the Lyapunov optimization framework, where the optimization objective is to minimize time-average failure probability subject to queue stability. Through extensive simulations, we show that the proposed scheduling algorithm outperforms the standard in both traffic jams and leisurely road environments.

Optimized modulation order for V2V communication over index-modulated radar signals

Embedding information messages in radar signals through index modulation is a promising approach for dual function radar and communication in automotive systems. In this paper, we optimize the index modulation order to maximize the communication performance without compromising the radar operation. We derive novel expressions for the number of successfully transmitted bits per symbol and the target detection probability as functions of the road layout, traffic conditions and index modulation order. Results show that in light traffic conditions, index modulation can achieve up to 12 bits/symbol when line of sight is present between the transmit and receive vehicles with up to 140% improvement compared to the case with absent line of sight. Finally, we show that the received radar signal can be used, at the receive vehicle, to estimate the location of the transmitting vehicle via a maximum-likelihood estimator.

Effect of audio-visual interaction on soundscape in the urban residential context: A virtual reality experiment

This research aims to study the independent and interaction effects of aural and visual indicators on soundscape descriptors in the residential area. A virtual reality (VR) experiment was conducted to reproduce audio-visual stimuli and to collect subjective data using the questionnaire. Typical visual elements and aural environment in residential areas were reproduced using Unity software. Ten audio-only stimuli and 42 audio-visual stimuli (combination of 14 visual stimuli and three aural stimuli) were evaluated for various soundscape descriptors by 32 normal-hearing participants. There are four research findings. Firstly, a visual distraction was found on the effect of crowd sound on pleasantness. Secondly, the independent effects of indicators were analyzed. The sound of heavy traffic negatively affects pleasantness, while no significant difference has been found between no traffic and light traffic conditions. The crowd sound and PgVI (Playground View Index) positively affect eventfulness, while roughness and GVI (Green View Index) have a negative effect on eventfulness. Thirdly, traffic sound was found as a moderator of other indicators’ effect on pleasantness and eventfulness. For instance, GVI (Green View Index) can positively affect pleasantness in no traffic and light traffic conditions, while GVI does not affect pleasantness in heavy traffic conditions. Lastly, the present study did not find calmness correlated with eventfulness in residential areas, contrary to the previous studies. A possible explanation for this result might be that the correlation between descriptors is context-dependent.

The effects of adaptive cruise control (ACC) headway time on young-experienced drivers' overtaking tendency in a driving simulator

The preference to maintain a certain desired speed is perhaps the most prevalent explanation for why a driver of a manually driven car decides to overtake a lead vehicle. Still, the motivation for overtaking is also affected by other factors such as aggressiveness, competitiveness, or sensation-seeking caused by following another vehicle. Whether such motivational factors for overtaking play a role in partially automated driving is yet to be determined. This study had three goals: (i) to investigate whether and how a driver's tendency to overtake a lead vehicle changes when driving a vehicle equipped with an adaptive cruise control (ACC) system. (ii) To study how such tendencies change when the headway time configuration of the ACC system varies. (iii) To examine how the manipulation of the speed and speed variance of the lead vehicle affect drivers' tendencies to overtake a lead vehicle. We conducted two different experiments, where the second experiment followed the first experiment's results. In each experiment, participants drove three 10–12 min simulated drives under light traffic conditions in a driving simulator under manual and level one (L1) automation driving conditions. The automation condition included an ACC with two headway time configurations. In the first experiment, it was 1 sec and 3 secs, and in the second, it was 1 sec and 2 secs. Each drive included six passing opportunities representing three different speeds of the lead vehicle (−3 km/h, +3 km/h, +6 km/h relative to the participant), with or without speed variance. Results show that drivers tended to overtake a lead vehicle more often in manual mode than in automated driving modes. In the first experiment, ACC with a headway time of 1 sec led to more overtaking events than ACC with 3 secs headway time. In addition, the relative speed of the lead vehicle and its speed variability affected overtaking tendencies. In the second experiment, the relative speed of the lead vehicle and its speed variability affected overtaking tendencies only when interacting with each other and with driving configuration. When the speed of the lead vehicle was +3 km/h and included variability, more overtaking events occurred in manual mode than both automation modes. This work has shown that driving with ACC might help reduce overtaking frequencies and more considerable when the headway time is set to 3 secs.

The effects of visual landscape and traffic type on soundscape perception in high-rise residential estates of an urban city

In dense urban cities with high-rise estates where large population of residents live in close proximity, the increasing noise exposure in soundscapes due to traffic noise, construction and other undesirable anthropophony in urban lived environments may cause adverse effects on the wellbeing of residents. In this study, soundscapes around such urban spaces are investigated using Singapore as a case study. This study aims to discover the current conditions of soundscapes around such spaces and whether traffic and landscape features have a sizeable effect on soundscape perception, as well as to develop a predictive model using soundscape indicators based on acoustics, psychoacoustics, and audio features. The results show that the soundscapes in the selected urban city’s heartlands are generally dominated by traffic (40%) and biophonic (36%) sources. This study identifies the significant effects of both traffic conditions and landscape features that affect soundscape perception. A predictive model is developed based on identified objective indicators and an alternate method to derive the total mask duration of positive sound events. The visibility of roadways and vehicles correlates negatively with soundscape perception and reaffirms the effects of road visibility on noise annoyance. However, light traffic conditions do not adversely affect the soundscape perception as compared to heavy traffic, suggesting tolerance for light traffic by the participants in residential settings. Thus, the present study recommends that urban planners should take into consideration the type of traffic infrastructure when planning residential developments.

A Novel vision based embedded framework system to detect and track dynamic vehicles

A vehicle tracking system is a smart device installed in vehicles to detect and track the moving vehicle. In the emerging world the number of vehicles on road has been increasing globally. Intelligent transport system has been explored better to make an efficient transport system and also for traffic arrangements. Hence there is a need for a system that tracks the vehicle and provide assistance to the driver. The study aims at developing a novel embedded driver assistance framework that could analyze the dynamics of vehicle in the front and rear surround views. In the proposed study, to detect and track the moving vehicles Gaussian Mixture Model (GMM) and Kalman filter is implemented thereby critical safety to the vehicles is enabled by calculating the distance along with the directions. The developed prototype contains 4 cameras each equipped with an embedded processor. In order for the system to run at a near real time pace, optimized vision-based techniques are used that detect vehicles that are near-by. The only modality used for sensing are the camera sensors which analyze the surroundings of the ego or the host vehicle. Object detection by GMM technique proves to be more accurate and reliable in light traffic conditions and during day time whereas during night time the detection technique is not that accurate. Hence the developed prototype includes ultrasonic sensors that calculates the distance between the objects by sound wave. Further the developed detection system is validated by analyzing Receiver Operating Characteristics. Thus vision based embedded computing framework proves to be more efficient method for tracking objects.

Potential benefit of photovoltaic pavement for mitigation of urban heat island effect

Pavements in roadway and parking lots occupy large urban areas and contribute to the development of urban heat island (UHI). Photovoltaic (PV) pavement can use PV panels on conventional asphalt concrete (AC) pavement to harvest solar energy at light traffic conditions. This study aimed to evaluate the potential benefit of PV pavement to mitigate UHI effect. First, the heat transfer models for AC and PV pavements were developed. The pavement surface temperature and heat output from pavement surface to near-surface environment were then calculated that were used as the indicator of pavement contribution to UHI effect. A parametric study was conducted to analyze the influences of front glass and wind speed on thermal performance of PV pavement. Varying the thickness and transmittance of front glass have shown noticeable influences on pavement temperature, while the change of heat output is limited. Although the increase of average wind speed results in lower pavement temperatures, the heat output experiences slightly increase. The comparison of PV pavement and conventional AC pavement shows that PV pavement can decrease surface temperature by 3–5 °C in summer and generate 11–12% less heat output at various climate conditions.

Fuzzy logic-based methodology for quantification of traffic congestion

This paper presents a fuzzy-based methodology for quantification of congestion level for traffic control on expressways using traffic flow speed and density. Inductive loop detector data on the Interstate 880 obtained through the Freeway Performance Measurement System were used to estimate congestion levels following the fuzzy logic approach. In comparison with the Highway Capacity Manual, the results generally show a good correspondence. However, unlike the Highway Capacity Manual that defines step-wise measurement of levels of service based entirely on density, the proposed fuzzy inference system allows a flexible combination between speed and density to provide a more detailed indication of congestion intensity to describe the gradual transition of traffic state. For comparison, the congestion indices evaluated with both density and speed were compared to those evaluated with either speed or density using the same data set. Results from this comparative study reinforce the statements from previous studies that expressway speed is conservative under free-flow and light traffic conditions, but decreases significantly just before the flow rate approaches the road capacity. The results also show significant differences between the congestion indices evaluated using a single quantity, while the congestion indices using both density and speed tend to neutralize in between and scale up in a stable manner with the levels of service. Considering the abstract nature of congestion terminology, it is necessary to quantity traffic congestion on the expressways using both variables to minimize the potential bias in representing the operation of expressway traffic properly, which is particularly important under heavy congested conditions.

An Improved CTM Model for Urban Signalized Intersections and Exploration of Traffic Evolution

In this paper is going to be proposed a Cell Transmission Model (CTM), its analysis and evaluation with a case study, which addresses in a detailed way the aspect of merging and diverging operations on urban arterials. All those few CTM models that have been developed so far, to model intersections, have some limitations and drawbacks. First, unlike the simple composition road networks, such as highways, urban arterials must include some complex parts called merge sand diverges, due to the fact of vibrational values of reduced capacity, reduced saturation flow rate, etc. In order to simulate an urban network/arterial it is not possible to neglect the traffic signal indication on the respective time step. The objective of this paper is to highlight the difference between the results of the original CTM and our proposed CTM and to provide evidence that the later one is better than the old one. The proposed and formulated model will be employed through an algorithm of CTM to model a segment- arterial road of Pristina (compound from signalized intersections). For the functionalization and testing of the proposed model is build the experimental setup that is compatible with the algorithm created on C# environment. Results show that the proposed model can describe light and congested traffic condition. In light traffic conditions, in great mass traffic flow is dictated by the traffic signal status, while in medium congestion is obtained a rapid increase of the density to each cell. Fluctuations of the density from the lowest to the highest values are obvious during the first three cycles to all cells of the artery in a congested traffic state. Doi: 10.28991/cej-2021-03091659 Full Text: PDF

Performance Analysis of Multi-Band Microwave and Millimeter-Wave Operation in 5G NR Systems

Blockage of millimeter-wave (mmWave) radio propagation paths in dense mobile scenarios requires advanced techniques to preserve session continuity in 5G New Radio (NR) systems. In this work, we employ the tools of stochastic geometry and queuing theory as well as rely on 3GPP cluster-based propagation modeling to formulate a mathematical framework, which captures session-level service dynamics of user equipment (UE) that supports multi-band operation. Accordingly, the sub-6 GHz NR base station (BS) is used to temporarily serve the sessions with strict throughput requirements that experience an outage at the mmWave NR BSs. We derive user- and system-centric key performance indicators, including new and ongoing session drop probabilities as well as radio resource utilization. Our numerical results confirm that the use of microwave BSs to serve mmWave sessions is only feasible in light traffic conditions. Particularly, the presence of throughput-hungry mmWave traffic increases the session drop probability at the sub-6 GHz band as well as decreases its utilization. Further, the support of sub-6 GHz radio may not improve the mmWave BS resource utilization, as many mmWave sessions are dropped during their service as a consequence of frequent blockage-induced outage situations.

Resilience of Urban Street Network Configurations under Low Demands

Urban street networks are subject to a variety of random disruptions. The impact of movement restrictions (e.g., one-way or left-turn restrictions) on the ability of a network to overcome these disruptions—that is, its resilience—has not been thoroughly studied. To address this gap, this paper investigates the resilience of one-way and two-way square grid street networks with and without left turns under light traffic conditions. Networks are studied using a simplified routing algorithm that can be examined analytically and a microsimulation that describes detailed vehicle dynamics. In the simplified method, routing choices are enumerated for all possible origin–destination (OD) combinations to identify how the removal of a link affects operations, both when knowledge of the disruption is and is not available at the vehicle’s origin. Disruptions on two-way networks that allow left turns tend to have little impact on travel distances because of the availability of multiple shortest paths between OD pairs and the flexibility in route modification. Two-way networks that restrict left turns at intersections only have a single shortest-distance path between any OD pair and thus experience larger increases in travel distance, even when the disruption is known ahead of time. One-way networks sometimes have multiple shortest-distance routes and thus travel distances increase less than two-way network without left turns when links are disrupted. These results reveal a clear tradeoff between improved efficiency and reduced resilience for networks that have movement restrictions, and can be used as a basis to study network resilience under more congested scenarios and in more realistic network structures.

Stabilizing the virtual response time in single-server processor sharing queues with slowly time-varying arrival rates

Motivated by the work of Whitt, who studied stabilization of the mean virtual waiting time (excluding service time) in a $GI_t/GI_t/1/FCFS$ queue, this paper investigates the stabilization of the mean virtual response time in a single-server processor sharing (PS) queueing system with a time-varying arrival rate and a service rate control (a $GI_t/GI_t/1/PS$ queue). We propose and compare a modified square-root (SR) control and a difference-matching (DM) control to stabilize the mean virtual response time of a $GI_t/GI_t/1/PS$ queue. Extensive simulation studies with various settings of arrival processes and service times show that the DM control outperforms the SR control for heavy-traffic conditions, and that the SR control performs better for light-traffic conditions.

Dissipation of traffic congestion using autonomous-based car-following model with modified optimal velocity

We investigate dynamical properties of traffic flow using the stochastic car-following model with modified optimal velocity on circular road. The safety distance following the two-second rule and autonomous vehicles obeying simple requirements are incorporated into the model. The dynamic safety distance increases in a light traffic condition where the average driving velocity is high, while decreases in a dense traffic condition in anticipation of slower traffic motion. The results show that the presence of the autonomous vehicles can enhance overall velocity and traffic current of the system, and postpone the traffic congestion. In a particular phase region, imposing a speed limit enables the system to leave the congested flow phase. The density-dependent speed limit in autonomous-free condition is obtained to achieve the optimal traffic flow.

A CASE FOR IMPLEMENTING SELF-ORGANISING TRAFFIC SIGNAL CONTROL ON SOUTH AFRICAN ROADS

Traffic signal optimisation may lead to the alleviation, to some extent, of urban traffic congestion, particularly by using real-time data rather than expected traffic flow data. Recent advances in radar technology have made it possible to observe detailed traffic flow data in and around roadway intersections in real time. The notion of self-organisation has relatively recently been proposed as a promising alternative to improve the effective allocation of green time, particularly under lighter traffic conditions. A fixed-time control strategy and seven self-organising algorithms are compared in a microscopic traffic simulation model of a provincial road in the Western Cape province of South Africa. Actual arrival rates are used as input for the model, while the algorithms are compared using six performance measure indicators, under both light and moderate traffic conditions. The results are used to make a case for the adoption of self-organising traffic signal control algorithms, especially under conditions of light to moderate traffic densities, since this can lead to significant improvements in traffic flow in terms of delay time, vehicle stops, and time spent travelling at unacceptably slow speeds through the road network.

Self-organisation in traffic signal control algorithms under light traffic conditions

Fixed-time control and vehicle-actuated control are two distinct types of traffic signal control. The latter control method involves switching traffic signals based on detected traffic flows and thus offers more flexibility (appropriate for lighter traffic conditions) than the former, which relies solely on cyclic, predetermined signal phases that are better suited for heavier traffic conditions. The notion of self-organisation has relatively recently been proposed as an alternative approach towards improving traffic signal control, particularly under light traffic conditions, due to its flexible nature and its potential to result in emergent behaviour. The effectiveness of five existing self-organising traffic signal control strategies from the literature and a fixed-control strategy are compared in this paper within a newly designed agent-based, microscopic traffic simulation model. Various shortcomings of three of these algorithms are identified and algorithmic improvements are suggested to remedy these deficiencies. The relative performance improvements resulting from these algorithmic modifications are then quantified by their implementation in the aforementioned traffic simulation model. Finally, a new self-organising algorithm is proposed that is particularly effective under lighter traffic conditions.

On the analysis of the law of the iterated logarithm in open queueing networks

ABSTRACTThe modern queueing theory is one of the powerful tools for a quantitative and qualitative analysis of communication systems, computer networks, transportation systems, and many other technical systems. The paper is designated to the analysis of queueing systems, arising in the network theory and communications theory (called open queueing network). We have proved here the theorem on the law of the iterated logarithm (LIL) for the virtual waiting time of a job in an open queueing network under heavy and light traffic conditions. Also, the work presents a survey of papers for the virtual waiting time of a job in heavy traffic. Finally, we present an application of the proved theorems to the technical model from computer network practice.