User-satisfaction based operational evaluation for uncontrolled intersections under mixed traffic

Operational Evaluation of Uncontrolled Intersections using Artificial Intelligence Techniques

Comparative Study of Pedestrian Crossing Behaviour at Uncontrolled Intersection and Midblock Locations

In the developing world, with increases in population, the number of vehicles is increasing tremendously. Traffic safety on roads has become a major concern even with advancements in technology and infrastructure. Traffic safety assessments and accident prediction based on accident data is a reactive approach. There are known drawbacks related to the reliability of accident data, especially in developing countries with large populations, such as India. It is, however, unethical to wait for accidents to occur before drawing statistically accurate conclusions regarding safety impacts. To overcome this impediment, one needs to develop accurate models that rely on surrogate safety measures (SSMs) for effective safety evaluations. The main advantage associated with the use of these models is that they can model crashes more frequently than in the real world and thereby imply an efficient and more statistically reliable proximal measure of traffic safety. The objective of this study is to examine the impact of management measures on traffic safety at a three-arm uncontrolled intersection with the use of microsimulation modeling under mixed traffic conditions. This examination was done by developing a unique methodology of measuring one SSM, postencroachment time (PET). This paper describes improvement in the accuracy of crash predictions by proposing a methodology to calculate PET.

For signalized locations, delay is one of the key parameters in assessing the level of service and redesigning the traffic signals. Around the world, Highway Capacity Manual (HCM) and Webster delay models are commonly used in calculating the vehicle delay at signalized intersections, notwithstanding that these models assume homogeneous traffic conditions and lane discipline. Furthermore, it is worth noting that previous studies have mostly focused on developing delay models for signalized intersections, whereas signalized midblock crosswalks were overlooked by past researchers. In view of this, the current study presents a modified vehicle delay model for signalized midblock crosswalks (SMCs) under mixed traffic conditions. Mixed traffic conditions refers to diverse vehicles, complex interactions, and no lane discipline on the road—conditions which are usually noticed in developing nations. The HCM vehicle delay model is modified in the current study by incorporating factors related to mixed traffic conditions and SMCs. To test the accuracy of the proposed model, it was validated with the field delay using data collected at other SMCs in Hyderabad, India. Field delay was calculated by plotting the measured queue length against the signal cycle length. The performance metrics of root mean square error (RMSE), mean absolute percentage error, Nash–Sutcliffe efficiency, RMSE-observations standard deviation ratio, and percent bias were used to test the accuracy of the proposed model. Results revealed that the proposed model yielded the lowest error rates and the highest correlation coefficients between modeled and actual vehicle delay. The maximum error between the field delay and the modeled delay was found to be less than 5%.

Pedestrian crossings are important for accessing the adjacent land use facilities in daily life. Improperly designed crossing facilities cause discomfort to pedestrians and may even jeopardize their safety as well as being a hindrance to the smooth flow of vehicle traffic. These problems exist especially in developing countries such as India, where mixed traffic conditions prevail and road discipline is essentially absent. Thus, the design of efficient crossing facilities considering the flow of both pedestrians and vehicles is of utmost importance in these countries. In this regard, the objective of the current study was to propose warrants for pedestrian crossing facilities in midblock sections under mixed traffic conditions. To achieve this objective, pedestrian–vehicle ( PV2) conflict analysis was carried out at eight different unprotected midblock crosswalks in Mumbai, India. Videographic surveys were conducted and vehicle and pedestrian volumes were extracted, along with pedestrian-crossing characteristics such as crossing difficulty, safety and traffic, and vehicle characteristics. The initial computed PV2-values were adjusted by different factors, and k-means cluster analysis was carried out to determine the threshold PV2-values for selection of a suitable crosswalk facility. The study also highlighted the importance of taking into consideration site characteristics for evaluation of a midblock crosswalk facility. The results of this study are expected to have a wide range of applications in the design of new crosswalk facilities or in the improvement of existing pedestrian crosswalk facilities under mixed traffic conditions.

Analysis of Demand Responsive Pelican Crossing in Mixed Traffic Conditions

Modelling behavioural interactions of drivers' in mixed traffic conditions

Merging process of U-turns at uncontrolled median openings under mixed traffic conditions

Median openings are one of the most commonly used road features, which are mainly used to allow U-turning movement in urban areas, and this study focuses mainly on modeling the behavior of U-turning vehicles at the median opening using a merging behavior approach. The purpose of the study is to estimate and model the critical gap of u-turning vehicles at the median opening under mixed traffic conditions. Under this study, the accepted gap, rejected gap, driver waiting time, merging time, and critical gap are estimated, and the modified Raff's method and modified INAFOGA method are used for the estimation of a critical gap. However, modified INAFOGA is used for the modeling of critical gaps under mixed traffic conditions. In this study, sixteen median openings were selected in Bahir Dar city, and data were collected using a video recording technique at each selected median opening during the peak hour of the day. The necessary data were extracted using Forevid analysis software tools. Different types of traffic are involved in the mixed traffic, and each vehicle type is categorized according to the Ethiopian Road Authority's 2013 design guide into seven different classes, such as 2-wheeler, 3-wheeler, passenger car, minibus, small bus and truck, medium bus, and medium truck. Among those traffic types, three vehicle classes (three-wheeler, passenger car, and minibus) were only considered due to the prohibition of U-turning movement for medium and large vehicles. For the modeling of critical gaps, waiting time and conflicting traffic flow are used as independent variables using the regression technique. Driver waiting time and the critical gap were found to be power related to passenger cars and minibuses and exponentially to three-wheelers. Conflicting traffic flow and critical gaps were power related to passenger cars and minibuses and linearly related to three-wheelers.

This paper presents a gray system theory-based method for the quantitative evaluation and ranking of the operational and safety performance of signalized intersections in urban areas under mixed traffic conditions. Mixed traffic conditions refer to traffic situations in which motor vehicles, bicycles, and pedestrians share a signalized intersection. Such mixed traffic is a typical phenomenon in many cities around the world in which the populations of urban areas are extremely large. Five index parameters are used in the proposed method: the degree of saturation, the average stopped delay, the queue length, the conflict ratio, and the separation ratio. These parameters represent the operational and safety performance of a signalized intersection with mixed traffic. They are inputted into the evaluation equations, which are developed according to the gray system theory. The method is applied to the performance evaluation of the intersections and network in the urban area of Changsha, China. The results show...

Variable speed limits (VSLs) have a potential to improve mobility and safety of motorway through harmonisation of traffic flow. However, the success of VSL is highly dependent on drivers’ compliance to the displayed speed limits. Emerging technologies in the field of connected autonomous vehicles (CAVs) is likely to revolutionise the way VSL will be operated in the near future. VSL can be integrated with CAVs where CAVs will automatically obey the displayed speed limits. However, 100% penetration rate of CAVs is a long‐term goal. At the initial stage of deployment, CAVs will coexist with manually driven vehicles on motorways. This study explores ways to implement VSL under a mixed traffic condition where CAVs and manually driven vehicles coexist in the traffic stream. A hybrid approach combining particle swarm optimisation with proportional‐integrated‐derivative is proposed to improve VSL implementation under a range of mixed traffic conditions. The simulation results showed that the proposed method successfully achieved the desired speed limits and rapidly stabilised the system at the initial and transient points at penetration rates of 50 and 75%, whereas the method encountered serious overshoots at lower penetration rates.

Dynamic prediction of queues and delays at signalized intersections utilize data obtained from automated traffic sensors as inputs for Intelligent Transportation Systems (ITS) applications. Errors are inevitable during automated data handling, especially when the traffic involved is heterogeneous and lacking in lane discipline. This paper presents a model-based estimation scheme that can handle both mixed traffic conditions and erroneous detector input data to estimate queue and, in turn, delay. The models were developed for Queue within Advance Detector (QWAD) and Queue beyond Advance Detector (QBAD) scenario. The statistical properties of detector errors were incorporated into the estimation scheme, and the scheme was tested for varying traffic conditions. The estimation scheme’s performance was evaluated using field data from a signalized intersection in Chennai, India, and simulated data. It is found that the incorporation of statistical properties of detector error allows accurate estimation of queues and delays despite erroneous data input.

The aim of this study was to develop three roundabout entry capacity models (RECMs) by employing evolutionary-based regression techniques such as genetic programming (GP), age-layered population structure genetic programming (ALPSGP) and grammatical evolution genetic programming (GEGP) in mixed traffic conditions. Necessary data were collected from 27 roundabouts located in eight states in India. The influence area for gap acceptance method was used to determine the critical gap. To assess the significance of the models and select the best, the modified rank index was applied. The results showed that the GEGP model performed better than the GP and ALPSGP models. The GEGP model is also applicable in practice because of its simplicity. Sensitivity analysis revealed that the critical gap is the prime variable in the development of RECMs. The findings of this study should be useful for traffic planners and designers in the capacity estimation of roundabouts in mixed traffic conditions in developing countries with traffic characteristics similar to those in India.

Highway dispersion models are routinely used for prediction of air quality along road and highway corridors. Various input parameters used by these models for prediction of air quality along the road corridors. In the present study, sensitivity analysis of CALINE4 model was carried out under mixed traffic conditions to identify the input parameters and the extent to which they influence the output (i.e., predicted concentration) of the model. The road corridor selected in Delhi city (India) was a stretch of National Highway-2 (NH-2) passing through the city. The selected corridor caters to both inter-city and intra-city traffic and had mixed traffic conditions. Carbon monoxide was selected as indicator pollutant for prediction and sensitivity analysis exercise. Sensitivity analysis of the CALINE4 model was carried out for three hours input datasets representing different meteorological (wind speed, wind direction, mixing height, stability class), traffic (traffic volume and emission factors) and road characteristic (roadway width) along with terrain (surface roughness) characteristic. Input parameters corresponding to selected datasets were varied separately and systematically and their impact on predicted CO concentrations was observed and quantified. It was observed that apart from source strength (traffic volume and emission factors), meteorological parameters viz., wind speed and wind direction influenced the prediction capabilities of model considerably. Whereas, surface roughness, mixing height had relatively less contribution in model's output.

This study introduces a novel feature-based long short-term memory (LSTM) neural network designed to predict the severity of pedestrian–vehicle interactions at unsignalized intersections, aiming to enhance traffic safety significantly. The LSTM model dynamically integrates real-time data variables such as pedestrian and vehicle speeds, distances, and types, enabling it to accurately predict potential hazardous interactions in mixed traffic conditions. Utilizing a comprehensive data set of over 4,300 pedestrian–vehicle interactions, the interactions were meticulously categorized from “Safe Passage” to “Conflict” based on detailed behavioral analyses. Training and validation of the LSTM model demonstrated high accuracy and strong generalization capabilities. The model demonstrated strong predictive capabilities across varying levels of pedestrian–vehicle interaction severity. It performed well in identifying Safe Passage interactions, with high precision and a balanced trade-off between precision and recall for Critical Events. The model also excelled in predicting conflicts, showing robustness in distinguishing these critical interactions. Further evaluation showed significant improvement over baseline models and consistent performance across different urban environments. After iterative retraining with external data, the model’s overall performance improved significantly, reflecting its capacity to generalize about diverse traffic conditions. The successful deployment of this LSTM model marks a significant advancement in real-time traffic safety technology. Its ability to provide accurate predictions of interaction severity offers a proactive tool for providing real-time warnings to mitigate pedestrian–vehicle collisions, highlighting its potential for integration into traffic management and autonomous vehicle systems. This study underscores the model’s applicability across various traffic environments, making it a vital asset for urban safety enhancements.