A neural network algorithm for queue length estimation based on the concept of k-leader connected vehicles

This paper presents a novel method to estimate queue length at signalised intersections using connected vehicle (CV) data. The proposed queue length estimation method does not depend on any conventional information such as arrival flow rate and parameters pertaining to traffic signal controllers. The model is applicable for real-time applications when there are sufficient training data available to train the estimation model. To this end, we propose the idea of “k-leader CVs” to be able to predict the queue which is propagated after the communication range of dedicated short-range communication (the communication platform used in CV system). The idea of k-leader CVs could reduce the risk of communication failure which is a serious concern in CV ecosystems. Furthermore, a linear regression model is applied to weigh the importance of input variables to be used in a neural network model. Vissim traffic simulator is employed to train and evaluate the effectiveness and robustness of the model under different travel demand conditions, a varying number of CVs (i.e. CVs’ market penetration rate) as well as various traffic signal control scenarios. As it is expected, when the market penetration rate increases, the accuracy of the model enhances consequently. In a congested traffic condition (saturated flow), the proposed model is more accurate compared to the undersaturated condition with the same market penetration rates. Although the proposed method does not depend on information of the arrival pattern and traffic signal control parameters, the results of the queue length estimation are still comparable with the results of the methods that highly depend on such information. The proposed algorithm is also tested using large size data from a CV test bed (i.e. Australian Integrated Multimodal Ecosystem) currently underway in Melbourne, Australia. The simulation results show that the model can perform well irrespective of the intersection layouts, traffic signal plans and arrival patterns of vehicles. Based on the numerical results, 20% penetration rate of CVs is a critical threshold. For penetration rates below 20%, prediction algorithms fail to produce reliable outcomes.

Influence of tire-derived aggregates mixed with ballast on ground-borne vibrations

In this paper, the use of recycled tire-derived aggregates (TDA) mixed with ballast material is evaluated in order to reduce the train-induced ground-borne vibrations. For this purpose, a series of field vibration measurements has been carried out at an executed pilot track. The prepared ballast layer was mixed with different percentages of TDA in three sections. Moreover, another test section with pure ballast is considered as a reference. The vibrations generated by a motor-powered draisine at two different speeds are then recorded. Records of vibration data are provided using four seismometers placed once longitudinally and once transversely beside different sections. The outputs are then processed in both velocity–time and velocity–frequency domains. To verify the vibration mitigation performance of TDA in real operation conditions, field measurements under the passage of two planned passenger and freight trains are finally arranged. Results show that the best TDA mixture ratio, i.e., 10% by weight, can reduce the transmitted vibrations up to 12 dB for frequencies above 31.5 Hz. According to the obtained efficiency and the very low cost of the recycled materials, this solution can be considered as a competitive vibration countermeasure.

Model tests for surge height of rock avalanche–debris flows based on momentum balance

Rock avalanche–debris flows triggered by earthquakes commonly take place in mountainous areas. When entering a body of water, due to good fluidity they can move for some time instead of halting in water. In this study, we proposed a method for calculating the surge height of rock avalanche–debris flows based on momentum balance and designed a series of model tests to validate this method. The experimental variables include the initial water depth, landslide velocity, and landslide volume. According to the experimental results, we analyzed the maximum wave height in sliding zone based on momentum balance. In addition, we investigated the surge height and proposed the calculation method in propagating zone and running up zone. In this way, we can find out the surge height in different areas when a rock avalanche–debris flow impacts into the water, which could provide a basis for analyzing the burst of barrier lakes.

An application of Bayesian multilevel model to evaluate variations in stochastic and dynamic transition of traffic conditions

This study seeks to investigate the variations associated with lane lateral locations and days of the week in the stochastic and dynamic transition of traffic regimes (DTTR). In the proposed analysis, hierarchical regression models fitted using Bayesian frameworks were used to calibrate the transition probabilities that describe the DTTR. Datasets of two sites on a freeway facility located in Jacksonville, Florida, were selected for the analysis. The traffic speed thresholds to define traffic regimes were estimated using the Gaussian mixture model (GMM). The GMM revealed that two and three regimes were adequate mixture components for estimating the traffic speed distributions for Site 1 and 2 datasets, respectively. The results of hierarchical regression models show that there is considerable evidence that there are heterogeneity characteristics in the DTTR associated with lateral lane locations. In particular, the hierarchical regressions reveal that the breakdown process is more affected by the variations compared to other evaluated transition processes with the estimated intra-class correlation (ICC) of about 73%. The transition from congestion on-set/dissolution (COD) to the congested regime is estimated with the highest ICC of 49.4% in the three-regime model, and the lowest ICC of 1% was observed on the transition from the congested to COD regime. On the other hand, different days of the week are not found to contribute to the variations (the highest ICC was 1.44%) on the DTTR. These findings can be used in developing effective congestion countermeasures, particularly in the application of intelligent transportation systems, such as dynamic lane-management strategies.

Influence of adverse weather on drivers’ perceived risk during car following based on driving simulations

Adverse weather has a considerable impact on the behavior of drivers, which puts vehicles and drivers in hazardous situations that can easily cause traffic accidents. This research examines how drivers’ perceived risk changes during car following under different adverse weather conditions by using driving simulation experiment. An expressway road scenario was built in a driving simulator. Eleven types of weather conditions, including clear sky, four levels of fog, four levels of rain and two levels of snow, were designed. Furthermore, to simulate the car-following behavior, three car-following situations were designed according to the motion of the lead car. Seven car-following indicators were extracted based on risk homeostasis theory. Then, the entropy weight method was used to integrate the selected indicators into an index to represent the drivers’ perceived risk. Multiple linear regression was applied to measure the influence of adverse weather conditions on perceived risk, and the coefficients were considered as indicators. The results demonstrate that both the weather conditions and road type have significant effects on car-following behavior. Drivers’ perceived risk tends to increase with the worsening weather conditions. Under conditions of extremely poor visibility, such as heavy dense fog, the measured drivers’ perceived risk is low due to the difficulties in vehicle operation and limited visibility.

Pedestrian perception-based level-of-service model at signalized intersection crosswalks

Pedestrian level of service (PLOS) is an important measure of performance in the analysis of existing pedestrian crosswalk conditions. Many researchers have developed PLOS models based on pedestrian delay, turning vehicle effect, etc., using the conventional regression method. However, these factors may not effectively reflect the pedestrians’ perception of safety while crossing the crosswalk. The conventional regression method has failed to estimate accurate PLOS because of the primary assumption of an arbitrary probability distribution and vagueness in the input data. Moreover, PLOS categories in existing studies are based on rigid threshold values and the boundaries that are not well defined. Therefore, it is an important attempt to develop a PLOS model with respect to pedestrian safety, convenience, and efficiency at signalized intersections. For this purpose, a video-graphic and user perception surveys were conducted at selected nine signalized intersections in Mumbai, India. The data such as pedestrian, traffic, and geometric characteristics were extracted, and significant variables were identified using Pearson correlation analysis. A consistent and statistically calibrated PLOS model was developed using fuzzy linear regression analysis. PLOS was categorized into six levels (A–F) based on the predicted user perception score, and threshold values for each level were estimated using the fuzzy c-means clustering technique. The developed PLOS model and threshold values were validated with the field-observed data. Statistical performance tests were conducted and the results provided more accurate and reliable solutions. In conclusion, this study provides a feasible alternative to measure pedestrian perception-based level of service at signalized intersections. The developed PLOS model and threshold values would be useful for planning and designing pedestrian facilities and also in evaluating and improving the existing conditions of pedestrian facilities at signalized intersections.

Data analytics approach for travel time reliability pattern analysis and prediction

Travel time reliability (TTR) is an important measure which has been widely used to represent the traffic conditions on freeways. The objective of this study is to develop a systematic approach to analyzing TTR on roadway segments along a corridor. A case study is conducted to illustrate the TTR patterns using vehicle probe data collected on a freeway corridor in Charlotte, North Carolina. A number of influential factors are considered when analyzing TTR, which include, but are not limited to, time of day, day of week, year, and segment location. A time series model is developed and used to predict the TTR. Numerical results clearly indicate the uniqueness of TTR patterns under each case and under different days of week and weather conditions. The research results can provide insightful and objective information on the traffic conditions along freeway segments, and the developed data-driven models can be used to objectively predict the future TTRs, and thus to help transportation planners make informed decisions.