Abstract At unsignalized midblock crosswalks (UMCs), visual obstructions created by bike lane buffers can substantially affect drivers’ pedestrian detection and yielding behavior. However, limited evidence is available regarding how different types of bike lane buffers influence driving performance through changes in visual attention and cognitive workload. To address this issue, four representative bike lane buffer scenarios—Lawn, Railing, Bush, and Tree—were developed in a driving simulation environment. Vehicle operation parameters and eye-tracking data were collected simultaneously to investigate drivers’ behavioral and visual responses while approaching a crosswalk. The results showed that highly obstructive buffers significantly delayed pedestrian detection and weakened drivers’ early risk perception. In the Bush and Tree scenarios, pedestrians were detected at distances of only about 18 m from the crosswalk, representing a reduction of more than 40% compared with the low-obstruction conditions. As a consequence, drivers exhibited lower terminal braking speeds, higher maximum deceleration rates, and more abrupt braking maneuvers. The mean braking initiation distance in the Bush and Tree scenarios was approximately 48 m, which was more than 10 m shorter than that observed under the Lawn and Railing conditions. Eye-tracking analyses further revealed that highly obstructive environments significantly increased fixation duration on roadside areas while reducing the effective visual search range. In addition, the proportions of saccades and blinks decreased to approximately 3%, whereas the coefficient of variation of pupil diameter increased to 0.23, indicating elevated cognitive workload and mental stress. These findings demonstrate that visual obstructions associated with bike lane buffers can adversely affect drivers’ hazard perception, visual search behavior, and braking responses. The study provides empirical evidence to support the safety evaluation and design optimization of bike lane buffers near unsignalized midblock crosswalks.
Abstract Short-term traffic flow prediction constitutes a core component of intelligent transportation systems, and it plays a critical role in alleviating traffic congestion, optimizing road-network operation and management, and improving urban travel efficiency. This paper proposes a novel short-term traffic flow prediction model that combines a temporal convolutional network with a bidirectional gated recurrent unit. To ensure the validity and reliability of subsequent modeling, three outlier detection approaches are utilized to preprocess raw traffic flow data. Specifically, the temporal convolutional network module is adopted to extract fine-grained short-range local features from traffic flow sequences and enhance feature information exploitation. The extracted spatiotemporal features are subsequently input into the BiGRU module to capture long-term temporal dependencies embedded in traffic flow data. Owing to this dual-module architecture, the model can fully excavate complex intrinsic correlations within traffic flow samples and attain favorable prediction accuracy. Moreover, an improved gray-wolf optimizer is developed to tune the hyperparameters of the combination model. This strategy effectively overcomes the drawbacks of traditional manual hyperparameter tuning, such as heavy computational burden and unstable model performance. To verify the effectiveness and generalization capability of the presented model, comprehensive experiments are carried out on two public traffic flow datasets that differ in geographical origin, sampling interval, and sample size. Comparative experimental results show that the proposed model yields lower prediction errors and better overall performance metrics, confirming its considerable practical application potential for real-world traffic prediction tasks.
Abstract The influence area of an intersection is the region where it affects both upstream and downstream traffic flow. Traffic flow may be influenced by factors such as queue formation, maneuvering, and drivers’ perception of required actions in response to surrounding stimuli. Understanding the boundaries of the influence area is crucial, because it can improve traffic operations, enhance safety analysis, and support data-driven design and control strategies for various types of intersections. This study aims to identify the influence area of different intersection types by incorporating the perception-reaction decision distance (PRD), and maneuver and queue-storage distance (MQD), as the primary contributing factors to its extent. The intersections examined in this analysis include a signalized intersection, a three-leg all-way stop-controlled (AWSC) intersection, and a three-leg single-lane roundabout intersection. The analysis addresses not only through movements but also all turning movements. The PRD calculation uses reaction time data to determine the influence an intersection exerts on a driver’s overall reaction. The MQD identification process involves measuring observed speed variations along vehicle trajectories. These two components together define the study’s identified influence area. High-resolution vehicle trajectory data (HRVTD) were employed to ensure accurate capture of vehicle behaviors within the influence area for each intersection type. The more detailed segment of data, with a temporal granularity of 3 s, provided a penetration rate of 2%–3% when compared with annual average daily traffic (AADT). The results underscore the importance of considering all movement types. Additionally, the PRD can account for up to 30.58% of the total influence distance at intersections, highlighting its critical role in defining the influence area of intersections.
Abstract This study proposes a minute-level tidal lane control framework for highway toll plazas operating under strongly time-varying and directionally imbalanced demand. Historical and real-time traffic volumes, lane-specific service rates, holiday indicators, and weather variables are used to generate 30-min-ahead directional flow forecasts with a Transformer–bidirectional long short-term memory model. The forecasts are then combined with overload-risk screening and a directional-imbalance measure based on the volume-to-capacity ratio to determine whether lane reversal should be implemented. Using field data from a major highway toll plaza in China, the proposed intelligent tidal lane control method reduces average travel time by about 20% during the morning peak and 22% during the evening peak relative to the traditional reactive strategy, with larger gains under high-demand tidal-surge conditions and limited unnecessary intervention under low-demand conditions. The study also provides calibration guidance and recommended ranges for the key thresholds α and d, offering a transferable parameter-calibration procedure and practical guidance for real-world toll-plaza operations.
Abstract Electric bike sharing (EBS), a convenient and efficient mobility solution, has become an integral part of urban transportation systems in many cities. To promote the sustainable development of EBS systems, it is vital to understand the spatiotemporal patterns of EBS demand and their relationships with influencing factors. Using 1 month of EBS trip data from Yangzhou, China, this study applied a nonnegative matrix factorization (NMF) model, combined with the space-time cube model and emerging hot spot analysis, to identify spatiotemporal patterns of EBS demand. The results show that EBS demand exhibits four distinct temporal patterns: (1) morning peak, (2) daytime, (3) evening peak, and (4) nighttime, each with unique spatial hot spot distributions. Subsequently, the study employed Light Gradient Boosting Machine (LightGBM) models to explore the complex relationships between EBS demand and the built environment within each of these patterns, with a pooled model as a benchmark. The analysis reveals that the relative importance of variables varies significantly across patterns. For instance, the importance of the percentage of residential district peaks in the morning peak pattern, while the percentage of commercial district and educational institutions are more prominent in the daytime, evening peak, and nighttime patterns. Moreover, these relationships exhibit pronounced nonlinearity. For example, the positive correlation between population density and EBS demand levels off at 2,000 people / km 2 for the morning peak pattern, but not until 5,000 people / km 2 for other patterns. These findings can guide operators in formulating refined operational strategies and assist policymakers in developing targeted interventions.
