Driver inattentiveness and distraction resulting in unsafe vehicle maneuvers are a significant safety concern because such behavior can directly lead to crashes. An effective technical countermeasure is to detect unsafe driving events and provide drivers with advanced warning information. This study presents an intervehicle safety warning information system. An inertial measurement unit consisting of an accelerometer and gyro sensor in addition to a Global Positioning System receiver was used to collect data for the developed algorithm. Vehicle position, speed, acceleration, and angular velocity data were analyzed and were used as inputs for the algorithm. A support vector machine classifier was also incorporated into the algorithm to identify further the severity of unsafe driving events. The performance evaluation results showed that the detection algorithm could capture longitudinal and transverse unsafe driving events. In addition, a prototype of the proposed warning information system was implemented on a test bed in support of vehicle-to-vehicle and vehicle-to-infrastructure communications. Extensive field tests have been conducted in the test bed to fine-tune the prototypical system. These results demonstrate that the system holds promise for improving drivers' safety and mitigating crash risks.
The recent advancement of vehicle positioning and wireless communication technologies facilitates the development of more sophisticated traffic control and information strategies. This study proposes a methodology for estimating lane-level travel times (L2TT) under an environment referred to as V2X, which includes vehicle-to-vehicle and vehicle-to-infrastructure communications. A framework is presented for a V2X-based traffic information system that is capable of transmitting vehicle positions and speeds, which are used as inputs of the proposed methodology. A concept of establishing temporal nodes and links based on the dynamic change in traffic conditions is proposed to estimate more reliable and accurate L2TT. VISSIM, a microscopic traffic simulator for multimodal traffic flow modeling, is used to evaluate the proposed travel time estimation method. Statistical analysis techniques including analysis of variance and a homogeneity test between data groups are adopted to derive more generalized conclusions. The evaluation results show that less than a 10% mean absolute percentage error was achievable with a 20% probe vehicle rate. It is expected that the proposed methodology will serve as a useful precursor to the development of a next-generation traffic information system in the robust wireless communications era.
SUMMARYBecause of the quality of raw data being an essential feature in determining the reliability of traffic information, an effective detection and correction of outliers in raw field-collected traffic data has been an interest for many researchers. Global positioning systems (GPS)-based traffic surveillance systems are capable of producing individual vehicle speeds that are vital for transportation researchers and practitioners in traffic management and information strategies. This study proposes a locally weighted regression (LWR)-based filtering method for individual vehicle speed data. To fully and systematically evaluate this proposed method, a technique to generate synthetic outliers and two approaches to inject synthetic outliers are presented. Parameters that affect the smoothing performance associated with LWR are devised and applied to obtain a more robust and reliable data correction method. For a comprehensive performance evaluation of the developed LWR method, comparisons to exponential smoothing (ES) and autoregressive integrated moving average (ARIMA) methods were conducted. Because the LWR-based filtering method outperformed both the ES and ARIMA methods, this study showed its useful benefits in filtering individual vehicle speed data.
In the cost–benefit analysis of urban transportation investment, a logsum-based benefit calculation is widely used. However, it is rarely applied to inter-regional transportation. In this study, we applied a logsum-based approach to the calculation of benefits for high-speed projects for inter-regional railways in Korea’s long-term transportation plan. Moreover, we applied a behavioral model in which an agent travels beyond the zones assumed by an aggregate model. In the case of South Korea, such a model is important for determining transportation priorities: whether to specialize in mobility improvement by investing in a high-speed railway project, such as the 300 km/h Korea Train eXpress (KTX), or to improve existing facilities, such as by building a relatively slower railroad (150–250 km/h) to enhance existing mobility and accessibility. In this context, if a new, relatively slow railroad were constructed adjacent to a high-speed railroad, the benefits would be negligible since the reduction in travel time would not sufficiently reflect accessibility improvements. Therefore, this study proposes the use of aggregate and agent-based models to evaluate projects to improve intercity railway service and conduct a case study with the proposed new methodology. A logsum was selected to account for the benefits of passenger cars on semi-high-speed and high-speed railroads simultaneously since it has been widely used to estimate the benefits of new modes or relatively slow modes. To calculate the logsum, this study used input data from both the aggregate and individual agent-based models, and found that an analysis of the feasibility of inter-regional railroad investment was possible. Moreover, the agent-based model can also be applied to inter-regional analysis. The proposed methods are expected to enable a more comprehensive evaluation of the transport system. In the case of the agent-based model, it is suggested that further studies undertake more detailed scenario analysis and travel time estimation.
Accurate and timely predictions of traffic conditions are required for congestion avoidance and route guidance in real-time freeway traffic operations. Special attention to winter operations is needed because prediction error could be amplified under severe weather conditions involving snow. This study employed a vehicle detection system to propose a speed prediction methodology that used the k–nearest neighbors algorithm. The speed prediction was further evaluated under different weather conditions with a road weather information system. Cross-comparisons of the mean absolute percentage error (MAPE) between three weather conditions (normal, light snow, and heavy snow) revealed that the MAPE tended to increase with increases in the forecasting time step (T) and snow intensity. The marginal MAPE over the time step was larger during heavy snow conditions than under normal and light snow conditions. These findings indicate that for winter freeway operations, the time step should be selected dynamically, depending on the weather conditions rather than with a static strategy for all conditions. To this end, this study proposes a framework to determine a dynamic forecasting T that is associated with weather conditions.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.