Abstract: This article investigates the application of Kalman filter with discrete wavelet analysis in short‐term traffic volume forecasting. Short‐term data are often corrupted by local noises, which may significantly affect prediction accuracy volumes. Discrete decomposition is used to divide original into several approximate and detailed such that model can then be applied denoised improved. Two types models based on Daubechies 4 Haar mother wavelets investigated. Traffic collected from...

In order to reduce passenger delays and prevent severe overcrowding in the subway system, it is necessary accurately predict short-term flow during special events. However, few studies have been conducted under these conditions. Traditional methods, such as autoregressive integrated moving average (ARIMA) model, were commonly used analyze regular traffic demands. These methods usually neglected volatility (heteroscedasticity) influenced by unexpected external factors. This paper, therefore,...

A variety of short-term traffic flow forecasting methods have been developed in the last two decades. However, due to complexity conditions and drawbacks existing those methods, predictions generally lack accuracy robustness. In response these problems, a fuzzy logic system methodology is proposed this study. The are used forecast compare with using dual-loop data collected from I-35 San Antonio, Texas. Forecasting results show that produces more accurate stable predictions. It also robust...

Agent-based approach is a popular tool for modelling and developing large-scale distributed systems such as urban traffic control system with dynamic flows. This study proposes multi-agent-based to optimize network signal control, which utilizes mathematical programming method the timing plans at intersections. To improve overall efficiency, we develop an online agent-based coordination scheme, underpinned by communication among different intersection agents. In addition, initial scheme that...

Enhancing hazmat truck safety through advanced driving assistance systems (ADAS) relies on both system efficacy and driver reactions. This study investigates the behaviors of drivers in response to forward collision warnings (FCWs). Traditional warning triggering methods struggle capture diverse immediate responses; therefore, our research employs a vision‐based framework for data extraction utilizes K‐means++ clustering method response‐based classification. Moreover, we propose an enhanced...

Purpose Advanced driving assistance system (ADAS) has been applied in commercial vehicles. This paper aims to evaluate the influence factors of vehicle drivers’ acceptance on ADAS and explore characteristics each key factors. Two most widely used functions, forward collision warning (FCW) lane departure (LDW), were considered this paper. Design/methodology/approach A random forests algorithm was acceptance. data 24 vehicles recorded from 1 November 21 December 2018, Jiangsu province. Respond...

Resolving conflicting transit signal priority (TSP) requests has become an emerging topic in public transportation studies. The main objective of TSP is to reduce schedule deviation and enhance the reliability bus service, whereas many previous studies have aimed at reducing delay. Furthermore, they did not take into account element waiting time experienced by passengers stops. Therefore, this paper selects in-bus passenger delay next stops as indexes measure level requests. Here, a decision...

The objective of this study is to investigate and evaluate the effects weather information (in terms accuracy frequency usage) on winter maintenance costs. To end, a general cost model presented, then methodology combining sensitivity analysis neural network methods proposed. Sensitivity used identify key input variables that significantly affect output variable. proposed method are applied case Iowa operations. results from show lane miles roadway maintained by units have most important...

The primary objective of this study was to develop a quantitative approach estimate bus dwell time and lost serving stop, which included acceleration deceleration time, dead for boarding alighting passengers. A polynomial model incorporating kinematics particle derived estimating time. In addition, descriptive statistics methods were used analyze case conducted show the applicability proposed with data collected from seven most common types stops in China. R-square Mean Absolute Percentage...

Safety performance at bus stops is generally evaluated by using historical traffic crash data or conflict data. However, in China, it quite difficult to obtain such mainly due the lack of management and organizational issues. In light this, primary objective this study develop a quantitative approach evaluate stop safety performance.The concept level-of-safety for introduced corresponding models are proposed quantify levels, which consider points, factors, geometric characteristics, signs...

This study proposed a model incorporating diffusion approximation method to explore the correlation between failure rate and bus-stop operation, which included bus arrival rate, service time, variation coefficient of headway, stop capacity. According results, linear relationship had more accurate reliable fitted values (with 6.98% MAPE 0.935 R-square) for single-berth stops exponential better performance 0.799 R-square 14.86% MAPE) multi-berth expression rate. The results sensitivity...

This study proposed a hybrid optimization model for urban bus transit route network design problem (TRNDP). Although several mathematical methods had been developed to make the tractable, relied on excessive assumptions, which resulted in over-simplification or idealization of problems. In light these considerations, multi-level and multi-mode method was introduced this study. A consisted three levels: skeleton network, arterial feeder network. The different levels were associated with modes...