This article addresses the problem of the accuracy of short-term traffic flow forecasting in the complex case of urban signalized arterial networks. A new, artificial intelligence (AI)-based approach is suggested for improving the accuracy of traffic predictions through suitably combining the forecasts derived from a set of individual predictors. This approach employs a fuzzy rule-based system (FRBS), which is augmented with an appropriate metaheuristic (direct search) technique to automate the tuning of the system parameters within an online adaptive rolling horizon framework. The proposed hybrid FRBS is used to nonlinearly combine traffic flow forecasts resulting from an online adaptive Kalman filter (KF) and an artificial neural network (ANN) model. The empirical results obtained from the model implementation into a real-world urban signalized arterial demonstrate the ability of the proposed approach to considerably overperform the given individual traffic predictors. © 2008 Computer-Aided Civil and Infrastructure Engineering

The market penetration of shared micro-mobility services (shared bikes, e-bikes, and e-scooters) suggest that young and highly educated people constitute a group of people that is more eager to use such services. However, little is known about the factors influencing their behavioral intention as a system. The analysis may provide insights on the adoption of shared micro-mobility services by modeling them as a system using multivariate ordered probit. This paper contributes to the existing literature by evaluating similarities and differences to these services focusing on assessing the behavioral intentions of a large sample of young and highly educated people that traditionally show a higher tendency of adopting technologically innovative services. It is hypothesized that the mobility patterns can affect people's adoption of these shared services in a car-dependent empirical setting. The analysis suggested that a variety of variables affect the behavioral intention to use shared micro-mobility services, such as employment situation, household size, travel patterns, level of awareness, and attitudinal variables in the form of perceptions on incentives and infrastructure. This study can enhance the current understanding of the factors affecting the behavioral intention, facilitating the development of policies toward such means of transportation. The results could convincingly answer key questions on the market adoption of these shared services, and characteristics of distinct market segments; thereby providing a deployment pathway for adoption. Additionally, the results could be useful to original equipment manufacturers for marketing and pricing-scheme decisions, planning agencies for policy-making decisions, and to transportation planners for provisions in infrastructure.