A multi-agent reinforcement learning for adaptive traffic signal control optimization.• Consider control unit at intersection as agent that can communicate with others through knowledge-sharing protocol.• Proposed algorithm achieves consistent improvements over baselines on both simulated and real-world data.
Although bus comfort is a crucial indicator of service quality, existing studies tend to focus on passenger load and ignore in-vehicle time, which can also affect passengers’ comfort perception. Therefore, by conducting surveys, this study examines passengers’ comfort perception while accounting for both factors. Then, using the survey data, it performs a two-way analysis of variance and shows that both in-vehicle time and passenger load significantly affect passenger comfort. Then, a bus comfort model is proposed to evaluate comfort level, followed by a sensitivity analysis. The method introduced in this study has theoretical implications for bus operators attempting to improve bus service quality.Electronic supplementary materialThe online version of this article (doi:10.1186/s40064-016-1694-7) contains supplementary material, which is available to authorized users.
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.