Search

Shared bicycles provide a green, environmentally friendly, and healthy mode of transportation that effectively addresses the "final mile" problem in urban travel. However, the uneven distribution of bicycles and the imbalance of user demand can significantly impact user experience and bicycle usage efficiency, which makes it necessary to predict bicycle demand. In this paper, we propose a novel shared-bicycle demand prediction method based on station clustering. First, to address the challenge of capturing patterns in station-level bicycle demand, which exhibits significant fluctuations, we employ a clustering method that combines graph information from the bicycle transfer graph and potential energy. This method aggregates closely related stations into corresponding prediction regions. Second, we use the GCN-CRU-AM (Graph Convolutional Network-Gated Recurrent Unit-Attention Mechanism) model to predict bicycle demand in each region. This model extracts the spatial information and correlation between regions, integrates time feature data and local weather data, and assigns weights to the input features. Finally, experimental results based on the data from Citi Bike System in New York City demonstrate that the proposed model achieves a more accurate demand prediction. [ABSTRACT FROM AUTHOR]

The manufacturing sector faces unprecedented challenges, including intense competition, a surge in product varieties, heightened customization demands, and shorter product life cycles. These challenges underscore the critical need to optimize manufacturing systems. Among the most enduring and complex challenges within this domain is production scheduling. In practical scenarios, setup time is whenever a machine transitions from processing one product to another. Job scheduling with setup times or associated costs has garnered significant attention in both manufacturing and service environments, prompting extensive research efforts. While previous studies on customer order scheduling primarily focused on orders or jobs to be processed across multiple machines, they often overlooked the crucial factor of setup time. This study addresses a sequence-dependent bi-criterion scheduling problem, incorporating order delivery considerations. The primary objective is to minimize the linear combination of the makespan and the sum of weighted completion times of each order. To tackle this intricate challenge, we propose pertinent dominance rules and a lower bound, which are integral components of a branch-and-bound methodology employed to obtain an exact solution. Additionally, we introduce a heuristic approach tailored to the problem's unique characteristics, along with three refined variants designed to yield high-quality approximate solutions. Subsequently, these three refined approaches serve as seeds to generate three distinct populations or chromosomes, each independently employed in a genetic algorithm to yield a robust approximate solution. Ultimately, we meticulously assess the efficacy of each proposed algorithm through comprehensive simulation trials., Competing Interests: The authors declare there are no competing interests., (©2024 Xu et al.)