The proliferation of e-commerce in recent years has been driven in part by the increasing ease of making purchases online and having them delivered directly to the consumer. However, these last-mile delivery logistics have become complex due to external factors (traffic, weather, etc.) affecting the delivery routes’ optimization. Intelligent Transportation Systems (ITS) also have a challenge that contributes to the need of delivery companies for traffic sensors in urban areas. The main purpose of this paper is to propose a framework that closes the gap on accurate traffic prediction tailored for last-mile delivery logistics, leveraging social media analysis along with traditional methods. This work can be divided into two stages: (1) traffic prediction, which utilizes advanced deep learning techniques such as Graph Convolutional and Long-Short Term Memory Neural Networks, as well as data from sources such as social media check-ins and Collaborative Innovation Networks (COINs); and (2) experimentation in both short- and long-term settings, examining the interactions of traffic, social media, weather, and other factors within the model. The proposed framework allows for the integration of additional analytical techniques to further enhance vehicle routing, including the use of simulation tools such as agent-based simulation, discrete-event simulation, and system dynamics.
Multi-Resolution Modeling (MRM) is a modeling technology that creates a model that expresses the same phenomenon at more than two different resolutions. Since the advent of distributed simulation systems, the MRM study began in the military field, where the modeling and simulation (M&S) was most actively developed and was recognized as an essential area in the integrated system of live, virtual and constructive (LVC) simulations. Models of the various resolutions had already been built based on the characteristics and training purposes of each weapon system, and the interoperability of these models was a primary task in the M&S community. In this study, we report the results from a systematic review of the MRM to address two questions: (1) What research has been done towards the MRM for integrating LVC system? (2) What are the research and technology challenges for the MRM implementation in the future? In total, 22 papers have been identified and studied in this review by following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. The structures of the significant 20 MRM implementation experiments in those papers are analyzed based on the relationship between the MRM and integrating the LVC system being implemented in the military. We explored the various issues related to the MRM. Then, we discussed the direction in which the MRM should move forward, comparing civilian modeling techniques with those being used in the military.
Multiple-resolution modeling (MRM) has emerged as a foundational paradigm in modern simulation, enabling the integration of models with varying levels of granularity to address complex and evolving operational demands. By supporting seamless transitions between high-resolution and low-resolution representations, MRM facilitates scalability and interoperability, particularly within distributed simulation environments such as military command and control systems. This paper provides a structured review and comparative analysis of prominent MRM methodologies, including multi-resolution entities (MRE), agent-based modeling (from a federation viewpoint), hybrid frameworks, and the novel MR mode, synchronizing resolution transitions with time advancement and interaction management. Each approach is evaluated across critical dimensions such as consistency, computational efficiency, flexibility, and integration with legacy systems. Emphasis is placed on the applicability of MRM in distributed military simulations, where it enables dynamic interplay between strategic-level planning and tactical-level execution, supporting real-time decision-making, mission rehearsal, and scenario-based training. The paper also explores emerging trends involving artificial intelligence (AI) and large language models (LLMs) as enablers for adaptive resolution management and automated model interoperability.
Multiple resolution modeling (MRM) is the future of distributed simulation. This article describes different definitions and notions related to MRM. MRM is a relatively new research area, and there is a demand for simulator integration from a modeling complexity point of view. This article also analyzes a taxonomy based on the experience of the researchers in detail. Finally, an example that uses the high-level architecture (HLA) is explained to illustrate the above definitions and, in particular, to look at the problems that are common to these distributed simulation configurations. The steps required to build an MRM distributed simulation system are introduced. The conclusions describe the lessons learned for this unique form of distributed simulation.