Many cities and countries strive to create smart transportation systems that use the abundance of multisource and multi-data on transport infrastructure functionality and improve human mobility, interests, and lifestyle. The challenges in a sustainable urban transportation system include behavioral visualization, road behavior classification, anomalies detection, and traffic prediction by the human operator. In this paper, an interactive visual analytics localization mapping framework (IVALMF) has been proposed to enhance the exploration by unified interactive interfaces of historical data and prediction of future traffic. Furthermore, low-cost traffic data analysis is introduced to enhance visual analytics related to analyzing motion and transport systems. Hypothetical information clustering analysis is integrated with IVALMF to enable the exploration, visual detection of rare events, testing hypotheses, and prevention of traffic flow supported by advanced data analytical algorithms of the behavioral similarities among roads. The simulation analysis is performed based on scalability and efficiency, proving the reliability of the proposed framework with 96.17%.

许多城市和国家都在努力创建智能交通系统，利用大量关于交通基础设施功能的多源和多数据，并改善人类的流动性、兴趣和生活方式。可持续城市交通系统面临的挑战包括行为可视化、道路行为分类、异常检测和人类操作员的交通预测。在本文中，提出了一种交互式可视化分析定位映射框架（IVALMF），以通过统一的历史数据交互界面和未来交通预测来增强探索。此外，还引入了低成本交通数据分析，以增强与分析运动和运输系统相关的可视化分析。假设信息聚类分析与 IVALMF 相结合，可以在道路之间行为相似性的高级数据分析算法的支持下进行探索、罕见事件的视觉检测、检验假设和预防交通流。基于可扩展性和效率进行仿真分析，证明了所提出框架的可靠性为 96.17%。