Visual Analytics to Generate Actionable Insights from Massive Public Transport Data

可视化分析从海量公共交通数据中生成可行的见解

• 批准号: 539032-2019
• 负责人: Mondal, Debajyoti
• 金额: $ 1.82万
• 依托单位: University of Saskatchewan
• 依托单位国家: 加拿大
• 项目类别: Engage Grants Program
• 财政年份: 2019
• 资助国家: 加拿大
• 起止时间: 2019-01-01 至 2020-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=681298
• 关键词: Visual; Analytics; Generate; Actionable; Insights

We propose to develop a visual analytics platform integrated with a probabilistic network model based on public transportation information. The platform will help users to gain insights into the public transit service and optimize the transit performances. Saskatoon Transit is continually collecting millions of ridership information through the smart-card (Go-Pass) based fare system. This creates a great opportunity to understand and improve various transportation planning activities. The City is interested in understanding the change in total ridership in different temporal scales, ridership between two city locations, the percentage of pick-ups that were on time, reliability of routes based on travel time, etc. They are also interested in questions such as common routes that people take to travel between pairs of locations and the corresponding ridership, and how a new route can influence the existing system. We plan to tackle these questions through a visual analytics approach which will integrate cutting edge scientific methods to handle the challenges that come with the complexity of temporal networks. We believe that our web platform will be a pioneering example that integrates visual analytics with a probabilistic network model built using historical trip data.Our platform will help Saskatoon Transit to monitor transit service performances and understand the impact of the service changes, and hence, contribute to the economic benefit. Optimized transit planning brings a positive environmental impact and showcasing the service performance to the people improves public satisfaction. We believe our project's success will encourage many other public transit systems to adapt our models and technologies throughout Canada and will greatly help the cities for planning activities.

我们建议开发一个可视化的分析平台，集成了基于公共交通信息的概率网络模型。该平台将帮助用户深入了解公共交通服务并优化交通性能。萨斯卡通交通是不断收集数以百万计的乘客信息，通过智能卡（去通行证）为基础的票价系统。这为理解和改进各种交通规划活动创造了一个很好的机会。城市感兴趣的是了解不同时间尺度下总乘客量的变化，两个城市位置之间的乘客量，准时接载的百分比，基于旅行时间的路线可靠性等，他们还对人们在成对位置之间旅行的常见路线和相应的乘客量等问题感兴趣，以及新路线如何影响现有系统。我们计划通过可视化分析方法来解决这些问题，该方法将整合尖端的科学方法，以应对时间网络复杂性带来的挑战。我们相信，我们的网络平台将是一个开创性的例子，它将可视化分析与使用历史出行数据构建的概率网络模型相结合。我们的平台将帮助萨斯卡通公交公司监控公交服务绩效，了解服务变化的影响，从而为经济效益做出贡献。优化的公交规划带来了积极的环境影响，并向人们展示了服务绩效，提高了公众满意度。我们相信，我们项目的成功将鼓励加拿大各地的许多其他公共交通系统采用我们的模式和技术，并将极大地帮助城市规划活动。