关键词: 交通智能卡数据, OD数据, 多元数据, 时空数据, 可视分析

Abstract: Abstract: Integrated Circuit Card can record a resident's mobile travel, reflecting the resident's origin-destination information. The existing spatio-temporal visualization work pays more attention to the movement pattern of residents and the division of urban functional areas, etc. but lacks a more comprehensive analysis of the spatial and temporal characteristics of traffic stations and external multiple environmental data. However, there is a lack of research that more comprehensively analyzes the flow spatio-temporal characteristics of traffic stations and multivariate data. How to extract the flow spatio-temporal characteristics of traffic stations from massive card swipe data and propose an abstract flow visualization method to display multiple spatio-temporal data is a problem that needs to be solved. Therefore, in order to solve the problem that direct visualization of the spatial distribution of large-scale card swiping data is easy to cause visual occlusion, a flow clustering method based on orthogonal non-negative matrix factorization is proposed. This method clusters the card swiping OD data and then visualizes it, which can reduce unnecessary occlusion. Aiming at the problem that it is difficult to combine and analyze multivariate spatiotemporal data types, a site multivariate time series data view is designed. This visualization method encodes the four types of multivariate data of the site flow and air quality, air temperature, relative humidity, and rainfall on the same time series, which improves the spatial rate of the view and can be compared and analyzed. In order to assist users to explore and analyze, an interactive visual analysis system based on OD stream and multivariate data was developed, and a variety of interactive operations were designed to improve the efficiency of user exploration. Finally, the validity of the system is verified based on the Singapore transit data set.

Key words: integrated circuit card, orgin destination data, multivariate data, spatio-temporal data, visual analysis