Visual Analytics in Urban Computing: An Overview

Nowadays, various data collected in urban context provide unprecedented opportunities for building a smarter city through urban computing. However, due to heterogeneity, high complexity and large volumes of these urban data, analyzing them is not an easy task, which often requires integrating human perception in analytical process, triggering a broad use of visualization. In this survey, we first summarize frequently used data types in urban visual analytics, and then elaborate on existing visualization techniques for time, locations and other properties of urban data. Furthermore, we discuss how visualization can be combined with automated analytical approaches. Existing work on urban visual analytics is categorized into two classes based on different outputs of such combinations: 1) For data exploration and pattern interpretation, we describe representative visual analytics tools designed for better insights of different types of urban data. 2) For visual learning, we discuss how visualization can help in three major steps of automated analytical approaches (i.e., cohort construction; feature selection & model construction; result evaluation & tuning) for a more effective machine learning or data mining process, leading to sort of artificial intelligence, such as a classifier, a predictor or a regression model. Finally, we outlook the future of urban visual analytics, and conclude the survey with potential research directions.

1 Introduction

With the development of science and technology, urbanization process has been accelerating worldwide, which on one hand improves people's life quality, on the other hand gives rise to serious problems, such as environmental pollution, traffic congestion and ever-increasing energy consumption. As data collection becomes easier and cheaper, a wider variety of big data in urban space, such as human mobility data and air quality data, are generated and become available. These data make it possible to tackle challenges that we are facing and help build smarter cities. For instance, we can analyze urban traffic congestions based on GPS trajectories collected from taxis  [1] and explore causes of air pollution by correlating air quality data with other related data sources, such as road network, traffic, and point of interests (POIs)  [2]. The findings could be used to support decision making and help better formulate city planning for the future. Inspired by the vision of better cities, urban computing has drawn more and more attentions of researchers from different fields, who aim to unlock the power of knowledge from big and heterogeneous data collected in urban context and apply this powerful information to tackle problems challenging us at present [3].