English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Past decades saw the rapid development of cities and the boom of urban population, but also the rise of many urban issues, such as traffic congestion, energy shortage, and pollution. The situation is continuing: as predicted by the United Nations, the world’s urban population will add another 2.5 billion by 2050, an increase of 66% over today’s total population. While the pressure on resources is unprecedented, increasing volume and diversity of data is at the same time being generated and collected with the help of new technologies. This calls for the integration of advanced information and computational technologies to develop intelligent solutions for urban issues. Indeed, there has been a variety of research in the AI community, pioneering in applying AI and data science to the practice of urban computing [1, 2]. These include the development of smart communities, smart home automation, intelligent transport systems, smart vehicle sharing systems, data-driven routing systems, smart grids, and smart energy solutions. One important branch of research on urban intelligence is a model-based approach (or AIbased approach) in which researchers are looking at various decision-making issues (e.g., planning, scheduling) in the urban domain, assuming the knowledge about the model is available or can be estimated. One example is to provide optimal policies for the government in consideration of people’s strategic behavior such as optimal pricing of taxi systems [3], optimal placement andmanagement of EV charging stations [4–5], and disaster response [6]. It is often very challenging to solve such decision-making problems due to the existence of many complex interdependent factors, many strategic players (e.g., people) with conflicting preferences, multi-level optimization, uncertainty about the environment, sequential decision making, and large (even infinite) strategy space. Another important branch of research focuses on urban intelligence—a data-driven approach in which researchers use real-world urban data to discover patterns, model behaviors, and predict the future. For example, patterns detected from human mobility data can be used to understand personal interests [7], discover urban functions [8], infer social relationships [9], and estimate air pollution [10]. The urban data cover a wide range of datasets collected from different sources, e.g., taxi trips, mobile phone locations, geotagged tweets, Points-of-Interest (POIs), household energy consumption, and sensor data from cyber physical systems. While each dataset has its own characteristics, there is an increasing trend on how to fuse the data collected from different sources and discover the patterns in a more holistic way [11], e.g., how to integrate trajectories with surrounding contexts to semantically understand human mobility [7] and how to utilize cross-domain data to estimate air quality [10]. The objective of this special issue is to highlight leading work in urban intelligence, to identify challenges, and to explore future topics in this area. The call for papers of this special issue was perceived very positively with 73 regular submissions, and 15 papers were finally accepted through a rigorous review process. The acceptance rate was therefore 20%. All articles are briefly presented in the following.

ACM TIST Special Issue on Urban Intelligence