Nycer

City service demand fluctuates across space and time. Although various data, such as 311 hotline data and social media data, have been used to explore the spatiotemporal patterns of city services, data uncertainty and the uneven distribution of service demand are overlooked to some extent and thus could result in bias. To overcome these shortcomings, top‐down collected city service data that fully cover urban areas are used as an emerging data source in this article. A visual analytical approach that employs a three‐dimensional model based on a space‐time cube combined with the Mann–Kendall algorithm is developed and applied in Xicheng District, Beijing, China. The results show that in comparison to other methods, the emerging data and visualization methods have more power to explain city services in terms of overall trends and micro‐scale details. For instance, city service cases demonstrate a significant downward trend. Meanwhile, the distribution of hotspots/coldspots is found to be related to the built environment and population density. For example, high‐incidence cases are located in some communities that are the key governance areas, indicating a demand to increase the staffing of grid administrators. The findings of this work can potentially benefit other cities in China and worldwide.

show abstract

Nycer

Cited by 5 publications

References 14 publications

Wireless Channel Quality Prediction using Sparse Gaussian Conditional Random Fields

Wireless Channel Quality Prediction using Sparse Gaussian Conditional Random Fields

DeepER: A Deep Learning based Emergency Resolution Time Prediction System

Visualizing spatiotemporal patterns of city service demand through a space‐time exploratory approach

Contact Info

Product

Resources

About