Data Modeling of Cities, a Machine Learning Application

Design Thinking: A Tool to Solve Challenging Problems

Evolution of urban land and population system coupling micro–dynamics and macro-stability: Trends and paths

The 2015 New York City Legionnaires' Disease Outbreak: A Case Study on a History-Making Outbreak.

With the rapid development of information technology and the popularity of the Internet, the era of big data has come. The urban traffic system continuously generates a large amount of traffic data, which are so large and diverse that the traditional data processing methods have been unable to effectively process and analyze them. Therefore, it is necessary to process and analyze urban traffic data with the help of emerging big data technologies and methods. Starting from introducing the characteristics of big data visualization platforms and common big data visualization tools and technologies, the article analyzes the scale and characteristics of urban traffic data and the limitations of traditional data analysis methods, discusses the advantages and application prospects of visualization platforms, and focuses on the four perspectives of data cleaning and pre-processing, traffic flow and congestion analysis, traffic behavior and trend analysis, traffic simulation, and planning support. The application of big data visualization platforms in urban traffic data analysis is discussed.

Regional complex system simulation optimization through linking governance and environment performance: A case study of water environmental carrying capacity based on the SDES model

This paper puts forward some reflections on the great change of thoughts and mythologies in urban design by technological breakthrough an presents the application of artificial intelligence in urban design. Firstly, it reviews and rethinks on the traditional philosophical bases and original thinking paradigms in urban design, facing up to the limitations and problems of existing design methods. Then by using philosophy of new materialism, new technologies such as machine learning and new data represented by multi-source urban data those having emerged in recent years in order to clarify the possibility of new technologies for urban analysis and design simulation. In particular, convolution neural network has been used to make a large-scale and fine discriminant on the style of urban texture and land use classification. Finally, based on discussions, the paper further clarifies the main direction of current research, which is the possibility of artificial intelligence intervening in urban complex systems and new technologies for urban analysis, designs and simulations. The authors believe that these explorations not only provide more accurate and intuitive analysis in research methods, but also provide the possibility to innovate existing design thoughts and methods by applying artificial intelligence technology to serve urban design research.

Local and global business interests assemble images of neighbourhoods from localised knowledge, including disparate forms of public data such as reviews, blog posts, and open data from municipalities and other organisations. (In)visible forms of working with and worrying about neighbourhood data can be understood as an engagement with the neighbourhood's reputation, or rather its symbolic trajectory: a set of tangible and intangible indicators through which an urban space is known and treated accordingly over time. This paper addresses ethical concerns that emerge from contemporary datafied urban ethnography. We consider a combination of large-scale and bespoke, quantitative, and qualitative analyses of available sources with sustained ethnographic engagement with a Dutch neighbourhood coping with a troubled reputation. While the latter activities can mitigate ethical issues stemming from the former, ethnography in turn raises further concerns of exploitation and risk exposure and should not be treated as a kind of 'ethical panacea' for big, open, or public data projects. A multifaceted and interrogative approach to data collection may offer a more rounded account of contemporary urban data practices by drawing upon distinct and possibly conflicting accounts of social life. The challenge is to prioritise under-represented and otherwise marginalised voices in both the design and the dissemination of research on urban data analytics.

For All White-Collar Workers: The Possibilities of Radicalism in New York City's Department Store Unions, 1934–1953. Daniel J. Opler. Columbus, OH: The Ohio State University Press, 2007, pp. 304, C...

Gender gap generators for bike share ridership: Evidence from Citi Bike system in New York City

The city is a growing centre of humanitarian concern. Yet, aid agencies, governments and donors are only beginning to comprehend the scale and, importantly, the complexity of the humanitarian challenge in urban areas. Using the case study of the Kathmandu Valley, Nepal, this paper examines the analytical utility of recent research on complex urban systems in strengthening scholarly understanding of urban disaster risk management, and outlines its operational relevance to disaster preparedness. Drawing on a literature review and 26 interviews with actors from across the Government of Nepal, the International Red Cross and Red Crescent Movement, non-governmental organisations, United Nations agencies, and at-risk communities, the study argues that complexity can be seen as a defining feature of urban systems and the risks that confront them. To manage risk in these systems effectively, preparedness efforts must be based on adaptive and agile approaches, incorporating the use of network analysis, partnerships, and new technologies.

Current urban agenda is interested in developing urban strategies to enhance urban resilience for cities. This paper examines the concept of urban resilience applied in the context of urban planning with specific attention to which are the capacities that make urban systems resilient. The knowledge and the understanding of these capacities are fundamental to set up suitable strategies. However, only few frameworks consider urban resilience and its capacity within the complexity of urban system. Through an in-depth literature review, this paper aims at providing a methodological framework both to recognize these capacities and analyze which are the main factors that mainly contribute to the achievement of these ability. The paper illustrates the first step of the application of a System Dynamics approach to analyze the redundancy capacity in order to define which are the key variables to enhance this capacity and also to determine which can be the impacts on the urban systems as a whole of the redundancy.

Predicting hourly origin–destination demand in bike sharing systems using hurdle models: Lisbon case study

Simulated Kalman Filter (SKF) is a population-based optimizer introduced in 2015 that is based on Kalman filtering, which consists of prediction, measurement, and estimation processes. The original SKF algorithm employs synchronous update mechanism in which the agents in SKF update their solutions after all fitness calculations, prediction process, and measurement process are completed. An alternative to synchronous update is asynchronous update. In asynchronous update, only one agent does fitness calculation, prediction, measurement, and estimation processes at one time. In this study, synchronous and asynchronous mechanisms are combined in SKF. At first, the SKF starts with synchronous update. If no improved solution is found, the SKF changes its update mechanism. Using the CEC2014 benchmark test suite, experimental results indicate that the proposed adaptive switching synchronous-asynchronous SKF outperforms the original SKF significantly.

The project aims to investigate the possibility of VR in a combination of visualizing high-dimensional urban data. Our study proposes a data-based tool for urban planners, architects, and researchers to 3D visualize and experience an urban quarter. Users have a possibility to choose a specific part of a city according to urban data input like buildings, streets, and landscapes. This data-based tool is based on an algorithm to translate data from Shapefiles (.sh) in a form of a virtual cube model. The tool can be scaled and hence applied globally. The goal of the study is to improve understanding of the connection and analysis of high-dimensional urban data beyond a two-dimensional static graph or three-dimensional image. Professionals may find an optimized condition between urban data through abstract simulation. By implementing this tool in the early design process, researchers have an opportunity to develop a new vision for extending and optimizing urban materials.

Clustering bike sharing stations using Quantum Machine Learning: A case study of Toronto, Canada