Urban insights: deep learning applied to governance in cities
Urban Insights: deep learning applied to governance in cities
Abstract
Cities in Brazil and around the world need to develop technologically and foster innovation to provide better services to their citizens. According to the United Nations, people living in urban areas worldwide are expected to represent more than 60% of the world's population by 2050 (UNITED NATIONS, 2014), which places greater pressure on public services provided by cities and force them to change and innovate. The data produced by the population and by the operation of public services itself are essential to have a holistic and complete view of the city, raising public governance to a higher level, in which decision making becomes data driven and considers public opinion. One of the most evolving technological developments in recent years for analyzing the vast amount of information generated by the billions of devices connected to the world wide web is Artificial Intelligence. Machine learning systems can be used to identify objects in images, transform speech into texts, search for relevant results, among others; Natural Language Processing (NLP) activities stand out in this group, especially subject categorization, sentiment analysis and language translation. The turning point in the adoption curve of machine learning algorithms in real applications came with the emergence of deep learning techniques. In the past, building such a system required specialized technical knowledge in this area so that learning systems, generally classifiers, could identify patterns from pure past data as inputs (LECUN et al., 2015). With the advent of Deep Learning techniques - which through multiple layers of representation transform pure data into larger, more abstract representations - Artificial Intelligence has become applicable in different areas of science, business, and government. However, even though there have been advances in the application of Artificial Intelligence methods in societal problems, there is a strong lack of technologies for urban services management. Building on the advances made during PIPE Phase 1 and PIPE High Technological Entrepreneur training program, this product development project aims to develop Daoura, a data intelligence platform for smart city management, from the transformation of manifestations of citizens in the Internet into relevant urban insights for understanding city needs and optimizing decision-making on urban issues. All the advances and learning gained from PIPE Phase 1 provided a solid understanding that the technological innovation proposed by the project is feasible and necessary. Once transformed into a marketable and scalable product, Daoura platform can have significant positive impacts on the modernization of urban management when, by understanding citizens in digital media and enabling broad citizen participation in city management from their own urban experiences, decision makers and solution makers, both from the private sector and the public sector, can in fact create environments that promote greater well-being and quality of life in the urban environment, which each day receives more and more people, making the platform an indispensable tool for the development of smart cities globally. (AU)
| Articles published in Agência FAPESP Newsletter about the research grant: |
| More itemsLess items |
| TITULO |
| Articles published in other media outlets ( ): |
| More itemsLess items |
| VEICULO: TITULO (DATA) |
| VEICULO: TITULO (DATA) |