Smartphones play a fundamental role in today's technologically-advanced community allowing people... more Smartphones play a fundamental role in today's technologically-advanced community allowing people to communicate (almost) anywhere in the world and share all kinds of contextual information (e.g., location and opinion). They are being manufactured with an increasing number of powerful embedded sensors of different categories (e.g., acoustic, sound, GPS), enabling a variety of new applications and services. Indeed, smartphones are being used for many personal sensing applications, such as for monitoring physical exercises, and for wide participatory sensing applications, which are not limited to a particular individual (e.g., traffic conditions and noise pollution) [Silva et al. 2013b]. Participatory sensing aims at monitoring large scale phenomena and require the active involvement of people to voluntarily share contextual information and/or make their sensed data available. Participatory sensing finds an effective platform for large scale reach in the increasing popularity of location-based social media applications, such as Instagram and Foursquare, which combine the features of online social networks with location-based services. These applications enable the observations of the actions of hundreds millions of people in large scale urban areas in (near) real time and over extended periods of time. This opens an unprecedented opportunity to revolutionize the way social science is done. Unlike traditional methods that rely on survey data, new techniques can be designed to exploit participatory data, which is much cheaper, more dynamic as it reflects current situations in (near) real time, and, more important, can easily reach planetary scale. Moreover, as we argue here, such participatory sensing applications have the potential to be a fundamental tool to better understand human urban interaction, leveraging our awareness to different aspects of our lives in urban scenarios.
This paper elaborates a multi-model approach to studying how local scenes change. We refer to thi... more This paper elaborates a multi-model approach to studying how local scenes change. We refer to this as the "4 D's" of scene change: development, differentiation, defense, and diffusion. Each posits somewhat distinct change processes, and has its own tradition of theory and empirical research, which we briefly review. After summarizing some major trends in scenes and amenities in the US context, for each change model, we present some initial findings, discussing data and methods throughout. Our overall goal is to point toward new research arcs on change models of scenes, and to give some clear examples and directions for how to think about and collect data to understand what makes some scenes change, others not, why, and in what directions.
Politics in different countries show diverse degrees of polarization, which tends to be stronger ... more Politics in different countries show diverse degrees of polarization, which tends to be stronger on social media, given how easy it became to connect and engage with like-minded individuals on the web. A way of reducing polarization would be by distributing cross-partisan news among individuals with distinct political orientations, i.e., “reaching the bubbles”. This study investigates whether this holds in the context of nationwide elections in Brazil and Canada. We collected politics-related tweets shared during the 2018 Brazilian presidential election and the 2019 Canadian federal election. Next, we proposed an updated centrality metric that enables identifying highly central bubble reachers, nodes that can distribute content among users with diverging political opinions—a fundamental metric for the proposed study. After that, we analyzed how users engage with news content shared by bubble reachers, its source, and its topics, considering its political orientation. Among other res...
Anais do XXXVII Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos (SBRC 2019), 2019
Considerando o crescente número de veículos nas cidades, aplicações capazes de informar a situaçã... more Considerando o crescente número de veículos nas cidades, aplicações capazes de informar a situação do tráfego nas vias se tornam mais utilizadas. Essas aplicações tem o objetivo de sugerir rotas, considerando congestionamentos e acidentes, identificados através de sensoriamento participativo. No entanto, existem outros problemas encontrados durante um percurso que afetam diretamente o usuário, como por exemplo, a criminalidade em uma determinada região. As regiões afetadas por uma alta incidência criminal podem evoluir durante o dia, dependendo do tipo do crime e da densidade de pessoas em uma determinada região. Portanto, esse trabalho tem o objetivo de propor um serviço capaz de identificar áreas com alta incidência criminal, levando em consideração a evolução do cenário, e sugerir rotas seguras que evitam essas regiões. A solução proposta permite obter uma rota mais segura sem comprometer o tempo do percurso, além disso, os resultados encontrados proporcionam verificar a capacida...
... Vinıcius FS Mota1, Thiago H. Silva1, José Marcos Silva Nogueira1 ... O modelo de mobilidade R... more ... Vinıcius FS Mota1, Thiago H. Silva1, José Marcos Silva Nogueira1 ... O modelo de mobilidade Reference Point Group (RPGM) representa o movimento aleatório de grupos de nós, sendo utilizado para simular cenários de emergência como campos de batalha e catástrofes ...
Nowadays, there is a shortage of real mobility data openly available. Thus, several works in the ... more Nowadays, there is a shortage of real mobility data openly available. Thus, several works in the literature generate synthetic mobility, which does not represent real mobility. Some of these works use contextual data to propose route recommendations but do not study the behavior of such data. In addition, the impact of each contextual data type changes according to the user's profile. To solve the problems mentioned above, CERVA is proposed, a contextual routing solution for vehicles with space-time risk. CERVA consists of three modules: contextual window identification, context mapping, and routing customization. The evaluation results show that CERVA recommends the best routes according to the user's profile. Resumo. Nos dias atuais existe uma escassez de dados de mobilidade reais disponíveis abertamente. Sendo assim, diversos trabalhos da literatura geram mobilidade sintética a qual não representa a mobilidade real. Alguns desses trabalhos fazem o uso de dados contextuais para propor recomendação de rotas, no entanto não estudam o comportamento de tais dados. Além disso, o impacto de cada tipo de dado contextual muda de acordo com o perfil do usuário. Para resolver os problemas citados anteriormenteé proposto o CERVA, uma solução de roteamento contextual para veículos com risco espaço-temporal. O CERVAé composto por três módulos, sendo: identificação das janelas contextuais, mapeamento de contexto, e personalização do roteamento. Os resultados da avaliação mostram que o CERVA recomenda as melhores rotas de acordo com o perfil do usuário.
Understand the time interval that an event is contained is key for different decision making serv... more Understand the time interval that an event is contained is key for different decision making services. For instance, a secure route suggestion needs crime data to identify crime hotspots inside a time window and select safe routes. Time windows help to separate distinct situations and focus the analysis within a time interval. Also, the result may provide an insight into the changes that occur during the day. With this in mind, this paper presents an approach to identify mobile and variable time windows with the goal of discovering hotspots, named MARTINI. The hotspots may be used by different types of services that want the granularity applied in this paper. The data is fragmented with the objective to identify the situation according to each day of the week, data type, and more. MARTINI utilizes a Gaussian Distribution Function to describe the event density of different data types and time intervals. In addition, it uses this representation to find out the changes that occur during the day. The results obtained show that MARTINI requires less time to recognize changes in the situation with a 10 minute sensitivity. In addition, it outperforms the smaller time window even with a 2 hour interval.
Sensor networks, connected vehicles and mobile devices are currently used as data collectors in u... more Sensor networks, connected vehicles and mobile devices are currently used as data collectors in urban environments, data which can be used to better understand the cities' dynamics. Specifically, the study of data-driven solutions to understand the behavior of cities and propose services to enhance the experiences of the citizens in their everyday life has become an active research topic. Many studies in this topic focus on exploring single data sources, and, to tackle this limitation we propose the SMAFramework to collect and integrate urban mobility data from heterogeneous sources. In this work, we propose a methodology that enables the standardization of spatiotemporal annotated data from sources such as Sensor Networks, Vehicular Networks, Social Media and the Web over a single data model (i.e., a Multi-Aspect Graph) and perform different analyses, such as the identification of taxi demand. To show the potential of this framework, we built and assessed a tool to evaluate spatiotemporal correlation of urban data from different sources. Real data collected from social media and a taxi system of the city of New York are used to evaluate this method. The obtained results allowed us to understand some of the applicabilities of the SMAFramework and also provided some insights on how to use it to resolve specific problems when analyzing mobility in urban environments. Using this methodology, we can obtain a better taxi positioning within the city by employing social media data.
In this study we evaluate a methodology for identifying cultural boundaries, which explores users... more In this study we evaluate a methodology for identifying cultural boundaries, which explores users' drink and food preferences extracted from the Social Web. We focus mainly on the better understanding of the importance of the time dimension on that methodology. Our results indicate that, in fact, take the time dimension into account helps to increase the precision of the results. Automatic identification of cultural differences might be useful to complement large-scale studies on cultural differences, process that can be costly using traditional methods, such as questionnaires. Besides that, it can help the development of new ubiquitous applications and services for the Social Web.
The dynamics of cities have been studied over the years with various applications such as urban p... more The dynamics of cities have been studied over the years with various applications such as urban planning, disease propagation, traffic forecasting, local recommendations and studies of human social behavior. However, with the technological evolution, especially the popularization of smartphones and the Internet, a new opportunity is presented to carry out such studies: the use of social media data for the population study. In this context, this paper aims to present a new way to compare cities, using as similarity measure of the pattern of social mobility of its inhabitants. To validate the study, 1,601,323 Foursquare check-ins were used spread over 10 cities in a period of 33 days.
This paper is part IV of “towards a model of urban evolution”. It demonstrates how the Toronto Ur... more This paper is part IV of “towards a model of urban evolution”. It demonstrates how the Toronto Urban Evolution Model (TUEM) can be used to encode city data, illuminate key features, demonstrate how formetic distance can be used to discover how spatial areas change over time, and identify similar spatial areas within and between cities. The data used in this study are reviews from Yelp. Each review can be interpreted as a formeme where the category of the business is a form, the reviewer is a group and the review is an activity. Yelp data from neighbourhoods in both Toronto and Montreal are encoded. A method for aggregating reviewers into groups with multiple members is introduced. Longitudinal analysis is performed for all Toronto neighbourhoods. Transversal analysis is performed between neighbourhoods within Toronto and between Toronto and Montreal. Similar neighbourhoods are identified validating formetic distance.
O livro Minicursos do XXXV Simposio Brasileiro de Redes de Computadores e Sistemas Distribuidos c... more O livro Minicursos do XXXV Simposio Brasileiro de Redes de Computadores e Sistemas Distribuidos contem os minicursos selecionados para apresentacao no XXXV Simposio Brasileiro de Redes de Computadores e Sistemas Distribuidos (SBRC), realizado em Belem-PA, entre os dias 15 e 19 de maio de 2017. O Livro dos Minicursos do SBRC tem sido tradicionalmente utilizado como material de estudo de alta qualidade por alunos de graduacao e pos-graduacao, bem como por profissionais da area. As sessoes de apresentacoes dos minicursos sao tambem uma importante oportunidade para atualizacao de conhecimentos da comunidade cientifica e para complementacao da formacao dos participantes. O principal objetivo dos Minicursos do SBRC e oferecer treinamento e atualizacao de curto prazo em temas normalmente nao cobertos nas grades curriculares e que possuem grande interesse entre academicos e profissionais.
In this study we evaluate a methodology for identifying cultural boundaries, which explores users... more In this study we evaluate a methodology for identifying cultural boundaries, which explores users' drink and food preferences extracted from the Social Web. We focus mainly on the better understanding of the importance of the time dimension on that methodology. Our results indicate that, in fact, take the time dimension into account helps to increase the precision of the results. Automatic identification of cultural differences might be useful to complement large-scale studies on cultural differences, process that can be costly using traditional methods, such as questionnaires. Besides that, it can help the development of new ubiquitous applications and services for the Social Web.
Proceedings of the 20th ACM International Conference on Modelling, Analysis and Simulation of Wireless and Mobile Systems, 2017
Smart cities emerge in computer science as a topic to cover how the technology of information and... more Smart cities emerge in computer science as a topic to cover how the technology of information and communication can be used in the urban centers to monitor its dynamics and allow the improvement of services for the citizens. In these urban centers, different methodologies are used in order to collect data and provide them to applications. These data come from several heterogeneous sources, thus there is an effort to integrate and standardize them before their use. Also, a significant amount of this data has spatio-temporal annotations, which may be used to analyze the city dynamics, such as the mobility flow. Due to these characteristics of the data generated in urban centers, and also the possibilities brought by their use and analyses, this work presents a novel approach to collect, integrate and perform some analysis tasks in mobility data from smart cities. Thus, the SMAFramework can analyze mobility patterns based on a Multi-Aspect Graph (MAG) data structure. To show the potential of the framework, it is proposed a method to analyze the saptiotemporal correlation between data from two different data sources in the same city. Real data collected from social media and a taxi system of the city of New York are used to evaluate this method. The obtained results allowed to understand some of the applicabilities of the framework and also provided some insights on how to use the framework to resolve specific problems when analyzing mobility in urban environments.
Urban computing is a field of study that among others objectives aims to help understand urban ph... more Urban computing is a field of study that among others objectives aims to help understand urban phenomenon envisioning to offer smarter urban services. Thus, an important aspect is the comprehension of functioning dynamics of businesses in the city. Performing this comprehension through time allows us, for instance, to use this information as a business descriptor that could be explored in new services. In this study, we collected and used a significant amount of data for business related to consumption of food and beverage in different cities in Brazil and the United States. Our main contributions are: (1) clustering and analysis of the collected time series representing the functioning dynamics of business in the city; (2) approach for identifying the signature that represents the behavior of certain categories of venues; (3) training and evaluation of an inference model for categories of establishments. Resumo. A computação urbana é uma área de estudo que visa, dentre outros objet...
The growing of cities has resulted in innumerable technical and managerial challenges for public ... more The growing of cities has resulted in innumerable technical and managerial challenges for public administrators such as energy consumption, pollution, urban mobility and even supervision of private and public spaces in an appropriate way. Urban Computing emerges as a promising paradigm to solve such challenges, through the extraction of knowledge, from a large amount of heterogeneous data existing in urban space. Moreover, Urban Computing correlates urban sensing, data management, and analysis to provide services that have the potential to improve the quality of life of the citizens of large urban centers. Consider this context, this chapter aims to present the fundamentals of Urban Computing and the steps necessary to develop an application in this area. To achieve this goal, the following questions will be investigated, namely: (i) What are the main research problems of Urban Computing?; (ii) What are the technological challenges for the implementation of services in Urban Computi...
Participatory sensing systems (PSS) have the potential to become fundamental tools for supporting... more Participatory sensing systems (PSS) have the potential to become fundamental tools for supporting the study, in large scale, of urban social behavior and city dynamics. To that end, this work characterizes the photo sharing system Instagram, considered one of the currently most popular PSSs on the Internet. Based on a dataset of approximately 2.3 million shared photos, we characterize user behavior in the system showing that there are several advantages and opportunities for large scale sensing, such as a global coverage at low cost, but also challenges, such as a very unequal photo sharing frequency, both spatially and temporally. Moreover, we present an application based on data obtained from Instagram to identify regions of interest in a city, which illustrates the promising potential of PSSs for the study of city dynamics.
Smartphones play a fundamental role in today's technologically-advanced community allowing people... more Smartphones play a fundamental role in today's technologically-advanced community allowing people to communicate (almost) anywhere in the world and share all kinds of contextual information (e.g., location and opinion). They are being manufactured with an increasing number of powerful embedded sensors of different categories (e.g., acoustic, sound, GPS), enabling a variety of new applications and services. Indeed, smartphones are being used for many personal sensing applications, such as for monitoring physical exercises, and for wide participatory sensing applications, which are not limited to a particular individual (e.g., traffic conditions and noise pollution) [Silva et al. 2013b]. Participatory sensing aims at monitoring large scale phenomena and require the active involvement of people to voluntarily share contextual information and/or make their sensed data available. Participatory sensing finds an effective platform for large scale reach in the increasing popularity of location-based social media applications, such as Instagram and Foursquare, which combine the features of online social networks with location-based services. These applications enable the observations of the actions of hundreds millions of people in large scale urban areas in (near) real time and over extended periods of time. This opens an unprecedented opportunity to revolutionize the way social science is done. Unlike traditional methods that rely on survey data, new techniques can be designed to exploit participatory data, which is much cheaper, more dynamic as it reflects current situations in (near) real time, and, more important, can easily reach planetary scale. Moreover, as we argue here, such participatory sensing applications have the potential to be a fundamental tool to better understand human urban interaction, leveraging our awareness to different aspects of our lives in urban scenarios.
This paper elaborates a multi-model approach to studying how local scenes change. We refer to thi... more This paper elaborates a multi-model approach to studying how local scenes change. We refer to this as the "4 D's" of scene change: development, differentiation, defense, and diffusion. Each posits somewhat distinct change processes, and has its own tradition of theory and empirical research, which we briefly review. After summarizing some major trends in scenes and amenities in the US context, for each change model, we present some initial findings, discussing data and methods throughout. Our overall goal is to point toward new research arcs on change models of scenes, and to give some clear examples and directions for how to think about and collect data to understand what makes some scenes change, others not, why, and in what directions.
Politics in different countries show diverse degrees of polarization, which tends to be stronger ... more Politics in different countries show diverse degrees of polarization, which tends to be stronger on social media, given how easy it became to connect and engage with like-minded individuals on the web. A way of reducing polarization would be by distributing cross-partisan news among individuals with distinct political orientations, i.e., “reaching the bubbles”. This study investigates whether this holds in the context of nationwide elections in Brazil and Canada. We collected politics-related tweets shared during the 2018 Brazilian presidential election and the 2019 Canadian federal election. Next, we proposed an updated centrality metric that enables identifying highly central bubble reachers, nodes that can distribute content among users with diverging political opinions—a fundamental metric for the proposed study. After that, we analyzed how users engage with news content shared by bubble reachers, its source, and its topics, considering its political orientation. Among other res...
Anais do XXXVII Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos (SBRC 2019), 2019
Considerando o crescente número de veículos nas cidades, aplicações capazes de informar a situaçã... more Considerando o crescente número de veículos nas cidades, aplicações capazes de informar a situação do tráfego nas vias se tornam mais utilizadas. Essas aplicações tem o objetivo de sugerir rotas, considerando congestionamentos e acidentes, identificados através de sensoriamento participativo. No entanto, existem outros problemas encontrados durante um percurso que afetam diretamente o usuário, como por exemplo, a criminalidade em uma determinada região. As regiões afetadas por uma alta incidência criminal podem evoluir durante o dia, dependendo do tipo do crime e da densidade de pessoas em uma determinada região. Portanto, esse trabalho tem o objetivo de propor um serviço capaz de identificar áreas com alta incidência criminal, levando em consideração a evolução do cenário, e sugerir rotas seguras que evitam essas regiões. A solução proposta permite obter uma rota mais segura sem comprometer o tempo do percurso, além disso, os resultados encontrados proporcionam verificar a capacida...
... Vinıcius FS Mota1, Thiago H. Silva1, José Marcos Silva Nogueira1 ... O modelo de mobilidade R... more ... Vinıcius FS Mota1, Thiago H. Silva1, José Marcos Silva Nogueira1 ... O modelo de mobilidade Reference Point Group (RPGM) representa o movimento aleatório de grupos de nós, sendo utilizado para simular cenários de emergência como campos de batalha e catástrofes ...
Nowadays, there is a shortage of real mobility data openly available. Thus, several works in the ... more Nowadays, there is a shortage of real mobility data openly available. Thus, several works in the literature generate synthetic mobility, which does not represent real mobility. Some of these works use contextual data to propose route recommendations but do not study the behavior of such data. In addition, the impact of each contextual data type changes according to the user's profile. To solve the problems mentioned above, CERVA is proposed, a contextual routing solution for vehicles with space-time risk. CERVA consists of three modules: contextual window identification, context mapping, and routing customization. The evaluation results show that CERVA recommends the best routes according to the user's profile. Resumo. Nos dias atuais existe uma escassez de dados de mobilidade reais disponíveis abertamente. Sendo assim, diversos trabalhos da literatura geram mobilidade sintética a qual não representa a mobilidade real. Alguns desses trabalhos fazem o uso de dados contextuais para propor recomendação de rotas, no entanto não estudam o comportamento de tais dados. Além disso, o impacto de cada tipo de dado contextual muda de acordo com o perfil do usuário. Para resolver os problemas citados anteriormenteé proposto o CERVA, uma solução de roteamento contextual para veículos com risco espaço-temporal. O CERVAé composto por três módulos, sendo: identificação das janelas contextuais, mapeamento de contexto, e personalização do roteamento. Os resultados da avaliação mostram que o CERVA recomenda as melhores rotas de acordo com o perfil do usuário.
Understand the time interval that an event is contained is key for different decision making serv... more Understand the time interval that an event is contained is key for different decision making services. For instance, a secure route suggestion needs crime data to identify crime hotspots inside a time window and select safe routes. Time windows help to separate distinct situations and focus the analysis within a time interval. Also, the result may provide an insight into the changes that occur during the day. With this in mind, this paper presents an approach to identify mobile and variable time windows with the goal of discovering hotspots, named MARTINI. The hotspots may be used by different types of services that want the granularity applied in this paper. The data is fragmented with the objective to identify the situation according to each day of the week, data type, and more. MARTINI utilizes a Gaussian Distribution Function to describe the event density of different data types and time intervals. In addition, it uses this representation to find out the changes that occur during the day. The results obtained show that MARTINI requires less time to recognize changes in the situation with a 10 minute sensitivity. In addition, it outperforms the smaller time window even with a 2 hour interval.
Sensor networks, connected vehicles and mobile devices are currently used as data collectors in u... more Sensor networks, connected vehicles and mobile devices are currently used as data collectors in urban environments, data which can be used to better understand the cities' dynamics. Specifically, the study of data-driven solutions to understand the behavior of cities and propose services to enhance the experiences of the citizens in their everyday life has become an active research topic. Many studies in this topic focus on exploring single data sources, and, to tackle this limitation we propose the SMAFramework to collect and integrate urban mobility data from heterogeneous sources. In this work, we propose a methodology that enables the standardization of spatiotemporal annotated data from sources such as Sensor Networks, Vehicular Networks, Social Media and the Web over a single data model (i.e., a Multi-Aspect Graph) and perform different analyses, such as the identification of taxi demand. To show the potential of this framework, we built and assessed a tool to evaluate spatiotemporal correlation of urban data from different sources. Real data collected from social media and a taxi system of the city of New York are used to evaluate this method. The obtained results allowed us to understand some of the applicabilities of the SMAFramework and also provided some insights on how to use it to resolve specific problems when analyzing mobility in urban environments. Using this methodology, we can obtain a better taxi positioning within the city by employing social media data.
In this study we evaluate a methodology for identifying cultural boundaries, which explores users... more In this study we evaluate a methodology for identifying cultural boundaries, which explores users' drink and food preferences extracted from the Social Web. We focus mainly on the better understanding of the importance of the time dimension on that methodology. Our results indicate that, in fact, take the time dimension into account helps to increase the precision of the results. Automatic identification of cultural differences might be useful to complement large-scale studies on cultural differences, process that can be costly using traditional methods, such as questionnaires. Besides that, it can help the development of new ubiquitous applications and services for the Social Web.
The dynamics of cities have been studied over the years with various applications such as urban p... more The dynamics of cities have been studied over the years with various applications such as urban planning, disease propagation, traffic forecasting, local recommendations and studies of human social behavior. However, with the technological evolution, especially the popularization of smartphones and the Internet, a new opportunity is presented to carry out such studies: the use of social media data for the population study. In this context, this paper aims to present a new way to compare cities, using as similarity measure of the pattern of social mobility of its inhabitants. To validate the study, 1,601,323 Foursquare check-ins were used spread over 10 cities in a period of 33 days.
This paper is part IV of “towards a model of urban evolution”. It demonstrates how the Toronto Ur... more This paper is part IV of “towards a model of urban evolution”. It demonstrates how the Toronto Urban Evolution Model (TUEM) can be used to encode city data, illuminate key features, demonstrate how formetic distance can be used to discover how spatial areas change over time, and identify similar spatial areas within and between cities. The data used in this study are reviews from Yelp. Each review can be interpreted as a formeme where the category of the business is a form, the reviewer is a group and the review is an activity. Yelp data from neighbourhoods in both Toronto and Montreal are encoded. A method for aggregating reviewers into groups with multiple members is introduced. Longitudinal analysis is performed for all Toronto neighbourhoods. Transversal analysis is performed between neighbourhoods within Toronto and between Toronto and Montreal. Similar neighbourhoods are identified validating formetic distance.
O livro Minicursos do XXXV Simposio Brasileiro de Redes de Computadores e Sistemas Distribuidos c... more O livro Minicursos do XXXV Simposio Brasileiro de Redes de Computadores e Sistemas Distribuidos contem os minicursos selecionados para apresentacao no XXXV Simposio Brasileiro de Redes de Computadores e Sistemas Distribuidos (SBRC), realizado em Belem-PA, entre os dias 15 e 19 de maio de 2017. O Livro dos Minicursos do SBRC tem sido tradicionalmente utilizado como material de estudo de alta qualidade por alunos de graduacao e pos-graduacao, bem como por profissionais da area. As sessoes de apresentacoes dos minicursos sao tambem uma importante oportunidade para atualizacao de conhecimentos da comunidade cientifica e para complementacao da formacao dos participantes. O principal objetivo dos Minicursos do SBRC e oferecer treinamento e atualizacao de curto prazo em temas normalmente nao cobertos nas grades curriculares e que possuem grande interesse entre academicos e profissionais.
In this study we evaluate a methodology for identifying cultural boundaries, which explores users... more In this study we evaluate a methodology for identifying cultural boundaries, which explores users' drink and food preferences extracted from the Social Web. We focus mainly on the better understanding of the importance of the time dimension on that methodology. Our results indicate that, in fact, take the time dimension into account helps to increase the precision of the results. Automatic identification of cultural differences might be useful to complement large-scale studies on cultural differences, process that can be costly using traditional methods, such as questionnaires. Besides that, it can help the development of new ubiquitous applications and services for the Social Web.
Proceedings of the 20th ACM International Conference on Modelling, Analysis and Simulation of Wireless and Mobile Systems, 2017
Smart cities emerge in computer science as a topic to cover how the technology of information and... more Smart cities emerge in computer science as a topic to cover how the technology of information and communication can be used in the urban centers to monitor its dynamics and allow the improvement of services for the citizens. In these urban centers, different methodologies are used in order to collect data and provide them to applications. These data come from several heterogeneous sources, thus there is an effort to integrate and standardize them before their use. Also, a significant amount of this data has spatio-temporal annotations, which may be used to analyze the city dynamics, such as the mobility flow. Due to these characteristics of the data generated in urban centers, and also the possibilities brought by their use and analyses, this work presents a novel approach to collect, integrate and perform some analysis tasks in mobility data from smart cities. Thus, the SMAFramework can analyze mobility patterns based on a Multi-Aspect Graph (MAG) data structure. To show the potential of the framework, it is proposed a method to analyze the saptiotemporal correlation between data from two different data sources in the same city. Real data collected from social media and a taxi system of the city of New York are used to evaluate this method. The obtained results allowed to understand some of the applicabilities of the framework and also provided some insights on how to use the framework to resolve specific problems when analyzing mobility in urban environments.
Urban computing is a field of study that among others objectives aims to help understand urban ph... more Urban computing is a field of study that among others objectives aims to help understand urban phenomenon envisioning to offer smarter urban services. Thus, an important aspect is the comprehension of functioning dynamics of businesses in the city. Performing this comprehension through time allows us, for instance, to use this information as a business descriptor that could be explored in new services. In this study, we collected and used a significant amount of data for business related to consumption of food and beverage in different cities in Brazil and the United States. Our main contributions are: (1) clustering and analysis of the collected time series representing the functioning dynamics of business in the city; (2) approach for identifying the signature that represents the behavior of certain categories of venues; (3) training and evaluation of an inference model for categories of establishments. Resumo. A computação urbana é uma área de estudo que visa, dentre outros objet...
The growing of cities has resulted in innumerable technical and managerial challenges for public ... more The growing of cities has resulted in innumerable technical and managerial challenges for public administrators such as energy consumption, pollution, urban mobility and even supervision of private and public spaces in an appropriate way. Urban Computing emerges as a promising paradigm to solve such challenges, through the extraction of knowledge, from a large amount of heterogeneous data existing in urban space. Moreover, Urban Computing correlates urban sensing, data management, and analysis to provide services that have the potential to improve the quality of life of the citizens of large urban centers. Consider this context, this chapter aims to present the fundamentals of Urban Computing and the steps necessary to develop an application in this area. To achieve this goal, the following questions will be investigated, namely: (i) What are the main research problems of Urban Computing?; (ii) What are the technological challenges for the implementation of services in Urban Computi...
Participatory sensing systems (PSS) have the potential to become fundamental tools for supporting... more Participatory sensing systems (PSS) have the potential to become fundamental tools for supporting the study, in large scale, of urban social behavior and city dynamics. To that end, this work characterizes the photo sharing system Instagram, considered one of the currently most popular PSSs on the Internet. Based on a dataset of approximately 2.3 million shared photos, we characterize user behavior in the system showing that there are several advantages and opportunities for large scale sensing, such as a global coverage at low cost, but also challenges, such as a very unequal photo sharing frequency, both spatially and temporally. Moreover, we present an application based on data obtained from Instagram to identify regions of interest in a city, which illustrates the promising potential of PSSs for the study of city dynamics.
Uploads
Papers by Thiago H Silva