Matrix Factorization Techniques for Recommender Systems

Environment and Planning B: Planning and Design

: The recent availability of geo-tagged images and rich geospatial data has inspired a number of algorithms for image based geolocalization. Most approaches predict the location of a query image by matching to ground-level images with known locations (e.g., street-view data). However, most of the Earth does not have ground-level reference photos available. Fortunately, more complete coverage is provided by oblique aerial or bird's eye imagery. In this work, we localize a ground-level query image by matching it to a reference database of aerial imagery. We use publicly available data to build a dataset of 78K aligned crossview image pairs. The primary challenge for this task is that traditional computer vision approaches cannot handle the wide baseline and appearance variation of these cross-view pairs. We use our dataset to learn a feature representation in which matching views are near one another and mismatched views are far apart. Our proposed approach, Where-CNN, is inspired by deep learning success in face verification and achieves significant improvements over traditional hand-crafted features and existing deep features learned from other large-scale databases. We show the effectiveness of Where-CNN in finding matches between street view and aerial view imagery and demonstrate the ability of our learned features to generalize to novel locations.

Learning Deep Representations for Ground to Aerial Geolocalization (Open Access)

Thank you for downloading cities of tomorrow an intellectual history of urban planning and design in the twentieth century. Maybe you have knowledge that, people have look numerous times for their favorite readings like this cities of tomorrow an intellectual history of urban planning and design in the twentieth century, but end up in malicious downloads. Rather than enjoying a good book with a cup of tea in the afternoon, instead they are facing with some infectious bugs inside their computer. cities of tomorrow an intellectual history of urban planning and design in the twentieth century is available in our book collection an online access to it is set as public so you can get it instantly. Our digital library saves in multiple locations, allowing you to get the most less latency time to download any of our books like this one. Kindly say, the cities of tomorrow an intellectual history of urban planning and design in the twentieth century is universally compatible with any devices to read.

Cities Of Tomorrow An Intellectual History Of Urban Planning And Design In The Twentieth Century

Street view imagery in urban analytics and GIS: A review

This paper presents a novel web-based platform that supports the analysis, integration, and visualization of large-scale and heterogeneous urban data, with application to city planning and decision-making. Motivated by the non-scalable character of conventional urban analytics methods, as well as by the interoperability challenges present in contemporary data silos, the illustrated system – coined SocialGlass – leverages the combined potential of diverse urban data sources. These include sensor and social media streams (Twitter, Instagram, Foursquare), publicly available municipal records, and resources from knowledge repositories. Through data science, semantic integration, and crowdsourcing techniques the platform enables the mapping of demographic information, human movement patterns, place popularity, traffic conditions, as well as citizens’ and visitors’ opinions and preferences about specific venues in a city. The paper further demonstrates an implemented prototype of the platform and its deployment in real-world use cases for monitoring, analyzing, and assessing city-scale events.

A Platform for Urban Analytics and Semantic Data Integration in City Planning

This demo presents Social Glass, a novel web-based platform that supports the analysis, valorisation, integration, and visualisation of large-scale and heterogeneous urban data in the domains of city planning and decision-making. The platform systematically combines publicly available social datasets from municipalities together with social media streams (e.g. Twitter, Instagram and Foursquare) and resources from knowledge repositories. It further enables the mapping of demographic information, human movement patterns, place popularity, traffic conditions, as well as citizens' and visitors' opinions and preferences with regard to specific venues in the city. Social Glass will be demonstrated through several real-world case studies, that exemplify the framework's conceptual properties, and its potential value as a solution for urban analytics and city-scale event monitoring and assessment.

Social Glass: A Platform for Urban Analytics and Decision-making Through Heterogeneous Social Data

Traditional methods for studying the activity dynamics of people and their social interactions in cities require time-consuming and resource-intensive observations and surveys. Dynamic online trails from geosocial networks (e.g. Twitter, Instagram, Flickr etc.) have been increasingly used as proxies for human activity, focusing on mobility behavior, spatial interaction, and social connectivity, among others. Social media records incorporate geo-tags, timestamps, textual components, user-profile attributes and points-of-interest (POI) features, which respectively address spatial, temporal, topical, demographic, and contextual dimensions of human activity. While the information contained in social media data is complex and high-dimensional, there is a lack of studies exploiting the combined potential of their information layers. This article introduces a framework that considers multiple dimensions (i.e. spatial, temporal, topical, and demographic) of information from social media data, and combines Geo-Self-Organizing Maps (GeoSOMs) in conjunction with contiguity-constrained hierarchical clustering, to identify homogeneous regions of social interaction in cities and, subsequently, estimate appropriate locations for new POIs. Drawing on the discovered regions, we build a Factorization Machine-based model to estimate appropriate locations for new POIs in different urban contexts. Using geo-referenced Twitter records and Foursquare data from Amsterdam, Boston, and Jakarta, we evaluate the potential of machine learning techniques in discovering knowledge about the geography of social dynamics from unstructured and high-dimensional social web data. Moreover, we demonstrate that the discovered homogeneous regions are significant predictors of new POI locations.

Regionalization of Social Interactions and Points-of-Interest Location Prediction With Geosocial Data

This paper presents a novel knowledge representation framework for smart city planning and management that enables the semantic integration of heterogeneous urban data from diverse sources. Currently, the combination of information across city agencies is cumbersome, as the increasingly available datasets are stored in disparate data silos, using different models and schemas for their description. To overcome this interoperability barrier, the presented framework employs a modular and scalable system architecture, comprising a comprehensive ontology capable of integrating data from various sectors within a city, a web ontology browser, and a web-based knowledge graph for online data discovery, mapping, and sharing across stakeholders. Linked Data, Semantic Web technologies, and ontology matching techniques are key to the framework’s implementation. The paper ultimately showcases an application example, where the framework is used as a semantic enrichment mechanism in a platform for urban analytics, focusing particularly on human-generated data integration.

/pdf/ontology-based-data-integration-from-heterogeneous-urban-48cp5nueel.pdf

Ontology-based data integration from heterogeneous urban systems: A knowledge representation framework for smart cities

The study of dynamic spatial and social phenomena in cities has evolved rapidly in the recent years, yielding new insights into urban dynamics. This evolution is strongly related to the emergence of new sources of data for cities (e.g. sensors, mobile phones, online social media etc.), which have potential to capture dimensions of social and geographic systems that are difficult to detect in traditional urban data (e.g. census data). However, as the available sources increase in number, the produced datasets increase in diversity. Besides heterogeneity, emerging social urban data are also characterized by multidimensionality. The latter means that the information they contain may simultaneously address spatial, social, temporal, and topical attributes of people and places. Therefore, integration and geospatial (statistical) analysis of multidimensional data remain a challenge. The question which, then, arises is how to integrate heterogeneous and multidimensional social urban data into the analysis of human activity dynamics in cities?  To address the above challenge, this thesis proposes the design of a framework of novel methods and tools for the integration, visualization, and exploratory analysis of large-scale and heterogeneous social urban data to facilitate the understanding of urban dynamics. The research focuses particularly on the spatiotemporal dynamics of human activity in cities, as inferred from different sources of social urban data. The main objective is to provide new means to enable the incorporation of heterogeneous social urban data into city analytics, and to explore the influence of emerging data sources on the understanding of cities and their dynamics.  In mitigating the various heterogeneities, a methodology for the transformation of heterogeneous data for cities into multidimensional linked urban data is, therefore, designed. The methodology follows an ontology-based data integration approach and accommodates a variety of semantic (web) and linked data technologies. A use case of data interlinkage is used as a demonstrator of the proposed methodology. The use case employs nine real-world large-scale spatiotemporal data sets from three public transportation organizations, covering the entire public transport network of the city of Athens, Greece.  To further encourage the consumption of linked urban data by planners and policy-makers, a set of webbased tools for the visual representation of ontologies and linked data is designed and developed. The tools – comprising the OSMoSys framework – provide graphical user interfaces for the visual representation, browsing, and interactive exploration of both ontologies and linked urban data.  After introducing methods and tools for data integration, visual exploration of linked urban data, and derivation of various attributes of people and places from different social urban data, it is examined how they can all be combined into a single platform. To achieve this, a novel web-based system (coined SocialGlass) for the visualization and exploratory analysis of human activity dynamics is designed. The system combines data from various geo-enabled social media (i.e. Twitter, Instagram, Sina Weibo) and LBSNs (i.e. Foursquare), sensor networks (i.e. GPS trackers, Wi-Fi cameras), and conventional socioeconomic urban records, but also has the potential to employ custom datasets from other sources.  A real-world case study is used as a demonstrator of the capacities of the proposed web-based system in the study of urban dynamics. The case study explores the potential impact of a city-scale event (i.e. the Amsterdam Light festival 2015) on the activity and movement patterns of different social categories (i.e. residents, non-residents, foreign tourists), as compared to their daily and hourly routines in the periods  before and after the event. The aim of the case study is twofold. First, to assess the potential and limitations of the proposed system and, second, to investigate how different sources of social urban data could influence the understanding of urban dynamics.  The contribution of this doctoral thesis is the design and development of a framework of novel methods and tools that enables the fusion of heterogeneous multidimensional data for cities. The framework could foster planners, researchers, and policy makers to capitalize on the new possibilities given by emerging social urban data. Having a deep understanding of the spatiotemporal dynamics of cities and, especially of the activity and movement behavior of people, is expected to play a crucial role in addressing the challenges of rapid urbanization. Overall, the framework proposed by this research has potential to open avenues of quantitative explorations of urban dynamics, contributing to the development of a new science of cities.

/pdf/revisiting-urban-dynamics-through-social-urban-data-4b8zkct49s.pdf

Achilleas Psyllidis

Papers

A Platform for Urban Analytics and Semantic Data Integration in City Planning

Social Glass: A Platform for Urban Analytics and Decision-making Through Heterogeneous Social Data

Regionalization of Social Interactions and Points-of-Interest Location Prediction With Geosocial Data

Ontology-based data integration from heterogeneous urban systems: A knowledge representation framework for smart cities

Revisiting Urban Dynamics through Social Urban Data