Lighting invariant urban street classification

In this paper we propose the hybrid use of illuminant invariant and RGB images to perform image classification of urban scenes despite challenging variation in lighting conditions. Coping with lighting change (and the shadows thereby invoked) is a non-negotiable requirement for long term autonomy using vision. One aspect of this is the ability to reliably classify scene components in the presence of marked and often sudden changes in lighting. This is the focus of this paper. Posed with the task of classifying all parts in a scene from a full colour image, we propose that lighting invariant transforms can reduce the variability of the scene, resulting in a more reliable classification. We leverage the ideas of “data transfer” for classification, beginning with full colour images for obtaining candidate scene-level matches using global image descriptors. This is commonly followed by superpixellevel matching with local features. However, we show that if the RGB images are subjected to an illuminant invariant transform before computing the superpixel-level features, classification is significantly more robust to scene illumination effects. The approach is evaluated using three datasets. The first being our own dataset and the second being the KITTI dataset using manually generated ground truth for quantitative analysis. We qualitatively evaluate the method on a third custom dataset over a 750m trajectory.

Urban image classification with semisupervised multiscale cluster kernels

This paper presents a semisupervised support vector machine (SVM) that integrates the information of both labeled and unlabeled pixels efficiently. Method's performance is illustrated in the relevant problem of very high resolution image classification of urban areas. The SVM is trained with the linear combination of two kernels: a base kernel working only with labeled examples is deformed by a likelihood kernel encoding similarities between labeled and unlabeled examples. Results obtained on very high resolution (VHR) multispectral and hyperspectral images show the relevance of the method in the context of urban image classification. Also, its simplicity and the few parameters involved make the method versatile and workable by unexperienced users.

Recomposing the City: New Directions in Urban Sound Art

The editorial introduces the invited edition of the journal based around our International Symposium for Recomposing the City, an interdisciplinary group which asks how the sound of urban spaces might be considered in new ways.

Recomposing the City: New Directions in Urban Sound Art

This special edition, which we were invited by the journal editors to edit, highlights the proceedings of our International Symposium on sound art and urban architecture. We selected these and other authors from multiple disciplines and practices, including sound art, planning, architecture, and anthropology to analyze how sound might be better understood in urban environments.

Classificação de sons urbanos usando motifs e MFCC

A classificação automática de sons urbanos é importante para o monitoramento ambiental. Este trabalho apresenta uma nova metodologia para classificar sons urbanos, que se baseia na descoberta de padrões frequentes (motifs) nos sinais sonoros e utiliza-los como atributos para a classificação. Para extrair os motifs é utilizado um método de descoberta multi-resolução baseada em SAX. Para a classificação são usadas árvores de decisão e SVMs. Esta nova metodologia é comparada com outra bastante utilizada baseada em MFCC. Para a realização de experiências foi utilizado o dataset UrbanSound disponível publicamente. Realizadas as experiências, foi possível concluir que os atributos motif são melhores que os MFCC a discriminar sons com timbres semelhantes e que os melhores resultados são conseguidos com ambos os tipos de atributos combinados. Neste trabalho foi também desenvolvida uma aplicação móvel para Android que permite utilizar os métodos de classificação desenvolvidos num contexto de vida real e expandir o dataset.

Contexts-management strategy in considering the security in urban computing based on urban design

Urban Computing (UrC) provides users with the situation-proper information by considering context of users, devices, and social and physical environment in urban life. With social network services, UrC makes it possible for people with common interests to organize a virtual-society through exchange of context information among them. In these cases, people and personal devices are vulnerable to fake and misleading context information which is transferred from unauthorized and unauthenticated servers by attackers. So called smart devices which run automatically on some context events are more vulnerable if they are not prepared for attacks. In this paper, we illustrate some UrC service scenarios, and show important context information, possible threats, protection method, and secure context management for people.

Comparing Patient-Centered Medical Home Implementation in Urban and Rural VHA Clinics: Results from the Patient Aligned Care Team (PACT) Initiative

Thesis (Master's)--University of Washington, 2016-06

Detection of rain in acoustic recordings of the environment using machine learning techniques

This thesis is concerned with the detection and prediction of rain in environmental recordings using different machine learning algorithms. The results obtained in this research will help ecologists to efficiently analyse environmental data and monitor biodiversity.

Facteurs socioenvironnementaux associés à la prévalence des limitations d’activités au Québec

Objectifs : Cette thèse porte sur l’association entre les caractéristiques socioenvironnementales des voisinages (milieux locaux) et la prévalence des limitations d’activités (ou handicap) dans la population québécoise. Elle a trois objectifs principaux : (1) clarifier les enjeux conceptuels et méthodologiques relatifs à l’étude des déterminants socioenvironnementaux des limitations d’activités; (2) décrire les contributions respectives de la composition socioéconomique des voisinages et de facteurs contextuels à la variabilité locale de la prévalence des limitations d’activités; (3) évaluer la présence d’interactions entre la santé fonctionnelle des personnes (incapacité) et des caractéristiques des voisinages en lien avec la prévalence des limitations d’activités. Méthodes : Une analyse de la littérature scientifique a été effectuée en lien avec le premier objectif de la thèse. En lien avec le deuxième objectif, des données pour le Québec du recensement canadien de 2001 (échantillon de 20% de la population) ont été utilisées pour estimer l’association entre la prévalence des limitations d’activités et des caractéristiques des voisinages : classification urbain-rural, composition socioéconomique (défavorisation matérielle et sociale) et facteurs contextuels (qualité des habitations, stabilité résidentielle et utilisation des transports actifs et collectifs). En lien avec le troisième objectif, des données pour la population urbaine du Québec issues de l’Enquête sur la santé dans les collectivités canadiennes (2003, 2005 et 2007/2008) ont permis de tester la présence d’interaction entre la santé fonctionnelle des personnes et des caractéristiques des voisinages (défavorisation matérielle et sociale, qualité des habitations, stabilité résidentielle et densité des services). Pour les analyses associées aux deux derniers objectifs, l’analyse des corrélats de la prévalence des limitations d’activités a été effectuée à l’aide de régressions logistiques multiniveaux. Résultats : Différents éléments conceptuels et opérationnels limitent la possibilité de faire une synthèse des analyses épidémiologiques portant sur les influences socioenvironnementales sur les limitations d’activités. Les résultats des analyses empiriques suggèrent que : (1) la variation géographique de la prévalence des limitations d’activités s’explique en grande partie par la composition socioéconomique des voisinages; (2) des facteurs contextuels sont associés à cette variation géographique; (3) les mesures relatives d’inégalités sous-estiment les disparités contextuelles dans la distribution des nombres absolus de personnes ayant une limitation d’activités; et (4) l’association entre la prévalence des limitations d’activités et la défavorisation sociale pourrait varier selon la santé fonctionnelle des personnes. Conclusions : Différentes caractéristiques socioenvironnementales sont potentiellement associées aux variations géographiques des limitations d’activités au Québec. Le développement d’indicateurs socioenvironnementaux favoriserait une connaissance plus précise de l’influence de ces caractéristiques socioenvironnementales sur les limitations d’activités et des mécanismes par lesquels s’exerce cette influence. L’établissement d’un système national de surveillance des aménagements territoriaux est proposé afin de soutenir la recherche et la prise de décision. Des indicateurs locaux d’accessibilité aux transports, aux espaces publics ainsi qu’aux services de proximité devraient être priorisés. Ces aspects de l’aménagement du territoire sont susceptibles de rejoindre plusieurs enjeux de santé publique et ils ont comme autre avantage d’être inclus dans différentes orientations québécoises ciblant le vieillissement en santé et la réduction des limitations d’activités.

Poluição sonora urbana: a influência de modificações em escapamentos de motocicletas na emissão de ruído

A poluição sonora urbana, em especial a gerada por motocicletas com escapamentos modificados, afeta indistintamente a saúde de toda população de diversas maneiras e tende a aumentar, ao contrário da emissão de gases, que vem se reduzindo ao longo dos anos. Com o objetivo de conter o ruído gerado pelo tráfego urbano, vários países desenvolvem procedimentos, leis e ações mitigatórias como barreiras acústicas e asfaltos fonoabsorventes, porém há grande quantidade de motocicletas, veículo tipicamente de alto potencial de incômodo e ruidoso, que circulam com sistemas de escapamento adulterados e emitem ainda mais excesso de ruído. A inspeção veicular é ferramenta importante no controle de emissões de gases poluentes de veículos em uso, mas falha em restringir aqueles que ultrapassam os limites legais de ruído e, somado a isto, há o agravante de o condutor submeter-se a poluição sonora que ele mesmo produz. A fiscalização de rua surge como alternativa de controle ambiental, mas algumas vezes é contestada por ser subjetiva ou por faltar uma metodologia simples, confiável e eficaz. Buscou-se então compreender a relação entre o aumento do nível sonoro da motocicleta com escapamento modificado ao circular no trânsito e a emissão sonora medida na condição de inspeção, o chamado ruído parado, para trazer subsídios à formação de métodos mais eficazes de fiscalização e controle. Para isto foram avaliadas motocicletas quanto à emissão de ruído em circulação e ruído parado e os resultados obtidos apontam que os escapamentos modificados possuem nível sonoro muito mais elevado que os originais, com forte correspondência entre os dois métodos de medição. Esta poluição sonora atinge de modo particularmente intenso os profissionais, motoboys, que modificam suas motocicletas, pois eles se submetem a todos os fatores que favorecem a perda auditiva por excesso de ruído. Outras questões surgiram em paralelo ao tema principal e foram brevemente avaliadas para se compor o quadro geral, como o nível sonoro de escapamentos não originais avaliados segundo os procedimentos de homologação, a contribuição que a motocicleta traz ao ruído urbano e que resultados estes trazem quanto ao torque e potência da motocicleta. Estes estudos indicaram que a motocicleta modificada contribui fortemente para a poluição sonora urbana, afetando principalmente o condutor e sem trazer ganhos efetivos em termos de potência e dirigibilidade.

EXPOSURE TO EXTREME HEAT EVENTS AND CHRONIC RESPIRATORY DISEASES AMONG A NATIONALLY REPRESENTATIVE SAMPLE OF THE UNITED STATES POPULATION

Previous studies have shown that extreme weather events are on the rise in response to our changing climate. Such events are projected to become more frequent, more intense, and longer lasting. A consistent exposure metric for measuring these extreme events as well as information regarding how these events lead to ill health are needed to inform meaningful adaptation strategies that are specific to the needs of local communities. Using federal meteorological data corresponding to 17 years (1997-2013) of the National Health Interview Survey, this research: 1) developed a location-specific exposure metric that captures individuals’ “exposure” at a spatial scale that is consistent with publicly available county-level health outcome data; 2) characterized the United States’ population in counties that have experienced higher numbers of extreme heat events and thus identified population groups likely to experience future events; and 3) developed an empirical model describing the association between exposure to extreme heat events and hay fever. This research confirmed that the natural modes of forcing (e.g., El Niño-Southern Oscillation), seasonality, urban-rural classification, and division of country have an impact on the number extreme heat events recorded. Also, many of the areas affected by extreme heat events are shown to have a variety of vulnerable populations including women of childbearing age, people who are poor, and older adults. Lastly, this research showed that adults in the highest quartile of exposure to extreme heat events had a 7% increased odds of hay fever compared to those in the lowest quartile, suggesting that exposure to extreme heat events increases risk of hay fever among US adults.

The effectiveness of using a simple ARIA based geographical classification to identify road crash patterns in rural and urban areas of Queensland

Research has noted a ‘pronounced pattern of increase with increasing remoteness' of death rates in road crashes. However, crash characteristics by remoteness are not commonly or consistently reported, with definitions of rural and urban often relying on proxy representations such as prevailing speed limit. The current paper seeks to evaluate the efficacy of the Accessibility / Remoteness Index of Australia (ARIA+) to identifying trends in road crashes. ARIA+ does not rely on road-specific measures and uses distances to populated centres to attribute a score to an area, which can in turn be grouped into 5 classifications of increasing remoteness. The current paper uses applications of these classifications at the broad level of Australian Bureau of Statistics' Statistical Local Areas, thus avoiding precise crash locating or dedicated mapping software. Analyses used Queensland road crash database details for all 31,346 crashes resulting in a fatality or hospitalisation occurring between 1st July, 2001 and 30th June 2006 inclusive. Results showed that this simplified application of ARIA+ aligned with previous definitions such as speed limit, while also providing further delineation. Differences in crash contributing factors were noted with increasing remoteness such as a greater representation of alcohol and ‘excessive speed for circumstances.' Other factors such as the predominance of younger drivers in crashes differed little by remoteness classification. The results are discussed in terms of the utility of remoteness as a graduated rather than binary (rural/urban) construct and the potential for combining ARIA crash data with census and hospital datasets.

The sound of music : sharing song selections between collocated strangers in public urban places

This paper presents Capital Music, a mobile application enabling real-time sharing of song choices with collocated urban dwellers. Due to the real-time, location-based peer-to-peer approach of the application, a user experience study was performed utilising the Wizard of Oz method. The study provides insight into how sharing non-privacy sensitive but personal data in an anonymous way can influence the user experience of people in public urban places. We discuss the findings in relation to how Capital Music influences the process of “cocooning” in public urban places, the practice of designing anonymous interactions between collocated strangers, and how the sharing of song choices can create a sense of commonality between anonymous users in the urban space. The outcomes of this study are relevant for future location-based social networking applications that aim to create interactions between collocated strangers.