Application of deep learning to heterogeneous open data for measuring urban environment and health

深度学习在异构开放数据中的应用以测量城市环境和健康

• 批准号: MR/S003983/1
• 负责人: Esra Suel
• 金额: $ 42.25万
• 依托单位: Imperial College London
• 依托单位国家: 英国
• 项目类别: Fellowship
• 财政年份: 2018
• 资助国家: 英国
• 起止时间: 2018 至 无数据
• 项目状态: 已结题
• 来源: https://gtr.ukri.org/projects?ref=MR%2FS003983%2F1
• 关键词: Application; deep; learning; heterogeneous; open

In today's world, there is a great deal of information from sources like Google Street View and mobile phone usages about our environment and movement. The promise of big data, in many research fields, business, policy-making alike, that it will transform and improve the way we do things. Researchers in environmental health are also increasingly interested to use of information generated by mobile phones, satellites, wearable devices, social media, etc. The main challenge, however, is that making sense of diverse data at such big scales is not easy. Further, these new datasets are characteristically very different from conventional survey based data, hence their analysis require new methods. To this end, promising advances in deep learning over the past five years have achieved close-to-human performance on visual tasks such as recognizing objects and classifying them (e.g., telling a chair apart from a bird). In this project, I aim to apply advanced machine learning techniques to answer important questions in environmental health. Specifically, the focus will be on analysing images captured by satellites and street view cameras, and data generated from mobile phones, and investigating what they can reveal about health outcomes and its environmental and social determinants.

在当今世界，谷歌街景和手机使用等来源提供了大量有关我们的环境和运动的信息。在许多研究领域、商业领域、政策制定领域，大数据承诺将改变和改进我们做事的方式。环境健康领域的研究人员也对使用手机、卫星、可穿戴设备、社交媒体等产生的信息越来越感兴趣。然而，主要的挑战是理解如此大规模的多样化数据并不容易。此外，这些新数据集的特征与传统的基于调查的数据有很大不同，因此它们的分析需要新的方法。为此，过去五年来深度学习取得了令人鼓舞的进展，在识别物体和对其进行分类（例如区分椅子和鸟）等视觉任务上取得了接近人类的表现。在这个项目中，我的目标是应用先进的机器学习技术来回答环境健康中的重要问题。具体来说，重点将是分析卫星和街景摄像机捕获的图像以及手机生成的数据，并调查它们可以揭示健康结果及其环境和社会决定因素。

项目成果

Do poverty and wealth look the same the world over? A comparative study of 12 cities from five high-income countries using street images.

• DOI: 10.1140/epjds/s13688-023-00394-6
• 发表时间: 2023
• 期刊: EPJ DATA SCIENCE
• 影响因子: 3.6
• 作者: Suel, Esra;Mueller, Emily;Bennett, James E.;Blakely, Tony;Doyle, Yvonne;Lynch, John;Mackenbach, Joreintje D.;Middel, Ariane;Mizdrak, Anja;Nathvani, Ricky;Brauer, Michael;Ezzati, Majid
• 通讯作者: Ezzati, Majid

Characterisation of urban environment and activity across space and time using street images and deep learning in Accra.

• DOI: 10.1038/s41598-022-24474-1
• 发表时间: 2022-11-28
• 期刊: SCIENTIFIC REPORTS
• 影响因子: 4.6
• 作者: Nathvani, Ricky;Clark, Sierra N.;Muller, Emily;Alli, Abosede S.;Bennett, James E.;Nimo, James;Moses, Josephine Bedford;Baah, Solomon;Metzler, A. Barbara;Brauer, Michael;Suel, Esra;Hughes, Allison F.;Rashid, Theo;Gemmell, Emily;Moulds, Simon;Baumgartner, Jill;Toledano, Mireille;Agyemang, Ernest;Owusu, George;Agyei-Mensah, Samuel;Arku, Raphael E.;Ezzati, Majid
• 通讯作者: Ezzati, Majid

Multimodal deep learning from satellite and street-level imagery for measuring income, overcrowding, and environmental deprivation in urban areas.

• DOI: 10.1016/j.rse.2021.112339
• 发表时间: 2021-05
• 期刊: Remote sensing of environment
• 影响因子: 13.5
• 作者: Suel E;Bhatt S;Brauer M;Flaxman S;Ezzati M
• 通讯作者: Ezzati M

Combining street imagery and spatial information for measuring socioeconomic status

结合街道图像和空间信息来衡量社会经济地位

• 发表时间: 2018
• 作者: Suel, E

Street-view greenspace exposure and objective sleep characteristics among children.

• DOI: 10.1016/j.envres.2022.113744
• 发表时间: 2022-11
• 期刊: ENVIRONMENTAL RESEARCH
• 影响因子: 8.3
• 作者: Jimenez, Marcia P.;Suel, Esra;Rifas-Shiman, Sheryl L.;Hystad, Perry;Larkin, Andrew;Hankey, Steve;Just, Allan C.;Redline, Susan;Oken, Emily;James, Peter
• 通讯作者: James, Peter