大数据在评价有关公共健康的建成环境中的应用：文献综述
The Application of Big Data in Assessing the Built Environment for Public Health: A Literature Review
张 昊
SUNY布法罗大学建筑与城市规划学院 博士
尹 力
SUNY布法罗大学建筑与城市规划学院 副教授，博士生导师
摘要: 大数据、机器学习等新技术和新方法可以突破传统研究的时空限制，高效客观地研究大量、多样和变化的信息。系统性地梳理过去10年大数据在建成环境和公共健康研究中应用的相关文献，从机器学习（machine learning）在街景分析中的应用和众包（crowdsourcing）分析两个方面进行探讨。研究表明，将机器学习应用于街景图像等大数据，可以识别人本尺度的信息，帮助规划设计有益健康的人居环境。众包分析可以实时收集大量跨区域的个人对建成环境的感知体验。大数据覆盖范围广、细节丰富，补充并优化了当前的研究方法。大数据分析的优点在于能够进行详实的跨区域研究，同时极大地减少了时间和安全隐患。其挑战在于数据的有效性、图像分辨率不一致，以及无法观察障碍物周围的环境特征。此外，一些数据仅限于视觉感知，不足以量化其他感官体验。尽管如此，大数据分析凭借对人居尺度环境的精确度量和个人感知体验的深入探讨，为研究建成环境和公共健康提供了有效途径。
Abstract: The advances in technology and method such as machine learning help break through the time and space limitations of traditional research. These methods are able to efficiently and objectively study a large amount of diverse and changing information. This paper systematically reviews the literature on the application of big data in the built environment and public health research in the past ten years (2011-2020). We focus on the application of machine learning in street view analysis and crowdsourcing analysis. The results suggest that applying machine learning to street-view images can analyze human-scale built environment information, thus promoting the planning and design of healthy cities. Crowdsourcing analysis facilitates the collection of a large number of individuals' real-time perceptions of the surroundings. The advantages of big data are reflected in its wide coverage and rich details. Therefore, big data analysis promotes in-depth, cross-regional research, while significantly reducing resource consumption and safety concerns. The challenge of the big data analysis lies in the validity of the data, the difference in image resolution, and the difficulty in observing environmental features around obstacles. Nevertheless, due to the objective measure of the human-scale built environment and in-depth exploration of individuals' perceptions, big data analysis optimizes traditional research methods, and provides an effective platform to study the relationship between the built environment and public health.
关键词：大数据；建成环境；公共健康；机器学习；众包
Keyword: big data; built environment; public health; machine learning; crowdsourcing
中图分类号：TU981
文献标识码: A
EWING R, HANDY S, BROWNSON R C, et al. Identifying and measuring urban design qualities related to walkability[J]. Journal of Physical Activity and Health, 2006, 3(s1): S223-S240.
PAPAS M A, ALBERG A J, EWING R, et al. The built environment and obesity[J]. Epidemiologic Reviews, 2007, 29(1): 129-143.
SALLIS J F, SAELENS B E, FRANK L D, et al. Neighborhood built environment and income: examining multiple health outcomes[J]. Social Science & Medicine, 2009, 68(7): 1285-1293.
FENG J, GLASS T A, CURRIERO F C, et al. The built environment and obesity: a systematic review of the epidemiologic evidence[J]. Health & Place, 2010, 16(2): 175-190.
ALFONZO M, GUO Z, LIN L, et al. Walking, obesity and urban design in Chinese neighborhoods[J]. Preventive Medicine, 2014, 69: S79-S85.
DAY K. Built environmental correlates of physical activity in China: a review[J]. Preventive Medicine Reports, 2016(3): 303-316.
EWING R, HANDY S. Measuring the unmeasurable: urban design qualities related to walkability[J]. Journal of Urban Design, 2009, 14(1): 65-84.
YIN L, WANG Z. Measuring visual enclosure for street walkability: using machine learning algorithms and Google Street View imagery[J]. Applied Geography, 2016, 76: 147-153.
YIN L. Street level urban design qualities for walkability: combining 2D and 3D GIS measures[J]. Computers, Environment and Urban Systems, 2017, 64: 288-296.
RUNDLE A G, BADER M D, RICHARDS C A, et al. Using Google Street View to audit neighborhood environments[J]. American Journal of Preventive Medicine, 2011, 40(1): 94-100.
HARA K, LI V, FROEHLICH J. Combining crowdsourcing and Google Street View to identify street-level accessibility problems[C]//Proceedings of the SIGCHI Conference on Human Factors in Computing Systems. New York: Association for Computing Machinery, 2013: 631-640.
SALESSES P, SCHECHTNER K, HIDALGO C A. The collaborative image of the city: mapping the inequality of urban perception[J]. PloS One, 2013, 8(7): e68400.
MITCHELL L, FRANK M R, HARRIS K D, et al. The geography of happiness: connecting Twitter sentiment and expression, demographics, and objective characteristics of place[J]. PloS One, 2013, 8(5): e64417.
WANG S, PAUL M J, DREDZE M. Exploring health topics in Chinese social media: an analysis of Sina Weibo[C]//AAAI Workshop on the World Wide Web and Public Health Intelligence, 2014, 23: 20-23.
SALHA G. Recommending quiet paths in Shanghai: a data science point of view[EB/OL]. (2019-01-09)[2020-08-05]. http://www.complexcity.org/2015/10/13/recommending-quiet-path.html.
ZHAO M, LIU X. Reprint of: regional risk assessment for urban major hazards based on GIS geoprocessing to improve public safety[J]. Safety Science, 2017, 97: 112-119.
KONTOKOSTA C E. The quantified community and neighborhood labs: a framework for computational urban science and civic technology innovation[J]. Journal of Urban Technology, 2016, 23(4): 67-84.
SU S, LI Z, XU M, et al. A geo-big data approach to intra-urban food deserts: transit-varying accessibility, social inequalities, and implications for urban planning[J]. Habitat International, 2017, 64: 22-40.
SUN Y, DU Y, WANG Y, et al. Examining associations of environmental characteristics with recreational cycling behaviour by street-level Strava data[J]. International Journal of Environmental Research and Public Health, 2017, 14(6): 644.
LONG Y, LIU L. How green are the streets? An analysis for central areas of Chinese cities using Tencent Street View[J]. PloS One, 2017, 12(2): e0171110.
ADLAKHA D. Quantifying the emerging technologies and big data for active living research[J]. Frontiers in Public Health, 2017(5): 105.
YANG Y. Using agent based modeling to study multiple risk factors and multiple health outcomes at multiple levels[J]. Annals of the New York Academy of Sciences, 2017, 1408(1): 7-14.
CHENG L, CHU S, ZONG W, et al. Use of Tencent Street View imagery for visual perception of streets[J]. ISPRS International Journal of Geo-Information, 2017, 6(9): 265.
NGUYEN Q C, SAJJADI M, MCCULLOUGH M, et al. Neighbourhood looking glass: 360º automated characterisation of the built environment for neighbourhood effects research[J]. Journal of Epidemiology Community Health, 2018, 72(3): 260-266.
TIMMINS K A, GREEN M A, RADLEY D, et al. How has big data contributed to obesity research? A review of the literature[J]. International Journal of Obesity, 2018, 42(12): 1951-1962.
RZOTKIEWICZ A, PEARSON A L, DOUGHERTY B V, et al. Systematic review of the use of Google Street View in health research: major themes, strengths, weaknesses and possibilities for future research[J]. Health & Place, 2018, 52: 240-246.
HELBICH M. Toward dynamic urban environmental exposure assessments in mental health research[J]. Environmental Research, 2018, 161: 129-135.
GU P, HAN Z, CAO Z, et al. Using open source data to measure street walkability and bikeability in China: a case of four cities[J]. Transportation Research Record 2672, 2018, 31: 63-75.
ZENK S N, TARLOV E, POWELL L M, et al. Weight and Veterans' Environments Study (WAVES) I and II: rationale, methods, and cohort characteristics[J]. American Journal of Health Promotion, 2018, 32(3): 779-794.
KESTENS Y, WINTERS M, FULLER D, et al. Interact: a comprehensive approach to assess urban form interventions through natural experiments[J]. BMC Public Health, 2019, 19(1): 1-11.
YE Y, RICHARD D, LU Y, et al. Measuring daily accessed street greenery: a human-scale approach for informing better urban planning practices[J]. Landscape and Urban Planning, 2019, 191: 103434.
WANG R, LIU Y, LU Y, et al. Perceptions of built environment and health outcomes for older Chinese in Beijing: a big data approach with street view images and deep learning technique[J]. Computers, Environment and Urban Systems, 2019, 78: 101386.
FAN Z, LIU C, CAI D, et al. Research on black spot identification of safety in urban traffic accidents based on machine learning method[J]. Safety Science, 2019, 118: 607-616.
ALDRED R. Built environment interventions to increase active travel: a critical review and 2019, 6(4): 309-315.
KIM J, AHN C R, NAM Y. The influence of built environment features on crowdsourced physiological responses of pedestrians in neighborhoods[J]. Computers, Environment and Urban Systems, 2019, 75: 161-169.
GUO L, LUO J, YUAN M, et al. The influence of urban planning factors on PM2.5 pollution exposure and implications: a case study in China based on remote sensing, LBS, and GIS data[J]. Science of the Total Environment, 2019, 659: 1585-1596.
YE Y, ZENG W, SHEN Q, et al. The visual quality of streets: a human-centred continuous measurement based on machine learning algorithms and street view images[J]. Environment and Planning B: Urban Analytics and City Science, 2019, 46(8): 1439-1457.
DENG C, DONG X, WANG H, et al. A data-driven framework for walkability measurement with open data: a case study of triple cities, New York[J]. ISPRS International Journal of Geo-Information, 2020, 9(1): 36.
WILKINS E, ARAVANI A, DOWNING A, et al. Evidence from big data in obesity research: international case studies[J]. International Journal of Obesity, 2020, 44(5): 1028-1040.
PHAN L, YU W, KERALIS J M, et al. Google Street View derived built environment indicators and associations with state-level obesity, physical activity, and chronic disease mortality in the United States[J]. International Journal of Environmental Research and Public Health, 2020, 17(10): 3659.
YIGITCANLAR T, DESOUZA K C, BUTLER L, et al. Contributions and risks of artificial intelligence (AI) in building smarter cities: insights from a systematic review of the literature[J]. Energies, 2020, 13(6): 1473.
ULLAH H, WAN W, HAIDERY S A, et al. Spatiotemporal patterns of visitors in urban green parks by mining social media big data based upon WHO reports[J]. IEEE Access, 2020, 8: 39197-39211.
LI S, WU C, LIN Y, et al. Urban morphology promotes urban vibrancy from the spatiotemporal and synergetic perspectives: a case study using multisource data in Shenzhen, China[J]. Sustainability, 2020, 12(12): 4829.
JIM C Y, SHAN X. Socioeconomic effect on perception of urban green spaces in Guangzhou, China[J]. Cities, 2013, 31: 123-131.
KRELLENBERG K, WELZ J, REYES-PÄCKE S. Urban green areas and their potential for social interaction–a case study of a socio-economically mixed neighbourhood in Santiago de Chile[J]. Habitat International, 2014, 44: 11-21.
CAIN K L, MILLSTEIN R A, SALLIS J F, et al. Contribution of streetscape audits to explanation of physical activity in four age groups based on the Microscale Audit of Pedestrian Streetscapes (MAPS)
