Measuring human activity spaces from GPS data with density ranking and summary curves

Chen, Yen‐Chi; Dobra, Adrian

doi:10.1214/19-aoas1311

Cited by 14 publications

(10 citation statements)

References 79 publications

(89 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Real-time geolocation data (e.g. those acquired by GPS sensors in smartphones) permit a detailed description for activity spaces for equipped individuals [26], but the complexity of these analyses [27][28][29][30] calls for a simplified approach for public health studies.…”

Section: Discussionmentioning

confidence: 99%

Risk of late cervical cancer screening according to prosperity and medical density in daily frequented neighborhoods in Greater Paris.

Traoré

Vallée

CHAUVIN

2019

Preprint

View full text Add to dashboard Cite

Background: The consideration of multiple spaces frequented daily by individuals is attracting interest for the analysis of socioterritorial health and healthcare inequalities in light of the high daily mobility in urban settings and the increasing availability of mobility data. Our objective was to estimate the associations between attributes of daily frequented neighborhoods and delayed cervical smear tests in the Greater Paris area. Methods: Data were extracted from the 2010 SIRS cohort survey. Participants could report three neighborhoods (residence, work, and the next most regularly frequented). All multivariate analyses were conducted: simple multilevel logistic regression models, cross-classified multilevel logistic regression models were used to simultaneously consider the three types of neighborhoods studied (residential, work or study, visit) with active and mobile women. Finally, associations with socioeconomic and medical diversity scores (adjusted for the five individual characteristics) were estimated by logistic regression models that took sampling design into consideration. Results: One-quarter of the women reported that they had not had a smear test in the previous three years. After adjusting for individual characteristics, there was a significant association between the socioeconomic and medical diversity scores for the multiple neighborhoods frequented and the risk of a delayed smear test. Women who reside and work in poor neighborhoods and whose next most regularly frequented neighborhood was also poor had a significantly higher risk of late cervical cancer screening. Conclusions: In the characterization of social and territorial inequalities in healthcare, social epidemiology and health geography show a growing interest in considering multiple spaces frequented daily by individuals. A cumulative exposure score, such as the one presented here, may be a relevant approach for analyzing their effects. Keywords: Multilevel analysis, neighborhood, daily mobility, cancer prevention, cervical cancer, social inequalities, Paris area

show abstract

Section: Discussionmentioning

confidence: 99%

Risk of late cervical cancer screening according to prosperity and medical density in daily frequented neighborhoods in Greater Paris.

Traoré

Vallée

CHAUVIN

2019

Preprint

View full text Add to dashboard Cite

show abstract

“…KDE allows us to estimate the probability density function from our finite dataset of detected street trees and corresponding GPS coordinates. However, KDE does not work well with GPS data [6]. Kernel Density Ranking (KDR) [6] is a better approach which is more conducive to GPS data.…”

Section: Kernel Density Ranking and Density Mapmentioning

confidence: 99%

“…However, KDE does not work well with GPS data [6]. Kernel Density Ranking (KDR) [6] is a better approach which is more conducive to GPS data. KDR is derived from KDE and thus we briefly explain the working of KDE first.…”

Section: Kernel Density Ranking and Density Mapmentioning

confidence: 99%

“…First, the category map takes the following as input -tree count of the route, GPS coordinates of the route and our predefined scale (tree count density index, refer Section 4.2) and outputs a map where the routes are coloured according to the index. Second, the density map takes the following as input -the GPS coordinates of the counted street trees and uses the Kernel Density Ranking (KDR) algorithm [6] to generate a map that showcases the density of street trees in a route. Note the detection and counting modules provide a separate output video with roadside tree detections and counts in mp4 format.…”

Section: The Systemmentioning

confidence: 99%

See 1 more Smart Citation

Automatic quantification and visualization of street trees

Bahety

Saluja

Sarvadevabhatla

et al. 2021

Proceedings of the Twelfth Indian Conference on Computer Vision, Graphics and Image Processing

View full text Add to dashboard Cite

Assessing the number of street trees is essential for evaluating urban greenery and can help municipalities employ solutions to identify tree-starved streets. It can also help identify roads with different levels of deforestation and afforestation over time. Yet, there has been little work in the area of street trees quantification. This work first explains a data collection setup carefully designed for counting roadside trees. We then describe a unique annotation procedure aimed at robustly detecting and quantifying trees. We work on a dataset of around 1300 Indian road scenes annotated with over 2500 street trees. We additionally use the five held-out videos covering 25 km of roads for counting trees. We finally propose a street tree detection, counting, and visualization framework using current object detectors and a novel yet simple counting algorithm owing to the thoughtful collection setup. We find that the high-level visualizations based on the density of trees on the routes and Kernel Density Ranking (KDR) provide a quick, accurate, and inexpensive way to recognize tree-starved streets. We obtain a tree detection mAP of 83.74% on the test images, which is a 2.73% improvement over our baseline. We propose Tree Count Density Classification Accuracy (TCDCA) as an evaluation metric to measure tree density. We obtain TCDCA of 96.77% on the test videos, with a remarkable improvement of 22.58% over baseline, and demonstrate that our counting module's performance is close to human level. Source code: https://github.com/iHubData-Mobility/public-tree-counting. CCS CONCEPTS• Computing methodologies → Computer vision.

show abstract

“…Even if real-time geolocation data (e.g. those acquired by GPS sensors in smartphones) permit a more detailed description of people's activity spaces [29], such data collection [30][31][32][33] are costly and time-consuming. Our simplified approach can then constitute a simplified but effective alternative to explore contextual effects of daily visited neighborhoods on health inequalities.…”

Section: Limitations and Strengthsmentioning

confidence: 99%

Risk of late cervical cancer screening in the Paris region according to social deprivation and medical densities in daily visited neighborhoods

Traoré

Vallée²,

Chauvin

2020

Int J Health Geogr

View full text Add to dashboard Cite

Background: Social and physical characteristics of the daily visited neighborhoods have gained an extensive interest in analyzing socio-territorial inequalities in health and healthcare. The objective of the present paper is to estimate and discuss the role of individual and contextual factors on participation in preventive health-care activities (smear screening) in the Greater Paris area focusing on the characteristics of daily visited neighborhoods in terms of medical densities and social deprivation. Methods: The study included 1817 women involved in the SIRS survey carried out in 2010. Participants could report three neighborhoods they regularly visit (residence, work/study, and the next most regularly visited). Two "cumulative exposure scores" have been computed from household income and medical densities (general practitioners and gynecologists) in these neighborhoods. Multilevel logistic regression models were used to measure association between late cervical screening (> 3 years) and characteristics of daily visited neighborhoods (residential, work or study, visit). Results: One-quarter of the women reported that they had not had a smear test in the previous 3 years. Late smear test was found to be more frequent among younger and older women, among women being single, foreigners and among women having a low-level of education and a limited activity space. After adjustment on individual characteristics, a significant association between the cumulative exposure scores and the risk of a delayed smear test was found: women who were exposed to low social deprivation and to low medical densities in the neighborhoods they daily visit had a significantly higher risk of late cervical cancer screening than their counterparts. Conclusions: For a better understanding of social and territorial inequalities in healthcare, there is a need for considering multiple daily visited neighborhoods. Cumulative exposure scores may be an innovative approach for analyzing contextual effects of daily visited neighborhoods rather than focusing on the sole residential neighborhood.

show abstract

Measuring human activity spaces from GPS data with density ranking and summary curves

Cited by 14 publications

References 79 publications

Risk of late cervical cancer screening according to prosperity and medical density in daily frequented neighborhoods in Greater Paris.

Risk of late cervical cancer screening according to prosperity and medical density in daily frequented neighborhoods in Greater Paris.

Automatic quantification and visualization of street trees

Risk of late cervical cancer screening in the Paris region according to social deprivation and medical densities in daily visited neighborhoods

Contact Info

Product

Resources

About