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

DOI10.1214/19-AOAS1311zbMATH Open1439.62249arXiv1708.05017OpenAlexW3016288971MaRDI QIDQ2179974FDOQ2179974

Authors: Yen-Chi Chen, Adrian Dobra 

Publication date: 13 May 2020

Published in: The Annals of Applied Statistics (Search for Journal in Brave)

Abstract: Activity spaces are fundamental to the assessment of individuals' dynamic exposure to social and environmental risk factors associated with multiple spatial contexts that are visited during activities of daily living. In this paper we survey existing approaches for measuring the geometry, size and structure of activity spaces based on GPS data, and explain their limitations. We propose addressing these shortcomings through a nonparametric approach called density ranking, and also through three summary curves: the mass-volume curve, the Betti number curve, and the persistence curve. We introduce a novel mixture model for human activity spaces, and study its asymptotic properties. We prove that the kernel density estimator which, at the present time, is one of the most widespread methods for measuring activity spaces is not a stable estimator of their structure. We illustrate the practical value of our methods with a simulation study, and with a recently collected GPS dataset that comprises the locations visited by ten individuals over a six months period.

Full work available at URL: https://arxiv.org/abs/1708.05017

Recommendations

• A statistical framework for measuring the temporal stability of human mobility patterns
• Kernel density estimation on a linear network
• Hierarchical conditional random fields for GPS-based activity recognition
• Mixture of hidden Markov models for accelerometer data
• Finding Popular Places

zbMATH Keywords

human mobilitykernel density estimationtopological data analysisactivity spaceglobal positioning systems (GPS)space-time geography

Mathematics Subject Classification ID

Density estimation (62G07) Applications of statistics to social sciences (62P25) Topological data analysis (62R40)

Cites Work

• Bandwidth selection for kernel density estimators of multivariate level sets and highest density regions
• Title not available (Why is that?)
• Persistent homology -- a survey
• Topology and data
• Computational topology. An introduction
• Title not available (Why is that?)
• Title not available (Why is that?)
• Barcodes: The persistent topology of data
• Minimum volume sets and generalized quantile processes
• Level sets and minimum volume sets of probability density functions.
• Asymptotic normality of plug-in level set estimates
• Estimation of density level sets with a given probability content
• Optimal rates for plug-in estimators of density level sets
• Generalized density clustering
• Geometry of measures in \(R^ n:\) Distribution, rectifiability, and densities
• Computational homology
• Title not available (Why is that?)
• Learning minimum volume sets
• Mass volume curves and anomaly ranking
• The Accumulated Persistence Function, a New Useful Functional Summary Statistic for Topological Data Analysis, With a View to Brain Artery Trees and Spatial Point Process Applications
• Measuring human activity spaces from GPS data with density ranking and summary curves
• Functional summaries of persistence diagrams
• Generalized cluster trees and singular measures

Cited In (3)

• Nonparametric estimation of highest density regions for COVID-19
• A data-adaptive method for estimating density level sets under shape conditions
• Measuring human activity spaces from GPS data with density ranking and summary curves

Uses Software

• lsbs

This page was built for publication: Measuring human activity spaces from GPS data with density ranking and summary curves

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2179974)