arxiv: 2605.08509 · v1 · submitted 2026-05-08 · 📊 stat.ME

Recognition: no theorem link

An Object-Oriented Spatial Statistics Approach for Human Activity Space Estimation

Adrian Dobra, Haoyang Wu, Yen-Chi Chen

Pith reviewed 2026-05-12 00:58 UTC · model grok-4.3

classification 📊 stat.ME

keywords GPS dataGIShuman mobilityactivity space estimationtime-weighted estimatorerror boundsspatial statisticsspace-time geography

0 comments

The pith

A time-weighted estimator using time distributions over GIS polygons and roads estimates human activity spaces from irregular GPS data.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper develops a statistical method for estimating where people spend their time by combining GPS observations with digital maps of places and routes. Daily mobility is represented as the share of time allocated to specific spatial polygons and road segments, which supports entity-specific patterns and level-gamma activity spaces. A time-weighted estimator addresses the common problem of uneven GPS sampling intervals, while a derived error bound measures the combined impact of location inaccuracies, misclassifications, missing time periods, boundary crossings, and day-to-day differences. Simulation studies and a real application show the approach identifies stable stay locations and travel paths, with separate stabilization rates for stationary and moving periods. This matters for any analysis that needs reliable summaries of individual movement in built environments.

Core claim

By characterizing daily mobility through the distribution of time across spatial polygons and road segments within the object-oriented spatial statistics framework, the time-weighted estimator recovers concentrated stationary anchors, interpretable travel corridors, and distinct stabilization behavior for dwelling and movement components from irregularly sampled GPS data, while the error bound quantifies effects of measurement error, nearest-entity misclassification, temporal gaps, boundary crossings, and day-to-day variability.

What carries the argument

The time-weighted estimator applied to the distribution of time across GIS polygons and road segments, which carries the estimation of entity-specific activity spaces and the error bound.

Load-bearing premise

That time distributions across spatial polygons and road segments, combined with the object-oriented framework, sufficiently capture entity-specific mobility patterns and that the derived error bound accurately accounts for all listed sources of variability without additional conditions on data quality or sampling.

What would settle it

A controlled GPS dataset with known true activity spaces in which the estimator fails to recover the stationary anchors or the observed discrepancies exceed the derived error bound when temporal gaps or measurement errors are present.

Figures

Figures reproduced from arXiv: 2605.08509 by Adrian Dobra, Haoyang Wu, Yen-Chi Chen.

**Figure 1.** Figure 1: Summary information for the GPS data recorded for the selected study participant. The left panel displays the histogram of recorded timestamps, showing irregular sampling across the observation window. The right panel shows the histogram of time intervals between successive observations, truncated at the 90th percentile of all intervals to suppress the influence of extreme gaps. 3. Our modeling framewor… view at source ↗

**Figure 2.** Figure 2: (a) An example spatial window containing spatial polygons and a road network; (b) An example polygonnetwork activity space (subset of all spatial polygons and road network with high activities) in this spatial window. The individual performs daily living activities within the spatial polygons A and can move between them on the road network L. We assume that this individual spends negligible time outside … view at source ↗

**Figure 3.** Figure 3: Illustration of the selection of an appropriate PN space shown in grey with respect to a set of GPS records shown in red. Left panel: an example of a PN space that is too dense. Right panel: an example of a PN space that is too sparse. Middle panel: an example of a PN space that is judiciously chosen to match the GPS data. Note that the road-network layers in each panel are privacy-preserving renderings u… view at source ↗

**Figure 4.** Figure 4: Illustration of the proposed data generating mechanism. Left column: study window with relevant spatial polygons and road network in two different days. Middle column: two sample latent trajectories comprising polygon dwell times (yellow) and path segments (blue, with a highlighted red sub-segment). The line segments the individual uses when moving between polygons are marked in red. Right panel: noisy G… view at source ↗

**Figure 5.** Figure 5: Misclassification can occur only if the measurement error moves the observed location across the assignment boundary. Thus, if the true location is farther than r0.95 from the boundary, then the misclassification probability is at most 0.05. We are ready to present the main result on the convergence rate of the estimation error. Theorem 3.1. Under Assumption 3.1, for each entity e ∈ E the asymptotic absol… view at source ↗

**Figure 6.** Figure 6: Synthetic map (top left panel) and five possible daily action vectors (other panels). Full details appear in Supplementary Material. The remaining panels in [PITH_FULL_IMAGE:figures/full_fig_p016_6.png] view at source ↗

**Figure 7.** Figure 7: First row: Spatial distribution of estimated timespent proportions across estimated time-spent proportion in building polygons (left panel) and on road segments (right panel). Darker blue indicates higher log(1 + pe); grey denotes zero. Second row: Estimated composed activity spaces at three coverage levels (90%, 95%, and 99%). Blue polygons correspond to building-based spaces (stationary exposure) wit… view at source ↗

**Figure 7.** Figure 7: Polygon aggregation 3 functions like aggregation 2, while polygon [PITH_FULL_IMAGE:figures/full_fig_p023_7.png] view at source ↗

**Figure 8.** Figure 8: Left panel: hierarchical clustering dendrogram of daily trajectories (single linkage, Levenshtein distance weighted by dwell time). Two main clusters are identified, along with a few outlier days. Middle and right panels: representative daily mobility patterns randomly chosen from clusters 1 and 2. The left panel of [PITH_FULL_IMAGE:figures/full_fig_p024_8.png] view at source ↗

**Figure 9.** Figure 9: Left panel: Last–crossing times (LCTs) for polygon–based activity spaces across different levels c. Dashed vertical lines mark the inclusion of new polygons: as the level of activity space increases polygon for workplace at c = 0.78 and polygons and other occasional sites at c = 0.99. Middle panel: LCTs for road–based activity spaces, which show a generally higher and more stable trend, reflecting persist… view at source ↗

**Figure 10.** Figure 10: GIS selection workflow displayed in WGS84 (EPSG:4326). Polygons and road segments are shown in green, while GPS observations are shown in red. Left panel: full infrastructure inside the data-driven bounding box. Middle: road subset chosen to maximize coverage of points within d0 = 150 m while limiting density. Right panel: polygons retained based on proximity to observations (nearest within 0.00135◦ ≈15… view at source ↗

**Figure 11.** Figure 11: Representative days from Cluster 1 (days 2, 10, 17). These days are dominated by stationary activity at the living place, indicating limited mobility. Cluster 2 (Day 4) 0.00 0.25 0.50 0.75 1.00 Normalized time (0 ... 1) Cluster 2 (Day 16) 0.00 0.25 0.50 0.75 1.00 Normalized time (0 ... 1) Cluster 2 (Day 22) 0.00 0.25 0.50 0.75 1.00 Normalized time (0 ... 1) [PITH_FULL_IMAGE:figures/full_fig_p036_11.png] view at source ↗

**Figure 12.** Figure 12: Representative days from Cluster 2 (days 4, 16, 22). These days show mobility between the living place and the main daytime hub, with minor variations such as detours or additional short-duration activities. We create five distinct daily activity patterns for this individual, as shown in [PITH_FULL_IMAGE:figures/full_fig_p036_12.png] view at source ↗

**Figure 13.** Figure 13: Spatial environment and true activity-time distribution used in the simulation study. Left panel: Map of the simulation layout, which consists of six polygons (home, restaurant, office, supermarket, park, and beach) and the connecting road network. Middle panel: True proportion of time spent in each polygon, computed from the activity-pattern model in [PITH_FULL_IMAGE:figures/full_fig_p042_13.png] view at source ↗

**Figure 14.** Figure 14: Overall time–use proportions and PN activity spaces in the simulation study. Top left panel: Estimated long-run proportion of time spent in each polygon. Top right panel: Estimated long-run proportion of time spent on each road segment. Bottom left panel: Level-γ PN activity spaces for polygons, showing the smallest sets of polygons that together account for γ ∈ {0.50, 0.70, 0.90, 0.95, 0.99} of total ti… view at source ↗

**Figure 15.** Figure 15: Clustering of the 90 simulated daily trajectories based on the time–weighted edit distance. Left panel: Affinity (distance) matrix ordered by hierarchical clustering. Distinct low-distance blocks along the diagonal indicate groups of days with highly similar activity sequences, corresponding closely to the five underlying daily activity patterns in the simulation design. Right panel: Single-linkage dend… view at source ↗

**Figure 16.** Figure 16: Stability analysis of the simulated mobility patterns over 90 days. Left panel: Daily activity-pattern labels, showing frequent alternation among the five patterns due to the weekday–weekend structure of the simulation design. Middle panel: Last-crossing time (LCT) for polygonbased activity spaces across coverage levels c. The sharp increases at c = 0.90 and c = 0.95 correspond to the addition of the… view at source ↗

read the original abstract

Human activity spaces are shaped by individual mobility and the built environment, motivating statistical methods that integrate GPS observations with GIS representations of places and routes. We propose a novel methodology to estimate activity spaces in built environments from GPS data within the Object Oriented Spatial Statistics framework. We characterize daily mobility through the distribution of time across spatial polygons and road segments, aiming to capture entity-specific time-use fractions and level-$\gamma$ activity spaces. We develop a time-weighted estimator to handle irregularly sampled GPS observations. We derive an error bound that quantifies the effects of measurement error, nearest-entity misclassification, temporal gaps, boundary crossings, and day-to-day variability. We also develop a map-augmented representation of daily activity patterns, a dwell-time-weighted distance for clustering daily trajectories, and polygon- and road-based stability summaries. Simulation studies and a real-data application demonstrate that the proposed framework recovers concentrated stationary anchors, interpretable travel corridors, and distinct stabilization behavior for dwelling and movement components, supporting the benefits of weighting under irregular sampling. KEYWORDS: GPS data, GIS, human mobility, space-time geography.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

The paper gives a workable time-weighted estimator plus error bound for GPS-based activity spaces in an object-oriented GIS setup, but the bound's treatment of dependent errors looks like the main weak point.

read the letter

The paper's core contribution is a time-weighted estimator for activity space estimation that handles irregular GPS sampling, combined with an error bound meant to cover measurement error, nearest-entity misclassification, temporal gaps, boundary crossings, and day-to-day variability. It also adds a map-augmented representation, a dwell-time-weighted distance for trajectory clustering, and polygon/road stability summaries, all inside the object-oriented spatial statistics frame. Simulations recover concentrated anchors and corridors, and the real-data example shows distinct stabilization patterns for dwelling versus movement, which suggests the weighting step adds value under irregular sampling. That integration of GPS tracks with GIS polygons and segments is practical for mobility and health applications. The soft spot is the error bound. The abstract and stress-test note give no sign that the derivation accounts for covariance or spatial dependence between the error sources; GPS error near boundaries can simultaneously inflate measurement error and misclassification, so an additive bound without regularity conditions on sampling density or GIS resolution risks understating total uncertainty. If the bound comes from separate first-order terms or calibrated constants, the claim that it quantifies all listed effects needs more explicit justification in the full text. The level-gamma parameter also appears without much discussion of sensitivity. This work is aimed at applied spatial statisticians and human geographers who already work with GPS/GIS data and want a structured way to incorporate time-use fractions and error awareness. A reader in that area would pick up usable ideas even if they adapt the bound. It deserves peer review because the framework is coherent, the validation steps are present, and the problem is real, though the theoretical error analysis will likely need tightening before publication.

Referee Report

1 major / 2 minor

Summary. The paper proposes an object-oriented spatial statistics framework for estimating human activity spaces from irregularly sampled GPS data integrated with GIS representations of polygons and road segments. It characterizes daily mobility via time distributions across these objects to capture entity-specific time-use fractions and level-γ activity spaces, introduces a time-weighted estimator, derives an error bound quantifying measurement error, nearest-entity misclassification, temporal gaps, boundary crossings, and day-to-day variability, and develops map-augmented daily patterns, dwell-time-weighted distances for clustering, and polygon/road-based stability summaries. Simulation studies and a real-data application are presented to show recovery of concentrated stationary anchors, interpretable travel corridors, and distinct stabilization for dwelling versus movement components.

Significance. If the error bound is shown to be rigorous and the time-weighted estimator demonstrably improves recovery under irregular sampling, the work offers a principled way to fuse GPS trajectories with GIS objects for activity-space estimation, with potential utility in mobility research and urban planning. The combination of a derived bound with empirical validation on both simulated and real data is a positive feature; the object-oriented framing may also aid interpretability of entity-specific patterns.

major comments (1)

[Error-bound derivation (methods section)] The central claim rests on the time-weighted estimator together with a derived error bound that 'quantifies the effects' of the five listed sources of variability (measurement error, misclassification, gaps, boundary crossings, day-to-day variability). The abstract provides no indication that the bound incorporates covariance terms or spatial dependence induced by GIS polygons and segments (e.g., GPS error near boundaries simultaneously inflating both measurement error and misclassification). If the bound is obtained via separate first-order expansions or simulation-calibrated constants without explicit regularity conditions on sampling density and GIS resolution, the total error can exceed the stated bound once autocorrelation or boundary effects are present. This directly affects whether the framework can be said to accurately account for all listed sources.

minor comments (2)

[Abstract] The abstract introduces 'level-γ activity spaces' without defining γ or its interpretation; a short clarification in the abstract or introduction would improve accessibility.
[Keywords] The keywords list omits 'activity space' and 'object-oriented statistics'; adding these would aid discoverability.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the careful and constructive review of our manuscript. The single major comment raises a valid point about the rigor of the error-bound derivation with respect to spatial dependence and regularity conditions. We address this below and indicate the revisions we will make.

read point-by-point responses

Referee: The central claim rests on the time-weighted estimator together with a derived error bound that 'quantifies the effects' of the five listed sources of variability (measurement error, misclassification, gaps, boundary crossings, day-to-day variability). The abstract provides no indication that the bound incorporates covariance terms or spatial dependence induced by GIS polygons and segments (e.g., GPS error near boundaries simultaneously inflating both measurement error and misclassification). If the bound is obtained via separate first-order expansions or simulation-calibrated constants without explicit regularity conditions on sampling density and GIS resolution, the total error can exceed the stated bound once autocorrelation or boundary effects are present. This directly affects whether the framework can be said to accurately account for all listed sources.

Authors: We appreciate the referee's observation on potential spatial dependence. The error bound is derived in the methods section by applying first-order expansions to each of the five sources individually and then aggregating them conservatively via the triangle inequality; this produces an upper bound that does not require explicit covariance modeling but is intended to remain valid under bounded dependence induced by the GIS geometry. We acknowledge that the manuscript does not currently state the necessary regularity conditions on sampling density and GIS resolution, nor does it explicitly discuss how boundary-induced autocorrelation is absorbed into the misclassification term. We will revise the methods section to add these conditions, include a short remark on the conservative nature of the bound, and expand the simulation studies to report empirical coverage under scenarios with induced spatial autocorrelation near polygon boundaries. revision: partial

Circularity Check

0 steps flagged

No circularity: estimator and error bound presented as derived from framework with independent validation

full rationale

The abstract and available text describe a time-weighted estimator developed to handle irregular GPS sampling and an error bound derived to quantify effects of measurement error, misclassification, gaps, boundary crossings, and day-to-day variability within the object-oriented spatial statistics framework. These are introduced as novel methodological contributions, followed by simulation studies and real-data application that demonstrate recovery of anchors and corridors. No equations or steps are shown that reduce the estimator or bound to fitted inputs by construction, self-definitional loops, or load-bearing self-citations. The derivation chain is presented as self-contained, with external validation via simulations rather than tautological renaming or ansatz smuggling. This is the expected non-finding for a methods paper whose central claims rest on explicit construction and empirical checks rather than circular reductions.

Axiom & Free-Parameter Ledger

1 free parameters · 2 axioms · 0 invented entities

Abstract-only review limits visibility into parameters and assumptions; the framework appears to introduce time allocation across objects and error quantification as core additions, with limited free parameters visible.

free parameters (1)

level-gamma
Defines the activity space level; value or selection rule not specified in abstract.

axioms (2)

domain assumption GPS observations can be mapped to spatial polygons and road segments to represent time-use fractions.
Invoked in the characterization of daily mobility.
domain assumption Irregular GPS sampling can be corrected via time-weighting without introducing bias beyond the quantified error bound.
Central to the estimator development.

pith-pipeline@v0.9.0 · 5490 in / 1423 out tokens · 35165 ms · 2026-05-12T00:58:34.809395+00:00 · methodology

discussion (0)

Reference graph

Works this paper leans on

47 extracted references · 47 canonical work pages

[1]

Baddeley, Gopalan Nair, Suman Rakshit, Greg McSwiggan, and Tilman M

A. Baddeley, Gopalan Nair, Suman Rakshit, Greg McSwiggan, and Tilman M. Davies. Analysing point patterns on networks — A review. Spatial Statistics, 42: 0 100435, 2021. Towards Spatial Data Science

work page 2021
[2]

Aaron Hipp, Philip M

David Berrigan, J. Aaron Hipp, Philip M. Hurvitz, Peter James, Marta M. Jankowska, Jacqueline Kerr, Francine Laden, Tammy Leonard, Robin A. McKinnon, Tiffany M. Powell-Wiley, Elizabeth Tarlov, Shannon N. Zenk, and The TREC Spatial and Contextual, Measures and Modeling Work Group . Geospatial and contextual approaches to energy balance and health. Annals o...

work page 2015
[3]

Stacey Bricka and Chandra R. Bhat. Comparative Analysis of Global Positioning System – Based and Travel Survey – Based Data . Transportation Research Record, 1972 0 (1): 0 9--20, January 2006. ISSN 0361-1981. doi:10.1177/0361198106197200102. URL https://doi.org/10.1177/0361198106197200102. Publisher: SAGE Publications Inc

work page doi:10.1177/0361198106197200102 1972
[4]

Urban form and household activity-travel behavior

Ron N Buliung and Pavlos S Kanaroglou. Urban form and household activity-travel behavior. Growth and Change, 37 0 (2): 0 172--199, 2006

work page 2006
[5]

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

Yen-Chi Chen and Adrian Dobra. Measuring human activity spaces from gps data with density ranking and summary curves. Annals of Applied Statistics, 14 0 (1): 0 409--432, 2020

work page 2020
[6]

Cressie, J

N. Cressie, J. Frey, B. Harck, and M. Smith. Spatial prediction on a river network. Journal of Agricultural, Biological and Environmental Statistics, 11: 0 127--150, 2006

work page 2006
[7]

A statistical framework for measuring the temporal stability of human mobility patterns

Zhihang Dong, Yen-Chi Chen, and Adrian Dobra. A statistical framework for measuring the temporal stability of human mobility patterns. Journal of Applied Statistics, 48 0 (1): 0 105--123, 2021. doi:10.1080/02664763.2019.1711363. URL https://doi.org/10.1080/02664763.2019.1711363

work page doi:10.1080/02664763.2019.1711363 2021
[8]

Entwisle

B. Entwisle. Putting people into place. Demography, 44: 0 687--703, 2007

work page 2007
[9]

Urban form, individual spatial footprints, and travel: Examination of space-use behavior

Yingling Fan and Asad J Khattak. Urban form, individual spatial footprints, and travel: Examination of space-use behavior. Transportation Research Record, 2082 0 (1): 0 98--106, 2008

work page 2082
[10]

A. S. Fotheringham and P. A. Rogerson. The M odifiable A real U nit P roblem ( M A U P ). In The SAGE handbook of spatial analysis, pages 105--124. Sage, 2008

work page 2008
[11]

R. G. Golledge. Human wayfinding and cognitive maps. In R. G. Golledge, editor, Wayfinding Behavior, pages 5--45. The Johns Hopkins University Press, Baltimore, 1999

work page 1999
[12]

R. G. Golledge and R. J. Stimson. Spatial Behavior. The Guildford Press, New York, 1997

work page 1997
[13]

H\" a gerstrand

T. H\" a gerstrand. What about people in regional science? Papers of the Regional Science Association, 24: 0 7--21, 1970

work page 1970
[14]

Abel, Alessandro Sorichetta, Arkadius Wi'sniowski, Ingmar Weber, and Andrew J

Christina Hughes, Emilio Zagheni, Guy J. Abel, Alessandro Sorichetta, Arkadius Wi'sniowski, Ingmar Weber, and Andrew J. Tatem. Inferring Migrations : Traditional Methods and New Approaches based on Mobile Phone , Social Media , and other Big Data : Feasibility study on Inferring (labour) mobility and migration in the European Union from big data and socia...

work page 2016
[15]

Malia Jones and Anne R. Pebley. Redefining neighborhoods using common destinations: social characteristics of activity spaces and home census tracts compared. Demography, 51 0 (3): 0 727--752, June 2014. ISSN 0070-3370. doi:10.1007/s13524-014-0283-z

work page doi:10.1007/s13524-014-0283-z 2014
[16]

The uncertain geographic context problem

Mei-Po Kwan. The uncertain geographic context problem. Annals of the Association of American Geographers, 102: 0 958--968, 2012

work page 2012
[17]

Beyond space (as we knew it): Toward temporally integrated geographies of segregation, health, and accessibility

Mei-Po Kwan. Beyond space (as we knew it): Toward temporally integrated geographies of segregation, health, and accessibility. Annals of the Association of American Geographers, 103: 0 1078--1086, 2013

work page 2013
[18]

Lapadat, Christian C

Alexandru M. Lapadat, Christian C. J. M. Tiberius, and Peter J. G. Teunissen. Experimental evaluation of smartphone accelerometer and low-cost dual frequency gnss sensors for deformation monitoring. Sensors, 21 0 (23): 0 7946, 2021. doi:10.3390/s21237946

work page doi:10.3390/s21237946 2021
[19]

Levenshtein

Vladimir I. Levenshtein. Binary codes capable of correcting deletions, insertions, and reversals. Soviet Physics Doklady, 10 0 (8): 0 707--710, 1966. Originally published in Doklady Akademii Nauk SSSR, 163:845–848 (1965)

work page 1966
[20]

Map-matching for low-sampling-rate gps trajectories

Yin Lou, Chengyang Zhang, Xing Xie, Yu Zheng, Wei Wang, and Yan Huang. Map-matching for low-sampling-rate gps trajectories. In Proceedings of 18th ACM SIGSPATIAL Conference on Advances in Geographical Information Systems, November 2009. URL https://www.microsoft.com/en-us/research/publication/map-matching-for-low-sampling-rate-gps-trajectories/

work page 2009
[21]

S. A. Matthews and T.-C. Yang. Spatial polygamy and contextual exposures ( S P A C E s): Promoting activity space approaches in research on place and health. The American Behavioral Scientist, 57: 0 1057--1081, 2013

work page 2013
[22]

J. D. Mazimpaka and S. Timpf. Trajectory data mining: A review of methods and applications. Journal of Spatial Information Science, 13: 0 61--99, 2016

work page 2016
[23]

Menafoglio and P

A. Menafoglio and P. Secchi. Statistical analysis of complex and spatially dependent data: A review of O bject O riented S patial S tatistics. European Journal of Operations Research, 258: 0 401--410, 2017

work page 2017
[24]

Urban activity spaces: Illustrations and application of a conceptual model for integrating the time and space dimensions

Tracy H Newsome, Wayne A Walcott, and Paul D Smith. Urban activity spaces: Illustrations and application of a conceptual model for integrating the time and space dimensions. Transportation, 25 0 (4): 0 357--377, 1998

work page 1998
[25]

Hidden markov map matching through noise and sparseness

Paul Newson and John Krumm. Hidden markov map matching through noise and sparseness. In 17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (ACM SIGSPATIAL GIS 2009), November 4-6, Seattle, WA, pages 336--343, November 2009. URL https://www.microsoft.com/en-us/research/publication/hidden-markov-map-matching-noise-sparseness/

work page 2009
[26]

Spatial Analysis along Networks

Atsuyuki Okabe and Kokichi Sugihara. Spatial Analysis along Networks. John Wiley and Sons, Ltd, 2012. ISBN 9781119967101. doi:https://doi.org/10.1002/9781119967101.fmatter. URL https://onlinelibrary.wiley.com/doi/abs/10.1002/9781119967101.fmatter

work page doi:10.1002/9781119967101.fmatter 2012
[27]

Survey Costs : Where are We and What is the Way Forward ? Journal of Survey Statistics and Methodology, 9 0 (5): 0 921--942, November 2021

Kristen Olson, James Wagner, and Raeda Anderson. Survey Costs : Where are We and What is the Way Forward ? Journal of Survey Statistics and Methodology, 9 0 (5): 0 921--942, November 2021. ISSN 2325-0984. doi:10.1093/jssam/smaa014. URL https://doi.org/10.1093/jssam/smaa014

work page doi:10.1093/jssam/smaa014 2021
[28]

Dgps enhancement to gps nmea output data: Dgps by correction projection to position-domain

Byungwoon Park, Jeongkeun Lee, Younsil Kim, Ho Yun, and Changdon Kee. Dgps enhancement to gps nmea output data: Dgps by correction projection to position-domain. The Journal of Navigation, 66 0 (2): 0 249--264, 2013. doi:10.1017/S0373463312000471

work page doi:10.1017/s0373463312000471 2013
[29]

Spatial Data Science With Applications in R

Edzer Pebesma and Roger Bivand. Spatial Data Science With Applications in R. Chapman and Hall/CRC, New York, 2023

work page 2023
[30]

Conceptualization and measurement of environmental exposure in epidemiology: Accounting for activity space related to daily mobility

Camille Perchoux, Basile Chaix, Steven Cummins, and Yan Kestens. Conceptualization and measurement of environmental exposure in epidemiology: Accounting for activity space related to daily mobility. Health & Place, 21: 0 86--93, 2013

work page 2013
[31]

Phillips, Brian L

Nolan E. Phillips, Brian L. Levy, Robert J. Sampson, Mario L. Small, and Ryan Q. Wang. The Social Integration of American Cities : Network Measures of Connectedness Based on Everyday Mobility Across Neighborhoods . Sociological Methods & Research, 50 0 (3): 0 1110--1149, August 2021. ISSN 0049-1241. doi:10.1177/0049124119852386. URL https://doi.org/10.117...

work page doi:10.1177/0049124119852386 2021
[32]

Why gps makes distances bigger than they are

Peter Ranacher, Richard Brunauer, Wolfgang Trutschnig, Stefan Van der Spek, and Siegfried Reich. Why gps makes distances bigger than they are. International Journal of Geographical Information Science, 30: 0 316--333, 2016

work page 2016
[33]

Richardson, Nora D

Douglas B. Richardson, Nora D. Volkow, Mei-Po Kwan, Robert M. Kaplan, Michael F. Goodchild, and Robert T. Croyle. Spatial turn in health research. Science, 339: 0 1390--1392, 2013

work page 2013
[34]

Sastry, B

N. Sastry, B. Ghosh- D astidar, J. Adams, and A. R. Pebley. The design of a multilevel survey of children, families, and communities: The L os A ngeles F amily and N eighborhood S urvey. Social Science Research, 35: 0 1000--1024, 2006

work page 2006
[35]

Schneider, Vitaly Belik, Thomas Couronn \'e , Zbigniew Smoreda, and Marta C

Christian M. Schneider, Vitaly Belik, Thomas Couronn \'e , Zbigniew Smoreda, and Marta C. Gonz \'a lez. Unravelling daily human mobility motifs. Journal of The Royal Society Interface, 10 0 (84): 0 20130246, 2013. doi:10.1098/rsif.2013.0246

work page doi:10.1098/rsif.2013.0246 2013
[36]

Sch\" o nfelder and K

S. Sch\" o nfelder and K. W. Axhausen. Activity spaces: measures of social exclusion? Transport Policy, 10: 0 273--286, 2003

work page 2003
[37]

Sch\" o nfelder and K

S. Sch\" o nfelder and K. W. Axhausen. On the variability of human activity spaces. In Martina Koll-Schretzenmayr, Marco Keiner, and Gustav Nussbaumer, editors, The Real and Virtual Worlds of Spatial Planning, pages 237--262. Springer Verlag, Berlin, Heidelberg, 2004

work page 2004
[38]

A suite of methods for representing activity space in a healthcare accessibility study

Jill E Sherman, John Spencer, John S Preisser, Wilbert M Gesler, and Thomas A Arcury. A suite of methods for representing activity space in a healthcare accessibility study. International journal of health geographics, 4 0 (1): 0 1--21, 2005

work page 2005
[39]

G lobal P ositioning S ystem S tandard P ositioning S ervice P erformance S tandard (5th ed.), 2020

United States Government . G lobal P ositioning S ystem S tandard P ositioning S ervice P erformance S tandard (5th ed.), 2020. URL https://www.gps.gov/technical/ps/2020-SPS-performance-standard.pdf

work page 2020
[40]

Small, and Robert J

Qi Wang, Nolan Edward Phillips, Mario L. Small, and Robert J. Sampson. Urban mobility and neighborhood isolation in America ’s 50 largest cities. Proceedings of the National Academy of Sciences of the United States of America, 115 0 (30): 0 7735--7740, July 2018. ISSN 0027-8424. doi:10.1073/pnas.1802537115. URL https://www.ncbi.nlm.nih.gov/pmc/articles/PM...

work page doi:10.1073/pnas.1802537115 2018
[41]

S. E. Wiehe, M. P. Kwan, J. Wilson, and J. D. Fortenberry. Adolescent health-risk behavior and community disorder. PloS One, 8: 0 e77667, 2013

work page 2013
[42]

David W. S. Wong and Shih-Lung Shaw. Measuring segregation: an activity space approach. Journal of geographical systems, 13 0 (2): 0 127--145, June 2011. ISSN 1435-5930. doi:10.1007/s10109-010-0112-x. URL https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3106997/

work page doi:10.1007/s10109-010-0112-x 2011
[43]

A statistical framework for analyzing activity pattern from gps data, 2025

Haoyang Wu, Yen-Chi Chen, and Adrian Dobra. A statistical framework for analyzing activity pattern from gps data, 2025. URL https://arxiv.org/abs/2504.04316

work page arXiv 2025
[44]

Yang et al

H. Yang et al. Exploring human mobility: A time-informed approach to pattern mining and sequence similarity. International Journal of Geographical Information Science, 2025. Discusses sequence similarity measures including edit distance, LCS, DTW for human mobility patterns

work page 2025
[45]

Demographic research with non-representative internet data

Emilio Zagheni and Ingmar Weber. Demographic research with non-representative internet data. International Journal of Manpower, 36 0 (1): 0 13--25, January 2015. ISSN 0143-7720. doi:10.1108/IJM-12-2014-0261. URL https://doi.org/10.1108/IJM-12-2014-0261. Publisher: Emerald Group Publishing Limited

work page doi:10.1108/ijm-12-2014-0261 2015
[46]

S. N. Zenk, A. J. Schulz, S. A. Matthews, A. Odoms- Y oung, J. Wilbur, L. Wegrzyn, K. Gibbs, C. Braunschweig, and C. Stokes. Activity space environment and dietary and physical activity behaviors: a pilot study. Health & Place, 17: 0 1150--1161, 2011

work page 2011
[47]

Zhai et al

W. Zhai et al. Detecting and clustering patterns of human activities using an augmented space–time-weighted edit distance method. Transportation Research Part C, 2019. Introduces weighted edit distance approaches to trajectory similarity

work page 2019