pith. sign in

arxiv: 2605.20429 · v1 · pith:XLQPFJNPnew · submitted 2026-05-19 · 📊 stat.AP

Design and Validation of a Grid-based Home Detection via Stay-Time (GHOST) Software for Mobile Location Data

Alessandra Recalde , Mustafa Sameen , Xiaojian Zhang , Xilei Zhao This is my paper

Pith reviewed 2026-05-21 06:35 UTC · model grok-4.3

classification 📊 stat.AP
keywords home detectionmobile location dataGPSgrid-based algorithmstay-time analysishuman mobilityalgorithm validation
0
0 comments X

The pith

The GHOST algorithm detects home locations from mobile GPS data more accurately than prior methods by counting nighttime and weekend grid visits.

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

This paper presents GHOST, an open-source method that divides location data into grids and selects the cell with the most visits during nighttime hours or weekend daytime to infer where someone lives. Accurate home detection from phone data matters for transportation planning, public health tracking, and emergency response because many studies start from this step. The authors test the method on a large Boston dataset of over 155,000 trips and on self-reported homes from ten volunteers in different states. They compare it to five existing algorithms and find lower average errors under various settings.

Core claim

GHOST infers proxy home locations by identifying the most frequently visited nighttime or weekend daytime grid cells based on customizable spatial and temporal filters. Validation using the BostonWalks dataset with 377 participants and ground-truth coordinates from ten volunteers across U.S. regions shows that GHOST outperforms five well-established algorithms in accuracy and robustness, with average errors as low as 22.3 meters under optimal configurations, and grid size emerges as the most influential parameter.

What carries the argument

Grid-based stay-time filtering that selects the single grid cell with highest visit frequency during chosen nighttime or weekend periods as the home proxy.

If this is right

  • More reliable home locations improve downstream analyses in transportation planning and public health studies.
  • Customizable spatial and temporal filters let users adapt the method to different data sampling rates and urban settings.
  • Open-source Python implementation allows direct application to other large mobile location datasets.
  • Emphasis on grid size as the dominant parameter guides future tuning of similar detection tools.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same grid-frequency logic could be applied to detect regular daytime locations such as workplaces without major redesign.
  • Performance differences between dense urban and sparse rural areas would clarify the method's robustness limits.
  • Combining GHOST outputs with other mobility metrics might yield more complete daily activity profiles from the same raw traces.

Load-bearing premise

Self-reported home coordinates from ten volunteers provide reliable ground truth that holds across diverse U.S. regions and noise patterns.

What would settle it

Obtain verified home addresses for a new group of at least 100 users via independent records and measure whether GHOST average location error stays below 25 meters on the same data.

Figures

Figures reproduced from arXiv: 2605.20429 by Alessandra Recalde, Mustafa Sameen, Xiaojian Zhang, Xilei Zhao.

Figure 1
Figure 1. Figure 1: Home Location Inference Algorithms 4.2 Algorithm Robustness and Advantages The GHOST algorithm incorporates several design decisions that make it particularly robust and advantageous for real-world applications: 4.2.1 Computational Efficiency Unlike traditional clustering methods that require pairwise distance calculations or iterative op￾timization, GHOST operates through simple spatial binning and aggreg… view at source ↗
Figure 2
Figure 2. Figure 2: Home Location Inference Algorithms 19 [PITH_FULL_IMAGE:figures/full_fig_p019_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: RMSE and MAE for Both Dataset locations can dominate the selection process, leading to inaccurate home estimates. Together, these approaches demonstrate a shared vulnerability: they are highly influenced by noise that does not represent true residential behavior. DBSCAN and A2 demonstrate comparatively improved resilience by incorporating built-in filtering mechanisms. DBSCAN requires a minimum density thr… view at source ↗
read the original abstract

Accurately detecting home locations from GPS data generated by mobile devices is a foundational step in human mobility research, with significant implications for transportation planning, public health, and emergency response. However, existing home detection algorithms often produce unreliable results for noisy real-world data and are barely validated due to a lack of ground-truth benchmarks. To tackle these limitations, this study presents the development and validation of a Grid-based home detection via Stay-Time (GHOST) algorithm, implemented as an open-source Python package. The algorithm infers proxy home locations by identifying the most frequently visited nighttime or weekend daytime grid cells based on customizable spatial and temporal filters. To validate its performance, we use the large-scale BostonWalks dataset, which includes over 155,000 trips from 377 participants in the Boston metropolitan area, to test robustness to noisy data. Additionally, we collected a ground-truth dataset for ten volunteers across different regions in the U.S., including Florida, Mississippi, and Colorado, along with their self-reported home coordinates, to evaluate GHOST across diverse mobility patterns and sampling conditions. We compared GHOST accuracy to that of 5 well-established home detection algorithms: All-time clustering method, Stay-point method, DBSCAN, K-MEANS++, and SciKit-Mobility Home Detection, across multiple parameter settings. Results show that GHOST outperforms all algorithms in accuracy and robustness, with average errors as low as 22.3 meters under optimal configurations. Our findings highlight the high accuracy and flexibility of our algorithm, with grid size being the most influential parameter during validation, demonstrating the potential of this algorithm for real-world mobile location data analysis.

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.

Referee Report

2 major / 2 minor

Summary. The manuscript presents GHOST, an open-source grid-based algorithm for inferring home locations from noisy mobile GPS data by selecting the most-visited grid cell during customizable nighttime or weekend daytime windows. Validation uses the BostonWalks dataset (155k+ trips, 377 participants) for robustness checks and a new ground-truth collection of self-reported home coordinates from 10 volunteers across U.S. regions; GHOST is compared to five baselines (all-time clustering, stay-point, DBSCAN, K-MEANS++, SciKit-Mobility) across parameter sweeps and is reported to achieve minimum average errors of 22.3 m while outperforming all comparators, with grid size identified as the dominant parameter.

Significance. If the quantitative superiority claim holds, the work supplies a practical, parameter-flexible, and openly available tool that could improve the reliability of home-location inference in mobility, public-health, and emergency-response studies. The explicit comparison to multiple baselines on both large-scale and ground-truthed data, together with the identification of grid size as the most influential parameter, offers actionable guidance for practitioners.

major comments (2)
  1. [Ground-truth validation section] Ground-truth validation section: The headline accuracy result (22.3 m average error and outperformance over all five baselines) is computed as distance to self-reported coordinates from only ten volunteers. With such a small n, the reported minimum error and relative ranking are sensitive to any systematic offset or high variance in the self-reports; the manuscript provides no independent verification of report precision, no error bars on the 22.3 m figure, and no power analysis, rendering the quantitative superiority claim under-powered for generalization across U.S. regions and data-noise regimes.
  2. [Results and parameter-sweep section] Results and parameter-sweep section: The claim that GHOST is robust to noisy data rests on the BostonWalks dataset, yet that dataset supplies no independent home labels. Consequently, robustness is demonstrated only via stability of inferred locations across parameter settings, not via absolute accuracy; this distinction should be clarified so that readers do not conflate the two validation regimes.
minor comments (2)
  1. [Methods] The manuscript should report the exact grid sizes, temporal filter thresholds, and stay-time cut-offs that produced the 22.3 m minimum so that the optimal configuration can be reproduced.
  2. [Figures] Figure captions and axis labels for the error-distribution plots would benefit from explicit units and sample-size annotations (n=10 for ground truth).

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback, which helps clarify the scope and limitations of our validation approaches. We address each major comment below and indicate the revisions we will make.

read point-by-point responses

  1. Referee: [Ground-truth validation section] Ground-truth validation section: The headline accuracy result (22.3 m average error and outperformance over all five baselines) is computed as distance to self-reported coordinates from only ten volunteers. With such a small n, the reported minimum error and relative ranking are sensitive to any systematic offset or high variance in the self-reports; the manuscript provides no independent verification of report precision, no error bars on the 22.3 m figure, and no power analysis, rendering the quantitative superiority claim under-powered for generalization across U.S. regions and data-noise regimes.

    Authors: We acknowledge that a ground-truth sample of ten volunteers limits statistical power and generalizability, and that self-reported coordinates lack independent verification. Collecting verified home locations at scale remains challenging due to privacy constraints. Our dataset does span multiple regions (Florida, Mississippi, Colorado) to sample diverse mobility patterns. In the revision we will add error bars (standard deviation and 95% confidence intervals) to the reported average errors, explicitly discuss the small-sample limitation and absence of report verification, and moderate claims about broad generalization. A formal power analysis was not performed; we will note this as a remaining limitation while retaining the comparative results as descriptive evidence of performance on the available data. revision: partial

  2. Referee: [Results and parameter-sweep section] Results and parameter-sweep section: The claim that GHOST is robust to noisy data rests on the BostonWalks dataset, yet that dataset supplies no independent home labels. Consequently, robustness is demonstrated only via stability of inferred locations across parameter settings, not via absolute accuracy; this distinction should be clarified so that readers do not conflate the two validation regimes.

    Authors: We agree that the distinction between the two validation regimes must be stated more explicitly. The BostonWalks dataset (155k+ trips, no home labels) is used solely to examine stability of inferred locations across parameter sweeps and noise levels. Absolute accuracy is evaluated only on the separate ground-truth dataset. We will revise the Results and Methods sections to label each analysis clearly and to caution readers against conflating stability with absolute accuracy. revision: yes

Circularity Check

0 steps flagged

No circularity: empirical validation uses external ground truth and baselines

full rationale

The paper describes a grid-based algorithm for inferring home locations from GPS traces and validates it through direct comparison to self-reported coordinates from 10 volunteers plus performance on the independent BostonWalks dataset against five published external algorithms. No equations define a quantity in terms of itself, no fitted parameters are relabeled as predictions, and no load-bearing premise rests on self-citation. All quantitative claims (error distances, outperformance rankings) are computed from observable data points external to the algorithm's own logic.

Axiom & Free-Parameter Ledger

2 free parameters · 1 axioms · 0 invented entities

The algorithm depends on user-chosen spatial and temporal filters whose optimal values are determined during validation rather than derived from first principles.

free parameters (2)
  • grid size
    Identified as the most influential parameter; chosen to balance spatial resolution against data sparsity in noisy GPS traces.
  • nighttime and weekend daytime temporal filters
    Customizable thresholds that define which GPS points are retained for home inference.
axioms (1)
  • domain assumption Nighttime and weekend daytime GPS points are more likely to occur at or near the true home location than other times.
    Invoked in the algorithm definition to select the proxy home grid cell.

pith-pipeline@v0.9.0 · 5841 in / 1301 out tokens · 28124 ms · 2026-05-21T06:35:01.634761+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

77 extracted references · 77 canonical work pages · 2 internal anchors

  1. [1]

    Staying at home is a privilege: evidence from fine-grained mobile phone location data in the U.S

    Huang, Xiao and Lu, Junyu and Gao, Song and Wang, Sicheng and Liu, Zhewei and Wei, Hanxue , year =. Staying at home is a privilege: evidence from fine-grained mobile phone location data in the U.S. during the COVID-19 pandemic , journal =

    work page

  2. [2]

    Geographical Analysis , volume =

    Saxon, James , title =. Geographical Analysis , volume =. doi:https://doi.org/10.1111/gean.12265 , url =. https://onlinelibrary.wiley.com/doi/pdf/10.1111/gean.12265 , year =

    work page doi:10.1111/gean.12265

  3. [3]

    Situational-aware multi-graph convolutional recurrent network (SA-MGCRN) for travel demand forecasting during wildfires , journal =

    Xiaojian Zhang and Xilei Zhao and Yiming Xu and Daniel Nilsson and Ruggiero Lovreglio , keywords =. Situational-aware multi-graph convolutional recurrent network (SA-MGCRN) for travel demand forecasting during wildfires , journal =. 2024 , issn =. doi:https://doi.org/10.1016/j.tra.2024.104242 , url =

    work page doi:10.1016/j.tra.2024.104242 2024

  4. [4]

    2014 , issue_date =

    Li, Weifeng and Cheng, Xiaoyun and Duan, Zhengyu and Yang, Dongyuan and Guo, Gaohua , title =. 2014 , issue_date =. doi:10.1155/2014/363502 , journal =

    work page doi:10.1155/2014/363502 2014

  5. [5]

    Journal of Advanced Transportation , volume =

    Yu, Qing and Li, Weifeng and Yang, Dongyuan and Zhang, Haoran , title =. Journal of Advanced Transportation , volume =. doi:https://doi.org/10.1155/2020/8835981 , url =. https://onlinelibrary.wiley.com/doi/pdf/10.1155/2020/8835981 , year =

    work page doi:10.1155/2020/8835981 2020

  6. [6]

    Behavioral changes during the COVID-19 pandemic decreased income diversity of urban encounters , volume=

    Yabe, Takahiro and Bueno, Bernardo García Bulle and Dong, Xiaowen and Pentland, Alex and Moro, Esteban , year=. Behavioral changes during the COVID-19 pandemic decreased income diversity of urban encounters , volume=. Nature Communications , publisher=. doi:10.1038/s41467-023-37913-y , number=

    work page doi:10.1038/s41467-023-37913-y

  7. [7]

    and Barabasi, Albert-Laszlo , year =

    Gonzalez, Marta C. and Barabasi, Albert-Laszlo , year =. Understanding Individual Human Mobility Patterns , volume =. Nature , doi =

    work page

  8. [8]

    Mobility patterns are associated with experienced income segregation in large US cities , volume =

    Moro, Esteban and Calacci, Dan and Dong, Xiaowen and Pentland, Alex , year =. Mobility patterns are associated with experienced income segregation in large US cities , volume =. Nature Communications , doi =

    work page

  9. [9]

    Estimating Wildfire Evacuation Decision and Departure Timing Using Large-Scale GPS Data , volume =

    Zhao, Xilei and Xu, Yiming and Lovreglio, Ruggiero and Kuligowski, Erica and Nilsson, Daniel and Cova, Thomas and Wu, Alex and Yan, Xiang , year =. Estimating Wildfire Evacuation Decision and Departure Timing Using Large-Scale GPS Data , volume =. Transportation Research Part D Transport and Environment , doi =

    work page

  10. [10]

    Estimating Origin-Destination flows using opportunistically collected mobile phone location data from one million users in Boston Metropolitan Area , volume =

    Calabrese, Francesco and Lorenzo, Giusy and Liu, Liang and Ratti, Carlo , year =. Estimating Origin-Destination flows using opportunistically collected mobile phone location data from one million users in Boston Metropolitan Area , volume =

    work page

  11. [11]

    and Lenormand, Maxime and Louail, Thomas and Menezes, Ronaldo and Ramasco, José J

    Barbosa, Hugo and Barthelemy, Marc and Ghoshal, Gourab and James, Charlotte R. and Lenormand, Maxime and Louail, Thomas and Menezes, Ronaldo and Ramasco, José J. and Simini, Filippo and Tomasini, Marcello , year=. Human mobility: Models and applications , volume=. doi:10.1016/j.physrep.2018.01.001 , journal=

    work page doi:10.1016/j.physrep.2018.01.001 2018

  12. [12]

    Mitigating biases in big mobility data: a case study of monitoring large-scale transit systems , volume =

    Wang, Feilong and Ban, Xuegang (Jeff) and Chen, Peng and Liu, Chenxi and Zhao, Rong , year =. Mitigating biases in big mobility data: a case study of monitoring large-scale transit systems , volume =. Transportation Letters The International Journal of Transportation Research , doi =

    work page

  13. [13]

    Inferring transportation modes from GPS trajectories using a convolutional neural network

    Sina Dabiri and Kevin P. Heaslip , title =. CoRR , volume =. 2018 , url =. 1804.02386 , timestamp =

    work page internal anchor Pith review Pith/arXiv arXiv 2018

  14. [14]

    EPJ Data Science , volume=

    Comparison of home detection algorithms using smartphone GPS data , author=. EPJ Data Science , volume=. 2024 , publisher=. doi:10.1140/epjds/s13688-023-00447-w , url=

    work page doi:10.1140/epjds/s13688-023-00447-w 2024

  15. [15]

    Using Mobile Positioning Data to Model Locations Meaningful to Users of Mobile Phones , volume =

    Ahas, Rein and Silm, Siiri and Järv, Olle and Saluveer, Erki and Tiru, Margus , year =. Using Mobile Positioning Data to Model Locations Meaningful to Users of Mobile Phones , volume =. Journal of Urban Technology , doi =

    work page

  16. [16]

    Modeling and Analyzing Urban Networks and Amenities With OSMnx.Geographical Analysis, 57(4):567–577, October 2025

    Boeing, Geoff , title =. Geographical Analysis , volume =. 2025 , pages =. doi:https://doi.org/10.1111/gean.70009 , url =

    work page doi:10.1111/gean.70009 2025

  17. [17]

    Kelsey Jordahl and Joris Van den Bossche and Martin Fleischmann and Jacob Wasserman and James McBride and Jeffrey Gerard and Jeff Tratner and Matthew Perry and Adrian Garcia Badaracco and Carson Farmer and Geir Arne Hjelle and Alan D. Snow and Micah Cochran and Sean Gillies and Lucas Culbertson and Matt Bartos and Nick Eubank and maxalbert and Aleksey Bil...

    work page doi:10.5281/zenodo.3946761 2020

  18. [18]

    Scikit-learn: Machine Learning in Python , volume =

    Pedregosa, Fabian and Varoquaux, Gael and Gramfort, Alexandre and Michel, Vincent and Thirion, Bertrand and Grisel, Olivier and Blondel, Mathieu and Prettenhofer, Peter and Weiss, Ron and Dubourg, Vincent and Vanderplas, Jake and Passos, Alexandre and Cournapeau, David and Brucher, Matthieu and Perrot, Matthieu and Duchesnay, Edouard and Louppe, Gilles , ...

    work page

  19. [19]

    , year =

    Schneider, Christian and Belik, Vitaly and Couronné, Thomas and Smoreda, Zbigniew and Gonzalez, Marta C. , year =. Unravelling daily human mobility motifs , volume =. Journal of the Royal Society, Interface / the Royal Society , doi =

    work page

  20. [20]

    Assessing the Quality of Home Detection from Mobile Phone Data for Official Statistics , volume=

    Vanhoof, Maarten and Reis, Fernando and Ploetz, Thomas and Smoreda, Zbigniew , year=. Assessing the Quality of Home Detection from Mobile Phone Data for Official Statistics , volume=. Journal of Official Statistics , publisher=. doi:10.2478/jos-2018-0046 , number=

    work page doi:10.2478/jos-2018-0046 2018

  21. [21]

    Accuracy of iPhone Locations: A Comparison of Assisted GPS, WiFi and Cellular Positioning , volume =

    Zandbergen, Paul A , year =. Accuracy of iPhone Locations: A Comparison of Assisted GPS, WiFi and Cellular Positioning , volume =. Transactions in GIS , doi =

    work page

  22. [22]

    DBSCAN Clustering Algorithm Based on Density , doi =

    Deng, Dingsheng , year =. DBSCAN Clustering Algorithm Based on Density , doi =

    work page

  23. [23]

    Scalable K-Means++ , volume =

    Bahmani, Bahman and Moseley, Benjamin and Vattani, Andrea and Kumar, Ravi and Vassilvitskii, Sergei , year =. Scalable K-Means++ , volume =. Proc. VLDB Endow. , doi =

    work page

  24. [24]

    K-Means++: The Advantages of Careful Seeding , volume =

    Arthur, David and Vassilvitskii, Sergei , year =. K-Means++: The Advantages of Careful Seeding , volume =. Proc. of the Annu. ACM-SIAM Symp. on Discrete Algorithms , doi =

    work page

  25. [25]

    Gupta , title =

    R. Gupta , title =. 2023 , url =

    work page 2023

  26. [26]

    On some properties of medians, percentiles, baselines, and thresholds in empirical bibliometric analysis , volume=

    Pislyakov, Vladimir , year=. On some properties of medians, percentiles, baselines, and thresholds in empirical bibliometric analysis , volume=. Journal of Informetrics , publisher=. doi:10.1016/j.joi.2022.101322 , number=

    work page doi:10.1016/j.joi.2022.101322 2022

  27. [27]

    Cynthia Chen and Xuegang (Jeff) Ban and Feilong Wang and Jingxing Wang and Choudhury Siddique and Rong Fan and Jaehun Lee , title =

    J.L. Cynthia Chen and Xuegang (Jeff) Ban and Feilong Wang and Jingxing Wang and Choudhury Siddique and Rong Fan and Jaehun Lee , title =. 2017 , number =

    work page 2017

  28. [28]

    Clustering to Reduce Spatial Data Set Size , journal =

    Boeing, Geoff , year =. Clustering to Reduce Spatial Data Set Size , journal =

    work page

  29. [29]

    Exploring the uncertainty of activity zone detection using digital footprints with multi-scaled DBSCAN , isbn =

    Liu, Xinyi and Huang, Qunying and Gao, Song , year =. Exploring the uncertainty of activity zone detection using digital footprints with multi-scaled DBSCAN , isbn =. doi:10.4324/9781003123842-5 , journal =

    work page doi:10.4324/9781003123842-5

  30. [30]

    Emre Celebi and Hassan A

    M. Emre Celebi and Hassan A. Kingravi and Patricio A. Vela , title =. Expert Systems with Applications , volume =. 2013 , doi =

    work page 2013

  31. [31]

    Electronics , volume =

    Mohiuddin Ahmed and Raihan Seraj and Syed Mohammed Shamsul Islam , title =. Electronics , volume =. 2020 , publisher =. doi:10.3390/electronics9081295 , url =

    work page doi:10.3390/electronics9081295 2020

  32. [32]

    Communications Physics , volume =

    Distorted insights from human mobility data , author =. Communications Physics , volume =. 2024 , publisher =. doi:10.1038/s42005-024-01909-x , url =

    work page doi:10.1038/s42005-024-01909-x 2024

  33. [33]

    arXiv preprint arXiv:1809.09911 , year =

    Performance and sensitivities of home detection from mobile phone data , author =. arXiv preprint arXiv:1809.09911 , year =

    work page arXiv

  34. [34]

    International Journal of Digital Earth , volume=

    Human mobility data in the COVID-19 pandemic: characteristics, applications, and challenges , author=. International Journal of Digital Earth , volume=. 2021 , publisher=

    work page 2021

  35. [35]

    2024 , month = feb, number =

    Bian, Ruijie Rebecca and Tolford, Tara , title =. 2024 , month = feb, number =

    work page 2024

  36. [36]

    arXiv preprint arXiv:2410.16462 , year=

    Comparative Analysis of Human Mobility Patterns: Utilizing Taxi and Mobile (SafeGraph) Data to Investigate Neighborhood-Scale Mobility in New York City , author=. arXiv preprint arXiv:2410.16462 , year=

    work page arXiv

  37. [37]

    Transactions in GIS , volume=

    Quality of hybrid location data drawn from GPS-enabled mobile phones: Does it matter? , author=. Transactions in GIS , volume=. 2020 , publisher=. doi:10.1111/tgis.12612 , pmid=

    work page doi:10.1111/tgis.12612 2020

  38. [38]

    Applied Sciences , volume=

    A Novel K-Means Clustering Algorithm with a Noise Algorithm for Capturing Urban Hotspots , author=. Applied Sciences , volume=. 2021 , publisher=

    work page 2021

  39. [39]

    Procedia Computer Science , year=

    Evaluating and Validating Stay Point Detection Algorithms with different GPS Log Intervals , author=. Procedia Computer Science , year=

    work page

  40. [40]

    2020 , eprint=

    A Data-Driven Travel Mode Share Estimation Framework based on Mobile Device Location Data , author=. 2020 , eprint=

    work page 2020

  41. [41]

    Journal of Statistical Software , volume=

    Scikit-mobility: A Python library for the analysis, generation, and risk assessment of mobility data , author=. Journal of Statistical Software , volume=. 2022 , doi=

    work page 2022

  42. [42]

    Computing in Civil Engineering 2019: Data, Sensing, and Analytics—Selected Papers from the ASCE International Conference on Computing in Civil Engineering 2019 , pages =

    Sadeghinasr, Behrang and Akhavan, Amin and Wang, Qian , title =. Computing in Civil Engineering 2019: Data, Sensing, and Analytics—Selected Papers from the ASCE International Conference on Computing in Civil Engineering 2019 , pages =. 2019 , publisher =

    work page 2019

  43. [43]

    Proceedings of the 16th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems , pages =

    Li, Qiang and Zheng, Yu and Xie, Xing and Chen, Yukun and Liu, Wei-Ying and Ma, Wei-Ying , title =. Proceedings of the 16th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems , pages =. 2008 , publisher =

    work page 2008

  44. [44]

    PLOS ONE , volume =

    Association between mobility patterns and COVID-19 transmission in the United States , author =. PLOS ONE , volume =. 2022 , doi =

    work page 2022

  45. [45]

    JMIR mHealth and uHealth , volume =

    Extracting and visualizing mobility patterns from GPS data collected using smartphones , author =. JMIR mHealth and uHealth , volume =. 2019 , doi =

    work page 2019

  46. [46]

    Proceedings of the National Academy of Sciences , volume =

    Understanding mobility-based segregation in cities , author =. Proceedings of the National Academy of Sciences , volume =. 2018 , doi =

    work page 2018

  47. [47]

    Where Chicagoans tweet the most: Semantic analysis of preferential return locations of Twitter users

    Understanding individual human mobility patterns , author =. arXiv preprint arXiv:1512.06880 , year =

    work page internal anchor Pith review Pith/arXiv arXiv

  48. [48]

    Mobility Patterns and User Dynamics in Racially Segregated Geographies of

    Bora, Nikhil and Chang, Yu-Han and Maheswaran, Ramesh , booktitle =. Mobility Patterns and User Dynamics in Racially Segregated Geographies of. 2014 , doi =

    work page 2014

  49. [49]

    Sustainability , volume =

    Analysis of Spatial Aggregation and Activity of the Urban Population of Almaty Based on Cluster Analysis , author =. Sustainability , volume =. 2025 , publisher =. doi:10.3390/su17073243 , url =

    work page doi:10.3390/su17073243 2025

  50. [50]

    Transportation Research Record: Journal of the Transportation Research Board , volume =

    Exploring Individual Activity-Travel Patterns Based on Geolocation Data from Mobile Phones , author =. Transportation Research Record: Journal of the Transportation Research Board , volume =. 2021 , doi =

    work page 2021

  51. [51]

    Future Transportation , volume =

    Identification of Individual Mobility Anchor Places and Patterns Based on Mobile Phone GPS Data , author =. Future Transportation , volume =. 2024 , doi =

    work page 2024

  52. [52]

    Applied Sciences , volume =

    Applied Techniques for Twitter Data Retrieval in an Urban Area: Insight for Trip Production Modeling , author =. Applied Sciences , volume =. 2023 , doi =

    work page 2023

  53. [53]

    scikit-mobility documentation: individual measures , howpublished =

    work page

  54. [54]

    Scientific Data , volume =

    A Combined Naturalistic Driving, Clinical, and Neurobehavioral Data Set for Investigating Aging and Dementia , author =. Scientific Data , volume =. 2025 , doi =

    work page 2025

  55. [55]

    Sensors , volume =

    Relationship of Community Mobility, Vital Space, and Faller Status in Older Adults , author =. Sensors , volume =. 2024 , doi =

    work page 2024

  56. [56]

    Sensors , volume =

    How Mobility and Sociality Reshape the Context: A Decade of Experience in Mobile CrowdSensing , author =. Sensors , volume =. 2021 , publisher =. doi:10.3390/s21196397 , url =

    work page doi:10.3390/s21196397 2021

  57. [57]

    IEEE Transactions on Pattern Analysis and Machine Intelligence , volume =

    Mean shift, mode seeking, and clustering , author =. IEEE Transactions on Pattern Analysis and Machine Intelligence , volume =. 1995 , doi =

    work page 1995

  58. [58]

    Takahiro Yabe and Nicholas K. W. Jones and P. Suresh C. Rao and Marta C. Gonzalez and Satish V. Ukkusuri , title =. Computers, Environment and Urban Systems , volume =. 2022 , doi =

    work page 2022

  59. [59]

    Spatiotemporal route estimation consistent with human mobility using cellular network data , year=

    Kanasugi, Hiroshi and Sekimoto, Yoshihide and Kurokawa, Mori and Watanabe, Takafumi and Muramatsu, Shigeki and Shibasaki, Ryosuke , booktitle=. Spatiotemporal route estimation consistent with human mobility using cellular network data , year=

    work page

  60. [60]

    Transportation Research Part D: Transport and Environment , volume =

    Effects of income inequality on evacuation, reentry and segregation after disasters , author =. Transportation Research Part D: Transport and Environment , volume =. 2020 , doi =

    work page 2020

  61. [61]

    International Journal of Online Engineering , year=

    T-DBSCAN: A spatiotemporal density clustering for GPS trajectory segmentation , author=. International Journal of Online Engineering , year=

    work page

  62. [62]

    Sensors , volume=

    Identification of stopping points in GPS trajectories using spatiotemporal clustering , author=. Sensors , volume=. 2023 , url=

    work page 2023

  63. [63]

    ISPRS International Journal of Geo-Information , volume=

    An improved DBSCAN algorithm to detect stops in individual trajectories , author=. ISPRS International Journal of Geo-Information , volume=. 2017 , url=

    work page 2017

  64. [64]

    Proceedings of the 2nd International Conference on Knowledge Discovery and Data Mining (KDD) , pages=

    A density-based algorithm for discovering clusters in large spatial databases with noise , author=. Proceedings of the 2nd International Conference on Knowledge Discovery and Data Mining (KDD) , pages=

    work page

  65. [65]

    Proceedings of the 18th International World Wide Web Conference , pages=

    Mining interesting locations and travel sequences from GPS trajectories , author=. Proceedings of the 18th International World Wide Web Conference , pages=. 2010 , url=

    work page 2010

  66. [66]

    ACM Transactions on Database Systems , volume=

    DBSCAN revisited, revisited: Why and how you should (still) use DBSCAN , author=. ACM Transactions on Database Systems , volume=

    work page

  67. [67]

    Pattern Recognition Letters , year=

    A grid-growing clustering algorithm for geo-spatial data , author=. Pattern Recognition Letters , year=

    work page

  68. [68]

    Pattern Recognition , year=

    Grid-based method for GPS trajectory analysis , author=. Pattern Recognition , year=

    work page

  69. [69]

    Transportation , year=

    Identification of activity stop locations in GPS trajectories , author=. Transportation , year=

    work page

  70. [70]

    and Bashan, N

    Meister, A. and Bashan, N. F. and Basu, R. and others , title =. Transportation , year =

    work page

  71. [71]

    and Zhou, X

    Li, Y. and Zhou, X. and Gu, J. and Guo, K. and Deng, W. , title =. Applied Sciences , year =

    work page

  72. [72]

    IEEE Transactions on Intelligent Transportation Systems , volume=

    Trip distribution modeling using mobile phone data: Emphasis on intra-zonal trips , author=. IEEE Transactions on Intelligent Transportation Systems , volume=. 2018 , publisher=

    work page 2018

  73. [73]

    Nature Physics , volume=

    Modelling the scaling properties of human mobility , author=. Nature Physics , volume=. 2010 , publisher=

    work page 2010

  74. [74]

    PLoS ONE , volume=

    Cross-comparative analysis of evacuation behavior after earthquakes using mobile phone data , author=. PLoS ONE , volume=. 2019 , doi=

    work page 2019

  75. [75]

    Palgrave Communications , volume=

    Exploring the use of mobile phone data for national migration statistics , author=. Palgrave Communications , volume=. 2019 , publisher=

    work page 2019

  76. [76]

    ISPRS International Journal of Geo-Information , volume=

    A review of urban mobility research using mobile phone data , author=. ISPRS International Journal of Geo-Information , volume=. 2022 , publisher=

    work page 2022

  77. [77]

    Journal of Transport Geography , volume=

    Mobile phone data for human mobility analysis: Opportunities and challenges , author=. Journal of Transport Geography , volume=. 2024 , publisher=

    work page 2024