pith. machine review for the scientific record. sign in

arxiv: 2605.14540 · v1 · submitted 2026-05-14 · 💻 cs.DC

Recognition: 2 theorem links

· Lean Theorem

Analysis of wireless network access logs for a hierarchical characterization of user mobility

Francisco Talavera , Isaac Lera , Carlos Guerrero
Authors on Pith no claims yet

Pith reviewed 2026-05-15 01:31 UTC · model grok-4.3

classification 💻 cs.DC
keywords user mobilityWi-Fi access logshierarchical modeltransition matrixclusteringcampus networkmobility simulationgeospatial grouping
0
0 comments X

The pith

Wi-Fi access logs can be grouped hierarchically by location to build lower-complexity user mobility models that match observed transition patterns.

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

This paper develops a method to build hierarchical models of how users move through a space using data from Wi-Fi access point connections. Access points are grouped recursively by their locations to create levels of detail, from individual buildings up to larger areas. Each group of users gets a transition matrix showing how they move between areas and a vector for how long they stay. The approach is tested on a university campus and found to match transition patterns well while using fewer resources than a single-level model covering the whole area.

Core claim

The paper claims that recursively grouping Wi-Fi access points into a geospatial hierarchy allows construction of user mobility models via clustering that achieve good accuracy on transition matrices with lower complexity than a flat model.

What carries the argument

Recursive geospatial grouping of access points into hierarchy levels, combined with clustering-based user profiling that assigns transition matrices and time vectors to user types.

If this is right

  • The hierarchical model reduces complexity for large-scale scenarios such as entire campuses.
  • Transition matrices derived from the model closely match those computed directly from the connection data.
  • The method supports simulation of user tracks as sequences of coverage areas in fog computing settings.
  • One area per building with three levels produces lower complexity than a single area for the whole space.

Where Pith is reading between the lines

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

  • Refining the time vector definition could involve adding time-of-day or day-of-week factors to improve stay-time accuracy.
  • The same recursive grouping technique might apply to other wireless infrastructures such as cellular base stations.
  • In fog scenarios the resulting tracks could be used directly for resource allocation without storing raw connection logs.

Load-bearing premise

That grouping access points solely by geospatial proximity creates levels that accurately reflect how users actually move between areas.

What would settle it

A direct comparison on the same dataset showing higher mean square error for transition matrices in the hierarchical model than in the flat model would falsify the accuracy claim.

Figures

Figures reproduced from arXiv: 2605.14540 by Carlos Guerrero, Francisco Talavera, Isaac Lera.

Figure 1
Figure 1. Figure 1: a shows an example of an user1 trajectory in the university cam￾pus of the UIB. The user follows the red line path over the background cam￾pus image, that also includes the coverage areas –represented with hexagons– and the AP of each area –represented with a numbered blue dot in the center of the hexagon–. This trajectory also follows a time distribution –the orange dots– that synthesizes the stay length … view at source ↗
Figure 1
Figure 1. Figure 1: Example of a user track and the corresponding mobility model. [PITH_FULL_IMAGE:figures/full_fig_p010_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Example of geospatial hierarchical modeling of user mobility. [PITH_FULL_IMAGE:figures/full_fig_p011_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Example of model adaptation between scenarios with different geospatial fea [PITH_FULL_IMAGE:figures/full_fig_p012_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Complete life-cycle of our proposed method for the hierarchical modeling of user [PITH_FULL_IMAGE:figures/full_fig_p013_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Example of the hierarchical approach for mobility modeling. [PITH_FULL_IMAGE:figures/full_fig_p017_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Example of device tracking log obtained with a commercial tool (Aruba Analytics [PITH_FULL_IMAGE:figures/full_fig_p022_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Example of three JSON files for the hierarchical level definition. [PITH_FULL_IMAGE:figures/full_fig_p025_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Euclidean distances between number of user sessions and average session times. [PITH_FULL_IMAGE:figures/full_fig_p027_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: Elbow method to detect the optimal number of clusters considering the distortion [PITH_FULL_IMAGE:figures/full_fig_p028_9.png] view at source ↗
Figure 10
Figure 10. Figure 10: Chord diagrams for three examples of the regions under study. [PITH_FULL_IMAGE:figures/full_fig_p031_10.png] view at source ↗
Figure 11
Figure 11. Figure 11: Elbow method to detect the optimal number of clusters considering the distor [PITH_FULL_IMAGE:figures/full_fig_p033_11.png] view at source ↗
read the original abstract

This paper presents a method that generates a hierarchical user mobility model from the analysis of the data available from Wi-Fi connections. The data obtained from the Wi-Fi infrastructure is defined in terms of the coverage areas of the access points that the users move through. These access points are recursively grouped into different levels of granularity based on their geospatial features. The track of a user is defined as a sequence of Wi-Fi access points, which is enough to simulate user mobility in, for example, fog scenarios. The hierarchical definition of the region under study is proposed to reduce the complexity of the model in high-scale scenarios and to increase the adaptability between scenarios with different geospatial features. The model creation is based on a user profiling method that uses a clustering algorithm and each user type is defined with a transition matrix between coverage areas and a time length vector for the areas. The method is applied to the case of the campus of the University of the Balearic Islands. From the analysis of the mean square error of the results, we determined that the proposed method obtains good results for the transition matrices, but that the time vector definition should be improved. The results also show lower complexity in the case of the hierarchical model, with one area for each building and three levels, in regard to a non-hierarchical model, with only one area and one level for the whole campus.

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

3 major / 1 minor

Summary. The paper proposes a hierarchical user mobility model derived from Wi-Fi access logs by recursively grouping access points into geospatial hierarchy levels, clustering users, and fitting per-cluster transition matrices and time-length vectors. Evaluated on University of the Balearic Islands campus data, it claims lower model complexity for a three-level building-based hierarchy versus a flat single-level model, with acceptable MSE on the transition matrices but explicitly noting that the time-vector component requires improvement.

Significance. If the hierarchy can be shown to preserve mobility patterns beyond in-sample fitting, the approach could offer a practical, lower-complexity alternative for simulating user movement in large-scale wireless and fog-computing environments. The grounding in real Wi-Fi logs is a positive feature, though the partial validation of the full model (matrix plus vector) limits immediate impact.

major comments (3)
  1. Abstract: the claim of 'good results' for transition matrices rests on MSE values computed directly on the same connection sequences used to construct the hierarchy and clusters, with no reported baselines, error bars, cross-validation, or held-out trajectory fidelity metrics; this leaves the central claim of effective hierarchical characterization only partially supported.
  2. Abstract: the time-length vector is acknowledged to need improvement yet forms an integral part of the user-profiling method; without a concrete fix or alternative formulation, the model's utility for full mobility simulation remains incomplete.
  3. The recursive geospatial grouping is asserted to reduce complexity while preserving mobility patterns, but no out-of-sample validation, simulation fidelity test, or comparison against actual user trajectories is described to confirm that the three-level building hierarchy does not distort movement sequences.
minor comments (1)
  1. The abstract would benefit from stating the total number of users, duration of the logs, and exact number of access points to allow readers to assess scale.

Simulated Author's Rebuttal

3 responses · 0 unresolved

We thank the referee for the constructive comments, which identify key areas where additional validation can strengthen the manuscript. We address each major comment below and will incorporate the suggested improvements in the revised version.

read point-by-point responses

  1. Referee: Abstract: the claim of 'good results' for transition matrices rests on MSE values computed directly on the same connection sequences used to construct the hierarchy and clusters, with no reported baselines, error bars, cross-validation, or held-out trajectory fidelity metrics; this leaves the central claim of effective hierarchical characterization only partially supported.

    Authors: We agree that the current MSE evaluation is performed on the same sequences used for model construction and lacks cross-validation, baselines, error bars, and held-out metrics. In the revision we will add 5-fold cross-validation on user trajectories, report standard deviations across folds as error bars, include a non-hierarchical baseline, and evaluate transition-matrix fidelity on held-out sequences to provide stronger support for the claim. revision: yes

  2. Referee: Abstract: the time-length vector is acknowledged to need improvement yet forms an integral part of the user-profiling method; without a concrete fix or alternative formulation, the model's utility for full mobility simulation remains incomplete.

    Authors: The manuscript already states that the time-vector component requires improvement. To address this, the revision will replace the current vector with an empirical cumulative distribution function derived directly from the observed connection durations per cluster; this formulation will be integrated into the user-profiling method and evaluated for simulation utility. revision: yes

  3. Referee: The recursive geospatial grouping is asserted to reduce complexity while preserving mobility patterns, but no out-of-sample validation, simulation fidelity test, or comparison against actual user trajectories is described to confirm that the three-level building hierarchy does not distort movement sequences.

    Authors: We acknowledge that the manuscript does not yet include out-of-sample validation or simulation fidelity tests. The revised version will add a held-out trajectory experiment: synthetic sequences generated from the three-level hierarchical model will be compared against real held-out user trajectories using sequence-edit distance and visit-frequency correlation to verify that mobility patterns are preserved while complexity is reduced. revision: yes

Circularity Check

0 steps flagged

No significant circularity in derivation chain

full rationale

The paper describes a data-driven construction: recursive geospatial grouping of access points into hierarchy levels, user clustering, and direct extraction of per-cluster transition matrices plus time vectors from the same Wi-Fi logs. The reported MSE analysis simply quantifies how closely these extracted matrices match the empirical frequencies in the input sequences, which is a standard in-sample fidelity check rather than any reduction of an output to its inputs by definition or self-citation. No equations, uniqueness theorems, ansatzes, or prior self-citations are invoked to force the result; the lower-complexity claim for the three-level building hierarchy follows directly from counting areas and levels after the grouping step. This is a descriptive modeling pipeline whose central claims remain independent of the circularity patterns.

Axiom & Free-Parameter Ledger

2 free parameters · 2 axioms · 0 invented entities

The approach rests on standard domain assumptions about spatial grouping and Markovian mobility plus a small number of fitted parameters for hierarchy depth and cluster count; no new entities are postulated.

free parameters (2)
  • number of hierarchy levels
    Set to three (access point, building, campus) for the reported experiment; chosen to balance granularity and complexity.
  • number of user clusters
    Determined by the clustering algorithm; exact count not stated but directly affects the set of transition matrices.
axioms (2)
  • domain assumption Access points can be recursively grouped by geospatial features into meaningful hierarchy levels that preserve mobility statistics.
    Invoked when defining the recursive grouping step that reduces model size.
  • domain assumption User mobility sequences are adequately captured by first-order transition matrices plus independent stay-time vectors per cluster.
    Underlying the profiling method and the reported MSE evaluation.

pith-pipeline@v0.9.0 · 5542 in / 1445 out tokens · 50049 ms · 2026-05-15T01:31:11.356123+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

56 extracted references · 56 canonical work pages

  1. [1]

    Eeckhout, K

    L. Eeckhout, K. de Bosschere, H. Neefs, Performance analysis through synthetic trace generation, in: 2000 IEEE International Symposium on Performance Analysis of Systems and Software. ISPASS (Cat. No.00EX422), 2000, pp. 1–6.doi:10.1109/ISPASS.2000.842273

    work page doi:10.1109/ispass.2000.842273 2000

  2. [2]

    Brogi, S

    A. Brogi, S. Forti, C. Guerrero, I. Lera, How to place your apps in the fog: State of the art and open challenges, Soft- ware: Practice and Experience 50 (5) 719–740.arXiv: https://onlinelibrary.wiley.com/doi/pdf/10.1002/spe.2766, doi:https://doi.org/10.1002/spe.2766. 36 URLhttps://onlinelibrary.wiley.com/doi/abs/10.1002/spe. 2766

    work page doi:10.1002/spe.2766

  3. [3]

    S. O. Ogundoyin, I. A. Kamil, Optimization techniques and applications in fog computing: An exhaustive survey, Swarm and Evolutionary Computation 66 (2021) 100937.doi:https: //doi.org/10.1016/j.swevo.2021.100937. URLhttps://www.sciencedirect.com/science/article/pii/ S2210650221000985

    work page doi:10.1016/j.swevo.2021.100937 2021

  4. [4]

    E. Toch, B. Lerner, E. Ben Zion, I. Ben-Gal, Analyzing large-scale human mobility data: a survey of machine learning methods and ap- plications, Knowledge and Information Systems 58.doi:10.1007/ s10115-018-1186-x

    work page

  5. [5]

    Zonoozi, P

    M. Zonoozi, P. Dassanayake, User mobility modeling and characteriza- tion of mobility patterns, IEEE Journal on Selected Areas in Commu- nications 15 (7) (1997) 1239–1252.doi:10.1109/49.622908

    work page doi:10.1109/49.622908 1997

  6. [6]

    Zhang, L

    H. Zhang, L. Dai, Mobility prediction: A survey on state-of-the-art schemes and future applications, IEEE Access 7 (2019) 802–822.doi: 10.1109/ACCESS.2018.2885821

    work page doi:10.1109/access.2018.2885821 2019

  7. [7]

    Noulas, S

    A. Noulas, S. Scellato, N. Lathia, C. Mascolo, Mining user mobility features for next place prediction in location-based services, in: 2012 IEEE 12th International Conference on Data Mining, 2012, pp. 1038– 1043.doi:10.1109/ICDM.2012.113

    work page doi:10.1109/icdm.2012.113 2012

  8. [8]

    M. S. Quessada, R. S. Pereira, W. Revejes, B. Sartori, E. N. Gotts- fritz, D. D. Lieira, M. A. da Silva, G. P. R. Filho, R. I. Meneguette, Itsmei: An intelligent transport system for monitoring traffic and event information, International Journal of Distributed Sensor Networks 16 (10) (2020) 1550147720963751.arXiv:https://doi.org/10.1177/ 1550147720963751...

    work page doi:10.1177/1550147720963751 2020

  9. [9]

    Secci, P

    S. Secci, P. Raad, P. Gallard, Linking virtual machine mobility to user mobility, IEEETransactionsonNetworkandServiceManagement13(4) (2016) 927–940.doi:10.1109/TNSM.2016.2592241. 37

    work page doi:10.1109/tnsm.2016.2592241 2016

  10. [10]

    L. F. Bittencourt, J. Diaz-Montes, R. Buyya, O. F. Rana, M. Parashar, Mobility-aware application scheduling in fog computing, IEEE Cloud Computing 4 (2) (2017) 26–35.doi:10.1109/MCC.2017.27

    work page doi:10.1109/mcc.2017.27 2017

  11. [11]

    Huang, P

    Z. Huang, P. Wang, F. Zhang, J. Gao, M. Schich, A mobility net- work approach to identify and anticipate large crowd gatherings, Transportation Research Part B: Methodological 114 (2018) 147–170. doi:https://doi.org/10.1016/j.trb.2018.05.016. URLhttps://www.sciencedirect.com/science/article/pii/ S0191261517310986

    work page doi:10.1016/j.trb.2018.05.016 2018

  12. [12]

    S. P. Hoogendoorn, P. H. L. Bovy, Pedestrian travel behavior modeling, Networks and Spatial Economics 5 (2) (2005) 193–216.doi:10.1007/ s11067-005-2629-y. URLhttps://doi.org/10.1007/s11067-005-2629-y

    work page doi:10.1007/s11067-005-2629-y 2005

  13. [13]

    Meijles, M

    E. Meijles, M. de Bakker, P. Groote, R. Barske, Analysing hiker movement patterns using gps data: Implications for park man- agement, Computers, Environment and Urban Systems 47 (2014) 44–57, progress in Movement Analysis – Experiences with Real Data. doi:https://doi.org/10.1016/j.compenvurbsys.2013.07.005. URLhttps://www.sciencedirect.com/science/article...

    work page doi:10.1016/j.compenvurbsys.2013.07.005 2014

  14. [14]

    I. Lera, T. Pérez, C. Guerrero, V. M. Eguíluz, C. Juiz, Analysing human mobility patterns of hiking activities through complex network theory, PLOS ONE 12 (5) (2017) 1–19.doi:10.1371/journal.pone.0177712. URLhttps://doi.org/10.1371/journal.pone.0177712

    work page doi:10.1371/journal.pone.0177712 2017

  15. [15]

    M. Luca, G. Barlacchi, B. Lepri, L. Pappalardo, A survey on deep learn- ing for human mobility, ACM Comput. Surv. 55 (1).doi:10.1145/ 3485125. URLhttps://doi.org/10.1145/3485125

    work page doi:10.1145/3485125

  16. [16]

    Mimouna, I

    A. Mimouna, I. Alouani, A. Ben Khalifa, Y. El Hillali, A. Taleb-Ahmed, A. Menhaj, A. Ouahabi, N. E. Ben Amara, Olimp: A heterogeneous multimodal dataset for advanced environment perception, Electronics 9 (4).doi:10.3390/electronics9040560. URLhttps://www.mdpi.com/2079-9292/9/4/560 38

    work page doi:10.3390/electronics9040560 2079

  17. [17]

    Barbosa-Filho, M

    H. Barbosa-Filho, M. Barthelemy, G. Ghoshal, C. James, M. Lenor- mand, T. Louail, R. P. de Menezes, J. J. Ramasco, F. Simini, M. Tomasini, Human mobility: Models and applications, Physics Re- ports 734 (2018) 1–74

    work page 2018

  18. [18]

    H. Xie, E. Tanin, L. Kulik, P. Scheuermann, G. Trajcevski, M. Fanaeep- our, Euler histogram tree: A spatial data structure for aggregate range queries on vehicle trajectories, in: Proceedings of the 7th ACM SIGSPA- TIAL International Workshop on Computational Transportation Sci- ence, IWCTS ’14, Association for Computing Machinery, New York, NY, USA, 2014...

    work page doi:10.1145/2674918.2674921 2014

  19. [19]

    Xu, S.-L

    Y. Xu, S.-L. Shaw, Z. Zhao, L. Yin, Z. Fang, Q. Li, Understanding aggregate human mobility patterns using passive mobile phone loca- tion data - a home-based approach, Transportation 42.doi:10.1007/ s11116-015-9597-y

    work page

  20. [20]

    Pappalardo, G

    L. Pappalardo, G. Barlacchi, R. Pellungrini, F. Simini, Human mobility from theory to practice:data, models and applications, in: Compan- ion Proceedings of The 2019 World Wide Web Conference, WWW ’19, Association for Computing Machinery, New York, NY, USA, 2019, p. 1311–1312.doi:10.1145/3308560.3320099. URLhttps://doi.org/10.1145/3308560.3320099

    work page doi:10.1145/3308560.3320099 2019

  21. [21]

    Kulkarni, B

    V. Kulkarni, B. Garbinato, 20 years of mobility modeling & prediction: Trends, shortcomings & perspectives, in: Proceedings of the 27th ACM SIGSPATIAL International Conference on Advances in Geographic In- formation Systems, SIGSPATIAL ’19, Association for Computing Ma- chinery, NewYork, NY,USA,2019, p.492–495.doi:10.1145/3347146. 3359110. URLhttps://doi....

    work page doi:10.1145/3347146 2019

  22. [22]

    S. M. King, F. Nawab, K. Obraczka, A survey of open source user activ- ity traces with applications to user mobility characterization and mod- eling (2021).arXiv:2110.06382

    work page arXiv 2021

  23. [23]

    J. Wang, X. Kong, F. Xia, L. Sun, Urban human mobility: Data-driven modeling and prediction, SIGKDD Explor. Newsl. 21 (1) (2019) 1–19. 39 doi:10.1145/3331651.3331653. URLhttps://doi.org/10.1145/3331651.3331653

    work page doi:10.1145/3331651.3331653 2019

  24. [24]

    Solmaz, D

    G. Solmaz, D. Turgut, A survey of human mobility models, IEEE Access 7 (2019) 125711–125731.doi:10.1109/ACCESS.2019.2939203

    work page doi:10.1109/access.2019.2939203 2019

  25. [25]

    Thornton, K

    F. Thornton, K. E. McNamara, C. Farbotko, O. Dun, H. Ransan- Cooper, E. Chevalier, P. Lkhagvasuren, Human mobility and environ- mental change: a survey of perceptions and policy direction, Population and Environment 40 (2018) 239–256

    work page 2018

  26. [26]

    A. Hess, K. A. Hummel, W. N. Gansterer, G. Haring, Data-driven hu- man mobility modeling: A survey and engineering guidance for mobile networking, ACM Comput. Surv. 48 (3).doi:10.1145/2840722. URLhttps://doi.org/10.1145/2840722

    work page doi:10.1145/2840722

  27. [27]

    Becker, R

    R. Becker, R. Cáceres, K. Hanson, S. Isaacman, J. M. Loh, M. Martonosi, J. Rowland, S. Urbanek, A. Varshavsky, C. Volinsky, Human mobility characterization from cellular network data, Commu- nications of the ACM 56 (1) (2013) 74–82

    work page 2013

  28. [28]

    T. S. Azevedo, R. L. Bezerra, C. A. V. Campos, L. F. M. de Moraes, An analysis of human mobility using real traces, in: 2009 IEEE Wireless Communications and Networking Conference, 2009, pp. 1–6.doi:10. 1109/WCNC.2009.4917569

    work page arXiv 2009

  29. [29]

    T. Wu, R. M. Rustamov, C. Goodall, Distributed learning of human mo- bility patterns from cellular network data, in: 2017 51st Annual Con- ference on Information Sciences and Systems (CISS), 2017, pp. 1–6. doi:10.1109/CISS.2017.7926085

    work page doi:10.1109/ciss.2017.7926085 2017

  30. [30]

    Thuillier, L

    E. Thuillier, L. Moalic, S. Lamrous, A. Caminada, Clustering weekly patterns of human mobility through mobile phone data, IEEE Transac- tions on Mobile Computing 17 (4) (2018) 817–830.doi:10.1109/TMC. 2017.2742953

    work page doi:10.1109/tmc 2018

  31. [31]

    M. W. Traunmueller, N. Johnson, A. Malik, C. E. Kon- tokosta, Digital footprints: Using wifi probe and locational data to analyze human mobility trajectories in cities, Com- puters, Environment and Urban Systems 72 (2018) 4–12. 40 doi:https://doi.org/10.1016/j.compenvurbsys.2018.07.006. URLhttps://www.sciencedirect.com/science/article/pii/ S0198971517305914

    work page doi:10.1016/j.compenvurbsys.2018.07.006 2018

  32. [32]

    M. Uras, R. Cossu, L. Atzori, Pma: a solution for people mobility mon- itoring and analysis based on wifi probes, in: 2019 4th International Conference on Smart and Sustainable Technologies (SpliTech), 2019, pp. 1–6.doi:10.23919/SpliTech.2019.8783040

    work page doi:10.23919/splitech.2019.8783040 2019

  33. [33]

    Oliveira, D

    L. Oliveira, D. Schneider, J. De Souza, W. Shen, Mobile device detection through wifi probe request analysis, IEEE Access 7 (2019) 98579–98588. doi:10.1109/ACCESS.2019.2925406

    work page doi:10.1109/access.2019.2925406 2019

  34. [34]

    Balzotti, A

    C. Balzotti, A. Bragagnini, M. Briani, E. Cristiani, Under- standing human mobility flows from aggregated mobile phone data, IFAC-PapersOnLine 51 (9) (2018) 25–30, 15th IFAC Symposium on Control in Transportation Systems CTS 2018. doi:https://doi.org/10.1016/j.ifacol.2018.07.005. URLhttps://www.sciencedirect.com/science/article/pii/ S2405896318307213

    work page doi:10.1016/j.ifacol.2018.07.005 2018

  35. [35]

    Hoteit, G

    S. Hoteit, G. Chen, A. C. Viana, M. C. Fiore, Spatio-Temporal Comple- tion of Call Detail Records for Human Mobility Analysis, in: Rencontres Francophones sur la Conception de Protocoles, l’Évaluation de Perfor- mance et l’Expérimentation des Réseaux de Communication, Quiberon, France, 2017. URLhttps://hal.archives-ouvertes.fr/hal-01516717

    work page 2017

  36. [36]

    W. Gao, G. Cao, Fine-grained mobility characterization: Steady and transient state behaviors, in: Proceedings of the Eleventh ACM Inter- national Symposium on Mobile Ad Hoc Networking and Computing, MobiHoc ’10, Association for Computing Machinery, New York, NY, USA, 2010, p. 61–70.doi:10.1145/1860093.1860103. URLhttps://doi.org/10.1145/1860093.1860103

    work page doi:10.1145/1860093.1860103 2010

  37. [37]

    Ashbrook, T

    D. Ashbrook, T. Starner, Learning significant locations and predicting user movement with gps, in: Proceedings. Sixth International Sympo- sium on Wearable Computers„ 2002, pp. 101–108.doi:10.1109/ISWC. 2002.1167224. 41

    work page doi:10.1109/iswc 2002

  38. [38]

    Y. Chon, H. Shin, E. Talipov, H. Cha, Evaluating mobility models for temporal prediction with high-granularity mobility data, in: 2012 IEEE International Conference on Pervasive Computing and Communications, 2012, pp. 206–212.doi:10.1109/PerCom.2012.6199868

    work page doi:10.1109/percom.2012.6199868 2012

  39. [39]

    Mathew, R

    W. Mathew, R. Raposo, B. Martins, Predicting future locations with hidden markov models, in: Proceedings of the 2012 ACM Conference on Ubiquitous Computing, UbiComp ’12, Association for Computing Ma- chinery, NewYork, NY,USA,2012, p.911–918.doi:10.1145/2370216. 2370421. URLhttps://doi.org/10.1145/2370216.2370421

    work page doi:10.1145/2370216 2012

  40. [40]

    Asahara, K

    A. Asahara, K. Maruyama, A. Sato, K. Seto, Pedestrian-movement pre- diction based on mixed markov-chain model, in: Proceedings of the 19th ACM SIGSPATIAL International Conference on Advances in Geo- graphic Information Systems, GIS ’11, Association for Computing Ma- chinery, New York, NY, USA, 2011, p. 25–33.doi:10.1145/2093973. 2093979. URLhttps://doi.or...

    work page doi:10.1145/2093973 2011

  41. [41]

    Gambs, M.-O

    S. Gambs, M.-O. Killijian, M. N. n. del Prado Cortez, Next place prediction using mobility markov chains, in: Proceedings of the First Workshop on Measurement, Privacy, and Mobility, MPM ’12, Asso- ciation for Computing Machinery, New York, NY, USA, 2012.doi: 10.1145/2181196.2181199. URLhttps://doi.org/10.1145/2181196.2181199

    work page doi:10.1145/2181196.2181199 2012

  42. [42]

    N. A. Amirrudin, S. H. S. Ariffin, N. N. N. A. Malik, N. E. Ghaz- ali, User’s mobility history-based mobility prediction in lte femtocells network, in: 2013 IEEE International RF and Microwave Conference (RFM), 2013, pp. 105–110.doi:10.1109/RFM.2013.6757228

    work page doi:10.1109/rfm.2013.6757228 2013

  43. [43]

    Yan, X.-P

    X.-Y. Yan, X.-P. Han, B.-H. Wang, T. Zhou, Diversity of individual mobility patterns and emergence of aggregated scaling laws, Scientific Reports 3 (1) (2013) 2678.doi:10.1038/srep02678. URLhttps://doi.org/10.1038/srep02678

    work page doi:10.1038/srep02678 2013

  44. [44]

    S.-Z. Yu, H. Kobayashi, A hidden semi-markov model with missing data and multiple observation sequences for mobility tracking, Signal Processing 83 (2) (2003) 235–250.doi:https: 42 //doi.org/10.1016/S0165-1684(02)00378-X. URLhttps://www.sciencedirect.com/science/article/pii/ S016516840200378X

    work page doi:10.1016/s0165-1684(02)00378-x 2003

  45. [45]

    W. Zhu, C. Zhang, S. Yao, X. Gao, J. Han, A spherical hidden markov model for semantics-rich human mobility modeling, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 32, 2018

    work page 2018

  46. [46]

    Fülöp, S

    P. Fülöp, S. Imre, S. Szabó, T. Szálka, Accurate mobility modeling and locationpredictionbasedonpatternanalysisofhandoverseriesinmobile networks, Mobile Information Systems 5 (3) (2009) 255–289

    work page 2009

  47. [47]

    J. Xie, Y. Wan, J. H. Kim, S. Fu, K. Namuduri, A survey and analysis of mobility models for airborne networks, IEEE Communications Surveys & Tutorials 16 (3) (2013) 1221–1238

    work page 2013

  48. [48]

    D. A. Menasce, A. F. A. Virgilio, Scaling for E Business: Technologies, Models, Performance, and Capacity Planning, 1st Edition, Prentice Hall PTR, USA, 2000

    work page 2000

  49. [49]

    C. Kurz, C. Guerrero, G. Haring, Extending tpc-w to allow for fine grained workload specification, WOSP ’05, Association for Comput- ing Machinery, New York, NY, USA, 2005, p. 167–174.doi:10.1145/ 1071021.1071039. URLhttps://doi.org/10.1145/1071021.1071039

    work page doi:10.1145/1071021.1071039 2005

  50. [50]

    Keramat Jahromi, M

    K. Keramat Jahromi, M. Zignani, S. Gaito, G. P. Rossi, Simulating human mobility patterns in urban areas, Sim- ulation Modelling Practice and Theory 62 (2016) 137–156. doi:https://doi.org/10.1016/j.simpat.2015.12.002. URLhttps://www.sciencedirect.com/science/article/pii/ S1569190X15001732

    work page doi:10.1016/j.simpat.2015.12.002 2016

  51. [51]

    Hardy, On the number of clusters, Computational Statis- tics and Data Analysis 23 (1) (1996) 83–96, classification

    A. Hardy, On the number of clusters, Computational Statis- tics and Data Analysis 23 (1) (1996) 83–96, classification. doi:https://doi.org/10.1016/S0167-9473(96)00022-9. URLhttps://www.sciencedirect.com/science/article/pii/ S0167947396000229

    work page doi:10.1016/s0167-9473(96)00022-9 1996

  52. [52]

    O. A. Abbas, Comparisons between data clustering algorithms., Inter- national Arab Journal of Information Technology (IAJIT) 5 (3). 43

    work page

  53. [53]

    Gouin-Vallerand, S

    C. Gouin-Vallerand, S. Rousseau, An indoor navigation platform for seeking internet of things devices in large indoor environment, GoodTechs ’19, Association for Computing Machinery, New York, NY, USA, 2019, p. 108–113.doi:10.1145/3342428.3342652. URLhttps://doi.org/10.1145/3342428.3342652

    work page doi:10.1145/3342428.3342652 2019

  54. [54]

    M. A. Syakur, B. K. Khotimah, E. M. S. Rochman, B. D. Satoto, Inte- gration k-means clustering method and elbow method for identification of the best customer profile cluster, IOP Conference Series: Materials Science and Engineering 336 (2018) 012017.doi:10.1088/1757-899x/ 336/1/012017. URLhttps://doi.org/10.1088/1757-899x/336/1/012017

    work page doi:10.1088/1757-899x/ 2018

  55. [55]

    Gupta, A

    H. Gupta, A. Vahid Dastjerdi, S. K. Ghosh, R. Buyya, ifogsim: A toolkit for modeling and simulation of resource management techniques in the internet of things, edge and fog computing environments, Software: Practice and Experience 47 (9) (2017) 1275–1296.arXiv: https://onlinelibrary.wiley.com/doi/pdf/10.1002/spe.2509, doi:https://doi.org/10.1002/spe.2509...

    work page doi:10.1002/spe.2509 2017

  56. [56]

    I. Lera, C. Guerrero, C. Juiz, Yafs: A simulator for iot scenarios in fog computing, IEEE Access 7 (2019) 91745–91758.doi:10.1109/ACCESS. 2019.2927895. 44

    work page doi:10.1109/access 2019