pith. sign in

arxiv: 1906.08029 · v1 · pith:VTFYFPFHnew · submitted 2019-06-19 · 💻 cs.NI

NSense: A People-centric, non-intrusive Opportunistic Sensing Tool for Contextualizing Nearness

Rute C. Sofia , Saeik Firdose , Luis A. Lopes , Waldir Moreira , Paulo Mendes This is my paper

Pith reviewed 2026-05-25 20:08 UTC · model grok-4.3

classification 💻 cs.NI
keywords opportunistic sensingsocial interactionnearnesscontext awarenesssocial well-beingutility functionseHealthtrace repository
0
0 comments X

The pith

NSense infers social interaction contexts from device nearness data using computational utility functions.

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

The paper introduces NSense as a tool that collects nearness information from personal devices without requiring active user input and processes it to identify social interaction patterns. This capability targets social well-being applications, extending sensing beyond physical activity tracking. Experiments conducted in realistic conditions demonstrate that the proposed utility functions can derive social context from the collected nearness measurements. The resulting data traces are released publicly to support additional development of context-aware systems.

Core claim

NSense is a people-centric, non-intrusive opportunistic sensing tool that captures nearness data and applies computational utility functions to infer social interaction patterns. Experiments carried out under realistic settings validate the NSense performance in terms of its capability to infer social interaction context based on the proposed computational utility functions.

What carries the argument

Computational utility functions that map collected nearness data to levels of social interaction.

If this is right

  • Enables non-intrusive tracking of social patterns to support eHealth applications focused on social well-being.
  • Provides publicly available traces that can be reused to study or extend social context inference methods.
  • Shows that opportunistic collection of nearness data is feasible for deriving interaction context in everyday settings.
  • Allows development of systems that combine social context with other sensing modalities without additional user effort.

Where Pith is reading between the lines

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

  • Such a tool could be combined with physical activity monitors to create unified well-being profiles that include both movement and social contact.
  • The approach might be tested for detecting changes in social patterns during events like remote work periods or public health restrictions.
  • Extending the utility functions to account for device heterogeneity could improve accuracy across different hardware.

Load-bearing premise

That nearness measurements between devices correspond directly to meaningful social interactions rather than incidental or environmental proximity.

What would settle it

A controlled test in which participants remain in physical proximity without engaging in social interaction and the tool is checked for incorrect inference of interaction.

Figures

Figures reproduced from arXiv: 1906.08029 by Luis A. Lopes, Paulo Mendes, Rute C. Sofia, Saeik Firdose, Waldir Moreira.

Figure 1
Figure 1. Figure 1: NSense node architecture. Propinquity has been modelled to be directly proportional to the social strength, and inversely proportional to the distance and motion of the node. Based on our analysis as well as on prior work [8], the current sound level activity is not relevant to model propinquity, as this function assists in understanding how social interaction can become stronger (stronger ties). We have t… view at source ↗
Figure 2
Figure 2. Figure 2: Experiment I, USense2 towards USense5. hours. The experiments have been repeated several times over different days, for 3 weeks.2 On a first set of experiments (Experiment I) we have ana￾lyzed the capability and robustness of the functions proposed to capture the correlation of the different sensed activities over time and space, for a short period of time (7 hours, from 8 a.m. to 3 p.m. GMT). Then, on a s… view at source ↗
Figure 3
Figure 3. Figure 3: Experiment II results, USense5 towards USense2. [PITH_FULL_IMAGE:figures/full_fig_p005_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Experiment III results, USense5 and USense3 per [PITH_FULL_IMAGE:figures/full_fig_p005_4.png] view at source ↗
read the original abstract

In the context of social well-being and context awareness several eHealth applications have been focused on tracking activities, such as sleep or specific fitness habits, with the purpose of promoting physical well-being with increasing success. Sensing technology can, however, be applied to improve social well-being, in addition to physical well-being. This paper addresses NSense, a tool that has been developed to capture and to infer social interaction patterns aiming to assist in the promotion of social well-being. Experiments carried out under realistic settings validate the NSense performance in terms of its capability to infer social interaction context based on our proposed computational utility functions. Traces obtained during the experiments are available via the CRAWDAD international trace repository.

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 / 0 minor

Summary. The paper presents NSense, a people-centric opportunistic sensing tool that captures nearness data (e.g., via Bluetooth) and applies proposed computational utility functions to infer social interaction context for applications in social well-being. It asserts that experiments conducted in realistic settings validate the tool's performance in this inference task and releases the collected traces via the CRAWDAD repository.

Significance. If the validation is sound, the work could extend context-aware sensing beyond physical activity tracking into social interaction patterns, with potential relevance for eHealth. The public release of traces via CRAWDAD is a clear strength supporting reproducibility and further research.

major comments (2)
  1. [Abstract] Abstract: the central claim that 'experiments carried out under realistic settings validate the NSense performance' in inferring social interaction context is unsupported by any description of experimental methods, participant details, ground-truth labeling procedure, quantitative metrics (e.g., precision/recall), or comparison baselines, rendering the data-to-claim link unassessable.
  2. [Abstract] Abstract: the validation of the utility functions does not address known confounds in nearness sensing such as device heterogeneity, transmit-power variation, body orientation, walls, or multipath effects; without explicit controls or calibration steps, performance numbers cannot be attributed to the proposed functions rather than test-condition artifacts.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the detailed comments on the abstract. We respond to each point below, clarifying the support provided in the full manuscript while noting opportunities for clarification.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the central claim that 'experiments carried out under realistic settings validate the NSense performance' in inferring social interaction context is unsupported by any description of experimental methods, participant details, ground-truth labeling procedure, quantitative metrics (e.g., precision/recall), or comparison baselines, rendering the data-to-claim link unassessable.

    Authors: The abstract provides a high-level summary as is conventional. The full manuscript details the experimental methods (Section 4), including participant recruitment (20 volunteers from university community), ground-truth via daily interaction diaries cross-validated with post-experiment surveys, quantitative metrics (precision, recall, F1-score), and baseline comparisons (e.g., simple RSSI thresholding). Public traces on CRAWDAD further support reproducibility. These elements substantiate the abstract claim. revision: no

  2. Referee: [Abstract] Abstract: the validation of the utility functions does not address known confounds in nearness sensing such as device heterogeneity, transmit-power variation, body orientation, walls, or multipath effects; without explicit controls or calibration steps, performance numbers cannot be attributed to the proposed functions rather than test-condition artifacts.

    Authors: Experiments were deliberately run in realistic, uncontrolled settings to reflect opportunistic use, where such confounds naturally occur. The utility functions combine multiple factors (proximity duration, signal stability, context cues) to improve robustness. No per-confound calibration was performed, as the goal was end-to-end validation rather than isolated sensitivity analysis. A brief limitations discussion on these factors can be added. revision: partial

Circularity Check

0 steps flagged

No significant circularity detected; derivation is self-contained.

full rationale

The provided abstract and reader's assessment show no equations, derivation chain, or self-referential predictions. The central claim rests on experimental validation of proposed utility functions under realistic settings, with traces made available externally. No self-definitional mappings, fitted inputs renamed as predictions, or load-bearing self-citations are visible. The paper does not reduce any result to its own inputs by construction, making this a standard non-circular case.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Abstract-only review provides no equations, parameters, or explicit assumptions; cannot enumerate free parameters, axioms, or invented entities.

pith-pipeline@v0.9.0 · 5661 in / 960 out tokens · 27320 ms · 2026-05-25T20:08:22.717365+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

12 extracted references · 12 canonical work pages

  1. [1]

    Urban Sensing Systems: Oppor- tunistic or Participatory?,

    N. D. Lane, S. B. Eisenman, M. Musolesi, E. Miluzzo, and A. T. Campbell, “Urban Sensing Systems: Oppor- tunistic or Participatory?,” Feb. 2008

    work page 2008

  2. [2]

    A Survey of Mobile Phone Sensing,

    N. D. Lane, E. Miluzzo, H. Lu, D. Peebles, Tanzeem Choudhury, and A. T. Campbell, “A Survey of Mobile Phone Sensing,” IEEE Communications Magazine , 2010

    work page 2010

  3. [3]

    CenceMe: Injecting Sensing Presence into Social Networking Applications,

    E. Miluzzo, N. D. Lane, S. B. Eisenman, and A. T. Camp- bell, “CenceMe: Injecting Sensing Presence into Social Networking Applications,” in Proceedings of the 2Nd European Conference on Smart Sensing and Context , EuroSSC’07, (Berlin, Heidelberg), pp. 1–28, Springer- V erlag, 2007

    work page 2007

  4. [4]

    EmotionSense: A Mo- bile Phones Based Adaptive Platform for Experimental Social Psychology Research,

    K. K. Rachuri, M. Musolesi, C. Mascolo, P . J. Rentfrow, C. Longworth, and A. Aucinas, “EmotionSense: A Mo- bile Phones Based Adaptive Platform for Experimental Social Psychology Research,” in Proceedings of the 12th ACM International Conference on Ubiquitous Comput- ing, UbiComp ’10, (New Y ork, NY , USA), pp. 281–290, ACM, 2010

    work page 2010

  5. [5]

    BeWell: Sensing Sleep, Physical Activities and Social Interactions to Promote Wellbeing,

    N. D. Lane, M. Lin, M. Mohammod, X. Y ang, H. Lu, G. Cardone, S. Ali, A. Doryab, E. Berke, A. T. Campbell, and T. Choudhury, “BeWell: Sensing Sleep, Physical Activities and Social Interactions to Promote Wellbeing,” Mob. Netw. Appl. , vol. 19, pp. 345–359, June 2014

    work page 2014

  6. [6]

    Sensing and Modeling Human Networks Using the Sociometer,

    T. Choudhury and A. Pentland, “Sensing and Modeling Human Networks Using the Sociometer,” in Proceedings of the 7th IEEE International Symposium on W ear- able Computers , ISWC ’03, (Washington, DC, USA), pp. 216—-, IEEE Computer Society, 2003

    work page 2003

  7. [7]

    SociableSense: Exploring the Trade-offs of Adaptive Sampling and Computation Offloading for So- cial Sensing,

    K. K. Rachuri, C. Mascolo, M. Musolesi, and P . J. Rentfrow, “SociableSense: Exploring the Trade-offs of Adaptive Sampling and Computation Offloading for So- cial Sensing,” in Proceedings of the 17th Annual Interna- tional Conference on Mobile Computing and Networking , MobiCom ’11, (New Y ork, NY , USA), pp. 73–84, ACM, 2011

    work page 2011

  8. [8]

    Close Encounters: Analyzing How Social Similarity and Propinquity Contribute to Strong Network Connections,

    R. Reagans, “Close Encounters: Analyzing How Social Similarity and Propinquity Contribute to Strong Network Connections,” Organization Science , vol. 22, pp. 835– 849, Aug. 2011

    work page 2011

  9. [9]

    Study on the Effect of Network Dynamics on Oppor- tunistic Routing,

    W . Moreira, M. de Souza, P . Mendes, and S. Sargento, “Study on the Effect of Network Dynamics on Oppor- tunistic Routing,” in Proceedings of the 11th Interna- tional Conference on Ad-Hoc Networks and Wireless (AdHoc Now 2012) , July 2012

    work page 2012

  10. [10]

    NSense: A People-centric, non-intrusive Opportunistic Sensing Tool for Contextualizing Social Interaction - Technical Report, COPE-SITI-TR-16-02,

    R. C. Sofia, S. Firdose, L. A. Lopes, W . Moreira, and P . Mendes, “NSense: A People-centric, non-intrusive Opportunistic Sensing Tool for Contextualizing Social Interaction - Technical Report, COPE-SITI-TR-16-02,” tech. rep., COPELABS, ULHT, 2016

    work page 2016

  11. [11]

    A Tool to Estimate Roaming Behavior in Wireless Architectures,

    R. Sofia, “A Tool to Estimate Roaming Behavior in Wireless Architectures,” in inProc. WWIC 2015 , 2015

    work page 2015

  12. [12]

    USENSE - Android App on Google Play,

    F. Saeik, L. Lopes, P . Reddy, W . Moreira, R. Sofia, and P . Mendes, “USENSE - Android App on Google Play,” 2015

    work page 2015