pith. sign in

arxiv: 2604.18141 · v1 · submitted 2026-04-20 · 📡 eess.SY · cs.SY

Frugal Geofencing via Energy-aware Sensing and Reporting

David E. Ruiz-Guirola , Miltiadis Filippou , Onel A. Lopez This is my paper

Pith reviewed 2026-05-10 04:09 UTC · model grok-4.3

classification 📡 eess.SY cs.SY
keywords geofencingenergy harvestingIoT devicesreinforcement learningintruder detectionenergy-aware sensingperimeter monitoringdirectional sensing
0
0 comments X

The pith

Energy-aware coordination of sensing and reporting allows reliable geofencing using fewer energy-harvesting IoT devices.

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

The paper proposes a framework for geofencing that accounts for the energy limitations of harvesting-powered IoT devices equipped with cameras. It models directional sensing power along with energy harvesting, sleeping, and reporting cycles to control when devices activate. By using reinforcement learning to place the devices instead of a uniform grid, the system achieves earlier intruder detection. Numerical evaluations indicate that this approach requires fewer devices while also improving how quickly and reliably intrusions are spotted. This matters because traditional setups waste energy on constant operation, limiting their practicality for long-term monitoring.

Core claim

The proposed energy-aware geofencing framework integrates a directional sensing power model with an operational representation of energy harvesting, sensing, sleeping, and reporting for camera-equipped EH IoTDs. Device activity is controlled by the access point hosting a mobile edge host and geofencing system. Reinforcement learning determines IoTD placement to enable earlier detection than uniform grids. Numerical results demonstrate that the coordinated configuration achieves frugal geofencing with fewer devices while improving detection timeliness and dependability.

What carries the argument

The energy-aware geofencing framework that combines directional sensing models with reinforcement learning for device placement and access point control of activity.

Load-bearing premise

The models for directional sensing power and the operational states of energy harvesting, sensing, sleeping, and reporting must accurately reflect real device behavior, and the access point must be able to reliably control each device's activity.

What would settle it

A field experiment deploying the proposed IoTD placements and comparing measured detection times, energy usage, and false negative rates against those of a uniform grid deployment under identical conditions.

Figures

Figures reproduced from arXiv: 2604.18141 by David E. Ruiz-Guirola, Miltiadis Filippou, Onel A. Lopez.

Figure 1
Figure 1. Figure 1: System model for energy-aware geofencing intrusion de [PITH_FULL_IMAGE:figures/full_fig_p002_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Detection sector of an IoTD (e.g., camera) showing the [PITH_FULL_IMAGE:figures/full_fig_p003_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Impact of IoTD density N and duty-cycle period τ on reliability and timeliness for the geofencing intrusion-detection task. The bottom row corresponds to the grid baseline and the top row to the proposed RL-based mobility-aware configuration. Columns report (left) detection rate Pdet, (center) early-detection probability Pearly, and (right) mean time-to-detect E[Tdet] (s). 100 101 102 103 Duty cycle (ms) 0… view at source ↗
Figure 4
Figure 4. Figure 4: Minimum required IoTD density Nmin(τ) to satisfy Pdet ≥ 0.999 reliability operating point as a function of the duty-cycle period (left). Detection-rate map with the 99.9% reliability frontier required for active A-IoT operation for the proposed RL-based proposal (center) and the grid baseline (right). The black dashed curve with red markers indicates Nmin(τ), the minimum IoTD density needed to achieve Pdet… view at source ↗
read the original abstract

Timely and accurate monitoring in geofencing scenarios is challenging when relying on ultra-low power Internet of Things devices (IoTDs) powered by energy harvesting (EH). This is mainly because frequent wake-ups for data acquisition and data uploading may quickly deplete their limited energy buffer. Conventional grid-like IoT deployments overlook these limitations and merely rely on continuously powered sensing. Herein, we propose an energy-aware geofencing framework for camera-equipped EH IoTDs deployed around a protected area and its surrounding perimeter zone. The framework integrates a directional sensing power model with an operational representation of EH, sensing, sleeping, and reporting, accounting for the limited field-of-view (FoV) and distance-dependent detection confidence of the IoTDs. Device activity is controlled by the coverage-providing access point, which hosts a mobile edge host and a facility geocencing system to ensure timely and reliable detection under tight energy constraints. Reinforcement learning is used to determine IoTD placement, enabling earlier intruder detection than uniform grid-based deployments. Numerical results show that the proposed coordinated sensing and reporting configuration achieves frugal geofencing with fewer devices, while concurrently improving detection timeliness and dependability.

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

1 major / 1 minor

Summary. The manuscript proposes an energy-aware geofencing framework for camera-equipped energy-harvesting IoT devices (IoTDs) around a protected area. It integrates a directional sensing power model (accounting for limited FoV and distance-dependent detection confidence) with an operational state machine for EH, sensing, sleeping, and reporting. Device activity is coordinated by an access point hosting a mobile edge host and geofencing system; reinforcement learning optimizes IoTD placement to enable earlier intruder detection than uniform grid deployments. Numerical results claim that the coordinated configuration achieves frugal geofencing with fewer devices while improving detection timeliness and dependability under energy constraints.

Significance. If the models hold, the work could advance sustainable IoT surveillance by demonstrating how energy-aware coordination and RL-based placement reduce required device count while enhancing reliability and speed, with relevance to perimeter security and monitoring in resource-limited settings.

major comments (1)
  1. [Numerical results / simulation evaluation] The central claim that numerical results show fewer devices plus improved timeliness and dependability (abstract and results section) is generated from the directional sensing power model and the EH/sensing/sleeping/reporting state machine. No section provides empirical calibration of these models against real camera-equipped EH hardware or field measurements of detection latency/energy buffer dynamics, rendering the reported gains conditional on unvalidated assumptions about model fidelity to physical behavior.
minor comments (1)
  1. [Abstract] The abstract is concise but would be strengthened by including at least one quantitative example of the claimed gains (e.g., device reduction percentage or latency improvement) rather than qualitative statements only.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the detailed review and constructive feedback on our manuscript. We address the major comment regarding model validation and simulation assumptions below, providing clarification on the scope of our work while committing to revisions that strengthen the presentation of limitations.

read point-by-point responses

  1. Referee: [Numerical results / simulation evaluation] The central claim that numerical results show fewer devices plus improved timeliness and dependability (abstract and results section) is generated from the directional sensing power model and the EH/sensing/sleeping/reporting state machine. No section provides empirical calibration of these models against real camera-equipped EH hardware or field measurements of detection latency/energy buffer dynamics, rendering the reported gains conditional on unvalidated assumptions about model fidelity to physical behavior.

    Authors: We agree that the evaluation relies on simulation using the proposed directional sensing power model and EH operational state machine, without new empirical calibration against physical hardware or field data. These models are constructed from established principles in the literature: the directional sensing component incorporates standard camera field-of-view constraints and distance-dependent detection confidence drawn from prior computer vision and sensor network studies, while the EH/sensing/sleeping/reporting state machine follows well-documented energy buffer dynamics for harvesting IoT devices. The central claims are therefore presented as performance gains under these modeled conditions rather than as hardware-validated results. In the revised manuscript, we will add a new subsection (e.g., in Section V or VI) explicitly discussing model assumptions, their grounding in cited prior work, and limitations concerning real-world fidelity. We will also incorporate a sensitivity analysis varying key parameters (e.g., detection confidence curves and energy harvesting rates) to demonstrate robustness. This addresses the concern by clarifying the simulation scope without altering the core numerical findings. revision: partial

Circularity Check

0 steps flagged

No circularity: RL optimization applied to independently specified energy/sensing model

full rationale

The paper defines a directional sensing power model and state machine for EH/sensing/sleep/reporting, then applies RL to optimize IoTD placement and reports simulation outcomes. No step reduces a claimed prediction to a fitted parameter by construction, nor does any load-bearing claim rest on self-citation chains or imported uniqueness theorems. The numerical results are generated from the forward simulation of the stated models rather than being tautological with the inputs.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Insufficient information from abstract only to identify specific free parameters, axioms, or invented entities; no explicit models or equations provided.

pith-pipeline@v0.9.0 · 5513 in / 1035 out tokens · 35063 ms · 2026-05-10T04:09:39.062185+00:00 · methodology

discussion (0)

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

Reference graph

Works this paper leans on

19 extracted references · 19 canonical work pages

  1. [1]

    Ruiz-Guirola and Prasoon Raghuwanshi and Gabriel M

    D. E. Ruiz-Guirola et al., “Context-awareness for Dependable Low-Power IoT,” arXiv preprint arXiv:2510.23125, 2025

    work page arXiv 2025

  2. [2]

    Ericsson Mobility Report,

    P. Jonsson, “Ericsson Mobility Report,” Ericsson, Tech. Rep., 2023

    work page 2023

  3. [3]

    Energy-Sustainable IoT Connectivity: Vision, Technological Enablers, Challenges, and Future Direc- tions,

    O. L. A. López et al., “Energy-Sustainable IoT Connectivity: Vision, Technological Enablers, Challenges, and Future Direc- tions,” IEEE Open J. Commun. Soc., vol. 4, pp. 2609–2666, 2023

    work page 2023

  4. [4]

    3GPP TS 38.391: NR; Ambient IoT Medium Access Control (MAC) Protocol,

    “3GPP TS 38.391: NR; Ambient IoT Medium Access Control (MAC) Protocol,” ETSI (3GPP), Tech. Rep. TS 138 391, 2025

    work page 2025

  5. [5]

    A Survey on Ambient IoT: Use Cases, Stan- dardization, Enabling Technologies, and Research Directions,

    J. Famaey et al., “A Survey on Ambient IoT: Use Cases, Stan- dardization, Enabling Technologies, and Research Directions,” Authorea Preprints, 2026

    work page 2026

  6. [6]

    Zero-Energy Devices for 6G: Technical Enablers at a Glance,

    O. López et al., “Zero-Energy Devices for 6G: Technical Enablers at a Glance,” IEEE Internet Things Mag., vol. 8, no. 3, pp. 14–22, 2025

    work page 2025

  7. [7]

    Collaborative Sensing in Internet of Things: A Comprehensive Survey,

    S. He et al., “Collaborative Sensing in Internet of Things: A Comprehensive Survey,” IEEE Commun. Surveys Tuts., vol. 24, no. 3, pp. 1435–1474, 2022

    work page 2022

  8. [8]

    Efficient Fault-Tolerant Information Barrier Coverage in Internet of Things,

    ——, “Efficient Fault-Tolerant Information Barrier Coverage in Internet of Things,” IEEE Trans. Wireless Commun., vol. 20, no. 12, pp. 7963–7976, 2021

    work page 2021

  9. [9]

    A Trajectory-Inspired Node Deployment Strategy in Solar Insecticidal Lamps Internet of Things Under Coverage and Maintenance Cost Considerations,

    F. Yang and L. Shu, “A Trajectory-Inspired Node Deployment Strategy in Solar Insecticidal Lamps Internet of Things Under Coverage and Maintenance Cost Considerations,” IEEE Trans. AgriFood Electron., vol. 2, no. 1, pp. 28–42, 2024

    work page 2024

  10. [10]

    Toward Optimal Deployment for Full-View Point Coverage in Camera Sensor Networks,

    K. Shi et al., “Toward Optimal Deployment for Full-View Point Coverage in Camera Sensor Networks,” IEEE Internet Things J., vol. 9, no. 21, pp. 22 008–22 021, 2022

    work page 2022

  11. [11]

    Full View Maximum Coverage of Camera Sensors: Moving Object Monitoring,

    H. Du et al., “Full View Maximum Coverage of Camera Sensors: Moving Object Monitoring,” ACM Trans. Sens. Netw., vol. 20, no. 3, pp. 1–23, 2024

    work page 2024

  12. [12]

    Optimization Method of Linear Barrier Coverage Deployment for Multistatic Radar,

    H. Li et al., “Optimization Method of Linear Barrier Coverage Deployment for Multistatic Radar,” J. Syst. Eng. Electron., vol. 34, no. 1, pp. 68–80, 2022

    work page 2022

  13. [13]

    Pre-Deployment Strategy for Maximizing Barrier Coverage in Wireless Sensor Network,

    V. Chowdary et al., “Pre-Deployment Strategy for Maximizing Barrier Coverage in Wireless Sensor Network,” Int. J. Sens. Wireless Commun. Control, vol. 11, no. 2, pp. 181–188, 2021

    work page 2021

  14. [14]

    Energy-Efficient Barrier Coverage Based on Nodes Alliance for Intrusion Detection in Underwater Sensor Networks,

    J. Chang et al., “Energy-Efficient Barrier Coverage Based on Nodes Alliance for Intrusion Detection in Underwater Sensor Networks,” IEEE Sensors J., vol. 22, no. 4, pp. 3766–3776, 2022

    work page 2022

  15. [15]

    Enhancing Network Lifespan in Wireless Sensor Networks Using Deep Learning Based Graph Neural Network,

    N. R. Sivakumar et al., “Enhancing Network Lifespan in Wireless Sensor Networks Using Deep Learning Based Graph Neural Network,” Phys. Commun., vol. 59, p. 102076, 2023

    work page 2023

  16. [16]

    Energy Management and Wake- up for IoT Networks Powered by Energy Harvesting,

    D. E. Ruíz-Guirola et al., “Energy Management and Wake- up for IoT Networks Powered by Energy Harvesting,” IEEE Internet Things J., pp. 1–1, 2026

    work page 2026

  17. [17]

    Intelligent Duty Cycling Manage- ment and Wake-up for Energy Harvesting IoT Networks with Correlated Activity,

    D. E. Ruiz-Guirola et al., “Intelligent Duty Cycling Manage- ment and Wake-up for Energy Harvesting IoT Networks with Correlated Activity,” in 58th Asilomar Conf. Signals, Syst. Comput., 2024

    work page 2024

  18. [18]

    WiseCam: Wisely Tuning Wireless Pan-Tilt Cameras for Cost-Effective Moving Object Tracking,

    E. Jinlong et al., “WiseCam: Wisely Tuning Wireless Pan-Tilt Cameras for Cost-Effective Moving Object Tracking,” in IEEE INFOCOM. IEEE, 2023, pp. 1–10

    work page 2023

  19. [19]

    Occupancy Prediction Using Low-Cost and Low-Resolution Heat Sensors for Smart Offices,

    B. Sirmacek and M. Riveiro, “Occupancy Prediction Using Low-Cost and Low-Resolution Heat Sensors for Smart Offices,” Sensors, vol. 20, no. 19, p. 5497, 2020

    work page 2020