EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Cost-Effective Train Presence Detection and Alerting Using Resource-Constrained Devices

Dimitrios Zorbas iD, Maral Baizhuminova iD, Dnislam Urazayev iD, Aida Eduard iD, Gulim Nurgazina iD, Nursultan Atymtay iD, Marko Ristin iD

Sensors · 01.10.2025 · 25 (19) · 6045

DOI: 10.3390/s25196045 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 01.10.2025. Verfasst von Dimitrios Zorbas und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Engineering & Digital Sciences, Nazarbayev University, Astana 010000, Kazakhstan. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Samruk-Kazyna JSC.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Early train detection is vital for ensuring the safety of railway personnel, particularly in remote locations where fixed signaling infrastructure is unavailable. Unlike many existing solutions that rely on high-power, high-cost sensors and compute platforms, this work presents a lightweight, low-cost, and portable framework designed to run entirely on resource-constrained microcontrollers with just kilobytes of Random Access Memory (RAM). The proposed system uses vibration data from low-cost accelerometers and employs a simple yet effective Linear Regression (LR) model for almost real-time prediction of train arrival times. To ensure feasibility on low-end hardware, a parallel-processing framework is introduced, enabling continuous data collection, Machine Learning (ML) inference, and wireless communication with strict timing and energy constraints. The decision-making process, including data preprocessing and ML prediction, completes in under 10 ms, and alerts are transmitted via LoRa, enabling kilometer-range communication. Field tests on active railway lines confirm that the system detects approaching trains 15 s in advance with no false negatives and a small number of explainable false positives. Power characterization demonstrates that the system can operate for more than 6 days on a 10 Ah battery, with potential for months of operation using wake-on-vibration modes.

Schlagwörter

Stichwörter der Autor:innen

LoRaMachine Learningedge computinglow-powerrailways

Autor:innen und Institutionen

  • School of Engineering & Digital Sciences, Nazarbayev University, Astana 010000, Kazakhstan.

ORCID-Profile: Dimitrios Zorbas, Maral Baizhuminova, Dnislam Urazayev, Aida Eduard, Gulim Nurgazina, Nursultan Atymtay, Marko Ristin

Förderung

  • Samruk-Kazyna JSC

Zitieren

APA

Zorbas, D., Baizhuminova, M., Urazayev, D., Eduard, A., Nurgazina, G., Atymtay, N., & Ristin, M. (2025). Cost-Effective Train Presence Detection and Alerting Using Resource-Constrained Devices. Sensors, 25(19), 6045. https://doi.org/10.3390/s25196045

Vancouver

Zorbas D, Baizhuminova M, Urazayev D, Eduard A, Nurgazina G, Atymtay N, et al. Cost-Effective Train Presence Detection and Alerting Using Resource-Constrained Devices. Sensors. 2025;25(19):6045. doi:10.3390/s25196045

BibTeX
@article{Zorbas2025,
  author = {Zorbas, Dimitrios and Baizhuminova, Maral and Urazayev, Dnislam and Eduard, Aida and Nurgazina, Gulim and Atymtay, Nursultan and Ristin, Marko},
  title = {Cost-Effective Train Presence Detection and Alerting Using Resource-Constrained Devices},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {19},
  pages = {6045},
  doi = {10.3390/s25196045}
}
Kostenlos starten →