EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Limited-Data Radar–Audio Fusion for Room-Level Intrusion Detection: Multi-Level Performance Evaluation and Cross-Environment Validation

Eduard Vladu, Luminita Rostas, Marius Neag iD, Alessandro Battigelli iD, Dominic Domnici, Gabriel Oltean

Sensors · 09.11.2026 · 26 (21) · 7095

DOI: 10.3390/s26217095 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 09.11.2026. Verfasst von Eduard Vladu und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Bases of Electronics, Faculty of Electronics, Telecommunications and Information Technology, Technical University of Cluj-Napoca, Memor…. Die Arbeit nennt 15 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Romanian Hub for Artificial Intelligence, Romanian Hub for Artificial Intelligence—HRIA, Technical University of Cluj-Napoca.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Camera-free indoor security requires privacy-preserving sensing robust to disturbances and compatible with edge deployment. This study presents a limited-data radar–audio framework for room-level intrusion-related alarm detection. Data were collected using two colocated Infineon CY8CKIT-062S2-AI boards providing 60 GHz radar macro-detection outputs and stereo audio. Radar-only, audio-only, feature-level early-fusion, and score-level late-fusion branches were evaluated using session-disjoint training, validation, and test subsets, followed by stateful alarm processing. On the independent Room 1 test subset, validation-selected maximum-score late fusion achieved an F1-score of 0.897, compared with 0.842 for radar-only, 0.789 for audio-only, and 0.854 for early fusion. Stateful processing reduced false positives from 4.19 to 2.58 per 100 negative windows while retaining an F1-score of 0.888. Raspberry Pi 5 replay preserved all reference decisions. A live proof-of-concept sustained early-fusion and stateful maximum-score late-fusion processing at 48.53 ms and 46.50 ms per window, respectively, below the 0.8 s update interval. Without retraining or parameter adaptation, transfer to a second room retained F1-scores of 0.864 at window level and 0.859 after stateful processing, although false-positive behavior was more environment-sensitive. These results support score-level radar–audio fusion for limited-data edge-oriented indoor intrusion detection.

Schlagwörter

Stichwörter der Autor:innen

acoustic sensingcamera-free monitoringedge AIindoor intrusion detectionmmWave radarmultimodal sensingradar–audio fusionstateful alarm evaluation

Autor:innen und Institutionen

  • Department of Bases of Electronics, Faculty of Electronics, Telecommunications and Information Technology, Technical University of Cluj-Napoca, Memorandumului Street No. 28, 400114 Cluj-Napoca, Romania.

ORCID-Profile: Marius Neag, Alessandro Battigelli

Förderung

  • Romanian Hub for Artificial Intelligence
  • Romanian Hub for Artificial Intelligence—HRIA
  • Technical University of Cluj-Napoca

Zitieren

APA

Vladu, E., Rostas, L., Neag, M., Battigelli, A., Domnici, D., & Oltean, G. (2026). Limited-Data Radar–Audio Fusion for Room-Level Intrusion Detection: Multi-Level Performance Evaluation and Cross-Environment Validation. Sensors, 26(21), 7095. https://doi.org/10.3390/s26217095

Vancouver

Vladu E, Rostas L, Neag M, Battigelli A, Domnici D, Oltean G. Limited-Data Radar–Audio Fusion for Room-Level Intrusion Detection: Multi-Level Performance Evaluation and Cross-Environment Validation. Sensors. 2026;26(21):7095. doi:10.3390/s26217095

BibTeX
@article{Vladu2026,
  author = {Vladu, Eduard and Rostas, Luminita and Neag, Marius and Battigelli, Alessandro and Domnici, Dominic and Oltean, Gabriel},
  title = {Limited-Data Radar–Audio Fusion for Room-Level Intrusion Detection: Multi-Level Performance Evaluation and Cross-Environment Validation},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {21},
  pages = {7095},
  doi = {10.3390/s26217095}
}
Kostenlos starten →