EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

AI-Driven Intrusion Detection With Seismic-Acoustic Fusion on Embedded Devices

Duy-Tan Ngo, Ngoc-Minh Pham, Manh-Dat Nguyen, Kim-Chi Tran, Duy-Phong Pham, Thien-Tan Nguyen

IEEE Access · 2026 · 14 · 31867-31880

DOI: 10.1109/access.2026.3665654 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Access, 2026. Verfasst von Duy-Tan Ngo und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Vietnam Academy of Science and Technology.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Modern security systems require robust, real-time solutions to detect anomalies in complex environments. This paper presents a novel multimodal framework integrating the SM-24 geophone and a condenser microphone, leveraging artificial intelligence (AI) to enhance detection performance. By combining seismic vibrations captured by the SM-24 geophone, digitized via the ADS1115 16-bit Analog-to-Digital Converter (ADC), with high-fidelity acoustic signals from the condenser microphone, our approach achieves superior accuracy and robustness compared to single-sensor systems. We propose a novel early-fusion framework that integrates standardized seismic PSD (64-D) and acoustic MFCC statistics (78-D) into a single 142-D input vector for a compact dense neural network (LDNN) optimized for resource-constrained embedded platforms, such as the Raspberry Pi 4, enabling efficient real-time processing. Advanced feature extraction techniques, including Mel frequency cepstral coefficients (MFCC) for audio and spectral analysis for seismic data, ensure computational efficiency while maintaining high accuracy. Experimental results demonstrate a detection accuracy of 93.8%, surpassing traditional single-sensor methods by at least 15% in noisy conditions. Evaluated across diverse scenarios, including perimeter surveillance and unauthorized activity detection, the system exhibits exceptional reliability. This work highlights the transformative potential of AI-driven multimodal sensing, offering a scalable, cost-effective solution for next-generation security applications on embedded devices.

Förderung

  • Vietnam Academy of Science and Technology

Zitieren

APA

Ngo, D., Pham, N., Nguyen, M., Tran, K., Pham, D., & Nguyen, T. (2026). AI-Driven Intrusion Detection With Seismic-Acoustic Fusion on Embedded Devices. IEEE Access, 14, 31867-31880. https://doi.org/10.1109/access.2026.3665654

Vancouver

Ngo D, Pham N, Nguyen M, Tran K, Pham D, Nguyen T. AI-Driven Intrusion Detection With Seismic-Acoustic Fusion on Embedded Devices. IEEE Access. 2026;14:31867-31880. doi:10.1109/access.2026.3665654

BibTeX
@article{Ngo2026,
  author = {Ngo, Duy-Tan and Pham, Ngoc-Minh and Nguyen, Manh-Dat and Tran, Kim-Chi and Pham, Duy-Phong and Nguyen, Thien-Tan},
  title = {AI-Driven Intrusion Detection With Seismic-Acoustic Fusion on Embedded Devices},
  journal = {IEEE Access},
  year = {2026},
  volume = {14},
  pages = {31867--31880},
  doi = {10.1109/access.2026.3665654}
}
Kostenlos starten →