S2-DyGNN: A Spectro-Spatial Dynamic Graph Neural Network for Acoustic Event Classification in Distributed Acoustic Sensing
Sensors · 12.07.2026 · 26 (14) · 4417
DOI: 10.3390/s26144417 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 12.07.2026. Verfasst von Seunghun Jeong und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of AI Convergence, Gwangju Institute of Science and Technology, Gwangju 61005, Republic of Korea. Die Arbeit nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Foundation of Korea.
Abstract (Originalsprache)
Distributed acoustic sensing (DAS) systems capture complex, nonlinear wave propagation across fiber-optic cables. Conventional event classification architectures, constrained by static physical topologies or isolated spatial grids, fail to effectively adapt to the dynamic feature relationships associated with such events, particularly when modeling complex spatiotemporal interactions across sensor arrays. To resolve these structural limitations, we introduce the Spectro-Spatial Dynamic Graph Neural Network (S2-DyGNN), whose architecture couples a two-dimensional frequency–time convolutional front-end with a dual-matrix graph neural network (GNN). First, the convolutional module extracts spectro-temporal features, explicitly capturing localized acoustic dynamics independent of inter-sensor interference. Subsequently, the graph module constructs a dual-matrix topology, fusing a static physical distance prior with a data-driven adjacency matrix that recalculates spatial connections frame by frame from input signals. When evaluated on a highly skewed nine-class DAS field dataset, S2-DyGNN outperformed other conventional models by achieving a peak macro-averaged F1-score of 86.6% and an overall accuracy of 94.0%. The dual-matrix graph topology prevented dominant background features from washing out sparse transient events, improving the minority “openclose” class F1-score to 55.7% compared to the 48.0% ceiling of a static graph topology. These results demonstrate that explicitly coupling localized spectro-temporal representations with physically anchored spatial topologies consistently outperforms models that process these domains in isolation, providing a highly robust and scalable solution for real-world continuous monitoring systems.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of AI Convergence, Gwangju Institute of Science and Technology, Gwangju 61005, Republic of Korea.
- Optical Precision Measurement Research Center, Korea Photonic Technology Institute, Gwangju 61007, Republic of Korea.
- Department of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology, Gwangju 61005, Republic of Korea.
ORCID-Profile: Seunghun Jeong, Huioon Kim, Young Ho Kim, Hyoyoung Jung, Hong Kook Kim
Förderung
- National Research Foundation of Korea
Zitieren
APA
Jeong, S., Kim, H., Kim, Y. H., Jung, H., & Kim, H. K. (2026). S2-DyGNN: A Spectro-Spatial Dynamic Graph Neural Network for Acoustic Event Classification in Distributed Acoustic Sensing. Sensors, 26(14), 4417. https://doi.org/10.3390/s26144417
Vancouver
Jeong S, Kim H, Kim YH, Jung H, Kim HK. S2-DyGNN: A Spectro-Spatial Dynamic Graph Neural Network for Acoustic Event Classification in Distributed Acoustic Sensing. Sensors. 2026;26(14):4417. doi:10.3390/s26144417
BibTeX
@article{Jeong2026,
author = {Jeong, Seunghun and Kim, Huioon and Kim, Young Ho and Jung, Hyoyoung and Kim, Hong Kook},
title = {S2-DyGNN: A Spectro-Spatial Dynamic Graph Neural Network for Acoustic Event Classification in Distributed Acoustic Sensing},
journal = {Sensors},
year = {2026},
volume = {26},
number = {14},
pages = {4417},
doi = {10.3390/s26144417}
}
EUVIMED