Adaptive-Sampling Mamba–Conv-TasNet for Single-Channel Blind Separation of Electromagnetic Signals
Sensors · 29.10.2026 · 26 (21) · 6844
DOI: 10.3390/s26216844 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 29.10.2026. Verfasst von Chao Zhou und 6 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Electronic and Electrical Engineering, Civil Aviation Flight University of China, Chengdu 618307, China. Die Arbeit nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: 2025 project of the Sichuan Flight Engineering Technology Research Center, Civil Aviation Flight University of China.
Abstract (Originalsprache)
In passive electromagnetic detection and positioning systems, the complex electromagnetic environment poses significant theoretical challenges to traditional single-channel blind source separation (SCBSS) algorithms. To address the need to balance separation quality, computational efficiency, resource use and generalisation across different detection conditions, we present the Adaptive-Sampling Mamba–Conv-TasNet, which integrates physically constrained front-end routing with local and long-range sequence modelling. A condition encoder estimates each mixture’s occupied bandwidth and characteristic time scale. It then selects the lowest-rate, anti-aliased profile that preserves the detected band. Four parallel convolutional kernels extract multiscale local features. The separator combines Conv-TasNet-based local modelling with Mamba-based long-range sequence modelling. A shared mask head produces two source-specific masks, and profile-specific decoders subsequently reconstruct two complex-baseband sources. Across three test sets and nine evaluated methods, the proposed model attains the lowest mean complex NMSE on every dataset and the lowest cross-domain log-PSD RMSE while maintaining moderate latency, model size and memory demand. These results indicate that the Adaptive-Sampling Mamba–Conv-TasNet offers a favourable overall trade-off among separation quality, computational efficiency, resource use and cross-domain generalisation relative to the evaluated methods.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Institute of Electronic and Electrical Engineering, Civil Aviation Flight University of China, Chengdu 618307, China.
- School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China.
ORCID-Profile: Xin Li
Förderung
- 2025 project of the Sichuan Flight Engineering Technology Research Center, Civil Aviation Flight University of China
Zitieren
APA
Zhou, C., Guo, Y., Li, X., Zhang, R., Han, Y., Huang, J., & Chen, X. (2026). Adaptive-Sampling Mamba–Conv-TasNet for Single-Channel Blind Separation of Electromagnetic Signals. Sensors, 26(21), 6844. https://doi.org/10.3390/s26216844
Vancouver
Zhou C, Guo Y, Li X, Zhang R, Han Y, Huang J, et al. Adaptive-Sampling Mamba–Conv-TasNet for Single-Channel Blind Separation of Electromagnetic Signals. Sensors. 2026;26(21):6844. doi:10.3390/s26216844
BibTeX
@article{Zhou2026,
author = {Zhou, Chao and Guo, Youcheng and Li, Xin and Zhang, Ruoning and Han, Yulin and Huang, Juncheng and Chen, Xuexin},
title = {Adaptive-Sampling Mamba–Conv-TasNet for Single-Channel Blind Separation of Electromagnetic Signals},
journal = {Sensors},
year = {2026},
volume = {26},
number = {21},
pages = {6844},
doi = {10.3390/s26216844}
}
EUVIMED