BioNet-A: Ultrasonic echo representation network for target discrimination using active SONAR
The Journal of the Acoustical Society of America · 01.07.2026 · 160 (1) · 160-173
DOI: 10.1121/10.0044331 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Journal of the Acoustical Society of America, online erschienen am 01.07.2026. Verfasst von Sangwook Park und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electronic and Semiconductor Engineering, Kangwon National University, Gangneung, Gangwon 25457, South Korea. Hauptthemen laut MEDLINE: Vocalization, Animal, Echolocation, Ultrasonic Waves, Biomimetics. Die Arbeit nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Science and ICT, South Korea, Office of Naval Research.
Abstract (Originalsprache)
Ultrasonic echoes provide critical cues for object perception, yet their millisecond duration and frequency-specific structure violate assumptions of conventional spectrogram-based convolutional models. Existing biomimetic front-end systems, including auditory spectrograms, cortical wavelets, and the biomimetic BioNet, either under-utilize model capacity on brief echoes or impose frequency shift-invariance suited to vocalizations but detrimental for echo discrimination. This study introduces BioNet5-A, a biomimetic encoder optimized for ultrasonic echoes. BioNet5-A is derived from an autoencoder pretrained on bat vocalizations and incorporates three architectural innovations: (1) spectrotemporal attention to concentrate capacity on the ∼2 ms echo segment and relax frequency-axis invariance; (2) multi-sized convolution/transposed-convolution modules that capture echo structure across multiple scales; and (3) a symmetric, weight-tied encoder–decoder to stabilize training and regularize the biomimetic code. Using a controlled ultrasonic dataset spanning multiple objects and noise conditions, BioNet5-A consistently outperforms auditory spectrogram, cortical wavelet, and the conventional BioNet, and shows improved clustering, discrimination, and robustness. Additionally, representations by the model remain compact and interpretable, aligning with bat midbrain physiology. These results position BioNet5-A as a practical front end for biosonar-inspired sensing and ultrasonic applications.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Electronic and Semiconductor Engineering, Kangwon National University, Gangneung, Gangwon 25457, South Korea.
- Department of Electrical Computer Engineering, Johns Hopkins University, Baltimore, Maryland 21218, USA.
ORCID-Profile: Sangwook Park, Mounya Elhilali
Förderung
- Ministry of Science and ICT, South Korea
- Office of Naval Research
Zitieren
APA
Park, S., & Elhilali, M. (2026). BioNet-A: Ultrasonic echo representation network for target discrimination using active SONAR. The Journal of the Acoustical Society of America, 160(1), 160-173. https://doi.org/10.1121/10.0044331
Vancouver
Park S, Elhilali M. BioNet-A: Ultrasonic echo representation network for target discrimination using active SONAR. The Journal of the Acoustical Society of America. 2026;160(1):160-173. doi:10.1121/10.0044331
BibTeX
@article{Park2026,
author = {Park, Sangwook and Elhilali, Mounya},
title = {BioNet-A: Ultrasonic echo representation network for target discrimination using active SONAR},
journal = {The Journal of the Acoustical Society of America},
year = {2026},
volume = {160},
number = {1},
pages = {160--173},
doi = {10.1121/10.0044331}
}
EUVIMED