BioNet-A: Ultrasonic echo representation network for target discrimination using active SONAR
Open Access
- 1 July 2026
- journal article
- Published by Acoustical Society of America (ASA) in The Journal of the Acoustical Society of America
- Vol. 160 (1) , 160-173
Abstract
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.Keywords
Funding Information
- Ministry of Science and ICT, South Korea (RS-2024-00358953)
- Office of Naval Research (N00014-23-1-2086)
This publication has 26 references indexed in Scilit:
- Recent advances of bat-inspired algorithm, its versions and applicationsNeural Computing and Applications, 2022
- Decision making in foraging batsCurrent Opinion in Neurobiology, 2020
- Bioinspired sonar reflectors as guiding beacons for autonomous navigationProceedings of the National Academy of Sciences, 2020
- Imaging-sonar-based Underwater Object Recognition Utilizing Object’s Yaw Angle Estimation with Deep LearningIFAC-PapersOnLine, 2020
- Three-Dimensional target recognition via sonar: A neural network modelNeural Networks, 1995
- Order and disorder in auditory cortical mapsCurrent Opinion in Neurobiology, 1995
- Frequency tuning and response latencies at three levels in the brainstem of the echolocating bat, Eptesicus fuscusJournal of Comparative Physiology A, 1994
- Frequency tuning properties of neurons in the inferior colliculus of an FM batJournal of Comparative Neurology, 1992
- Comparative collicular tonotopy in two bat species adapted to movement detection,Hipposideros speoris andMegaderma lyraJournal of Comparative Physiology A, 1988
- Silhouettes: A graphical aid to the interpretation and validation of cluster analysisJournal of Computational and Applied Mathematics, 1987