{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T14:54:33Z","timestamp":1782917673299,"version":"3.54.5"},"reference-count":38,"publisher":"Acoustical Society of America (ASA)","issue":"1","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100014188","name":"Ministry of Science and ICT, South Korea","doi-asserted-by":"publisher","award":["RS-2024-00358953"],"award-info":[{"award-number":["RS-2024-00358953"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","award":["N00014-23-1-2086"],"award-info":[{"award-number":["N00014-23-1-2086"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["pubs.aip.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,1]]},"abstract":"<jats:p>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 \u223c2\u2009ms 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\u2013decoder 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.<\/jats:p>","DOI":"10.1121\/10.0044331","type":"journal-article","created":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T14:18:28Z","timestamp":1782915508000},"page":"160-173","update-policy":"https:\/\/doi.org\/10.1063\/aip-crossmark-policy-page","source":"Crossref","is-referenced-by-count":0,"title":["BioNet-A: Ultrasonic echo representation network for target discrimination using active SONAR"],"prefix":"10.1121","volume":"160","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5009-2394","authenticated-orcid":false,"given":"Sangwook","family":"Park","sequence":"first","affiliation":[{"name":"Department of Electronic and Semiconductor Engineering, Kangwon National University 1 , Gangneung, Gangwon 25457,","place":["South Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2597-738X","authenticated-orcid":false,"given":"Mounya","family":"Elhilali","sequence":"additional","affiliation":[{"name":"Department of Electrical Computer Engineering, Johns Hopkins University 2 , Baltimore, Maryland 21218,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"231","published-online":{"date-parts":[[2026,7,1]]},"reference":[{"issue":"19","key":"2026070109523878100_c1","doi-asserted-by":"publisher","first-page":"16387","DOI":"10.1007\/s00521-022-07662-y","article-title":"Recent advances of bat-inspired algorithm, its versions and applications","volume":"34","year":"2022","journal-title":"Neural Comput. Applic."},{"key":"2026070109523878100_c2","first-page":"657","article-title":"Multiscale scattering for audio classification","year":"2011"},{"key":"2026070109523878100_c3","doi-asserted-by":"publisher","first-page":"4882","DOI":"10.1523\/JNEUROSCI.4342-06.2007","article-title":"Spectrotemporal receptive fields in the inferior colliculus revealing selectivity for spectral motion in conspecific vocalizations","volume":"27","year":"2007","journal-title":"J. Neurosci."},{"key":"2026070109523878100_c4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1080\/03610927408827101","article-title":"A dendrite method for cluster analysis","volume":"3","year":"1974","journal-title":"Commun. Stat."},{"key":"2026070109523878100_c5","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1002\/cne.903190106","article-title":"Frequency tuning properties of neurons in the inferior colliculus of an FM bat","volume":"319","year":"1992","journal-title":"J. Comp. Neurol."},{"key":"2026070109523878100_c6","first-page":"238","volume-title":"The Inferior Colliculus: A Hub for the Central Auditory System","year":"2002"},{"key":"2026070109523878100_c7","doi-asserted-by":"publisher","first-page":"887","DOI":"10.1121\/1.1945807","article-title":"Multiresolution spectrotemporal analysis of complex sounds","volume":"118","year":"2005","journal-title":"J. Acoust. Soc. Am."},{"key":"2026070109523878100_c8","unstructured":"Chi, T., and Shamma, S. (2005). \u201cNSL MATLAB Toolbox,\u201d http:\/\/www.isr.umd.edu\/ speech\/nsltools.tar.gz (Last viewed June 25, 2026)."},{"key":"2026070109523878100_c9","doi-asserted-by":"publisher","first-page":"1013","DOI":"10.1109\/JSEN.2015.2496945","article-title":"Robust sonar-based underwater object recognition against angle-of-view variation","volume":"16","year":"2016","journal-title":"IEEE Sens. J."},{"key":"2026070109523878100_c10","doi-asserted-by":"publisher","first-page":"224","DOI":"10.1109\/TPAMI.1979.4766909","article-title":"A cluster separation measure","volume":"1","year":"1979","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2026070109523878100_c11","unstructured":"Dehghani, N., and Levin, M. (2024). \u201cBio-inspired AI: Integrating biological complexity into artificial intelligence,\u201d https:\/\/arxiv.org\/abs\/2411.15243 (Last viewed June 25, 2026)."},{"key":"2026070109523878100_c12","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1016\/0893-6080(94)00057-S","article-title":"Three-dimensional target recognition via sonar: A neural network model","volume":"8","year":"1995","journal-title":"Neural Netw."},{"key":"2026070109523878100_c13","doi-asserted-by":"publisher","first-page":"2447","DOI":"10.1121\/10.0017922","article-title":"Convolutional neural network with data augmentation for object classification in automotive ultrasonic sensing","volume":"153","year":"2023","journal-title":"J. Acoust. Soc. Am."},{"key":"2026070109523878100_c14","doi-asserted-by":"publisher","first-page":"1060","DOI":"10.1121\/10.0024753","article-title":"Relevance of phase information for object classification in automotive ultrasonic sensing using convolutional neural networks","volume":"155","year":"2024","journal-title":"J. Acoust. Soc. Am."},{"key":"2026070109523878100_c15","doi-asserted-by":"publisher","first-page":"2556","DOI":"10.1121\/10.0036385","article-title":"Object classification in automotive ultrasonic surround sensing using a compact 2\u2009\u00d7\u20092 sensor array and a convolutional neural network","volume":"157","year":"2025","journal-title":"J. Acoust. Soc. Am."},{"key":"2026070109523878100_c16","first-page":"33","article-title":"A linear systems view to the concept of STRF","volume-title":"Handbook of Modern Techniques in Auditory Cortex","author":"Depireux","year":"2013"},{"key":"2026070109523878100_c17","doi-asserted-by":"publisher","first-page":"330","DOI":"10.1109\/JOE.2010.2044912","article-title":"Methods for identifying and controlling sonar clutter","volume":"35","year":"2010","journal-title":"IEEE J. Oceanic Eng."},{"key":"2026070109523878100_c18","doi-asserted-by":"publisher","first-page":"671","DOI":"10.1007\/BF00192716","article-title":"Frequency tuning and response latencies at three levels in the brainstem of the echolocating bat, Eptesicus fuscus","volume":"174","year":"1994","journal-title":"J. Comp. Physiol. A"},{"key":"2026070109523878100_c19","first-page":"80","article-title":"One hundred ways to process time, frequency, rate and scale in the central auditory system: A pattern-recognition meta-analysis","volume":"9","year":"2015","journal-title":"Front. Comput. Neurosci."},{"key":"2026070109523878100_c20","doi-asserted-by":"publisher","first-page":"189673","DOI":"10.1109\/ACCESS.2020.3031297","article-title":"Bat-G2 net: Bat-inspired graphical visualization network guided by radiated ultrasonic call","volume":"8","year":"2020","journal-title":"IEEE Access"},{"key":"2026070109523878100_c21","doi-asserted-by":"publisher","first-page":"1176","DOI":"10.3390\/s19051176","article-title":"Classification of sonar targets in air: A neural network approach","volume":"19","year":"2019","journal-title":"Sens. (Basel)"},{"key":"2026070109523878100_c22","doi-asserted-by":"publisher","first-page":"2207","DOI":"10.1121\/1.1398051","article-title":"Auditory scene analysis by echolocation in bats","volume":"110","year":"2001","journal-title":"J. Acoust. Soc. Am."},{"key":"2026070109523878100_c23","first-page":"2763","article-title":"Frequency dynamic convolution: Frequency-adaptive pattern recognition for sound event detection","year":"2022"},{"key":"2026070109523878100_c24","doi-asserted-by":"publisher","first-page":"ENEURO.0525-20.2021","DOI":"10.1523\/ENEURO.0525-20.2021","article-title":"Natural statistics as inference principles of auditory tuning in biological and artificial midbrain networks","volume":"8","year":"2021","journal-title":"eNeuro."},{"key":"2026070109523878100_c25","first-page":"6265","article-title":"Biomimetic mappings for active sonar object recognition in clutter","year":"2024"},{"key":"2026070109523878100_c26","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1016\/j.conb.2019.12.006","article-title":"Decision making in foraging bats","volume":"60","year":"2020","journal-title":"Curr. Opin. Neurobiol."},{"key":"2026070109523878100_c27","first-page":"4635","article-title":"Adjusting for chance clustering comparison measures","volume":"17","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"2026070109523878100_c28","first-page":"410","article-title":"V-measure: A conditional entropy-based external cluster evaluation measure","author":"Eisner","year":"2007"},{"key":"2026070109523878100_c29","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1016\/0377-0427(87)90125-7","article-title":"Silhouettes: A graphical aid to the interpretation and validation of cluster analysis","volume":"20","year":"1987","journal-title":"J. Comput. Appl. Math."},{"key":"2026070109523878100_c30","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1007\/BF00612436","article-title":"Comparative collicular tonotopy in two bat species adapted to movement detection, Hipposideros speoris and Megaderma lyra","volume":"163","year":"1988","journal-title":"J. Comp. Physiol. A"},{"key":"2026070109523878100_c31","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1016\/0959-4388(95)80010-7","article-title":"Order and disorder in auditory cortical maps","volume":"5","year":"1995","journal-title":"Curr. Opin. Neurobiol."},{"key":"2026070109523878100_c32","doi-asserted-by":"publisher","first-page":"1367","DOI":"10.1073\/pnas.1909890117","article-title":"Bioinspired sonar reflectors as guiding beacons for autonomous navigation","volume":"117","year":"2020","journal-title":"Proc. Natl. Acad. Sci. U.S.A."},{"key":"2026070109523878100_c33","unstructured":"Song, T., and Zhang, W. (2024). \u201cFrequency-aware convolution for sound event detection,\u201d https:\/\/arxiv.org\/abs\/2403.13252 (Last viewed June 25, 2026)."},{"key":"2026070109523878100_c34","doi-asserted-by":"publisher","first-page":"15475","DOI":"10.1016\/j.ifacol.2020.12.2371","article-title":"Imaging-sonar-based underwater object recognition utilizing object's yaw angle estimation with deep learning","volume":"53","year":"2020","journal-title":"IFAC PapersOnLine"},{"key":"2026070109523878100_c35","doi-asserted-by":"publisher","first-page":"853","DOI":"10.1098\/rspb.2008.1505","article-title":"Echolocating bats emit a highly directional sonar sound beam in the field","volume":"276","year":"2009","journal-title":"Proc. R. Soc. B"},{"key":"2026070109523878100_c36","doi-asserted-by":"publisher","first-page":"690","DOI":"10.3390\/jmse11040690","article-title":"AUV-based side-scan sonar real-time method for underwater-target detection","volume":"11","year":"2023","journal-title":"J. Mar. Sci. Eng."},{"key":"2026070109523878100_c37","first-page":"2837","article-title":"Information theoretic measures for clusterings comparison: Variants, properties, normalization and correction for chance","volume":"11","year":"2010","journal-title":"J. Mach. Learn. Res."},{"key":"2026070109523878100_c38","doi-asserted-by":"publisher","first-page":"824","DOI":"10.1109\/18.119739","article-title":"Auditory representations of acoustic signals","volume":"38","year":"1992","journal-title":"IEEE Trans. Inform. Theory"}],"container-title":["The Journal of the Acoustical Society of America"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.aip.org\/asa\/jasa\/article-pdf\/160\/1\/160\/21061357\/160_1_10.0044331.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.aip.org\/asa\/jasa\/article-pdf\/160\/1\/160\/21061357\/160_1_10.0044331.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T14:18:40Z","timestamp":1782915520000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.aip.org\/jasa\/article\/160\/1\/160\/3397204\/BioNet-A-Ultrasonic-echo-representation-network"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,1]]},"references-count":38,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,7,1]]}},"URL":"https:\/\/doi.org\/10.1121\/10.0044331","relation":{},"ISSN":["1520-8524"],"issn-type":[{"value":"1520-8524","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,7]]},"published":{"date-parts":[[2026,7,1]]}}}