{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T21:37:41Z","timestamp":1783287461421,"version":"3.54.6"},"reference-count":26,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Recovery and Resilience Plan (NRRP), Mission 4 Component 2 Investment 1.4","award":["3138"],"award-info":[{"award-number":["3138"]}]},{"name":"National Recovery and Resilience Plan (NRRP), Mission 4 Component 2 Investment 1.4","award":["3175"],"award-info":[{"award-number":["3175"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Robotics"],"abstract":"<jats:p>The escalating conflict between cetaceans and fisheries underscores the need for efficient mitigation strategies that balance conservation priorities with economic viability. This study presents a TinyML-driven approach deploying an optimized Convolutional Neural Network (CNN) on a Raspberry Pi Zero 2 W for real-time detection of bottlenose dolphin whistles, leveraging spectrogram analysis to address acoustic monitoring challenges. Specifically, a CNN model previously developed for classifying dolphins\u2019 vocalizations and originally implemented with TensorFlow was converted to TensorFlow Lite (TFLite) with architectural optimizations, reducing the model size by 76%. Both TensorFlow and TFLite models were trained on 22 h of underwater recordings taken in controlled environments and processed into 0.8 s spectrogram segments (300 \u00d7 150 pixels). Despite reducing model size, TFLite models maintained the same accuracy as the original TensorFlow model (87.8% vs. 87.0%). Throughput and latency were evaluated by varying the thread allocation (1\u20138 threads), revealing the best performance at 4 threads (quad-core alignment), achieving an inference latency of 120 ms and sustained throughput of 8 spectrograms\/second. The system demonstrated robustness in 120 h of continuous stress tests without failure, underscoring its reliability in marine environments. This work achieved a critical balance between computational efficiency and detection fidelity (F1-score: 86.9%) by leveraging quantized, multithreaded inference. These advancements enable low-cost devices for real-time cetacean presence detection, offering transformative potential for bycatch reduction and adaptive deterrence systems. This study bridges artificial intelligence innovation with ecological stewardship, providing a scalable framework for deploying machine learning in resource-constrained settings while addressing urgent conservation challenges.<\/jats:p>","DOI":"10.3390\/robotics14050067","type":"journal-article","created":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T06:54:28Z","timestamp":1747724068000},"page":"67","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Real-Time Dolphin Whistle Detection on Raspberry Pi Zero 2 W with a TFLite Convolutional Neural Network"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9438-4791","authenticated-orcid":false,"given":"Rocco","family":"De Marco","sequence":"first","affiliation":[{"name":"Institute of Biological Resources and Marine Biotechnology (IRBIM), National Research Council (CNR), 60125 Ancona, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5362-3776","authenticated-orcid":false,"given":"Francesco","family":"Di Nardo","sequence":"additional","affiliation":[{"name":"Dipartimento di Ingegneria Dell\u2019Informazione, Universit\u00e0 Politecnica delle Marche, 60131 Ancona, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2907-8998","authenticated-orcid":false,"given":"Alessandro","family":"Rongoni","sequence":"additional","affiliation":[{"name":"Dipartimento di Ingegneria Dell\u2019Informazione, Universit\u00e0 Politecnica delle Marche, 60131 Ancona, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4765-8427","authenticated-orcid":false,"given":"Laura","family":"Screpanti","sequence":"additional","affiliation":[{"name":"Dipartimento di Ingegneria Dell\u2019Informazione, Universit\u00e0 Politecnica delle Marche, 60131 Ancona, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9346-2113","authenticated-orcid":false,"given":"David","family":"Scaradozzi","sequence":"additional","affiliation":[{"name":"Dipartimento di Ingegneria Dell\u2019Informazione, Universit\u00e0 Politecnica delle Marche, 60131 Ancona, Italy"},{"name":"ANcybernetics, Universit\u00e0 Politecnica delle Marche, 60131 Ancona, Italy"},{"name":"National Biodiversity Future Center, 90133 Palermo, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,5,19]]},"reference":[{"key":"ref_1","unstructured":"Notarbartolo di Sciara, G. (2002). Interactions between Cetacean and Fisheries in the Mediterranean Sea. Cetaceans of the Mediterranean and Black Seas: State of Knowledge and Conservation Strategies, ACCOBAMS Secretariat."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Li Veli, D., Petetta, A., Barone, G., Ceciarini, I., Franchi, E., Marsili, L., Pietroluongo, G., Mazzoldi, C., Holcer, D., and D\u2019Argenio, S. (2023). Fishers\u2019 Perception on the Interaction between Dolphins and Fishing Activities in Italian and Croatian Waters. Diversity, 15.","DOI":"10.3390\/d15020133"},{"key":"ref_3","unstructured":"Gonzalvo, J., and Carpentieri, P. (2023). Depredation by Marine Mammals in Fishing Gear\u2014A Review of the Mediterranean Sea, Black Sea and Contiguous Atlantic Area; Studies and Reviews (General Fisheries Commission for the Mediterranean), No. 102, FAO."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"E345","DOI":"10.1111\/j.1748-7692.2011.00544.x","article-title":"Odontocete Bycatch and Depredation in Longline Fisheries: A Review of Available Literature and of Potential Solutions","volume":"28","author":"Hamer","year":"2012","journal-title":"Mar. Mamm. Sci."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Gregorietti, M., Papale, E., Ceraulo, M., de Vita, C., Pace, D.S., Tranchida, G., Mazzola, S., and Buscaino, G. (2021). Acoustic Presence of Dolphins through Whistles Detection in Mediterranean Shallow Waters. J. Mar. Sci. Eng., 9.","DOI":"10.3390\/jmse9010078"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1017\/S0025315407054677","article-title":"Effects of Pingers on the Behaviour of Bottlenose Dolphins","volume":"87","author":"Leeney","year":"2007","journal-title":"J. Mar. Biol. Assoc."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"2241","DOI":"10.1002\/aqc.3588","article-title":"Artisanal Fishing, Dolphins, and Interactive Pinger: A Study from a Passive Acoustic Perspective","volume":"31","author":"Buscaino","year":"2021","journal-title":"Aquat. Conserv. Mar. Freshw. Ecosyst."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"201","DOI":"10.3354\/esr00464","article-title":"To Ping or Not to Ping: The Use of Active Acoustic Devices in Mitigating Interactions between Small Cetaceans and Gillnet Fisheries","volume":"19","author":"Dawson","year":"2013","journal-title":"Endang. Species Res."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"301","DOI":"10.3354\/esr00104","article-title":"Do Pingers Reduce Interactions between Bottlenose Dolphins and Nets around the Balearic Islands?","volume":"5","author":"Brotons","year":"2008","journal-title":"Endang. Species Res."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1016\/j.fishres.2007.12.016","article-title":"Pingers as Deterrents of Bottlenose Dolphins Interacting with Trammel Nets","volume":"92","author":"Gazo","year":"2008","journal-title":"Fish. Res."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"De Marco, R., Di Nardo, F., Lucchetti, A., Virgili, M., Petetta, A., Li Veli, D., Screpanti, L., Bartolucci, V., and Scaradozzi, D. (2023). The Development of a Low-Cost Hydrophone for Passive Acoustic Monitoring of Dolphin\u2019s Vocalizations. Remote Sens., 15.","DOI":"10.3390\/rs15071946"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"23406","DOI":"10.1109\/ACCESS.2024.3365349","article-title":"A Machine Learning-Oriented Survey on Tiny Machine Learning","volume":"12","author":"Capogrosso","year":"2024","journal-title":"IEEE Access"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1595","DOI":"10.1016\/j.jksuci.2021.11.019","article-title":"A Review on TinyML: State-of-the-Art and Prospects","volume":"34","author":"Ray","year":"2021","journal-title":"J. King Saud Univ. Comput. Inf. Sci."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"127141","DOI":"10.1109\/ACCESS.2024.3454815","article-title":"Convolutional Neural Networks for Enhancing Detection of Dolphin Whistles in a Dense Acoustic Environment","volume":"12","author":"Scaradozzi","year":"2024","journal-title":"IEEE Access"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Nur Korkmaz, B., Diamant, R., Danino, G., and Testolin, A. (2023). Automated detection of dolphin whistles with convolutional networks and transfer learning. Front. Artif. Intell., 6.","DOI":"10.3389\/frai.2023.1099022"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"108792","DOI":"10.1016\/j.ecolind.2022.108792","article-title":"Semantic segmentation-based whistle extraction of Indo-Pacific bottlenose dolphin residing at the coast of Jeju Island","volume":"137","author":"Jin","year":"2022","journal-title":"Ecol. Indicat."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"3861","DOI":"10.1121\/10.0007291","article-title":"Automated classification of tursiops aduncus whistles based on a depth-wise separable convolutional neural network and data augmentation","volume":"150","author":"Li","year":"2021","journal-title":"J. Acoust. Soc. Am."},{"key":"ref_18","unstructured":"Raspberry Pi Foundation (2025, March 01). Raspberry Pi Hardware Specifications. Available online: https:\/\/www.raspberrypi.com\/documentation\/computers\/raspberry-pi.html."},{"key":"ref_19","unstructured":"Espressif Systems (2025, March 01). Espressif Modules Specifications. Available online: https:\/\/www.espressif.com\/en\/products\/modules."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Padua, D. (2011). HDF5. Encyclopedia of Parallel Computing, Springer.","DOI":"10.1007\/978-0-387-09766-4"},{"key":"ref_21","unstructured":"Warden, P., and Situnayake, D. (2019). TinyML: Machine Learning with TensorFlow Lite on Arduino and Ultra-Low-Power Microcontrollers, O\u2019Reilly Media. [2nd ed.]."},{"key":"ref_22","unstructured":"Jones, P. (2025). Mastering Deep Learning with TensorFlow: From Fundamentals to Real-World Deployment, Walzone Press."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1111\/j.2517-6161.1974.tb00994.x","article-title":"Cross-Validatory Choice and Assessment of Statistical Predictions","volume":"36","author":"Stone","year":"1974","journal-title":"J. R. Stat. Soc. Ser. B (Methodol.)"},{"key":"ref_24","unstructured":"De Marco, R. (2025). TinyML Model Performance Testing Suite, Zenodo."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"96892","DOI":"10.1109\/ACCESS.2023.3294111","article-title":"A Comprehensive Survey on TinyML","volume":"11","author":"Abadade","year":"2023","journal-title":"IEEE Access"},{"key":"ref_26","unstructured":"Raspberry Pi Foundation (2025, March 01). Thermal Control Specifications. Available online: https:\/\/www.raspberrypi.com\/documentation\/computers\/raspberry-pi.html#frequency-management-and-thermal-control."}],"container-title":["Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2218-6581\/14\/5\/67\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:35:20Z","timestamp":1760031320000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2218-6581\/14\/5\/67"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":26,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2025,5]]}},"alternative-id":["robotics14050067"],"URL":"https:\/\/doi.org\/10.3390\/robotics14050067","relation":{},"ISSN":["2218-6581"],"issn-type":[{"value":"2218-6581","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,19]]}}}