{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T08:52:24Z","timestamp":1773391944616,"version":"3.50.1"},"reference-count":21,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T00:00:00Z","timestamp":1773360000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>\n                    In response to the demand for precise feeding in high-density aquaculture, this study established a dynamic prediction model for fish feeding intensity by integrating vibration signal quantification and deep learning. Through multidimensional experiments (fish size: 50\u2013300\u202fg; stocking density: 20\u201360 fish\/group; feeding speed: 1-3\u202fg\/s; feed particle size: 2#4#6#), we quantified the three-axis displacement signals of\n                    <jats:italic>Micropterus salmoides<\/jats:italic>\n                    during feeding. Results demonstrated significant effects of all parameters on water surface fluctuations (\n                    <jats:italic>p<\/jats:italic>\n                    \u202f&amp;lt;\u202f0.05). Vibration displacement exhibited linear relationships with fish size and density. The 300\u202fg group showed 109.7% higher peak amplitude than the 50\u202fg group, while the 60-fish density group exceeded the 20-fish group by 141.9%. Optimal palatability (4#) reduced fluctuation frequency by 42%. A predictive model for feeding vibration patterns was developed, incorporating fish size (S), density (D), feeding speed (V), feed particle size (\n                    <jats:italic>\u03a6<\/jats:italic>\n                    ), real-time triaxial vibration sum, and time series (t) as inputs to predict the summed vibration displacement at t\u202f+\u202f5\u202fs, which serves as a quantitative proxy for feeding intensity. The Long Short-Term Memory (LSTM) model accurately captured fish feeding dynamics (RMSE\u202f=\u202f69.43\u202f\u03bcm, MAE\u202f=\u202f48.00\u202f\u03bcm, R\n                    <jats:sup>2<\/jats:sup>\n                    \u202f=\u202f0.883). In comparative analysis, the LSTM outperformed Gated Recurrent Unit (GRU) and Transformer models in forecasting accuracy. Deployed on an embedded system (Orange Pi AiPRO), closed-loop tests demonstrated superior performance: residual feed rates were \u2264 0.8% across all trials, outperforming optical flow (2.69% residuals) and graph neural network (6.58% residuals) methods. The space complexity of the vibration-LSTM approach was only 6.4\u201331.8% of GCN-based approaches, enabling cost-effective (&amp;lt;$200) real-time control.\n                  <\/jats:p>","DOI":"10.3389\/frai.2026.1656290","type":"journal-article","created":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T06:46:38Z","timestamp":1773384398000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Quantification of feeding intensity and feeding control of largemouth bass based on water surface vibration characteristics"],"prefix":"10.3389","volume":"9","author":[{"given":"Yufei","family":"Zhang","sequence":"first","affiliation":[{"name":"Fishery Machinery and Instruction Research Institute","place":["Shanghai, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andong","family":"Liu","sequence":"additional","affiliation":[{"name":"Fishery Machinery and Instruction Research Institute","place":["Shanghai, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yulei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Fishery Machinery and Instruction Research Institute","place":["Shanghai, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Ni","sequence":"additional","affiliation":[{"name":"Fishery Machinery and Instruction Research Institute","place":["Shanghai, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haigen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Fishery Machinery and Instruction Research Institute","place":["Shanghai, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongqiao","family":"Song","sequence":"additional","affiliation":[{"name":"Fishery Machinery and Instruction Research Institute","place":["Shanghai, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Wang","sequence":"additional","affiliation":[{"name":"Fishery Machinery and Instruction Research Institute","place":["Shanghai, China"]},{"name":"School of Navigation and Naval Architecture, Dalian Ocean University","place":["Dalian, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyan","family":"Cheng","sequence":"additional","affiliation":[{"name":"Laiyang Fishery Technology Extension Station","place":["Yantai, Shandong, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,3,13]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"102360","DOI":"10.1016\/j.aquaeng.2023.102360","article-title":"Industry 4.0-based smart systems in aquaculture: a comprehensive review","volume":"103","author":"Biazi","year":"2023","journal-title":"Aquac. Eng."},{"key":"ref2","first-page":"1724","article-title":"Learning phrase representations using RNN encoder-decoder for statistical machine translation","author":"Cho","year":"2014"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"102345","DOI":"10.1016\/j.aquaeng.2023.102345","article-title":"Feeding intensity assessment of aquaculture fish using mel spectrogram and deep learning algorithms","volume":"102","author":"Du","year":"","journal-title":"Aquac. Eng."},{"key":"ref4","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1016\/j.biosystemseng.2024.08.001","article-title":"Harnessing multimodal data fusion to advance accurate identification of fish feeding intensity","volume":"246","author":"Du","year":"2024","journal-title":"Biosyst. Eng."},{"key":"ref5","doi-asserted-by":"publisher","first-page":"108310","DOI":"10.1016\/j.compag.2023.108310","article-title":"Feature fusion strategy and improved ghostnet for accurate recognition of fish feeding behavior","volume":"214","author":"Du","year":"","journal-title":"Comput. Electron. Agric."},{"key":"ref6","doi-asserted-by":"publisher","first-page":"108676","DOI":"10.1016\/j.compag.2024.108676","article-title":"Digital twins in intensive aquaculture \u2014 challenges, opportunities and future prospects","volume":"218","author":"F\u00f8re","year":"2024","journal-title":"Comput. Electron. Agric."},{"key":"ref7","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref8","doi-asserted-by":"publisher","first-page":"742008","DOI":"10.1016\/j.aquaculture.2024.742008","article-title":"DCA-MVIT: fused DSGated convolution and CA attention for fish feeding behavior recognition in recirculating aquaculture systems","volume":"598","author":"Hu","year":"2025","journal-title":"Aquaculture"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"18799","DOI":"10.1038\/s41598-021-98383-0","article-title":"Evaluation of fish feeder manufactured from local raw materials","volume":"11","author":"Khater","year":"2021","journal-title":"Sci. Rep."},{"key":"ref10","doi-asserted-by":"publisher","first-page":"56","DOI":"10.3969\/j.issn.1007-9580.2023.03.007","article-title":"Study on feeding rule and baiting method of fish based on six axis sensor","volume":"50","author":"Pan","year":"2023","journal-title":"Fish. Moderniz."},{"key":"ref11","volume-title":"Feature extraction and classification of swallowing and chewing sounds of single largemouth bass (","author":"Qi","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"102178","DOI":"10.1016\/j.aquaeng.2021.102178","article-title":"Evaluating fish feeding intensity in aquaculture with convolutional neural networks","volume":"94","author":"Ubina","year":"2021","journal-title":"Aquac. Eng."},{"key":"ref13","first-page":"5998","volume-title":"Attention is all you need. Advances in neural information processing systems, 30 (Neur IPS 2017)","author":"Vaswani","year":"2017"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"1021688","DOI":"10.3389\/fmars.2022.1021688","article-title":"Modified kinetic energy feature-based graph convolutional network for fish appetite grading using time-limited data in aquaculture","volume":"9","author":"Wei","year":"2022","journal-title":"Front. Mar. Sci."},{"key":"ref15","doi-asserted-by":"publisher","first-page":"107201","DOI":"10.1016\/j.compag.2022.107201","article-title":"Application of intelligent and unmanned equipment in aquaculture: a review","volume":"199","author":"Wu","year":"2022","journal-title":"Comput. Electron. Agric."},{"key":"ref16","volume-title":"Swimming fish adaptive feeding device and method based on water surface fluctuation information","author":"Xiang","year":"2022"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"236","DOI":"10.6041\/j.issn.1000-1298.2022.10.025","article-title":"Recognition of fish feeding intensity based on improved LRCN","volume":"53","author":"Xu","year":"2022","journal-title":"Trans. Chin. Soc. Agric. Mach."},{"key":"ref18","doi-asserted-by":"publisher","first-page":"107580","DOI":"10.1016\/j.compag.2022.107580","article-title":"Fish school feeding behavior quantification using acoustic signal and improved swin transformer","volume":"204","author":"Zeng","year":"2023","journal-title":"Comput. Electron. Agric."},{"key":"ref19","doi-asserted-by":"publisher","first-page":"294","DOI":"10.11841\/j.issn.1007-4333.2025.02.25","article-title":"Research on the international competitiveness of fishery industry in China and its influential factors","volume":"30","author":"Zheng","year":"2025","journal-title":"J. China Agric. Univ."},{"key":"ref20","doi-asserted-by":"publisher","first-page":"975","DOI":"10.1111\/raq.12218","article-title":"Intelligent feeding control methods in aquaculture with an emphasis on fish: a review","volume":"10","author":"Zhou","year":"2018","journal-title":"Rev. Aquac."},{"key":"ref21","doi-asserted-by":"publisher","first-page":"38","DOI":"10.11975\/j.issn.1002-6819.2022.07.005","article-title":"Research progress on intelligent feeding methods in fish farming","volume":"38","author":"Zhu","year":"2022","journal-title":"Trans. Chin. Soc. Agric. Engineer."}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1656290\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T06:46:46Z","timestamp":1773384406000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1656290\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,13]]},"references-count":21,"alternative-id":["10.3389\/frai.2026.1656290"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1656290","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,13]]},"article-number":"1656290"}}