{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T04:44:11Z","timestamp":1758343451961,"version":"3.44.0"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"15","license":[{"start":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T00:00:00Z","timestamp":1758240000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T00:00:00Z","timestamp":1758240000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"DOI":"10.1007\/s11227-025-07806-6","type":"journal-article","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T09:39:50Z","timestamp":1758274790000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Underwater acoustic target recognition based on multi-scale feature and CRDNet"],"prefix":"10.1007","volume":"81","author":[{"given":"Jing","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanru","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xudong","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinglong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lili","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Wei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pei","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongxin","family":"Tan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,9,19]]},"reference":[{"issue":"1","key":"7806_CR1","doi-asserted-by":"publisher","first-page":"25385","DOI":"10.1038\/s41598-024-76564-x","volume":"14","author":"S Liao","year":"2024","unstructured":"Liao S, Xiao W, Wang Y (2024) Dynamic hybrid parallel computing of the ray model for solving underwater acoustic fields in vast sea. Sci Rep 14(1):25385. https:\/\/doi.org\/10.1038\/s41598-024-76564-x","journal-title":"Sci Rep"},{"issue":"10","key":"7806_CR2","doi-asserted-by":"publisher","first-page":"1428","DOI":"10.3390\/jmse10101428","volume":"10","author":"P Li","year":"2022","unstructured":"Li P, Wu J, Wang Y et al (2022) STM: spectrogram transformer model for underwater acoustic target recognition. J Mar Sci Eng 10(10):1428","journal-title":"J Mar Sci Eng"},{"key":"7806_CR3","doi-asserted-by":"publisher","unstructured":"Wang P, Peng Y (2020) Research on feature extraction and recognition method of underwater acoustic target based on deep convolutional network. In: 2020 IEEE International Conference on Advances in Electrical Engineering and Computer Applications (AEECA), pp 863\u2013868. https:\/\/doi.org\/10.1109\/AEECA49918.2020.9213504","DOI":"10.1109\/AEECA49918.2020.9213504"},{"key":"7806_CR4","doi-asserted-by":"publisher","DOI":"10.3390\/rs16173333","volume":"16","author":"S Feng","year":"2024","unstructured":"Feng S, Ma S, Zhu X, Yan M (2024) Artificial intelligence-based underwater acoustic target recognition: a survey. Remote Sens 16:3333. https:\/\/doi.org\/10.3390\/rs16173333","journal-title":"Remote Sens"},{"issue":"2","key":"7806_CR5","doi-asserted-by":"publisher","first-page":"384","DOI":"10.3390\/jmse11020384","volume":"11","author":"X Luo","year":"2023","unstructured":"Luo X, Chen L, Zhou H et al (2023) A survey of underwater acoustic target recognition methods based on machine learning. J Mar Sci Eng 11(2):384","journal-title":"J Mar Sci Eng"},{"key":"7806_CR6","doi-asserted-by":"crossref","unstructured":"Woo S, Debnath S, Hu R et al (2023) ConvNeXt V2: Co-designing and scaling convnets with masked autoencoders. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 16133\u201316142","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"7806_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2020.108227","volume":"166","author":"J Jiang","year":"2020","unstructured":"Jiang J, Shi T, Huang M et al (2020) Multi-scale spectral feature extraction for underwater acoustic target recognition. Measurement 166:108227","journal-title":"Measurement"},{"key":"7806_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2023.115784","volume":"287","author":"A Zhou","year":"2023","unstructured":"Zhou A, Li X, Zhang W et al (2023) An attention-based multi-scale convolution network for intelligent underwater acoustic signal recognition. Ocean Eng 287:115784","journal-title":"Ocean Eng"},{"key":"7806_CR9","first-page":"1","volume":"83","author":"X Pan","year":"2024","unstructured":"Pan X, Sun J, Feng TH et al (2024) Underwater target recognition based on adaptive multi-feature fusion network. Multimedia Tools Appl 83:1\u201321","journal-title":"Multimedia Tools Appl"},{"key":"7806_CR10","doi-asserted-by":"publisher","first-page":"1058474","DOI":"10.3389\/fphy.2022.1058474","volume":"10","author":"D Zhao","year":"2022","unstructured":"Zhao D, Lei Y, Xu J et al (2022) A comparative study of four types of multi-scale entropies in feature extraction of underwater acoustic signals for potential GNSS positioning applications. Front Phys 10:1058474","journal-title":"Front Phys"},{"key":"7806_CR11","unstructured":"National Park Service (2022) Soundclips. Available at: https:\/\/www.nps.gov\/glba\/learn\/nature\/soundclips"},{"key":"7806_CR12","doi-asserted-by":"publisher","unstructured":"Song H, Wang H, Xiao S, Wang Y, Zhong Z, Yu L, Shan M, Liu B (2025) Underwater acoustic target recognition based on multi-scale residuals and dual attention mechanism. In: IEEE 7th International Conference on Communications, Information System and Computer Engineering (CISCE), pp 285\u2013289. https:\/\/doi.org\/10.1109\/CISCE65916.2025.11065495","DOI":"10.1109\/CISCE65916.2025.11065495"},{"issue":"5","key":"7806_CR13","doi-asserted-by":"publisher","DOI":"10.3390\/app12052626","volume":"12","author":"SJ Kim","year":"2022","unstructured":"Kim SJ, Chung YJ (2022) Multi-scale features for transformer model to improve the performance of sound event detection. Appl Sci 12(5):2626","journal-title":"Appl Sci"},{"issue":"8","key":"7806_CR14","doi-asserted-by":"publisher","first-page":"11449","DOI":"10.1007\/s11063-023-11383-1","volume":"55","author":"F Hu","year":"2023","unstructured":"Hu F, Song P, He R et al (2023) MSARN: a multi-scale attention residual network for end-to-end environmental sound classification. Neural Process Lett 55(8):11449\u201311465","journal-title":"Neural Process Lett"},{"issue":"6","key":"7806_CR15","doi-asserted-by":"publisher","first-page":"1353","DOI":"10.1177\/09544070221089757","volume":"237","author":"X Wang","year":"2023","unstructured":"Wang X, Song Y, Su L et al (2023) Recognition of abnormal car door noise based on multi-scale feature fusion. Proc Inst Mech Eng D J Automob Eng 237(6):1353\u20131364","journal-title":"Proc Inst Mech Eng D J Automob Eng"},{"issue":"8","key":"7806_CR16","doi-asserted-by":"publisher","first-page":"1144","DOI":"10.1166\/jno.2022.3305","volume":"17","author":"Q Chen","year":"2022","unstructured":"Chen Q, Wu Z, Zhong Q et al (2022) Heart sound classification based on mel-frequency cepstrum coefficient features and multi-scale residual recurrent neural networks. J Nanoelectron Optoelectron 17(8):1144\u20131153","journal-title":"J Nanoelectron Optoelectron"},{"key":"7806_CR17","doi-asserted-by":"publisher","first-page":"1180595","DOI":"10.3389\/fphy.2023.1180595","volume":"11","author":"N Zhou","year":"2023","unstructured":"Zhou N, Wang L (2023) Triple feature extraction method based on multi-scale dispersion entropy and multi-scale permutation entropy in sound-based fault diagnosis. Front Phys 11:1180595","journal-title":"Front Phys"},{"issue":"3","key":"7806_CR18","doi-asserted-by":"publisher","first-page":"1754","DOI":"10.1121\/10.0009671","volume":"151","author":"Y Hu","year":"2022","unstructured":"Hu Y, Sun X, He L et al (2022) A generalized network based on multi-scale densely connection and residual attention for sound source localization and detection. J Acoust Soc Am 151(3):1754\u20131768","journal-title":"J Acoust Soc Am"},{"key":"7806_CR19","doi-asserted-by":"publisher","first-page":"27369","DOI":"10.1038\/s41598-025-12452-2","volume":"15","author":"D Zeng","year":"2025","unstructured":"Zeng D, Yan S, Yang J, Pan X (2025) An efficient deep learning approach with frequency and channel optimization for underwater acoustic target recognition. Sci Rep 15:27369. https:\/\/doi.org\/10.1038\/s41598-025-12452-2","journal-title":"Sci Rep"},{"key":"7806_CR20","doi-asserted-by":"publisher","first-page":"1329","DOI":"10.3390\/jmse13071329","volume":"13","author":"J Li","year":"2025","unstructured":"Li J, Wang J, Xu T, Shu J, Liu Y, Ma Y, Xu Y (2025) Dynamic stochastic model optimization for underwater acoustic navigation via singular value decomposition. J Mar Sci Eng 13:1329. https:\/\/doi.org\/10.3390\/jmse13071329","journal-title":"J Mar Sci Eng"},{"issue":"8","key":"7806_CR21","doi-asserted-by":"publisher","first-page":"2573","DOI":"10.3390\/s25082573","volume":"25","author":"F Ji","year":"2025","unstructured":"Ji F, Lu S, Ni J, Li Z, Feng W (2025) Underwater target recognition method based on singular spectrum analysis and channel attention convolutional neural network. Sensors (Basel) 25(8):2573. https:\/\/doi.org\/10.3390\/s25082573","journal-title":"Sensors (Basel)"},{"key":"7806_CR22","doi-asserted-by":"publisher","first-page":"871","DOI":"10.1007\/s11802-024-5742-6","volume":"23","author":"S Gao","year":"2024","unstructured":"Gao S, Li W, Zhang Y et al (2024) Extraction of acoustic normal mode depth functions using range-difference method with vertical linear array data. J Ocean Univ China 23:871\u2013882. https:\/\/doi.org\/10.1007\/s11802-024-5742-6","journal-title":"J Ocean Univ China"},{"issue":"3","key":"7806_CR23","doi-asserted-by":"publisher","first-page":"1769","DOI":"10.1007\/s10916-010-9636-3","volume":"36","author":"D Chang","year":"2012","unstructured":"Chang D, Wang C, Jiang C (2012) Singular value decomposition based feature extraction technique for physiological signal analysis. J Med Syst 36(3):1769\u20131777. https:\/\/doi.org\/10.1007\/s10916-010-9636-3","journal-title":"J Med Syst"},{"key":"7806_CR24","doi-asserted-by":"crossref","unstructured":"Kristomo D (2019) Dimensionality reduction of speech signals using singular value decomposition and Karhunen-Loeve. In: Proceedings of International Conference on Information System and Technology (ICIST), SCITEPRESS","DOI":"10.5220\/0009432200780084"},{"key":"7806_CR25","doi-asserted-by":"crossref","unstructured":"Grondin F, Glass J (2018) SVD-PHAT: a fast sound source localization method. arXiv preprint arXiv:1811.11785v2","DOI":"10.1109\/ICASSP.2019.8683253"},{"issue":"18","key":"7806_CR26","doi-asserted-by":"publisher","DOI":"10.3390\/rs15184506","volume":"15","author":"Y Wang","year":"2023","unstructured":"Wang Y, Tian Y, Liu J et al (2023) Multi-stage multi-scale local feature fusion for infrared small target detection. Remote Sens 15(18):4506","journal-title":"Remote Sens"},{"key":"7806_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2023.109752","volume":"216","author":"L Yu","year":"2024","unstructured":"Yu L, Xu F, Qu Y et al (2024) Speech emotion recognition based on multi-dimensional feature extraction and multi-scale feature fusion. Appl Acoust 216:109752","journal-title":"Appl Acoust"},{"issue":"10","key":"7806_CR28","doi-asserted-by":"publisher","first-page":"3153","DOI":"10.3390\/s24103153","volume":"24","author":"H Guo","year":"2024","unstructured":"Guo H, Liu W (2024) Dmaf-net: deep multi-scale attention fusion network for hyperspectral image classification with limited samples. Sensors 24(10):3153","journal-title":"Sensors"},{"issue":"4","key":"7806_CR29","doi-asserted-by":"publisher","first-page":"4797","DOI":"10.1007\/s11042-021-11138-x","volume":"81","author":"S Pang","year":"2022","unstructured":"Pang S, Chen Z, Yin F (2022) Lightweight multi-scale aggregated residual attention networks for image super-resolution. Multimedia Tools Appl 81(4):4797\u20134819","journal-title":"Multimedia Tools Appl"},{"key":"7806_CR30","doi-asserted-by":"publisher","first-page":"1216181","DOI":"10.3389\/fnins.2023.1216181","volume":"17","author":"H Pan","year":"2023","unstructured":"Pan H, Yang H, Xie L et al (2023) Multi-scale fusion visual attention network for facial micro-expression recognition. Front Neurosci 17:1216181","journal-title":"Front Neurosci"},{"key":"7806_CR31","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1016\/j.patrec.2022.12.026","volume":"166","author":"Y Deng","year":"2023","unstructured":"Deng Y, Hu X, Li B et al (2023) Multi-scale self-attention-based feature enhancement for detection of targets with small image sizes. Pattern Recognit Lett 166:46\u201352","journal-title":"Pattern Recognit Lett"},{"key":"7806_CR32","unstructured":"Xie Y, Chen T, Xu J (2023) Advancing underwater acoustic target recognition via adaptive data pruning and smoothness-inducing regularization. arXiv preprint arXiv:2304.11907"},{"issue":"1","key":"7806_CR33","doi-asserted-by":"publisher","first-page":"69","DOI":"10.3390\/jmse11010069","volume":"11","author":"A Jin","year":"2023","unstructured":"Jin A, Zeng X (2023) A novel deep learning method for underwater target recognition based on Res-Dense convolutional neural network with attention mechanism. J Mar Sci Eng 11(1):69","journal-title":"J Mar Sci Eng"},{"key":"7806_CR34","doi-asserted-by":"crossref","unstructured":"Tan J, Pan X (2023) Underwater acoustic target recognition based on convolutional neural network and multi-feature fusion. In: Proceedings of 3rd International Conference on Computer Vision and Pattern Analysis (ICCPA 2023), SPIE, vol 12754, pp 778\u2013784","DOI":"10.1117\/12.2684510"},{"key":"7806_CR35","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1016\/j.apacoust.2016.06.008","volume":"113","author":"D Santos-Dom\u00ednguez","year":"2016","unstructured":"Santos-Dom\u00ednguez D, Torres-Guijarro S, Cardenal-L\u00f3pez A et al (2016) ShipsEar: an underwater vessel noise database. Appl Acoust 113:64\u201369","journal-title":"Appl Acoust"},{"key":"7806_CR36","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.107983","volume":"133","author":"S Yang","year":"2024","unstructured":"Yang S, Jin A, Zeng X et al (2024) Underwater acoustic target recognition based on sub-band concatenated Mel spectrogram and multidomain attention mechanism. Eng Appl Artif Intell 133:107983","journal-title":"Eng Appl Artif Intell"},{"issue":"11","key":"7806_CR37","doi-asserted-by":"publisher","DOI":"10.3390\/e24111657","volume":"24","author":"J Li","year":"2022","unstructured":"Li J, Wang B, Cui X et al (2022) Underwater acoustic target recognition based on attention residual network. Entropy 24(11):1657","journal-title":"Entropy"},{"key":"7806_CR38","doi-asserted-by":"publisher","unstructured":"Ong JB, Ng WK, Kuo CC (2018) Convolutional neural networks with transformed input based on robust tensor network decomposition. arXiv preprint arXiv:1812.02622. https:\/\/doi.org\/10.48550\/arXiv.1812.02622","DOI":"10.48550\/arXiv.1812.02622"},{"key":"7806_CR39","doi-asserted-by":"crossref","unstructured":"Park DS, Chan W, Zhang Y et al (2019) SpecAugment: A simple data augmentation method for automatic speech recognition. arXiv preprint arXiv:1904.08779","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"7806_CR40","unstructured":"Nam H, Lee J, Kim S et al (2021) FilterAugment: an acoustic environmental data augmentation method. arXiv preprint arXiv:2110.03282"},{"key":"7806_CR41","doi-asserted-by":"crossref","unstructured":"Liu C, Doll\u00e1r P, He K et al (2020) Are labels necessary for neural architecture search? In: Proceedings of European Conference on Computer Vision (ECCV)","DOI":"10.1007\/978-3-030-58548-8_46"},{"key":"7806_CR42","doi-asserted-by":"crossref","unstructured":"Woo S, Park J, Lee JY, Kweon IS (2018) CBAM: Convolutional block attention module. In: Proc Eur Conf on Computer Vision (ECCV)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"7806_CR43","doi-asserted-by":"crossref","unstructured":"Wang H, Zheng S, Chen Y et al (2023) CAM++: a fast and efficient network for speaker verification using context-aware masking. arXiv preprint arXiv:2303.00332","DOI":"10.21437\/Interspeech.2023-1513"},{"key":"7806_CR44","doi-asserted-by":"crossref","unstructured":"Okabe K, Koshinaka T, Shinoda K (2018) Attentive statistics pooling for deep speaker embedding. In: Proceedings of Interspeech, pp 2252\u20132256","DOI":"10.21437\/Interspeech.2018-993"},{"key":"7806_CR45","doi-asserted-by":"publisher","first-page":"3214","DOI":"10.21437\/Interspeech.2015-647","volume":"2015","author":"V Peddinti","year":"2015","unstructured":"Peddinti V, Povey D, Khudanpur S (2015) A time delay neural network architecture for efficient modeling of long temporal contexts. Proc Interspeech 2015:3214\u20133218. https:\/\/doi.org\/10.21437\/Interspeech.2015-647","journal-title":"Proc Interspeech"},{"key":"7806_CR46","doi-asserted-by":"publisher","unstructured":"Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: Proc IEEE Conf on Computer Vision and Pattern Recognition (CVPR), pp 2261\u20132269. https:\/\/doi.org\/10.1109\/CVPR.2017.243","DOI":"10.1109\/CVPR.2017.243"},{"key":"7806_CR47","unstructured":"Kingma DP, Ba J (2015) Adam: a method for stochastic optimization. In: Proceedings of the International Conference on Learning Representations (ICLR)4"},{"key":"7806_CR48","first-page":"6","volume-title":"Deep Learning","author":"I Goodfellow","year":"2016","unstructured":"Goodfellow I, Bengio Y, Courville A (2016) Deep Learning. MIT Press, Chapter, p 6"},{"key":"7806_CR49","unstructured":"Loshchilov I, Hutter F (2017) SGDR: Stochastic gradient descent with warm restarts. In: Proceedings of the International Conference on Learning Representations (ICLR)"},{"issue":"Nov","key":"7806_CR50","first-page":"2579","volume":"9","author":"L van der Maaten","year":"2008","unstructured":"van der Maaten L, Hinton G (2008) Visualizing data using t-SNE. J Mach Learn Res 9(Nov):2579\u20132605","journal-title":"J Mach Learn Res"},{"key":"7806_CR51","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.115270","volume":"183","author":"M Irfan","year":"2021","unstructured":"Irfan M, Islam MR, Kim JM, Kim TS (2021) DeepShip: an underwater acoustic benchmark dataset and a separable convolution based autoencoder for classification. Expert Syst Appl 183:115270. https:\/\/doi.org\/10.1016\/j.eswa.2021.115270","journal-title":"Expert Syst Appl"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-025-07806-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-025-07806-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-025-07806-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T22:03:06Z","timestamp":1758319386000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-025-07806-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,19]]},"references-count":51,"journal-issue":{"issue":"15","published-online":{"date-parts":[[2025,10]]}},"alternative-id":["7806"],"URL":"https:\/\/doi.org\/10.1007\/s11227-025-07806-6","relation":{},"ISSN":["1573-0484"],"issn-type":[{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,19]]},"assertion":[{"value":"19 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 August 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 September 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The author(s) declared no potential conflicts of interest with respect to the research, authorship, and\/or publication of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"1358"}}