{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T23:11:09Z","timestamp":1771542669972,"version":"3.50.1"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T00:00:00Z","timestamp":1732579200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T00:00:00Z","timestamp":1732579200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100000332","name":"Royal Society of Edinburgh","doi-asserted-by":"publisher","award":["2970"],"award-info":[{"award-number":["2970"]}],"id":[{"id":"10.13039\/501100000332","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Cogn Comput"],"published-print":{"date-parts":[[2025,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Subsea pipelines are the backbone of the modern oil and gas industry, transporting a total of 28% of global oil production. Due to several factors, such as corrosion or deformations, the pipelines might degrade over time, which might lead to serious economic and environmental damages if not addressed promptly. Therefore, it is crucial to detect any serious damage to subsea pipelines before they cause dangerous catastrophes. Inspections of subsea pipelines are usually made using a Remote Operating Vehicle and the inspection data is usually processed manually, which is subject to human errors, and requires experienced Remote Operating Vehicle operators. It is thus necessary to automate the inspection process to enable more efficiency as well as reduce costs. Besides, it is recognised that specific challenges of noisy and low-quality inspection data arising from the underwater environment prevent the industry from taking full advantage of the recent development in the Artificial Intelligence field to the problem of subsea pipeline inspection. In this paper, we developed an ensemble of deep learning classifiers to further improve the performance of single deep learning models in classifying anomalous events on the subsea pipeline inspection data. The output of the proposed ensemble was combined based on a weighted combining method. The weights of base classifiers were found by minimising the difference between the weighted combining result and the given associated ground truth annotation information. Three inspection datasets, gathered from different oil and gas companies in the United Kingdom, were analysed. These datasets were recorded under varying conditions and include a range of anomalies. The results showed that the proposed ensemble achieves around 78% accuracy on two datasets and more than 99% accuracy on one dataset, which is better compared to base classifiers and two popular ensembles.<\/jats:p>","DOI":"10.1007\/s12559-024-10377-y","type":"journal-article","created":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T09:14:13Z","timestamp":1732612453000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Event Classification on Subsea Pipeline Inspection Data Using an Ensemble of Deep Learning Classifiers"],"prefix":"10.1007","volume":"17","author":[{"given":"Truong","family":"Dang","sequence":"first","affiliation":[]},{"given":"Tien Thanh","family":"Nguyen","sequence":"additional","affiliation":[]},{"given":"Alan Wee-Chung","family":"Liew","sequence":"additional","affiliation":[]},{"given":"Eyad","family":"Elyan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,26]]},"reference":[{"key":"10377_CR1","unstructured":"\u2018Global crude oil onshore and offshore production distribution 2025\u2019, Statista. [Online]. Available: https:\/\/www.statista.com\/statistics\/624138\/distribution-of-crude-oil-production-worldwide-onshore-and-offshore\/"},{"key":"10377_CR2","doi-asserted-by":"publisher","first-page":"409","DOI":"10.1016\/j.psep.2022.03.049","volume":"161","author":"D Eastvedt","year":"2022","unstructured":"Eastvedt D, Naterer G, Duan X. Detection of faults in subsea pipelines by flow monitoring with regression supervised machine learning. Process Saf Environ Prot. 2022;161:409\u201320.","journal-title":"Process Saf Environ Prot"},{"issue":"7","key":"10377_CR3","doi-asserted-by":"publisher","first-page":"5737","DOI":"10.1109\/TIE.2019.2931491","volume":"67","author":"B Cai","year":"2020","unstructured":"Cai B, et al. Remaining useful life estimation of structure systems under the influence of multiple causes: subsea pipelines as a case study. IEEE Trans Industr Electron. 2020;67(7):5737\u201347.","journal-title":"IEEE Trans Industr Electron"},{"key":"10377_CR4","doi-asserted-by":"publisher","first-page":"540","DOI":"10.1016\/j.oceaneng.2015.04.025","volume":"104","author":"P Davis","year":"2015","unstructured":"Davis P, Brockhurst J. Subsea pipeline infrastructure monitoring: A framework for technology review and selection. Ocean Eng. 2015;104:540\u20138.","journal-title":"Ocean Eng"},{"issue":"2","key":"10377_CR5","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1016\/S0952-1976(97)00001-8","volume":"11","author":"P Zingaretti","year":"1998","unstructured":"Zingaretti P, Zanoli SM. Robust real-time detection of an underwater pipeline. Eng Appl Artif Intell. 1998;11(2):257\u201368.","journal-title":"Eng Appl Artif Intell"},{"key":"10377_CR6","doi-asserted-by":"publisher","first-page":"104987","DOI":"10.1016\/j.autcon.2023.104987","volume":"154","author":"P Xia","year":"2023","unstructured":"Xia P, You H, Du J. Visual-haptic feedback for ROV subsea navigation control. Autom Constr. 2023;154:104987.","journal-title":"Autom Constr"},{"key":"10377_CR7","doi-asserted-by":"publisher","first-page":"101687","DOI":"10.1016\/j.aei.2022.101687","volume":"53","author":"Y Liu","year":"2022","unstructured":"Liu Y, Bao Y. Review on automated condition assessment of pipelines with machine learning. Adv Eng Inform. 2022;53:101687.","journal-title":"Adv Eng Inform"},{"key":"10377_CR8","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1016\/j.autcon.2014.05.003","volume":"45","author":"MS El-Abbasy","year":"2014","unstructured":"El-Abbasy MS, Senouci A, Zayed T, Mirahadi F, Parvizsedghy L. Artificial neural network models for predicting condition of offshore oil and gas pipelines. Autom Constr. 2014;45:50\u201365.","journal-title":"Autom Constr"},{"key":"10377_CR9","unstructured":"Chen H, Ye H, LV C, Su H. \u2018Application of support vector machine learning to leak detection and location in pipelines.\u2019 In Proceedings of the 21st IEEE Instrumentation and Measurement Technology Conference, 2004. pp. 2273\u20132277."},{"issue":"3","key":"10377_CR10","doi-asserted-by":"publisher","first-page":"674","DOI":"10.3390\/s20030674","volume":"20","author":"A Stamoulakatos","year":"2020","unstructured":"Stamoulakatos A, et al. Automatic annotation of subsea pipelines using deep learning. Sensors. 2020;20(3):674.","journal-title":"Sensors."},{"key":"10377_CR11","doi-asserted-by":"publisher","first-page":"112062","DOI":"10.1016\/j.oceaneng.2022.112062","volume":"261","author":"X Li","year":"2022","unstructured":"Li X, Guo M, Zhang R, Chen G. A data-driven prediction model for maximum pitting corrosion depth of subsea oil pipelines using SSA-LSTM approach. Ocean Eng. 2022;261:112062.","journal-title":"Ocean Eng"},{"key":"10377_CR12","first-page":"1","volume":"72","author":"M Zhang","year":"2023","unstructured":"Zhang M, Guo Y, Xie Q, Zhang Y, Wang D, Chen J. Estimation of defect size and cross-sectional profile for the oil and gas pipeline using visual deep transfer learning neural network. IEEE Trans Instrum Meas. 2023;72:1\u201313.","journal-title":"IEEE Trans Instrum Meas"},{"key":"10377_CR13","doi-asserted-by":"publisher","first-page":"110546","DOI":"10.1016\/j.ymssp.2023.110546","volume":"200","author":"J Chen","year":"2023","unstructured":"Chen J, Cao L, Song G. Detection of the pipeline elbow erosion by percussion and deep learning. Mech Syst Signal Process. 2023;200:110546.","journal-title":"Mech Syst Signal Process"},{"key":"10377_CR14","doi-asserted-by":"publisher","first-page":"113238","DOI":"10.1016\/j.measurement.2023.113238","volume":"219","author":"Z Zhang","year":"2023","unstructured":"Zhang Z, Xu C, Xie J, Zhang Y, Liu P, Liu Z. MFCC-LSTM framework for leak detection and leak size identification in gas-liquid two-phase flow pipelines based on acoustic emission. Measurement. 2023;219:113238.","journal-title":"Measurement"},{"issue":"7","key":"10377_CR15","doi-asserted-by":"publisher","first-page":"1883","DOI":"10.1109\/TIM.2017.2673024","volume":"66","author":"J Feng","year":"2017","unstructured":"Feng J, Li F, Lu S, Liu J, Ma D. Injurious or noninjurious defect identification from mfl images in pipeline inspection using convolutional neural network. IEEE Trans Instrum Meas. 2017;66(7):1883\u201392.","journal-title":"IEEE Trans Instrum Meas"},{"key":"10377_CR16","first-page":"1","volume":"72","author":"C Wang","year":"2023","unstructured":"Wang C, Wang Z, Liu W, Shen Y, Dong H. A novel deep offline-to-online transfer learning framework for pipeline leakage detection with small samples. IEEE Trans Instrum Meas. 2023;72:1\u201313.","journal-title":"IEEE Trans Instrum Meas"},{"key":"10377_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s12559-024-10257-5","volume":"16","author":"T Dang","year":"2024","unstructured":"Dang T, Nguyen T, Mccall J, Elyan E, Moreno-Garc\u00eda C. Two-layer ensemble of deep learning models for medical image segmentation. Cogn Comput. 2024;16:1\u201320.","journal-title":"Cogn Comput"},{"key":"10377_CR18","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1016\/j.neunet.2020.03.007","volume":"126","author":"M Baldeon Calisto","year":"2020","unstructured":"Baldeon Calisto M, Lai-Yuen SK. AdaEn-Net: An ensemble of adaptive 2D\u20133D fully convolutional networks for medical image segmentation. Neural Netw. 2020;126:76\u201394.","journal-title":"Neural Netw."},{"key":"10377_CR19","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J. \u2018Deep Residual Learning for Image Recognition.\u2019in IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2016;770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"10377_CR20","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1016\/j.inffus.2017.03.008","volume":"39","author":"RF Alvear-Sandoval","year":"2018","unstructured":"Alvear-Sandoval RF, Figueiras-Vidal AR. On building ensembles of stacked denoising auto-encoding classifiers and their further improvement. Information Fusion. 2018;39:41\u201352.","journal-title":"Information Fusion"},{"key":"10377_CR21","unstructured":"Lakshminarayanan B, Pritzel A, Blundell C. \u2018Simple and scalable predictive uncertainty estimation using deep ensembles.\u2019 In Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS). 2017;6405\u20136416."},{"key":"10377_CR22","doi-asserted-by":"publisher","first-page":"123527","DOI":"10.1016\/j.eswa.2024.123527","volume":"249","author":"DK Jain","year":"2024","unstructured":"Jain DK, Zhao X, Garcia S, Neelakandan S. Robust multi-modal pedestrian detection using deep convolutional neural network with ensemble learning model. Expert Syst Appl. 2024;249:123527.","journal-title":"Expert Syst Appl"},{"key":"10377_CR23","doi-asserted-by":"publisher","first-page":"126435","DOI":"10.1016\/j.neucom.2023.126435","volume":"549","author":"C Pel\u00e1ez-Rodr\u00edguez","year":"2023","unstructured":"Pel\u00e1ez-Rodr\u00edguez C, et al. Deep learning ensembles for accurate fog-related low-visibility events forecasting. Neurocomputing. 2023;549:126435.","journal-title":"Neurocomputing"},{"key":"10377_CR24","unstructured":"Huang G, Li Y, Pleiss G, Liu Z, Hopcroft JE, Weinberger KQ. \u2018Snapshot Ensembles: Train 1, get M for free.\u2019 arXiv:1704.00109 [cs]. 2017."},{"key":"10377_CR25","doi-asserted-by":"crossref","unstructured":"Bai Q, Bai Y. \u201814 - Pipeline Spans and VIV Fatigue.\u2019 in Subsea Pipeline Design, Analysis, and Installation. 2014;337\u2013363.","DOI":"10.1016\/B978-0-12-386888-6.00014-6"},{"key":"10377_CR26","unstructured":"Simonyan K, Zisserman A. \u2018Very Deep Convolutional Networks for Large-Scale Image Recognition.\u2019 arXiv 1409.1556 [cs]. 2014."},{"key":"10377_CR27","unstructured":"Vaswani A, et al. \u2018Attention is All you Need.\u2019 In Advances in Neural Information Processing Systems. 2017;6000\u20136010."},{"key":"10377_CR28","doi-asserted-by":"crossref","unstructured":"Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z. \u2018rethinking the inception architecture for computer vision.\u2019 In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2016;2818\u20132826.","DOI":"10.1109\/CVPR.2016.308"},{"issue":"1","key":"10377_CR29","first-page":"4278","volume":"31","author":"C Szegedy","year":"2017","unstructured":"Szegedy C, Ioffe S, Vanhoucke V, Alemi AA. Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning. Proc Thirty-First AAAI Conf Artif Intell. 2017;31(1):4278\u201384.","journal-title":"Proc Thirty-First AAAI Conf Artif Intell"},{"key":"10377_CR30","doi-asserted-by":"crossref","unstructured":"Huang G, Liu Z, Maaten LVD, Weinberger KQ. \u2018densely connected convolutional networks.\u2019 In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2017 Jul;2261\u20132269.","DOI":"10.1109\/CVPR.2017.243"},{"key":"10377_CR31","doi-asserted-by":"crossref","unstructured":"Chollet F. \u2018Xception: Deep learning with depthwise separable convolutions.\u2019 in IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2017;1800\u20131807.","DOI":"10.1109\/CVPR.2017.195"},{"key":"10377_CR32","unstructured":"Dosovitskiy A, et al. \u2018An Image is Worth 16x16 Words: Transformers for image recognition at scale.\u2019 In International Conference on Learning Representations (ICLR). 2021."},{"key":"10377_CR33","doi-asserted-by":"crossref","unstructured":"Tu Z, et al. \u2018MaxViT: Multi-axis Vision Transformer.\u2019 In European Conference on Computer Vision (ECCV); 2022. 459\u2013479.","DOI":"10.1007\/978-3-031-20053-3_27"},{"key":"10377_CR34","doi-asserted-by":"crossref","unstructured":"Liu Z, et al. \u2018Swin transformer: hierarchical vision transformer using shifted windows.\u2019 In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV); 2021.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"10377_CR35","unstructured":"Zhuang F, et al. \u2018A comprehensive survey on transfer learning.\u2019 arXiv: 1911.02685 [cs]; 2019."},{"key":"10377_CR36","unstructured":"Krizhevsky A, Sutskever I, Hinton GE. \u2018ImageNet classification with deep convolutional neural networks.\u2019 In Advances in Neural Information Processing Systems; 2012."},{"key":"10377_CR37","unstructured":"Kingma D, Ba J. \u2018Adam: a method for stochastic optimization.\u2019 International Conference on Learning Representations (ICLR); 2014."},{"key":"10377_CR38","doi-asserted-by":"crossref","unstructured":"Dang T, Nguyen TT, McCall J, Liew AW-C. \u2018Ensemble learning based on classifier prediction confidence and comprehensive learning particle swarm optimisation for medical image segmentation.\u2019 in 2022 IEEE Symposium Series on Computational Intelligence (SSCI); 2022. pp. 269\u2013276.","DOI":"10.1109\/SSCI51031.2022.10022114"},{"key":"10377_CR39","doi-asserted-by":"crossref","unstructured":"Nguyen TT, Pham NV, Dang T, Luong AV, McCall J, Liew AW-C. \u2018Multi-layer heterogeneous ensemble with classifier and feature selection.\u2019 In Proceedings of the 2020 Genetic and Evolutionary Computation Conference (GECCO); 2020. pp. 725\u2013733.","DOI":"10.1145\/3377930.3389832"},{"key":"10377_CR40","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1016\/j.ins.2019.03.067","volume":"490","author":"TT Nguyen","year":"2019","unstructured":"Nguyen TT, Dang MT, Liew AW, Bezdek JC. A weighted multiple classifier framework based on random projection. Inf Sci. 2019;490:36\u201358.","journal-title":"Inf Sci"},{"issue":"1","key":"10377_CR41","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1137\/S1064827595289108","volume":"21","author":"MA Branch","year":"1999","unstructured":"Branch MA, Coleman TF, Li Y. A Subspace, interior, and conjugate gradient method for large-scale bound-constrained minimization problems. SIAM J Sci Comput. 1999;21(1):1\u201323.","journal-title":"SIAM J Sci Comput"},{"key":"10377_CR42","unstructured":"Chen T, Kornblith S, Norouzi M, Hinton G. \u2018A simple framework for contrastive learning of visual representations.\u2019 In Proceedings of the 37th International Conference on Machine Learning, in ICML\u201920. JMLR.org, 2020."},{"key":"10377_CR43","unstructured":"Tan M, Le Q. \u2018EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks.\u2019 In: Proceedings of the 36th International Conference on Machine Learning, Chaudhuri K, Salakhutdinov R, editors. In Proceedings of Machine Learning Research. PMLR; 2019 Jun. vol. 97, pp. 6105\u20136114."},{"key":"10377_CR44","doi-asserted-by":"crossref","unstructured":"Han K, Pham T, Vu TH, Dang T, McCall J, Nguyen TT. \u2018VEGAS: a variable length-based genetic algorithm for ensemble selection in deep ensemble learning.\u2019 Springer; 2021. pp. 168\u2013180.","DOI":"10.1007\/978-3-030-73280-6_14"},{"key":"10377_CR45","doi-asserted-by":"crossref","unstructured":"Kuhn M, Johnson K. Applied Predictive Modeling. Springer, 2013.","DOI":"10.1007\/978-1-4614-6849-3"}],"container-title":["Cognitive Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12559-024-10377-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12559-024-10377-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12559-024-10377-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T07:36:30Z","timestamp":1740814590000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s12559-024-10377-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,26]]},"references-count":45,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,2]]}},"alternative-id":["10377"],"URL":"https:\/\/doi.org\/10.1007\/s12559-024-10377-y","relation":{},"ISSN":["1866-9956","1866-9964"],"issn-type":[{"value":"1866-9956","type":"print"},{"value":"1866-9964","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,26]]},"assertion":[{"value":"8 May 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 September 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 November 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This article does not contain any studies with human participants performed by any of the authors.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}},{"value":"The authors declare no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}}],"article-number":"10"}}