{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T03:37:56Z","timestamp":1768880276675,"version":"3.49.0"},"reference-count":23,"publisher":"Fuji Technology Press Ltd.","issue":"1","funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"crossref","award":["2023YFC3007003"],"award-info":[{"award-number":["2023YFC3007003"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100015314","name":"China University of Geosciences","doi-asserted-by":"crossref","award":["SKJ2023080"],"award-info":[{"award-number":["SKJ2023080"]}],"id":[{"id":"10.13039\/501100015314","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JACIII","J. Adv. Comput. Intell. Intell. Inform."],"published-print":{"date-parts":[[2026,1,20]]},"abstract":"<jats:p>Fracture identification is an important aspect of assessing rock mass stability. However, manual evaluation of borehole fracture images can be time consuming and lacks quantitative precision, particularly because of the complex shapes of fractures and the challenges in accurately annotating those images. To address these issues, this study uses the YOLOv8 model as a baseline and enhances its feature extraction capability by adding the efficient channel attention (ECA) module. In addition, the wise-intersection over union (WIoU) loss function is adopted to improve the model ability to precisely capture fracture edges. Experimental results showed that adding either the ECA module or the WIoU loss function to the baseline model effectively improved recognition performance. Among various attention modules, ECA achieved the best results. For the four metrics, namely box mAP@50, box mAP@50\u201395, mask mAP@50, and mask mAP@50\u201395, the model with only ECA demonstrated notable improvements, as did the model with only WIoU. Furthermore, the model that combined both the ECA module and WIoU loss achieved increases of 5.1% and 4.0% for box mAP@50 and box mAP@50\u201395, respectively, and 3.9% and 4.5% for mask mAP@50 and mask mAP@50\u201395, respectively. These combined improvements were greater than the sum of the individual enhancements, indicating a synergistic effect. Tests on new boreholes demonstrated that the proposed model could effectively identify fractures in borehole TV images. However, owing to differences in data distribution, certain small fractures might still be missed. Further efforts are required in future work to enhance the generalizability of the model.<\/jats:p>","DOI":"10.20965\/jaciii.2026.p0167","type":"journal-article","created":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T15:02:06Z","timestamp":1768834926000},"page":"167-175","source":"Crossref","is-referenced-by-count":0,"title":["Intelligent Identification of Subsurface Rock Mass Fractures Based on YOLOv8 with Efficient Channel Attention (ECA)"],"prefix":"10.20965","volume":"30","author":[{"given":"Zhenkun","family":"Wu","sequence":"first","affiliation":[{"name":"School of Automation, China University of Geosciences, No.388 Lumo Road, Hongshan District, Wuhan, Hubei 430074, China"}]},{"given":"Yu","family":"Ke","sequence":"additional","affiliation":[{"name":"School of Future Technology, China University of Geosciences, No.388 Lumo Road, Hongshan District, Wuhan, Hubei 430074, China"}]},{"given":"Yang","family":"Li","sequence":"additional","affiliation":[{"name":"China Solibase Engineering Co., Ltd., Yard 3 Huihai Middle Road, Shunyi District, Beijing 101300, China"}]},{"given":"Hui","family":"Gao","sequence":"additional","affiliation":[{"name":"Faculty of Engineering, China University of Geosciences, No.388 Lumo Road, Hongshan District, Wuhan, Hubei 430074, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8369-4954","authenticated-orcid":true,"given":"Wangyong","family":"He","sequence":"additional","affiliation":[{"name":"School of Automation, China University of Geosciences, No.388 Lumo Road, Hongshan District, Wuhan, Hubei 430074, China"}]},{"given":"Songcheng","family":"Tan","sequence":"additional","affiliation":[{"name":"Faculty of Engineering, China University of Geosciences, No.388 Lumo Road, Hongshan District, Wuhan, Hubei 430074, China"}]},{"given":"Longchen","family":"Duan","sequence":"additional","affiliation":[{"name":"Faculty of Engineering, China University of Geosciences, No.388 Lumo Road, Hongshan District, Wuhan, Hubei 430074, China"}]}],"member":"8550","published-online":{"date-parts":[[2026,1,20]]},"reference":[{"key":"key-10.20965\/jaciii.2026.p0167-1","doi-asserted-by":"crossref","unstructured":"L. Peng, W. Chao, S. Li, and B. Feng, \u201cResearch on crack detection method of airport runway based on twice-threshold segmentation,\u201d 2015 5th Int. Conf. on Instrumentation and Measurement, Computer, Communication and Control (IMCCC), pp. 1716-1720, 2015. https:\/\/doi.org\/10.1109\/IMCCC.2015.364","DOI":"10.1109\/IMCCC.2015.364"},{"key":"key-10.20965\/jaciii.2026.p0167-2","doi-asserted-by":"crossref","unstructured":"D. Xu, Y. Zhao, Y. Jiang, C. Zhang, B. Sun, and X. He, \u201cUsing improved edge detection method to detect mining-induced ground fissures identified by unmanned aerial vehicle remote sensing,\u201d Remote Sensing, Vol.13, No.18, Article No.3652, 2021. https:\/\/doi.org\/10.3390\/rs13183652","DOI":"10.3390\/rs13183652"},{"key":"key-10.20965\/jaciii.2026.p0167-3","doi-asserted-by":"crossref","unstructured":"H. Xu, Y. Tian, S. Lin, and S. Wang, \u201cResearch of image segmentation algorithm applied to concrete bridge cracks,\u201d 2013 IEEE Third Int. Conf. on Information Science and Technology (ICIST), pp. 1637-1640, 2013. https:\/\/doi.org\/10.1109\/ICIST.2013.6747851","DOI":"10.1109\/ICIST.2013.6747851"},{"key":"key-10.20965\/jaciii.2026.p0167-4","doi-asserted-by":"crossref","unstructured":"P. del Rio-Barral, M. Soilan, S. M. Gonzalez-Collazo, and P. Arias, \u201cPavement crack detection and clustering via region-growing algorithm from 3D MLS point clouds,\u201d Remote Sensing, Vol.14, No.22, Article No.5866, 2022. https:\/\/doi.org\/10.3390\/rs14225866","DOI":"10.3390\/rs14225866"},{"key":"key-10.20965\/jaciii.2026.p0167-5","doi-asserted-by":"crossref","unstructured":"M. M. Hittawe, S. M. Muddamsetty, D. Sidibe, and F. Meriaudeau, \u201cMultiple features extraction for timber defects detection and classification using SVM,\u201d 2015 IEEE Int. Conf. on Image Processing (ICIP), pp. 427-431, 2015. https:\/\/doi.org\/10.1109\/ICIP.2015.7350834","DOI":"10.1109\/ICIP.2015.7350834"},{"key":"key-10.20965\/jaciii.2026.p0167-6","doi-asserted-by":"crossref","unstructured":"Y. Shi, L. Cui, Z. Qi, F. Meng, and Z. Chen, \u201cAutomatic road crack detection using random structured forests,\u201d IEEE Trans. on Intelligent Transportation Systems, Vol.17, No.12, pp. 3434-3445, 2016. https:\/\/doi.org\/10.1109\/TITS.2016.2552248","DOI":"10.1109\/TITS.2016.2552248"},{"key":"key-10.20965\/jaciii.2026.p0167-7","doi-asserted-by":"crossref","unstructured":"A. Cubero-Fernandez, F. J. Rodriguez-Lozano, R. Villatoro, J. Olivares, and J. M. Palomares, \u201cEfficient pavement crack detection and classification,\u201d J. on Image and Video Processing, Vol.2017, No.1, Article No.39, 2017. https:\/\/doi.org\/10.1186\/s13640-017-0187-0","DOI":"10.1186\/s13640-017-0187-0"},{"key":"key-10.20965\/jaciii.2026.p0167-8","doi-asserted-by":"crossref","unstructured":"M. Azarafza et al., \u201cApplication of the modified Q-slope classification system for sedimentary rock slope stability assessment in Iran,\u201d Engineering Geology, Vol.264, No.1, Article No.105349. https:\/\/doi.org\/10.1016\/j.enggeo.2019.105349","DOI":"10.1016\/j.enggeo.2019.105349"},{"key":"key-10.20965\/jaciii.2026.p0167-9","doi-asserted-by":"crossref","unstructured":"L. A. O. Martins, F. L. C. Padua, and P. E. M. Almeida, \u201cAutomatic detection of surface defects on rolled steel using computer vision and artificial neural networks,\u201d 36th Annual Conf. on IEEE Industrial Electronics Society (IECON 2010), pp. 1081-1086, 2010. https:\/\/doi.org\/10.1109\/IECON.2010.5675519","DOI":"10.1109\/IECON.2010.5675519"},{"key":"key-10.20965\/jaciii.2026.p0167-10","doi-asserted-by":"crossref","unstructured":"O. Ronneberger, P. Fischer, and T. Brox, \u201cU-Net: Convolutional networks for biomedical image segmentation,\u201d arXiv:1505.04597, 2015. https:\/\/doi.org\/10.48550\/arXiv.1505.04597","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"key-10.20965\/jaciii.2026.p0167-11","doi-asserted-by":"crossref","unstructured":"K. He, G. Gkioxari, P. Dollar, and R. Girshick, \u201cMask R-CNN,\u201d 2017 IEEE Int. Conf. on Computer Vision (ICCV), pp. 2980-2988, 2017. https:\/\/doi.org\/10.1109\/ICCV.2017.322","DOI":"10.1109\/ICCV.2017.322"},{"key":"key-10.20965\/jaciii.2026.p0167-12","doi-asserted-by":"crossref","unstructured":"C. V. Dung and L. D. Anh, \u201cAutonomous concrete crack detection using deep fully convolutional neural network,\u201d Automation in Construction, Vol.99, pp. 52-58, 2019. https:\/\/doi.org\/10.1016\/j.autcon.2018.11.028","DOI":"10.1016\/j.autcon.2018.11.028"},{"key":"key-10.20965\/jaciii.2026.p0167-13","doi-asserted-by":"crossref","unstructured":"X. Liu, H. Wang, H. Jing, A. Shao, and L. Wang, \u201cResearch on intelligent identification of rock types based on Faster R-CNN method\u201d IEEE Access, Vol.8, pp. 21804-21812, 2020. https:\/\/doi.org\/DOI:10.1109\/ACCESS.2020.2968515","DOI":"10.1109\/ACCESS.2020.2968515"},{"key":"key-10.20965\/jaciii.2026.p0167-14","doi-asserted-by":"crossref","unstructured":"X. Yang, H. Li, Y. Yu, X. Luo, T. Huang, and X. Yang, \u201cAutomatic pixel-level crack detection and measurement using fully convolutional network,\u201d Computer-Aided Civil and Infrastructure Engineering, Vol.33, No.12, pp. 1090-1109, 2018. https:\/\/doi.org\/10.1111\/mice.12412","DOI":"10.1111\/mice.12412"},{"key":"key-10.20965\/jaciii.2026.p0167-15","doi-asserted-by":"crossref","unstructured":"Z. Zhang, Q. Liu, and Y. Wang, \u201cRoad extraction by deep residual U-Net,\u201d IEEE Geoscience and Remote Sensing Letters, Vol.15, No.5, pp. 749-753, 2018. https:\/\/doi.org\/10.1109\/LGRS.2018.2802944","DOI":"10.1109\/LGRS.2018.2802944"},{"key":"key-10.20965\/jaciii.2026.p0167-16","doi-asserted-by":"crossref","unstructured":"Z. Liu, Y. Cao, Y. Wang, and W. Wang, \u201cComputer vision-based concrete crack detection using u-net fully convolutional networks,\u201d Automation in Construction, Vol.104, No.8, pp. 129-139, 2019. https:\/\/doi.org\/10.1016\/j.autcon.2019.04.005","DOI":"10.1016\/j.autcon.2019.04.005"},{"key":"key-10.20965\/jaciii.2026.p0167-17","doi-asserted-by":"crossref","unstructured":"Y. Yuan, N. Zhang, and C. Han, \u201cAutomated identification of fissure trace in mining roadway via deep learning,\u201d J. of Rock Mechanics and Geotechnical Engineering, Vol.15, No.8, pp. 2039-2052, 2023. https:\/\/doi.org\/10.1016\/j.jrmge.2022.12.018","DOI":"10.1016\/j.jrmge.2022.12.018"},{"key":"key-10.20965\/jaciii.2026.p0167-18","doi-asserted-by":"crossref","unstructured":"S. Zhao, G. Zhang, D. Zhang, D. Tan, and H. Huang, \u201cA hybrid attention deep learning network for refined segmentation of cracks from shield tunnel lining images,\u201d J. of Rock Mechanics and Geotechnical Engineering, Vol.15, No.12, pp. 3105-3117, 2023. https:\/\/doi.org\/10.1016\/j.jrmge.2023.02.025","DOI":"10.1016\/j.jrmge.2023.02.025"},{"key":"key-10.20965\/jaciii.2026.p0167-19","doi-asserted-by":"crossref","unstructured":"L. O. Dias et al., \u201cAutomatic detection of fractures and breakouts patterns in acoustic borehole image logs using fast-region convolutional neural networks,\u201d J. of Petroleum Science and Engineering, Vol.191, Article No.107099, 2020. https:\/\/doi.org\/10.1016\/j.petrol.2020.107099","DOI":"10.1016\/j.petrol.2020.107099"},{"key":"key-10.20965\/jaciii.2026.p0167-20","doi-asserted-by":"crossref","unstructured":"S. Han et al., \u201cAutomatic borehole fracture detection and characterization with tailored Faster R-CNN and simplified Hough transform,\u201d Engineering Applications of Artificial Intelligence, Vol.126, Article No.107024, 2023. https:\/\/doi.org\/10.1016\/j.engappai.2023.107024","DOI":"10.1016\/j.engappai.2023.107024"},{"key":"key-10.20965\/jaciii.2026.p0167-21","doi-asserted-by":"crossref","unstructured":"C. Liu et al., \u201cIntelligent recognition and identification of fracture types and parameters for borehole images based on developed convolutional neural networks and post-processing,\u201d Engineering Fracture Mechanics, Vol.292, Article No.109624, 2023. https:\/\/doi.org\/10.1016\/j.engfracmech.2023.109624","DOI":"10.1016\/j.engfracmech.2023.109624"},{"key":"key-10.20965\/jaciii.2026.p0167-22","doi-asserted-by":"crossref","unstructured":"Q. Wang et al., \u201cECA-Net: Efficient channel attention for deep convolutional neural networks,\u201d 2020 IEEE\/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), pp. 11531-11539, 2020. https:\/\/doi.org\/10.1109\/CVPR42600.2020.01155","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"key-10.20965\/jaciii.2026.p0167-23","unstructured":"Z. Tong, Y. Chen, Z. Xu, and R. Yu, \u201cWise-IoU: Bounding box regression loss with dynamic focusing mechanism,\u201d arXiv:2301.10051, 2023. https:\/\/doi.org\/10.48550\/arXiv.2301.10051"}],"container-title":["Journal of Advanced Computational Intelligence and Intelligent Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.fujipress.jp\/main\/wp-content\/themes\/Fujipress\/hyosetsu.php?ppno=jacii003000010015","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T15:03:22Z","timestamp":1768835002000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.fujipress.jp\/jaciii\/jc\/jacii003000010167"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,20]]},"references-count":23,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1,20]]},"published-print":{"date-parts":[[2026,1,20]]}},"URL":"https:\/\/doi.org\/10.20965\/jaciii.2026.p0167","relation":{},"ISSN":["1883-8014","1343-0130"],"issn-type":[{"value":"1883-8014","type":"electronic"},{"value":"1343-0130","type":"print"}],"subject":[],"published":{"date-parts":[[2026,1,20]]}}}