{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T07:04:54Z","timestamp":1777705494651,"version":"3.51.4"},"reference-count":26,"publisher":"SAGE Publications","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IFS"],"published-print":{"date-parts":[[2024,3,5]]},"abstract":"<jats:p>The mining belt conveyor is one of the most important modules in coal mine, whose safety always be threatened by the foreign objects. Although the traditional target detection methods achieve promising results in various computer vision tasks, the performance heavily depends on sufficient labelled data. However, in real-world production scenario, it is difficult to acquire huge number of images with foreign objects. The obtained datasets lacking of capacity and diversity are not suitable for training supervised learning-based foreign objects detection models. To address this concern, we propose a novel method for detecting the foreign objects on the surface of underground coal conveyor belt via improved GANomaly. The proposed foreign objects detection method employs generative adversarial networks (GAN) with attention gate to capture the distribution of normality in both high-dimensional image space and low-dimensional latent vector space. Only the normal images without foreign object are utilized to adversarially train the proposed network, including a U-shape generator to reconstruct the input image and a discriminator to classify real images from reconstructed ones. Then the combination of the difference between the input and generated images as well as the difference between latent representations are utilized as the anomaly score to evaluate whether the input image contain foreign objects. Experimental results over 707 images from real-world industrial scenarios demonstrate that the proposed method achieves an area under the receiver operating characteristic curve of 0.864 and is superior to the previous GAN-based anomaly detection methods.<\/jats:p>","DOI":"10.3233\/jifs-230647","type":"journal-article","created":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T13:33:25Z","timestamp":1706016805000},"page":"5841-5851","source":"Crossref","is-referenced-by-count":1,"title":["Intelligent detection of foreign objects over coal flow based on improved GANomaly"],"prefix":"10.1177","volume":"46","author":[{"given":"Yong","family":"Wang","sequence":"first","affiliation":[{"name":"School of Information and Electrical Control Engineering, China University of Mining and Technology, Xuzhou, China"},{"name":"Gaozhuang Coal Mine, Zaozhuang Mining Group Co Ltd, Jining, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhipeng","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Information and Electrical Control Engineering, China University of Mining and Technology, Xuzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yihan","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Information and Electrical Control Engineering, China University of Mining and Technology, Xuzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunyu","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Information and Electrical Control Engineering, China University of Mining and Technology, Xuzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Zou","sequence":"additional","affiliation":[{"name":"School of Information and Electrical Control Engineering, China University of Mining and Technology, Xuzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","reference":[{"issue":"5","key":"10.3233\/JIFS-230647_ref1","doi-asserted-by":"crossref","first-page":"1149","DOI":"10.1007\/s40789-020-00389-y","article-title":"Virtualstraightening of scraper conveyor based on the position and attitudesolution of industrial robot model","volume":"8","author":"Li","year":"2021","journal-title":"International Journal of Coal Science & Technology"},{"key":"10.3233\/JIFS-230647_ref2","doi-asserted-by":"crossref","first-page":"150231","DOI":"10.1016\/j.scitotenv.2021.150231","article-title":"Life cycle assessmentof underground coal mining in China","volume":"805","author":"Tao","year":"2022","journal-title":"Science of the Total Environment"},{"key":"10.3233\/JIFS-230647_ref3","doi-asserted-by":"crossref","first-page":"110757","DOI":"10.1016\/j.measurement.2022.110757","article-title":"Foreign object detection for railway ballastlesstrackbeds: A semisupervised learning method","volume":"190","author":"Chen","year":"2022","journal-title":"Measurement"},{"issue":"2021","key":"10.3233\/JIFS-230647_ref4","first-page":"108493","article-title":"Metalobject detection for electric vehicle inductive power transfersystems based on hyperspectral imaging","volume":"168","author":"Tian","journal-title":"Measurement"},{"key":"10.3233\/JIFS-230647_ref5","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1016\/j.powtec.2020.08.088","article-title":"Cascade network fordetection of coal and gangue in the production context","volume":"377","author":"Lv","year":"2021","journal-title":"Powder Technology"},{"issue":"22","key":"10.3233\/JIFS-230647_ref6","doi-asserted-by":"crossref","first-page":"6566","DOI":"10.1364\/AO.422498","article-title":"Coal and gangueidentification method based on the intensity image of lidar anddensenet","volume":"60","author":"Xing","year":"2021","journal-title":"Applied Optics"},{"key":"10.3233\/JIFS-230647_ref7","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1016\/j.minpro.2017.10.010","article-title":"Separating coal and gangue usingthree-dimensional laser scanning","volume":"169","author":"Wang","year":"2017","journal-title":"International Journal of Mineral Processing"},{"issue":"10","key":"10.3233\/JIFS-230647_ref8","first-page":"8043","article-title":"Nondestructiveidentification of coal and gangue via near-infrared spectroscopybased on improved broad learning","volume":"69","author":"Zou","year":"2020","journal-title":"IEEE Transactions onInstrumentation and Measurement"},{"issue":"2021","key":"10.3233\/JIFS-230647_ref9","first-page":"109853","article-title":"A multi-scale image anddynamic candidate region-based automatic detection of foreigntargets intruding the railway perimeter","volume":"185","author":"Li","journal-title":"Measurement"},{"key":"10.3233\/JIFS-230647_ref10","doi-asserted-by":"crossref","first-page":"116905","DOI":"10.1016\/j.eswa.2022.116905","article-title":"Dsg-fusion:Infrared and visible image fusion via generative adversarialnetworks and guided filter","volume":"200","author":"Yang","year":"2022","journal-title":"Expert Systems with Applications"},{"issue":"1","key":"10.3233\/JIFS-230647_ref11","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1080\/19392699.2017.1290609","article-title":"Identification of coal and gangue by feed-forward neuralnetwork based on data analysis","volume":"39","author":"Hou","year":"2019","journal-title":"International Journal of Coal Preparation and Utilization"},{"issue":"8","key":"10.3233\/JIFS-230647_ref12","doi-asserted-by":"crossref","first-page":"603","DOI":"10.1080\/19392699.2018.1496912","article-title":"Research on methods to differentiate coaland gangue using image processing and a support vector machine","volume":"41","author":"Wang","year":"2021","journal-title":"International Journal of Coal Preparation and Utilization"},{"key":"10.3233\/JIFS-230647_ref13","doi-asserted-by":"crossref","first-page":"120475","DOI":"10.1016\/j.fuel.2021.120475","article-title":"Maceral groupsanalysis of coal based on semantic segmentation of photomicrographsvia the improved u-net","volume":"294","author":"Lei","year":"2021","journal-title":"Fuel"},{"key":"10.3233\/JIFS-230647_ref14","doi-asserted-by":"crossref","first-page":"659","DOI":"10.1109\/JSTARS.2020.2968179","article-title":"Spectral-spatialexploration for hyperspectral image classification via the fusion offully convolutional networks","volume":"13","author":"Zou","year":"2020","journal-title":"IEEE Journal of Selected Topicsin Applied Earth Observations and Remote Sensing"},{"key":"10.3233\/JIFS-230647_ref15","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TIM.2021.3118090","article-title":"Multiscale featureinteractive network for multifocus image fusion","volume":"70","author":"Liu","year":"2021","journal-title":"IEEETransactions on Instrumentation and Measurement"},{"issue":"1","key":"10.3233\/JIFS-230647_ref16","doi-asserted-by":"crossref","first-page":"134","DOI":"10.1049\/ipr2.12339","article-title":"Coal gangue detectionand recognition algorithm based on deformable convolution yolov3","volume":"16","author":"Li","year":"2021","journal-title":"IET Image Processing"},{"issue":"24","key":"10.3233\/JIFS-230647_ref18","doi-asserted-by":"crossref","first-page":"9504","DOI":"10.3390\/en15249504","article-title":"Coal mine belt conveyor foreignobjects recognition method of improved yolov5 algorithm withdefogging and deblurring","volume":"15","author":"Mao","year":"2022","journal-title":"Energies"},{"key":"10.3233\/JIFS-230647_ref19","first-page":"2022","article-title":"detection of foreign matter in coal mine transportationbelt based on convolution neural network","author":"Ma","journal-title":"ScientificProgramming"},{"issue":"11","key":"10.3233\/JIFS-230647_ref20","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1145\/3422622","article-title":"Generative adversarialnetworks","volume":"63","author":"Goodfellow","year":"2020","journal-title":"Communications of the ACM"},{"issue":"5","key":"10.3233\/JIFS-230647_ref21","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3453155","article-title":"Deep learning-basedanomaly detection in cyber-physical systems: Progress andopportunities","volume":"54","author":"Luo","year":"2021","journal-title":"ACM Computing Surveys (CSUR)"},{"key":"10.3233\/JIFS-230647_ref27","doi-asserted-by":"crossref","first-page":"168236","DOI":"10.1109\/ACCESS.2019.2954475","article-title":"Noise-robustwagon text extraction based on defect-restore generative adversarialnetwork","volume":"7","author":"Lei","year":"2019","journal-title":"IEEE Access"},{"key":"10.3233\/JIFS-230647_ref29","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1016\/j.patrec.2021.03.009","article-title":"Perception matters: Exploring imperceptible and transferableanti-forensics for gan-generated fake face imagery detection","volume":"146","author":"Wang","year":"2021","journal-title":"Pattern Recognition Letters"},{"issue":"5","key":"10.3233\/JIFS-230647_ref30","doi-asserted-by":"crossref","first-page":"969","DOI":"10.1109\/JSTSP.2020.2994523","article-title":"Gan-generated image detectionwith self-attention mechanism against gan generator defect","volume":"14","author":"Mi","year":"2020","journal-title":"IEEE Journal of Selected Topics in Signal Processing"},{"issue":"3","key":"10.3233\/JIFS-230647_ref31","doi-asserted-by":"crossref","first-page":"530","DOI":"10.3390\/rs14030530","article-title":"Da-imrn:Dual-attention-guided interactive multi-scale residual network forhyperspectral image classification","volume":"14","author":"Zou","year":"2022","journal-title":"Remote Sensing"},{"key":"10.3233\/JIFS-230647_ref32","doi-asserted-by":"crossref","first-page":"1438","DOI":"10.1016\/j.procs.2022.01.182","article-title":"A french-to-english machinetranslation model using transformer network","volume":"199","author":"Tian","year":"2022","journal-title":"Procedia ComputerScience"},{"key":"10.3233\/JIFS-230647_ref33","doi-asserted-by":"crossref","first-page":"110500","DOI":"10.1016\/j.measurement.2021.110500","article-title":"Intelligent fault diagnosis of rollingbearings under imbalanced data conditions using attention-based deeplearning method","volume":"189","author":"Li","year":"2022","journal-title":"Measurement"}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/JIFS-230647","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:44:01Z","timestamp":1777455841000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/JIFS-230647"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,5]]},"references-count":26,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.3233\/jifs-230647","relation":{},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,5]]}}}