{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T07:29:56Z","timestamp":1785223796812,"version":"3.55.0"},"reference-count":46,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2023,4]]},"DOI":"10.1016\/j.eswa.2022.119391","type":"journal-article","created":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T13:53:45Z","timestamp":1669902825000},"page":"119391","update-policy":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":32,"special_numbering":"C","title":["Representation and compression of Residual Neural Networks through a multilayer network based approach"],"prefix":"10.1016","volume":"215","author":[{"given":"Alessia","family":"Amelio","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0002-1947-8667","authenticated-orcid":false,"given":"Gianluca","family":"Bonifazi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Francesco","family":"Cauteruccio","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0002-1140-4209","authenticated-orcid":false,"given":"Enrico","family":"Corradini","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0003-3692-3600","authenticated-orcid":false,"given":"Michele","family":"Marchetti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0003-1360-8499","authenticated-orcid":false,"given":"Domenico","family":"Ursino","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0003-1509-783X","authenticated-orcid":false,"given":"Luca","family":"Virgili","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2022.119391_b1","series-title":"Structural compression of convolutional neural networks","author":"Abbasi-Asl","year":"2017"},{"key":"10.1016\/j.eswa.2022.119391_b2","doi-asserted-by":"crossref","unstructured":"Aghli,\u00a0N., & Ribeiro,\u00a0E. (2021). Combining Weight Pruning and Knowledge Distillation for CNN Compression. In Proc. of the international conference on computer vision and pattern recognition (CVPR\u201921) (pp. 3191\u20133198). virtual event.","DOI":"10.1109\/CVPRW53098.2021.00356"},{"key":"10.1016\/j.eswa.2022.119391_b3","doi-asserted-by":"crossref","first-page":"618","DOI":"10.1016\/j.neucom.2021.11.067","article-title":"Fault detection and diagnosis with a novel source-aware autoencoder and deep residual neural network","volume":"488","author":"Amini","year":"2022","journal-title":"Neurocomputing"},{"key":"10.1016\/j.eswa.2022.119391_b4","series-title":"Building efficient convnets using redundant feature pruning","author":"Ayinde","year":"2018"},{"key":"10.1016\/j.eswa.2022.119391_b5","series-title":"Neural networks: tricks of the trade","first-page":"421","article-title":"Stochastic gradient descent tricks","author":"Bottou","year":"2012"},{"issue":"1","key":"10.1016\/j.eswa.2022.119391_b6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/2200000016","article-title":"Distributed optimization and statistical learning via the alternating direction method of multipliers","volume":"3","author":"Boyd","year":"2011","journal-title":"Foundations and Trends\u00ae in Machine Learning"},{"issue":"12","key":"10.1016\/j.eswa.2022.119391_b7","doi-asserted-by":"crossref","first-page":"3048","DOI":"10.1109\/TPAMI.2018.2874634","article-title":"Shallowing deep networks: Layer-wise pruning based on feature representations","volume":"41","author":"Chen","year":"2019","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"7","key":"10.1016\/j.eswa.2022.119391_b8","doi-asserted-by":"crossref","first-page":"5113","DOI":"10.1007\/s10462-020-09816-7","article-title":"A comprehensive survey on model compression and acceleration","volume":"53","author":"Choudhary","year":"2020","journal-title":"Artificial Intelligence Review"},{"key":"10.1016\/j.eswa.2022.119391_b9","doi-asserted-by":"crossref","unstructured":"Damacharla,\u00a0P., Rao,\u00a0A., Ringenberg,\u00a0J., & Javaid,\u00a0A. Y. (2021). TLU-Net: A Deep Learning Approach for Automatic Steel Surface Defect Detection. In Proc. of the international conference on applied artificial intelligence (ICAPAI\u201921) (pp. 1\u20136). virtual event.","DOI":"10.1109\/ICAPAI49758.2021.9462060"},{"key":"10.1016\/j.eswa.2022.119391_b10","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2022.116933","article-title":"On art authentication and the rijksmuseum challenge: A residual neural network approach","volume":"200","author":"Dobbs","year":"2022","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2022.119391_b11","series-title":"Covid-resnet: A deep learning framework for screening of COVID19 from radiographs","author":"Farooq","year":"2020"},{"key":"10.1016\/j.eswa.2022.119391_b12","first-page":"1","article-title":"Fault detection on seismic structural images using a nested residual U-net","volume":"60","author":"Gao","year":"2021","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"issue":"6","key":"10.1016\/j.eswa.2022.119391_b13","doi-asserted-by":"crossref","first-page":"945","DOI":"10.3390\/electronics11060945","article-title":"A survey on efficient convolutional neural networks and hardware acceleration","volume":"11","author":"Ghimire","year":"2022","journal-title":"Electronics"},{"key":"10.1016\/j.eswa.2022.119391_b14","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2021.108057","article-title":"Mitigating severe over-parameterization in deep convolutional neural networks through forced feature abstraction and compression with an entropy-based heuristic","volume":"119","author":"Gowdra","year":"2021","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.eswa.2022.119391_b15","doi-asserted-by":"crossref","unstructured":"Han,\u00a0D., Kim,\u00a0J., & Kim,\u00a0J. (2017). Deep Pyramidal Residual Networks. In Proc. of the international conference on computer vision and pattern recognition (CVPR\u201917) (pp. 5927\u20135935). Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.668"},{"key":"10.1016\/j.eswa.2022.119391_b16","doi-asserted-by":"crossref","unstructured":"He,\u00a0Y., Lin,\u00a0J., Liun,\u00a0Z., Wang,\u00a0H., Li,\u00a0L. J., & Han,\u00a0S. (2018). Amc: Automl for model compression and acceleration on mobile devices. In Proc. of the European conference on computer vision (ECCV\u201918) (pp. 784\u2013800). Munich, Germany.","DOI":"10.1007\/978-3-030-01234-2_48"},{"key":"10.1016\/j.eswa.2022.119391_b17","doi-asserted-by":"crossref","unstructured":"He,\u00a0K., Zhang,\u00a0X., Ren,\u00a0S., & Sun,\u00a0J. (2016a). Deep Residual Learning for Image Recognition. In Proc. of the international conference on computer vision and pattern recognition (CVPR\u201916) (pp. 770\u2013778). Las Vegas, NV, USA: https:\/\/2.zoppoz.workers.dev:443\/http\/dx.doi.org\/10.1109\/CVPR.2016.90.","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.eswa.2022.119391_b18","doi-asserted-by":"crossref","unstructured":"He,\u00a0K., Zhang,\u00a0X., Ren,\u00a0S., & Sun,\u00a0J. (2016b). Identity mappings in deep residual networks. In Proc. of the European conference on computer vision (ECCV\u201916) (pp. 630\u2013645). Amsterdam, The Netherlands.","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"10.1016\/j.eswa.2022.119391_b19","doi-asserted-by":"crossref","unstructured":"He,\u00a0Y., Zhang,\u00a0X., & Sun,\u00a0J. (2017). Channel pruning for accelerating very deep neural networks. In Proc. of the international conference on computer vision (ICCV\u201917) (pp. 1389\u20131397). Venice, Italy.","DOI":"10.1109\/ICCV.2017.155"},{"key":"10.1016\/j.eswa.2022.119391_b20","series-title":"Proc. of the international conference on computer vision and pattern recognition (CVPR\u201917)","first-page":"2261","article-title":"Densely connected convolutional networks","author":"Huang","year":"2017"},{"key":"10.1016\/j.eswa.2022.119391_b21","doi-asserted-by":"crossref","unstructured":"Huang,\u00a0G., Sun,\u00a0Y., Liu,\u00a0Z., Sedra,\u00a0D., & Weinberger,\u00a0K. Q. (2016). Deep networks with stochastic depth. In Proc. of the European conference on computer vision (ECCV\u201916) (pp. 646\u2013661). Amsterdam, The Netherlands.","DOI":"10.1007\/978-3-319-46493-0_39"},{"issue":"14","key":"10.1016\/j.eswa.2022.119391_b22","doi-asserted-by":"crossref","first-page":"3476","DOI":"10.1049\/ipr2.12239","article-title":"Crowd activity recognition in live video streaming via 3D-ResNet and region graph convolution network","volume":"15","author":"Kang","year":"2021","journal-title":"IET Image Processing"},{"key":"10.1016\/j.eswa.2022.119391_b23","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2021.116014","article-title":"Broken stitch detection method for sewing operation using CNN feature map and image-processing techniques","volume":"188","author":"Kim","year":"2022","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2022.119391_b24","doi-asserted-by":"crossref","unstructured":"Kim,\u00a0H., Khan,\u00a0M., & Kyung,\u00a0C. (2019). Efficient neural network compression. In Proc. of the international conference on computer vision and pattern rrecognition (CVPR\u201919) (pp. 12569\u201312577). Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.01285"},{"issue":"3","key":"10.1016\/j.eswa.2022.119391_b25","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1093\/comnet\/cnu016","article-title":"Multilayer networks","volume":"2","author":"Kivel\u00e4","year":"2014","journal-title":"Journal of Complex Networks"},{"key":"10.1016\/j.eswa.2022.119391_b26","unstructured":"Koratana,\u00a0A., Kang,\u00a0D., Bailis,\u00a0P., & Zaharia,\u00a0M. (2019). Lit: Learned intermediate representation training for model compression. In Proc. of the international conference on machine learning (ICML\u201919) (pp. 3509\u20133518). Long Beach, CA, USA."},{"key":"10.1016\/j.eswa.2022.119391_b27","series-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"10.1016\/j.eswa.2022.119391_b28","article-title":"A hybrid deep CNN-cov-19-res-net transfer learning architype for an enhanced brain tumor detection and classification scheme in medical image processing","volume":"76","author":"Kumar","year":"2022","journal-title":"Biomedical Signal Processing and Control"},{"key":"10.1016\/j.eswa.2022.119391_b29","doi-asserted-by":"crossref","first-page":"18967","DOI":"10.1109\/ACCESS.2018.2814605","article-title":"An improved ResNet based on the adjustable shortcut connections","volume":"6","author":"Li","year":"2018","journal-title":"IEEE Access"},{"key":"10.1016\/j.eswa.2022.119391_b30","unstructured":"Li,\u00a0H., Kadav,\u00a0A., Durdanovic,\u00a0I., Samet,\u00a0H., & Graf,\u00a0H. P. (2016). Pruning filters for efficient convnets. In Proc. of the international conference on learning representations (ICLR\u201917). Toulon, France."},{"key":"10.1016\/j.eswa.2022.119391_b31","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2021.114680","article-title":"A clinical decision support system for predicting cirrhosis stages via high frequency ultrasound images","volume":"175","author":"Liu","year":"2021","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2022.119391_b32","series-title":"An entropy-based pruning method for cnn compression","author":"Luo","year":"2017"},{"key":"10.1016\/j.eswa.2022.119391_b33","doi-asserted-by":"crossref","unstructured":"Luo,\u00a0J., Wu,\u00a0J., & Lin,\u00a0W. (2017). Thinet: A filter level pruning method for deep neural network compression. In Proc. of the international conference on computer vision (ICCV\u201917) (pp. 5058\u20135066). Honolulu, HI, USA.","DOI":"10.1109\/ICCV.2017.541"},{"key":"10.1016\/j.eswa.2022.119391_b34","doi-asserted-by":"crossref","unstructured":"Ma,\u00a0X., Yuan,\u00a0G., Lin,\u00a0S., Li,\u00a0Z., Sun,\u00a0H., & Wang,\u00a0Y. (2019). Resnet can be pruned 60\u00d7: Introducing network purification and unused path removal (p-rm) after weight pruning. In Proc. of the international symposium on nanoscale architectures (NANOARCH\u201919) (pp. 1\u20132). Qingdao, China.","DOI":"10.1109\/NANOARCH47378.2019.181304"},{"key":"10.1016\/j.eswa.2022.119391_b35","doi-asserted-by":"crossref","unstructured":"Minnehan,\u00a0B., & Savakis,\u00a0A. (2019). Cascaded projection: End-to-end network compression and acceleration. In Proc. of the international conference on computer vision and pattern recognition (CVPR\u201919) (pp. 10715\u201310724). Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.01097"},{"key":"10.1016\/j.eswa.2022.119391_b36","unstructured":"Polino,\u00a0A., Pascanu,\u00a0R., & Alistarh,\u00a0D. (2018). Model compression via distillation and quantization. In Proc. of the international conference on learning representations, (ICLR\u201918). Vancouver, British Columbia, Canada."},{"key":"10.1016\/j.eswa.2022.119391_b37","doi-asserted-by":"crossref","first-page":"68985","DOI":"10.1109\/ACCESS.2021.3078184","article-title":"Isplinception: an inception-ResNet deep learning architecture for human activity recognition","volume":"9","author":"Ronald","year":"2021","journal-title":"IEEE Access"},{"issue":"2","key":"10.1016\/j.eswa.2022.119391_b38","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1007\/s11760-020-01760-x","article-title":"A dynamic CNN pruning method based on matrix similarity","volume":"15","author":"Shao","year":"2021","journal-title":"Signal, Image and Video Processing"},{"key":"10.1016\/j.eswa.2022.119391_b39","unstructured":"Veit,\u00a0A., Wilber,\u00a0M., & Belongie,\u00a0S. (2016). Residual Networks Behave like Ensembles of Relatively Shallow Networks. In Proc. of the international conference on neural information processing systems (NIPS\u201916) (pp. 550\u2013558). Barcelona, Spain."},{"key":"10.1016\/j.eswa.2022.119391_b40","doi-asserted-by":"crossref","unstructured":"Wang,\u00a0W., Sun,\u00a0Y., Eriksson,\u00a0B., Wang,\u00a0W., & Aggarwal,\u00a0V. (2018). Wide compression: Tensor ring nets. In Proc. of the international conference on computer vision and pattern recognition (CVPR\u201918) (pp. 9329\u20139338). Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00972"},{"key":"10.1016\/j.eswa.2022.119391_b41","doi-asserted-by":"crossref","unstructured":"Xie,\u00a0S., Girshick,\u00a0R., Doll\u00e1r,\u00a0P., Tu,\u00a0X., & He,\u00a0K. (2017). Aggregated residual transformations for deep neural networks. In Proc. of the international conference on computer vision and pattern recognition (CVPR\u201917) (pp. 1492\u20131500). Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.634"},{"key":"10.1016\/j.eswa.2022.119391_b42","doi-asserted-by":"crossref","first-page":"55802","DOI":"10.1109\/ACCESS.2021.3068597","article-title":"Diagnosis support model of cardiomegaly based on CNN using ResNet and explainable feature map","volume":"9","author":"Yoo","year":"2021","journal-title":"IEEE Access"},{"key":"10.1016\/j.eswa.2022.119391_b43","doi-asserted-by":"crossref","DOI":"10.1016\/j.measurement.2021.109642","article-title":"A deep attention residual neural network-based remaining useful life prediction of machinery","volume":"181","author":"Zeng","year":"2021","journal-title":"Measurement"},{"key":"10.1016\/j.eswa.2022.119391_b44","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2021.115673","article-title":"Cs-resnet: cost-sensitive residual convolutional neural network for PCB cosmetic defect detection","volume":"185","author":"Zhang","year":"2021","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2022.119391_b45","series-title":"Proc. of international joint conference on neural networks (IJCNN\u201921)","first-page":"1","article-title":"Identity-linked group channel pruning for deep neural networks","author":"Zhang","year":"2021"},{"key":"10.1016\/j.eswa.2022.119391_b46","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2021.114566","article-title":"ERV-net: An efficient 3D residual neural network for brain tumor segmentation","volume":"170","author":"Zhou","year":"2021","journal-title":"Expert Systems with Applications"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/api.elsevier.com\/content\/article\/PII:S0957417422024095?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/api.elsevier.com\/content\/article\/PII:S0957417422024095?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T06:13:58Z","timestamp":1760681638000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417422024095"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4]]},"references-count":46,"alternative-id":["S0957417422024095"],"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1016\/j.eswa.2022.119391","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2023,4]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Representation and compression of Residual Neural Networks through a multilayer network based approach","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1016\/j.eswa.2022.119391","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2022 Elsevier Ltd. All rights reserved.","name":"copyright","label":"Copyright"}],"article-number":"119391"}}