{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T08:26:20Z","timestamp":1769588780213,"version":"3.49.0"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2022,10,18]],"date-time":"2022-10-18T00:00:00Z","timestamp":1666051200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,10,18]],"date-time":"2022-10-18T00:00:00Z","timestamp":1666051200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62171156"],"award-info":[{"award-number":["62171156"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2023,6]]},"DOI":"10.1007\/s10489-022-04251-3","type":"journal-article","created":{"date-parts":[[2022,10,18]],"date-time":"2022-10-18T04:03:31Z","timestamp":1666065811000},"page":"13867-13881","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["An efficient lightweight CNN acceleration architecture for edge computing based-on FPGA"],"prefix":"10.1007","volume":"53","author":[{"given":"Ruidong","family":"Wu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6831-5779","authenticated-orcid":false,"given":"Bing","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Ping","family":"Fu","sequence":"additional","affiliation":[]},{"given":"Haolin","family":"Chen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,10,18]]},"reference":[{"key":"4251_CR1","doi-asserted-by":"crossref","unstructured":"Alzubaidi L, Zhang J, Humaidi AJ, Al-Dujaili A, Duan Y, Al-Shamma O, Santamar\u00eda J, Fadhel MA, Al-Amidie M, Farhan L (2021) Review of deep learning: concepts, cnn architectures, challenges, applications, future directions. pp 1\u201374. Springer","DOI":"10.1186\/s40537-021-00444-8"},{"issue":"10","key":"4251_CR2","first-page":"1415","volume":"65","author":"L Bai","year":"2018","unstructured":"Bai L, Zhao Y, Huang X (2018) A cnn accelerator on fpga using depthwise separable convolution. IEEE Trans Circ Syst II: Express Briefs 65(10):1415\u20131419","journal-title":"IEEE Trans Circ Syst II: Express Briefs"},{"issue":"5","key":"4251_CR3","doi-asserted-by":"publisher","first-page":"8553","DOI":"10.1109\/JIOT.2019.2920283","volume":"6","author":"V Bianchi","year":"2019","unstructured":"Bianchi V, Bassoli M, Lombardo G, Fornacciari P, Mordonini M, De Munari I (2019) Iot wearable sensor and deep learning: an integrated approach for personalized human activity recognition in a smart home environment. IEEE Internet Things J 6(5):8553\u20138562","journal-title":"IEEE Internet Things J"},{"key":"4251_CR4","doi-asserted-by":"crossref","unstructured":"Chollet F (2017) Xception: deep learning with depthwise separable convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 1251\u20131258","DOI":"10.1109\/CVPR.2017.195"},{"key":"4251_CR5","doi-asserted-by":"crossref","unstructured":"Cong J, Xiao B (2014) Minimizing computation in convolutional neural networks. In: International conference on artificial neural networks, pp 281\u2013290. Springer","DOI":"10.1007\/978-3-319-11179-7_36"},{"key":"4251_CR6","doi-asserted-by":"publisher","first-page":"278","DOI":"10.1016\/j.sysarc.2018.12.008","volume":"97","author":"W Ding","year":"2019","unstructured":"Ding W, Huang Z, Huang ZA, Tian LA, Wang HA, Feng SA (2019) Designing efficient accelerator of depthwise separable convolutional neural network on fpga. J Syst Archit 97:278\u2013 286","journal-title":"J Syst Archit"},{"issue":"4","key":"4251_CR7","first-page":"755","volume":"67","author":"AA Gilan","year":"2019","unstructured":"Gilan AA, Emad M, Alizadeh B (2019) Fpga-based implementation of a real-time object recognition system using convolutional neural network. IEEE Trans Circ Syst II: Express Briefs 67(4):755\u2013759","journal-title":"IEEE Trans Circ Syst II: Express Briefs"},{"issue":"99","key":"4251_CR8","first-page":"1","volume":"PP","author":"W Huang","year":"2021","unstructured":"Huang W, Wu H, Chen Q, Luo C, Huang Y (2021) Fpga-based high-throughput cnn hardware accelerator with high computing resource utilization ratio. IEEE Trans Neural Netw Learn Syst PP (99):1\u201315","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"4251_CR9","unstructured":"Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning (ICML), pp 448\u2013456. PMLR"},{"key":"4251_CR10","doi-asserted-by":"crossref","unstructured":"Jacob B, Kligys S, Chen B, Zhu M, Tang M, Howard A, Adam H, Kalenichenko D (2018) Quantization and training of neural networks for efficient integer-arithmetic-only inference. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 2704\u2013 2713","DOI":"10.1109\/CVPR.2018.00286"},{"issue":"1","key":"4251_CR11","first-page":"274","volume":"66","author":"A Jafari","year":"2018","unstructured":"Jafari A, Ganesan A, Thalisetty CSK, Sivasubramanian V, Oates T, Mohsenin T (2018) Sensornet: a scalable and low-power deep convolutional neural network for multimodal data classification. IEEE Trans Circ Syst I: Regular Papers 66(1):274\u2013 287","journal-title":"IEEE Trans Circ Syst I: Regular Papers"},{"issue":"12","key":"4251_CR12","doi-asserted-by":"publisher","first-page":"2816","DOI":"10.1109\/TVLSI.2019.2941250","volume":"27","author":"S Kala","year":"2019","unstructured":"Kala S, Jose BR, Mathew J, Nalesh S (2019) High-performance cnn accelerator on fpga using unified winograd-gemm architecture. IEEE Trans Very Large Scale Integration (VLSI) Syst 27(12):2816\u20132828","journal-title":"IEEE Trans Very Large Scale Integration (VLSI) Syst"},{"key":"4251_CR13","doi-asserted-by":"crossref","unstructured":"Liao S, Samiee A, Deng C, Bai Y, Yuan B (2019) Compressing deep neural networks using toeplitz matrix: algorithm design and fpga implementation. In: ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 1443\u20131447. IEEE","DOI":"10.1109\/ICASSP.2019.8683556"},{"key":"4251_CR14","doi-asserted-by":"crossref","unstructured":"Lin M, Ji R, Wang Y, Zhang Y, Zhang B, Tian Y, Shao L (2020) Hrank: filter pruning using high-rank feature map. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 1529\u20131538","DOI":"10.1109\/CVPR42600.2020.00160"},{"key":"4251_CR15","doi-asserted-by":"crossref","unstructured":"Liu X, Yang J, Zou C, Chen Q, Yan X, Chen Y, Cai C (2021) Collaborative edge computing with fpga-based cnn accelerators for energy-efficient and time-aware face tracking system, pp 252\u2013266. IEEE","DOI":"10.1109\/TCSS.2021.3059318"},{"issue":"3","key":"4251_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3079758","volume":"10","author":"Z Liu","year":"2017","unstructured":"Liu Z, Dou Y, Jiang J, Xu J, Li S, Zhou Y, Xu Y (2017) Throughput-optimized fpga accelerator for deep convolutional neural networks. ACM Transactions on Reconfigurable Technology and Systems (TRETS) 10(3):1\u201323","journal-title":"ACM Transactions on Reconfigurable Technology and Systems (TRETS)"},{"key":"4251_CR17","doi-asserted-by":"crossref","unstructured":"Ma N, Zhang X, Zheng HT, Sun J (2018) Shufflenet v2: practical guidelines for efficient cnn architecture design. In: Proceedings of the European conference on computer vision (ECCV), pp 116\u2013 131","DOI":"10.1007\/978-3-030-01264-9_8"},{"issue":"2","key":"4251_CR18","doi-asserted-by":"publisher","first-page":"424","DOI":"10.1109\/TCAD.2018.2884972","volume":"39","author":"Y Ma","year":"2018","unstructured":"Ma Y, Cao Y, Vrudhula S, Seo Js (2018) Automatic compilation of diverse cnns onto high-performance fpga accelerators. IEEE Trans Comput-Aided Des Integrated Circ Syst 39(2):424\u2013 437","journal-title":"IEEE Trans Comput-Aided Des Integrated Circ Syst"},{"issue":"7","key":"4251_CR19","doi-asserted-by":"publisher","first-page":"1354","DOI":"10.1109\/TVLSI.2018.2815603","volume":"26","author":"Y Ma","year":"2018","unstructured":"Ma Y, Cao Y, Vrudhula S, Seo Js (2018) Optimizing the convolution operation to accelerate deep neural networks on fpga. IEEE Trans Very Large Scale Integration (VLSI) Syst 26(7):1354\u20131367","journal-title":"IEEE Trans Very Large Scale Integration (VLSI) Syst"},{"issue":"4","key":"4251_CR20","doi-asserted-by":"publisher","first-page":"843","DOI":"10.1109\/TCAD.2019.2897634","volume":"39","author":"Y Ma","year":"2019","unstructured":"Ma Y, Cao Y, Vrudhula S, Seo JS (2019) Performance modeling for cnn inference accelerators on fpga. IEEE Trans Comput-Aided Des Integr Circ Syst 39(4):843\u2013856","journal-title":"IEEE Trans Comput-Aided Des Integr Circ Syst"},{"key":"4251_CR21","unstructured":"Mathieu M, Henaff M, LeCun Y (2014) Fast training of convolutional networks through ffts. In: 2nd International Conference on Learning Representations, ICLR 2014"},{"key":"4251_CR22","doi-asserted-by":"publisher","first-page":"101887","DOI":"10.1016\/j.sysarc.2020.101887","volume":"113","author":"D Moolchandani","year":"2021","unstructured":"Moolchandani D, Kumar A, Sarangi SR (2021) Accelerating cnn inference on asics: a survey. J Syst Archit 113:101887","journal-title":"J Syst Archit"},{"key":"4251_CR23","doi-asserted-by":"publisher","first-page":"107628","DOI":"10.1016\/j.compeleceng.2021.107628","volume":"97","author":"AK Mukhopadhyay","year":"2022","unstructured":"Mukhopadhyay AK, Majumder S, Chakrabarti I (2022) Systematic realization of a fully connected deep and convolutional neural network architecture on a field programmable gate array. Comput Electr Eng 97:107628","journal-title":"Comput Electr Eng"},{"key":"4251_CR24","doi-asserted-by":"crossref","unstructured":"Palossi D, Conti F, Benini L (2019) An open source and open hardware deep learning-powered visual navigation engine for autonomous nano-uavs. In: 2019 15th International Conference on Distributed Computing in Sensor Systems (DCOSS), pp 604\u2013611. IEEE","DOI":"10.1109\/DCOSS.2019.00111"},{"key":"4251_CR25","doi-asserted-by":"crossref","unstructured":"Sandler M, Howard A, Zhu M, Zhmoginov A, Chen LC (2018) Mobilenetv2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 4510\u20134520","DOI":"10.1109\/CVPR.2018.00474"},{"issue":"6","key":"4251_CR26","first-page":"1941","volume":"65","author":"J Wang","year":"2017","unstructured":"Wang J, Lin J, Wang Z (2017) Efficient hardware architectures for deep convolutional neural network. IEEE Trans Circ Syst I: Regular Papers 65(6):1941\u20131953","journal-title":"IEEE Trans Circ Syst I: Regular Papers"},{"issue":"10","key":"4251_CR27","doi-asserted-by":"publisher","first-page":"2254","DOI":"10.1109\/TCAD.2019.2944584","volume":"39","author":"S Wang","year":"2019","unstructured":"Wang S, Ananthanarayanan G, Zeng Y, Goel N, Pathania A, Mitra T (2019) High-throughput cnn inference on embedded arm big. little multicore processors. IEEE Trans Comput-Aided Des Integr Circ Syst 39(10):2254\u20132267","journal-title":"IEEE Trans Comput-Aided Des Integr Circ Syst"},{"issue":"1","key":"4251_CR28","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1109\/TVLSI.2019.2939726","volume":"28","author":"Y Yu","year":"2019","unstructured":"Yu Y, Wu C, Zhao T, Wang K, He L (2019) Opu: an fpga-based overlay processor for convolutional neural networks. IEEE Trans Very Large Scale Integr VLSI Syst 28(1):35\u201347","journal-title":"IEEE Trans Very Large Scale Integr VLSI Syst"},{"key":"4251_CR29","doi-asserted-by":"crossref","unstructured":"Zeng H, Chen R, Zhang C, Prasanna V (2018) A framework for generating high throughput cnn implementations on fpgas. In: Proceedings of the 2018 ACM\/SIGDA international symposium on field-programmable gate arrays, pp 117\u2013126","DOI":"10.1145\/3174243.3174265"},{"key":"4251_CR30","doi-asserted-by":"crossref","unstructured":"Zhang C, Li P, Sun G, Guan Y, Xiao B, Cong J (2015) Optimizing fpga-based accelerator design for deep convolutional neural networks. In: Proceedings of the 2015 ACM\/SIGDA international symposium on field-programmable gate arrays, pp 161\u2013170","DOI":"10.1145\/2684746.2689060"},{"key":"4251_CR31","doi-asserted-by":"crossref","unstructured":"Zhang Y, Li X (2020) Fast convolutional neural networks with fine-grained ffts. In: Proceedings of the ACM international conference on parallel architectures and compilation techniques, pp 255\u2013265","DOI":"10.1145\/3410463.3414642"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-022-04251-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-022-04251-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-022-04251-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,31]],"date-time":"2023-05-31T06:31:03Z","timestamp":1685514663000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-022-04251-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,18]]},"references-count":31,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2023,6]]}},"alternative-id":["4251"],"URL":"https:\/\/doi.org\/10.1007\/s10489-022-04251-3","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,18]]},"assertion":[{"value":"7 October 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 October 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}