{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T16:09:33Z","timestamp":1782403773288,"version":"3.54.5"},"reference-count":73,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,2,26]],"date-time":"2025-02-26T00:00:00Z","timestamp":1740528000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,2,26]],"date-time":"2025-02-26T00:00:00Z","timestamp":1740528000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Real-Time Image Proc"],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1007\/s11554-025-01647-5","type":"journal-article","created":{"date-parts":[[2025,2,26]],"date-time":"2025-02-26T21:20:18Z","timestamp":1740604818000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Accelerating convolutional neural networks on FPGA platforms: a high-performance design methodology using OpenCL"],"prefix":"10.1007","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6569-0116","authenticated-orcid":false,"given":"Soufien","family":"Gdaim","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abdellatif","family":"Mtibaa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,2,26]]},"reference":[{"key":"1647_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.120609","author":"JP Miranda Miguel","year":"2023","unstructured":"Miranda Miguel, J.P., et al.: Analysis of neural networks trained with evolutionary algorithms for the classification of breast cancer histological images. Expert Syst Appl (2023). https:\/\/doi.org\/10.1016\/j.eswa.2023.120609","journal-title":"Expert Syst Appl"},{"key":"1647_CR2","doi-asserted-by":"publisher","first-page":"1299","DOI":"10.1007\/s11280-020-00778-y","volume":"24","author":"Y Koo","year":"2021","unstructured":"Koo, Y., et al.: OpenCL-Darknet: implementation and optimization of OpenCL-based deep learning object detection framework. World Wide Web 24, 1299\u20131319 (2021). https:\/\/doi.org\/10.1007\/s11280-020-00778-y","journal-title":"World Wide Web"},{"key":"1647_CR3","unstructured":"Trinh D, et al.: Design and analysis of an FPGA-based CNN for exercise recognition, 2023 TRON symposium (TRONSHOW), Tokyo, Japan. pp. 1-8 (2023)"},{"key":"1647_CR4","doi-asserted-by":"publisher","unstructured":"Gao, Z., et al.: FPGA Implementation of CNN-LSTM Classifier in Speech Emotion Recognition System,\u00a02023 International Conference on High Performance Big Data and Intelligent Systems (HDIS), Macau, China. pp. 47\u201352 https:\/\/doi.org\/10.1109\/HDIS60872.2023.10499604 (2023)","DOI":"10.1109\/HDIS60872.2023.10499604"},{"issue":"1","key":"1647_CR5","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1109\/JAS.2020.1003474","volume":"8","author":"M Al-Sharman","year":"2021","unstructured":"Al-Sharman, M., et al.: A sensorless state estimation for a safety-oriented cyber-physical system in urban driving: deep learning approach. IEEE\/CAA J Autom Sinica 8(1), 169\u2013178 (2021). https:\/\/doi.org\/10.1109\/JAS.2020.1003474","journal-title":"IEEE\/CAA J Autom Sinica"},{"key":"1647_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.105972","author":"S Gdaim","year":"2023","unstructured":"Gdaim, S., Mtibaa, A., Mimouni, M.F.: Artificial neural network-based DTC of an induction machine with experimental implementation on FPGA. Eng Appl Artif Intell. (2023). https:\/\/doi.org\/10.1016\/j.engappai.2023.105972","journal-title":"Eng Appl Artif Intell."},{"key":"1647_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysarc.2022.102818","author":"Y Yan","year":"2023","unstructured":"Yan, Y., et al.: An efficient real-time accelerator for high-accuracy DNN-based optical flow estimation in FPGA. J Syst Archit (2023). https:\/\/doi.org\/10.1016\/j.sysarc.2022.102818","journal-title":"J Syst Archit"},{"key":"1647_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysarc.2021.102163","author":"S Mittal","year":"2021","unstructured":"Mittal, S., Gupta, H., Srivastava, S.: A survey on hardware security of DNN models and accelerators. J Syst Archit (2021). https:\/\/doi.org\/10.1016\/j.sysarc.2021.102163","journal-title":"J Syst Archit"},{"key":"1647_CR9","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-021-03795-4","author":"T Chia-Heng","year":"2021","unstructured":"Chia-Heng, T., Sun, Q., Mu-Hsuan, C.: On designing the adaptive computation framework of distributed deep learning models for Internet-of-Things applications. J Supercomput. (2021). https:\/\/doi.org\/10.1007\/s11227-021-03795-4","journal-title":"J Supercomput."},{"key":"1647_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.micpro.2022.104441","author":"R Machupalli","year":"2022","unstructured":"Machupalli, R., Hossain, M., Mandal, M.: Review of ASIC accelerators for deep neural network. Microprocess Microsyst (2022). https:\/\/doi.org\/10.1016\/j.micpro.2022.104441","journal-title":"Microprocess Microsyst"},{"key":"1647_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2019.04.016","author":"Y Jiang","year":"2019","unstructured":"Jiang, Y., et al.: BitStream: an efficient framework for inference of binary neural networks on CPUs. Pattern Recogn Lett (2019). https:\/\/doi.org\/10.1016\/j.patrec.2019.04.016","journal-title":"Pattern Recogn Lett"},{"key":"1647_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.mejo.2024.106197","author":"Y Liu","year":"2024","unstructured":"Liu, Y., et al.: Improving the computational efficiency and flexibility of FPGA-based CNN accelerator through loop optimization. Microelectron J (2024). https:\/\/doi.org\/10.1016\/j.mejo.2024.106197","journal-title":"Microelectron J"},{"key":"1647_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2023.110166","author":"M Nobari","year":"2023","unstructured":"Nobari, M., Jahanirad, H.: FPGA-based implementation of deep neural network using stochastic computing. Appl Soft Comput. (2023). https:\/\/doi.org\/10.1016\/j.asoc.2023.110166","journal-title":"Appl Soft Comput."},{"key":"1647_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10617-021-09256-8","volume":"26","author":"Y You","year":"2022","unstructured":"You, Y., et al.: New paradigm of FPGA-based computational intelligence from surveying the implementation of DNN accelerators. Des. Autom. Embed. Syst. 26, 1\u201327 (2022). https:\/\/doi.org\/10.1007\/s10617-021-09256-8","journal-title":"Des. Autom. Embed. Syst."},{"key":"1647_CR15","unstructured":"Hemsoth N, Morgan TP.: FPGA Frontiers: New Applications in Reconfigurable Computing. Next Platform Press, 16 janv. 2017. Accessed: 20\/08\/2024. Available: https:\/\/www.nextplatform.com\/2017\/01\/16\/fpga-frontiers-new-applications-reconfigurable-computing\/"},{"key":"1647_CR16","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1016\/j.procs.2024.03.217","volume":"233","author":"S Sreedhar Kumar","year":"2024","unstructured":"Sreedhar Kumar, S., et al.: Medical ChatBot assistance for primary clinical guidance using machine learning techniques. Proc Comput Sci. 233, 279\u2013287 (2024). https:\/\/doi.org\/10.1016\/j.procs.2024.03.217","journal-title":"Proc Comput Sci."},{"key":"1647_CR17","doi-asserted-by":"publisher","first-page":"100432","DOI":"10.1016\/j.mlwa.2022.100432","volume":"10","author":"N Aydin","year":"2022","unstructured":"Aydin, N., et al.: Prediction of financial distress of companies with artificial neural networks and decision trees models. Mach Learn Appl 10, 100432 (2022). https:\/\/doi.org\/10.1016\/j.mlwa.2022.100432","journal-title":"Mach Learn Appl"},{"key":"1647_CR18","doi-asserted-by":"publisher","first-page":"100467","DOI":"10.1016\/j.jii.2023.100467","volume":"34","author":"J Huang","year":"2023","unstructured":"Huang, J., et al.: A masked graph neural network model for real-time gastric polyp detection in Healthcare 4.0. J Ind Inf Integr 34, 100467 (2023). https:\/\/doi.org\/10.1016\/j.jii.2023.100467","journal-title":"J Ind Inf Integr"},{"key":"1647_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.renene.2023.02.130","author":"C Brester","year":"2023","unstructured":"Brester, C., et al.: Evaluating neural network models in site-specific solar PV forecasting using numerical weather prediction data and weather observations. Renew Energy (2023). https:\/\/doi.org\/10.1016\/j.renene.2023.02.130","journal-title":"Renew Energy"},{"issue":"2","key":"1647_CR20","doi-asserted-by":"publisher","first-page":"1627","DOI":"10.1007\/s10462-022-10209-1","volume":"56","author":"P Ma","year":"2023","unstructured":"Ma, P., et al.: A state-of-the-art survey of object detection techniques in microorganism image analysis: from classical methods to deep learning approaches. Artif. Intell. Rev. 56(2), 1627\u20131698 (2023). https:\/\/doi.org\/10.1007\/s10462-022-10209-1","journal-title":"Artif. Intell. Rev."},{"issue":"1","key":"1647_CR21","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000050","volume":"11","author":"J Li","year":"2022","unstructured":"Li, J., et al.: Recent advances in end-to-end automatic speech recognition. APSIPA Trans Signal Inf Process 11(1), e8 (2022). https:\/\/doi.org\/10.1561\/116.00000050","journal-title":"APSIPA Trans Signal Inf Process"},{"key":"1647_CR22","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1007\/s10462-022-10183-8","volume":"56","author":"JY-L Chan","year":"2023","unstructured":"Chan, J.Y.-L., et al.: State of the art: a review of sentiment analysis based on sequential transfer learning. Artif Intell Rev 56, 749\u2013780 (2023). https:\/\/doi.org\/10.1007\/s10462-022-10183-8","journal-title":"Artif Intell Rev"},{"key":"1647_CR23","doi-asserted-by":"publisher","unstructured":"Yan S, et al. Multiview transformers for video recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 3333\u20133343. https:\/\/doi.org\/10.48550\/arXiv.2201.04288","DOI":"10.48550\/arXiv.2201.04288"},{"key":"1647_CR24","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1007\/s10462-024-10721-6","volume":"57","author":"X Zhao","year":"2024","unstructured":"Zhao, X., et al.: A review of convolutional neural networks in computer vision. Artif. Intell. Rev. 57, 99 (2024). https:\/\/doi.org\/10.1007\/s10462-024-10721-6","journal-title":"Artif. Intell. Rev."},{"key":"1647_CR25","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1016\/j.vlsi.2021.08.004","volume":"81","author":"A Saidi","year":"2021","unstructured":"Saidi, A., et al.: FPGA-based implementation of classification techniques: a survey. Integration. 81, 280\u2013299 (2021). https:\/\/doi.org\/10.1016\/j.vlsi.2021.08.004","journal-title":"Integration."},{"key":"1647_CR26","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1016\/j.future.2022.07.009","volume":"137","author":"X Song","year":"2022","unstructured":"Song, X., Xie, T., Fischer, S.: Accelerating kNN search in high dimensional datasets on FPGA by reducing external memory access. Future Gen Comput Syst. 137, 189\u2013200 (2022). https:\/\/doi.org\/10.1016\/j.future.2022.07.009","journal-title":"Future Gen Comput Syst."},{"key":"1647_CR27","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3197906","author":"J Kim","year":"2022","unstructured":"Kim, J., Kang, J.-K., Kim, Y.: A low-cost fully integer-based CNN accelerator on FPGA for real-time traffic sign recognition. IEEE Access. (2022). https:\/\/doi.org\/10.1109\/ACCESS.2022.3197906","journal-title":"IEEE Access."},{"key":"1647_CR28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.matcom.2020.12.011","volume":"185","author":"G Prabakaran","year":"2021","unstructured":"Prabakaran, G., et al.: FPGA based effective agriculture productivity prediction system using fuzzy support vector machine. Math Comput Simul. 185, 1\u201316 (2021). https:\/\/doi.org\/10.1016\/j.matcom.2020.12.011","journal-title":"Math Comput Simul."},{"key":"1647_CR29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.vlsi.2022.11.005","volume":"89","author":"H Awano","year":"2023","unstructured":"Awano, H., Hashimoto, M.: B2N2: Resource efficient Bayesian neural network accelerator using Bernoulli sampler on FPGA. Integration. 89, 1\u20138 (2023). https:\/\/doi.org\/10.1016\/j.vlsi.2022.11.005","journal-title":"Integration."},{"key":"1647_CR30","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3017552","author":"N Paulino","year":"2020","unstructured":"Paulino, N., et al.: Optimizing OpenCL code for performance on FPGA: k-means case study with integer data sets. IEEE Access (2020). https:\/\/doi.org\/10.1109\/ACCESS.2020.3017552","journal-title":"IEEE Access"},{"key":"1647_CR31","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2017.39","author":"K Kara","year":"2017","unstructured":"Kara, K., et al.: FPGA-accelerated dense linear machine learning: a precision-convergence trade-off. 25th Annual International Symposium on Field-Programmable Custom Computing Machines. IEEE (2017). https:\/\/doi.org\/10.1109\/FCCM.2017.39","journal-title":"IEEE"},{"key":"1647_CR32","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1016\/j.procs.2022.04.036","volume":"202","author":"Z Wanga","year":"2022","unstructured":"Wanga, Z., et al.: Briefly analysis about CNN accelerator based on FPGA. International Conference on Identification, Information and Knowledge on the internet of Things, 2021. Proc Comput Sci. 202, 277\u2013282 (2022). https:\/\/doi.org\/10.1016\/j.procs.2022.04.036","journal-title":"Proc Comput Sci."},{"key":"1647_CR33","doi-asserted-by":"publisher","first-page":"23413","DOI":"10.1007\/s11042-016-4036-4","volume":"76","author":"H Tan","year":"2017","unstructured":"Tan, H., He, X., Wang, Z., Liu, G.: Parallel implementation and optimization of high-definition video real-time dehazing. Int J Multimed Tools Appl 76, 23413\u201323434 (2017). https:\/\/doi.org\/10.1007\/s11042-016-4036-4","journal-title":"Int J Multimed Tools Appl"},{"issue":"2","key":"1647_CR34","doi-asserted-by":"publisher","first-page":"262","DOI":"10.1007\/s10766-016-0425-6","volume":"45","author":"R Sotomayor","year":"2017","unstructured":"Sotomayor, R., et al.: Automatic CPU\/GPU generation of multi-versioned OpenCL Kernels for C++ Scientific Applications. Int. J. Parallel Prog. 45(2), 262\u2013282 (2017). https:\/\/doi.org\/10.1007\/s10766-016-0425-6","journal-title":"Int. J. Parallel Prog."},{"key":"1647_CR35","doi-asserted-by":"publisher","first-page":"17407","DOI":"10.1007\/s00521-021-06327-6","volume":"33","author":"M Yijie","year":"2021","unstructured":"Yijie, M., Salcic, Z.: Deep learning with accelerated execution: toward a real-time video analysis system. Neural Comput Appl. 33, 17407\u201317424 (2021). https:\/\/doi.org\/10.1007\/s00521-021-06327-6","journal-title":"Neural Comput Appl."},{"key":"1647_CR36","doi-asserted-by":"publisher","first-page":"105455","DOI":"10.1109\/ACCESS.2020.3000009","volume":"8","author":"S Li","year":"2020","unstructured":"Li, S., et al.: A Novel FPGA accelerator design for real-time and ultra-low power deep convolutional neural networks compared with Titan X GPU. IEEE Access. 8, 105455\u2013105471 (2020). https:\/\/doi.org\/10.1109\/ACCESS.2020.3000009","journal-title":"IEEE Access."},{"key":"1647_CR37","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1007\/s11554-017-0745-9","volume":"17","author":"S Tatsumi","year":"2020","unstructured":"Tatsumi, S., et al.: An FPGA accelerator for PatchMatch multi-view stereo using OpenCL. J. Real-Time Image Proc. 17, 215\u2013227 (2020). https:\/\/doi.org\/10.1007\/s11554-017-0745-9","journal-title":"J. Real-Time Image Proc."},{"key":"1647_CR38","doi-asserted-by":"publisher","first-page":"491","DOI":"10.1016\/j.sysarc.2019.02.013","volume":"97","author":"K Shata","year":"2019","unstructured":"Shata, K., Elteir, M., A. EL-Zoghabi,: Optimized implementation of OpenCL kernels on FPGAs. J Syst Archit 97, 491\u2013505 (2019). https:\/\/doi.org\/10.1016\/j.sysarc.2019.02.013","journal-title":"J Syst Archit"},{"key":"1647_CR39","doi-asserted-by":"publisher","first-page":"102922","DOI":"10.1016\/j.parco.2022.102922","volume":"111","author":"T Nakamura","year":"2022","unstructured":"Nakamura, T., et al.: Spatial- and time- division multiplexing in CNN accelerator. Parallel Comput. 111, 102922 (2022). https:\/\/doi.org\/10.1016\/j.parco.2022.102922","journal-title":"Parallel Comput."},{"key":"1647_CR40","doi-asserted-by":"publisher","unstructured":"Bensalem H, Blaqui\u00e8re Y, Savaria Y.: An Efficient OpenCL-Based Implementation of a SHA-3 Co-Processor on an FPGA-Centric Platform. In:\u00a0IEEE Transactions on Circuits and Systems II: Express Briefs. (2023) https:\/\/doi.org\/10.1109\/TCSII.2022.3223179.","DOI":"10.1109\/TCSII.2022.3223179"},{"key":"1647_CR41","doi-asserted-by":"publisher","first-page":"212979","DOI":"10.1109\/ACCESS.2020.3040081","volume":"8","author":"H Bensalem","year":"2020","unstructured":"Bensalem, H., Blaqui\u00e8re, Y., Savaria, Y.: In-FPGA instrumentation framework for OpenCL-based designs. IEEE Access 8, 212979\u2013212994 (2020). https:\/\/doi.org\/10.1109\/ACCESS.2020.3040081","journal-title":"IEEE Access"},{"key":"1647_CR42","doi-asserted-by":"publisher","unstructured":"Hu Y, Liu Y, Liu Z.: A Survey on Convolutional Neural Network Accelerators: GPU, FPGA and ASIC. 14th International Conference on Computer Research and Development (ICCRD), Shenzhen, China. pp. 100\u2013107. (2022) http:\/\/doi.https:\/\/doi.org\/10.1109\/ICCRD54409.2022.9730377.","DOI":"10.1109\/ICCRD54409.2022.9730377"},{"key":"1647_CR43","doi-asserted-by":"publisher","first-page":"1715","DOI":"10.1007\/s11277-024-11443-2","volume":"137","author":"A Samanta","year":"2024","unstructured":"Samanta, A., et al.: Survey on hardware accelerator design of deep learning for edge devices. Wireless Pers. Commun. 137, 1715\u20131760 (2024). https:\/\/doi.org\/10.1007\/s11277-024-11443-2","journal-title":"Wireless Pers. Commun."},{"key":"1647_CR44","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1016\/j.vlsi.2019.07.005","volume":"69","author":"X Feng","year":"2019","unstructured":"Feng, X., et al.: Computer vision algorithms and hardware implementations: a survey. Integration. 69, 309\u2013320 (2019). https:\/\/doi.org\/10.1016\/j.vlsi.2019.07.005","journal-title":"Integration."},{"key":"1647_CR45","doi-asserted-by":"publisher","first-page":"104188","DOI":"10.1016\/j.dsp.2023.104188","volume":"141","author":"S Zhao","year":"2023","unstructured":"Zhao, S., et al.: Acceleration and implementation of convolutional neural networks based on FPGA. Digital Signal Process 141, 104188 (2023). https:\/\/doi.org\/10.1016\/j.dsp.2023.104188","journal-title":"Digital Signal Process"},{"key":"1647_CR46","doi-asserted-by":"publisher","DOI":"10.1016\/j.micpro.2021.104363","author":"K Bjerge","year":"2021","unstructured":"Bjerge, K., et al.: A scalable and efficient convolutional neural network accelerator using HLS for a system-on-chip design. Microprocess Microsyst. (2021). https:\/\/doi.org\/10.1016\/j.micpro.2021.104363","journal-title":"Microprocess Microsyst."},{"key":"1647_CR47","doi-asserted-by":"publisher","unstructured":"Xiao Q, et al.: Exploring heterogeneous algorithms for accelerating deep convolutional neural networks on FPGAs. 54th ACM\/EDAC\/IEEE Design Automation Conference (DAC), Austin, TX, USA, pp. 1\u20136. (2017) https:\/\/doi.org\/10.1145\/3061639.3062244.","DOI":"10.1145\/3061639.3062244"},{"key":"1647_CR48","doi-asserted-by":"publisher","unstructured":"Ma Y, et al.: An automatic RTL compiler for high-throughput FPGA implementation of diverse deep convolutional neural networks. International Conference on Field Programmable Logic and Applications (FPL), Belgium. (2017) https:\/\/doi.org\/10.23919\/FPL.2017.8056824.","DOI":"10.23919\/FPL.2017.8056824"},{"key":"1647_CR49","unstructured":"Huyuan L.: Acceleration of Deep Learning on FPGA. Electronic Theses and Dissertations. University of Windsor. http:\/\/scholar.uwindsor.ca\/etd\/5947. (2017)"},{"key":"1647_CR50","volume-title":"An efficient FPGA accelerator design for optimized CNNs using OpenCL. Architecture of computing systems\u2014ARCS 2019. Lecture notes in computer science","author":"M Vemparala","year":"2019","unstructured":"Vemparala, M., Frickenstein, A., Stechele, W.: An efficient FPGA accelerator design for optimized CNNs using OpenCL. Architecture of computing systems\u2014ARCS 2019. Lecture notes in computer science, vol. 11479. Springer, Cham (2019)"},{"key":"1647_CR51","doi-asserted-by":"publisher","DOI":"10.1016\/j.memori.2023.100041","author":"RP Singh","year":"2023","unstructured":"Singh, R.P., et al.: A time domain 2D OaA-based convolutional neural networks accelerator. Memories Mater, Dev Circ Syst (2023). https:\/\/doi.org\/10.1016\/j.memori.2023.100041","journal-title":"Memories Mater, Dev Circ Syst"},{"issue":"4","key":"1647_CR52","doi-asserted-by":"publisher","first-page":"1591","DOI":"10.1109\/TCSI.2023.3234640","volume":"70","author":"S Kim","year":"2023","unstructured":"Kim, S., et al.: A CNN Inference Accelerator on FPGA With Compression and Layer-Chaining Techniques for Style Transfer Applications. IEEE Trans Circuits Syst I Regular Papers 70(4), 1591\u20131604 (2023). https:\/\/doi.org\/10.1109\/TCSI.2023.3234640","journal-title":"IEEE Trans Circuits Syst I Regular Papers"},{"key":"1647_CR53","doi-asserted-by":"publisher","DOI":"10.1016\/j.mejo.2024.106134","author":"J Cao","year":"2024","unstructured":"Cao, J., et al.: An optimized EEGNet processor for low-power and real-time EEG classification in wearable brain\u2013computer interfaces. Microelectron J (2024). https:\/\/doi.org\/10.1016\/j.mejo.2024.106134","journal-title":"Microelectron J"},{"key":"1647_CR54","doi-asserted-by":"publisher","unstructured":"Escobedo J, Lin M.: Graph-Theoretically Optimal Memory Banking for Stencil-Based Computing Kernels. International Symposium on Field-Programmable Gate Arrays ACM 2018. New York, USA. pp 199\u2013208. https:\/\/doi.org\/10.1145\/3174243.3174251","DOI":"10.1145\/3174243.3174251"},{"key":"1647_CR55","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-022-3772-8","volume":"66","author":"W He","year":"2023","unstructured":"He, W., et al.: Chip design with machine learning: a survey from algorithm perspective. SCIENCE CHINA Inf. Sci. 66, 211101 (2023). https:\/\/doi.org\/10.1007\/s11432-022-3772-8","journal-title":"SCIENCE CHINA Inf. Sci."},{"key":"1647_CR56","doi-asserted-by":"publisher","DOI":"10.1016\/j.cam.2022.114980","author":"S Stepanov","year":"2023","unstructured":"Stepanov, S., Spiridonov, D., Mai, T.: Prediction of numerical homogenization using deep learning for the Richards equation. J Comput Appl Math (2023). https:\/\/doi.org\/10.1016\/j.cam.2022.114980","journal-title":"J Comput Appl Math"},{"issue":"8","key":"1647_CR57","doi-asserted-by":"publisher","first-page":"10173","DOI":"10.1109\/TPAMI.2023.3250241","volume":"45","author":"L Huang","year":"2023","unstructured":"Huang, L., et al.: Normalization techniques in training dnns: methodology, analysis and application. IEEE Trans. Pattern Anal. Mach. Intell. 45(8), 10173\u201310196 (2023). https:\/\/doi.org\/10.1109\/TPAMI.2023.3250241","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1647_CR58","doi-asserted-by":"publisher","DOI":"10.1080\/02564602.2020.1740615","author":"MP Uddin","year":"2021","unstructured":"Uddin, M.P., Mamun, M.A., Hossain, M.A.: PCA-based feature reduction for hyperspectral remote sensing image classification. IETE Tech Rev (2021). https:\/\/doi.org\/10.1080\/02564602.2020.1740615","journal-title":"IETE Tech Rev"},{"key":"1647_CR59","doi-asserted-by":"publisher","first-page":"1266","DOI":"10.3390\/electronics11081266","volume":"11","author":"JA Pandian","year":"2022","unstructured":"Pandian, J.A., et al.: A five convolutional layer deep convolutional neural network for plant leaf disease detection. Electronics 11, 1266 (2022). https:\/\/doi.org\/10.3390\/electronics11081266","journal-title":"Electronics"},{"key":"1647_CR60","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2020.2978475","author":"X Zeng","year":"2020","unstructured":"Zeng, X., et al.: Addressing irregularity in sparse neural networks through a cooperative software\/hardware approach. IEEE Trans Comput (2020). https:\/\/doi.org\/10.1109\/TC.2020.2978475","journal-title":"IEEE Trans Comput"},{"key":"1647_CR61","doi-asserted-by":"publisher","DOI":"10.2991\/ijcis.d.200120.002","author":"HJ Jie","year":"2020","unstructured":"Jie, H.J., Wanda, P.: RunPool: a dynamic pooling layer for convolution neural network. International J Comput Intell Syst (2020). https:\/\/doi.org\/10.2991\/ijcis.d.200120.002","journal-title":"International J Comput Intell Syst"},{"key":"1647_CR62","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108797","author":"T Zheng","year":"2022","unstructured":"Zheng, T., et al.: Gradient rectified parameter unit of the fully connected layer in convolutional neural networks. Knowl-Based Syst (2022). https:\/\/doi.org\/10.1016\/j.knosys.2022.108797","journal-title":"Knowl-Based Syst"},{"key":"1647_CR63","doi-asserted-by":"publisher","first-page":"104824","DOI":"10.1016\/j.micpro.2023.104824","volume":"98","author":"R Gadea-Giron\u00e9s","year":"2023","unstructured":"Gadea-Giron\u00e9s, R., et al.: Task parallelism-based architectures on FPGA to optimize the energy efficiency of AI at the edge. Microprocess Microsyst. 98, 104824 (2023). https:\/\/doi.org\/10.1016\/j.micpro.2023.104824","journal-title":"Microprocess Microsyst."},{"key":"1647_CR64","unstructured":"GNU Project. (2001). gprof: The GNU Profiler. GNU Compiler Collection (GCC). Retrieved from https:\/\/ftp.gnu.org\/old-gnu\/Manuals\/gprof-2.9.1\/html_mono\/gprof.html"},{"key":"1647_CR65","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1145\/989393.989401","volume":"39","author":"SL Graham","year":"2004","unstructured":"Graham, S.L., Kessler, P.B., McKusick, M.K.: Gprof: A call graph execution profiler. ACM Sigplan Notices. 39, 49\u201357 (2004). https:\/\/doi.org\/10.1145\/989393.989401","journal-title":"ACM Sigplan Notices."},{"key":"1647_CR66","doi-asserted-by":"publisher","first-page":"419","DOI":"10.1016\/j.future.2023.12.003","volume":"153","author":"K Jurczuk","year":"2024","unstructured":"Jurczuk, K., et al.: Adaptive in-memory representation of decision trees for GPU-accelerated evolutionary induction. Futur. Gener. Comput. Syst. 153, 419\u2013430 (2024). https:\/\/doi.org\/10.1016\/j.future.2023.12.003","journal-title":"Futur. Gener. Comput. Syst."},{"key":"1647_CR67","doi-asserted-by":"publisher","DOI":"10.18517\/ijaseit.9.1.6948","author":"D Giardino","year":"2019","unstructured":"Giardino, D., et al.: FPGA implementation of hand-written number recognition based on CNN. Int J Adv Sci, Eng Inf Technol. (2019). https:\/\/doi.org\/10.18517\/ijaseit.9.1.6948","journal-title":"Int J Adv Sci, Eng Inf Technol."},{"key":"1647_CR68","doi-asserted-by":"publisher","unstructured":"Tsai TH, et al.: Implementation of FPGA-based Accelerator for Deep Neural Networks.\u00a0IEEE International Symposium on Design and Diagnostics of Electronic Circuits & Systems (DDECS), Cluj-Napoca, Romania. (2019) https:\/\/doi.org\/10.1109\/DDECS.2019.8724665","DOI":"10.1109\/DDECS.2019.8724665"},{"key":"1647_CR69","doi-asserted-by":"publisher","first-page":"14356","DOI":"10.1007\/s11227-021-03849-7","volume":"77","author":"I Westby","year":"2021","unstructured":"Westby, I., et al.: FPGA acceleration on a multi-layer perceptron neural network for digit recognition. J. Supercomput. 77, 14356\u201314373 (2021). https:\/\/doi.org\/10.1007\/s11227-021-03849-7","journal-title":"J. Supercomput."},{"key":"1647_CR70","doi-asserted-by":"publisher","unstructured":"Wu SY.: Research and implementation of FPGA-based convolutional neural network accelerator. IEEE 6th International Conference on Pattern Recognition and Artificial Intelligence (PRAI), Haikou, China. (2023) https:\/\/doi.org\/10.1109\/PRAI59366.2023.10332112","DOI":"10.1109\/PRAI59366.2023.10332112"},{"key":"1647_CR71","doi-asserted-by":"publisher","unstructured":"Yue Z, Ma J.: Design and Implementation of Handwritten Digit Recognition Accelerator Based on Systolic Array. The 3rd International Conference on Artificial Intelligence and Industrial Technology Applications (AIITA 2023), China. https:\/\/doi.org\/10.1088\/1742-6596\/2562\/1\/012078","DOI":"10.1088\/1742-6596\/2562\/1\/012078"},{"key":"1647_CR72","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10222859","author":"M Cho","year":"2021","unstructured":"Cho, M., Kim, Y.: FPGA-based convolutional neural network accelerator with resource-optimized approximate multiply-accumulate unit. Electronics (2021). https:\/\/doi.org\/10.3390\/electronics10222859","journal-title":"Electronics"},{"key":"1647_CR73","doi-asserted-by":"publisher","unstructured":"Rui Xiao, et al. FPGA Implementation of CNN for Handwritten Digit Recognition. 2020 IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference (ITNEC 2020). https:\/\/doi.org\/10.1109\/ITNEC48623.2020.9085002","DOI":"10.1109\/ITNEC48623.2020.9085002"}],"container-title":["Journal of Real-Time Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-025-01647-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11554-025-01647-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-025-01647-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,3]],"date-time":"2025-05-03T06:25:11Z","timestamp":1746253511000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11554-025-01647-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,26]]},"references-count":73,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,4]]}},"alternative-id":["1647"],"URL":"https:\/\/doi.org\/10.1007\/s11554-025-01647-5","relation":{},"ISSN":["1861-8200","1861-8219"],"issn-type":[{"value":"1861-8200","type":"print"},{"value":"1861-8219","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,26]]},"assertion":[{"value":"7 December 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 February 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 February 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All authors certify that they have no affiliations with or involvement in any organization or entity with any financial interest or non-financial interest in the subject matter or materials discussed in this manuscript. The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"67"}}