{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T06:40:17Z","timestamp":1771656017613,"version":"3.50.1"},"reference-count":31,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"19","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Electron. Express"],"published-print":{"date-parts":[[2022,10,10]]},"DOI":"10.1587\/elex.19.20220370","type":"journal-article","created":{"date-parts":[[2022,9,7]],"date-time":"2022-09-07T22:08:46Z","timestamp":1662588526000},"page":"20220370-20220370","source":"Crossref","is-referenced-by-count":8,"title":["Design and implementation of an efficient CNN accelerator for low-cost FPGAs"],"prefix":"10.1587","volume":"19","author":[{"given":"Yan","family":"Xu","sequence":"first","affiliation":[{"name":"School of Microelectronics, Hefei University of Technology"}]},{"given":"Shuaishuai","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Microelectronics, Hefei University of Technology"}]},{"given":"Ning","family":"Li","sequence":"additional","affiliation":[{"name":"School of Microelectronics, Hefei University of Technology"}]},{"given":"Hao","family":"Xiao","sequence":"additional","affiliation":[{"name":"School of Microelectronics, Hefei University of Technology"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"crossref","unstructured":"[1] J. Duan and X. Liu: \u201cOnline monitoring of green pellet size distribution in haze-degraded images based on VGG16-LU-net and haze judgment,\u201d IEEE Trans. Instrum. Meas. <b>70<\/b> (2021) 1 (DOI: 10.1109\/TIM.2021.3052018).","DOI":"10.1109\/TIM.2021.3052018"},{"key":"2","doi-asserted-by":"crossref","unstructured":"[2] B. Li and Y. He: \u201cAn improved ResNet based on the adjustable shortcut connections,\u201d IEEE Access <b>6<\/b> (2018) 18967 (DOI: 10.1109\/ACCESS.2018.2814605).","DOI":"10.1109\/ACCESS.2018.2814605"},{"key":"3","doi-asserted-by":"crossref","unstructured":"[3] X. Shi, <i>et al.<\/i>: \u201cAn improved bearing fault diagnosis scheme based on hierarchical fuzzy entropy and alexnet network,\u201d IEEE Access <b>9<\/b> (2021) 61710 (DOI: 10.1109\/ACCESS.2018.2814605).","DOI":"10.1109\/ACCESS.2021.3073708"},{"key":"4","doi-asserted-by":"crossref","unstructured":"[4] F. Chollet: \u201cXception: deep learning with depthwise separable convolutions,\u201d CVPR (2017) 1800 (DOI: 10.1109\/CVPR.2017.195).","DOI":"10.1109\/CVPR.2017.195"},{"key":"5","doi-asserted-by":"crossref","unstructured":"[5] M. Sandler, <i>et al.<\/i>: \u201cMobileNetV2: inverted residuals and linear bottlenecks,\u201d CVPR (2018) 4510 (DOI: 10.1109\/CVPR.2018.00474).","DOI":"10.1109\/CVPR.2018.00474"},{"key":"6","doi-asserted-by":"crossref","unstructured":"[6] H. Pan, <i>et al.<\/i>: \u201cA new image recognition and classification method combining transfer learning algorithm and mobilenet model for welding defects,\u201d IEEE Access <b>8<\/b> (2020) 119951 (DOI: 10.1109\/ACCESS.2020.3005450).","DOI":"10.1109\/ACCESS.2020.3005450"},{"key":"7","doi-asserted-by":"crossref","unstructured":"[7] K. Kadam, <i>et al.<\/i>: \u201cDetection and localization of multiple image splicing using MobileNet V1,\u201d IEEE Access <b>9<\/b> (2021) 162499 (DOI: 10.1109\/ACCESS.2021.3130342).","DOI":"10.1109\/ACCESS.2021.3130342"},{"key":"8","doi-asserted-by":"crossref","unstructured":"[8] X. Zhang, <i>et al.<\/i>: \u201cShuffleNet: an extremely efficient convolutional neural network for mobile devices,\u201d CVPR (2018) 6848 (DOI: 10.1109\/CVPR.2018.00716).","DOI":"10.1109\/CVPR.2018.00716"},{"key":"9","doi-asserted-by":"crossref","unstructured":"[9] B. Jacob, <i>et al.<\/i>: \u201cQuantization and training of neural networks for efficient integer-arithmetic-only inference,\u201d CVPR (2018) 2704 (DOI: 10.1109\/CVPR.2018.00286).","DOI":"10.1109\/CVPR.2018.00286"},{"key":"10","doi-asserted-by":"crossref","unstructured":"[10] X. Wei, <i>et al.<\/i>: \u201cMixed-precision quantization for CNN-based remote sensing scene classification,\u201d IEEE Geosci. Remote Sens. Lett. <b>18<\/b> (2021) 1721 (DOI: 10.1109\/LGRS.2020.3007575).","DOI":"10.1109\/LGRS.2020.3007575"},{"key":"11","doi-asserted-by":"crossref","unstructured":"[11] J. Xu, <i>et al.<\/i>: \u201cA memory-efficient CNN accelerator using segmented logarithmic quantization and multi-cluster architecture,\u201d IEEE Trans. Circuits Syst. II, Exp. Briefs <b>68<\/b> (2021) 2142 (DOI: 10.1109\/TCSII.2020.3038897).","DOI":"10.1109\/TCSII.2020.3038897"},{"key":"12","doi-asserted-by":"crossref","unstructured":"[12] J. Shan, <i>et al.<\/i>: \u201cPower-optimal mapping of CNN applications to cloud-based multi-FPGA platforms,\u201d IEEE Trans. Circuits Syst. II, Exp. Briefs <b>67<\/b> (2020) 3073 (DOI: 10.1109\/TCSII.2020.2998284).","DOI":"10.1109\/TCSII.2020.2998284"},{"key":"13","doi-asserted-by":"crossref","unstructured":"[13] J. Li, <i>et al.<\/i>: \u201cSqueezeFlow: a sparse CNN accelerator exploiting concise convolution rules,\u201d IEEE Trans. Comput. <b>68<\/b> (2019) 1663 (DOI: 10.1109\/TC.2019.2924215).","DOI":"10.1109\/TC.2019.2924215"},{"key":"14","doi-asserted-by":"crossref","unstructured":"[14] T. Wang, <i>et al.<\/i>: \u201cFPDeep: scalable acceleration of CNN training on deeply-pipelined FPGA clusters,\u201d IEEE Trans. Comput. <b>69<\/b> (2020) 1143 (DOI: 10.1109\/TC.2020.3000118).","DOI":"10.1109\/TC.2020.3000118"},{"key":"15","doi-asserted-by":"crossref","unstructured":"[15] N.M. Cicek, <i>et al.<\/i>: \u201cGeneral reuse-centric CNN accelerator,\u201d IEEE Trans. Comput. <b>71<\/b> (2022) 880 (DOI: 10.1109\/TC.2021.3064608).","DOI":"10.1109\/TC.2021.3064608"},{"key":"16","doi-asserted-by":"crossref","unstructured":"[16] B. Li, <i>et al.<\/i>: \u201cDynamic dataflow scheduling and computation mapping techniques for efficient depthwise separable convolution acceleration,\u201d IEEE Trans. Circuits Syst. I, Reg. Papers <b>68<\/b> (2021) 3279 (DOI: 10.1109\/TCSI.2021.3078541).","DOI":"10.1109\/TCSI.2021.3078541"},{"key":"17","doi-asserted-by":"crossref","unstructured":"[17] J. Kim, <i>et al.<\/i>: \u201cA resource efficient integer-arithmetic-only FPGA-based CNN accelerator for real-time facial emotion recognition,\u201d IEEE Access <b>9<\/b> (2021) 104367 (DOI: 10.1109\/ACCESS.2021.3099075).","DOI":"10.1109\/ACCESS.2021.3099075"},{"key":"18","doi-asserted-by":"crossref","unstructured":"[18] J. Faraone, <i>et al.<\/i>: \u201cAddNet: deep neural networks using FPGA-optimized multipliers,\u201d IEEE Trans. Very Large Scale Integr. (VLSI) Syst. <b>28<\/b> (2020) 115 (DOI: 10.1109\/TVLSI.2019.2939429).","DOI":"10.1109\/TVLSI.2019.2939429"},{"key":"19","doi-asserted-by":"crossref","unstructured":"[19] D.T. Nguyen, <i>et al.<\/i>: \u201cA high-throughput and power-efficient FPGA implementation of YOLO CNN for object detection,\u201d IEEE Trans. Very Large Scale Integr. (VLSI) Syst. <b>27<\/b> (2019) 1861 (DOI: 10.1109\/TVLSI.2019.2905242).","DOI":"10.1109\/TVLSI.2019.2905242"},{"key":"20","doi-asserted-by":"crossref","unstructured":"[20] H. Xiao, <i>et al.<\/i>: \u201cEfficient hardware accelerator for compressed sparse deep neural network,\u201d IEICE Trans. Inf. &amp; Syst. <b>E104-D<\/b> (2021) 772 (DOI: 10.1587\/transinf.2020EDL8153).","DOI":"10.1587\/transinf.2020EDL8153"},{"key":"21","doi-asserted-by":"crossref","unstructured":"[21] D.T. Nguyen, <i>et al.<\/i>: \u201cLayer-specific optimization for mixed data flow with mixed precision in FPGA design for CNN-based object detectors,\u201d IEEE Trans. Circuits Syst. Video Technol. <b>32<\/b> (2021) 2450 (DOI: 10.1109\/TCSVT.2020.3020569).","DOI":"10.1109\/TCSVT.2020.3020569"},{"key":"22","doi-asserted-by":"crossref","unstructured":"[22] L. Bai, <i>et al.<\/i>: \u201cA CNN accelerator on FPGA using depthwise separable convolution,\u201d IEEE Trans. Circuits Syst. II, Exp. Briefs <b>65<\/b> (2018) 1415 (DOI: 10.1109\/TCSII.2018.2865896).","DOI":"10.1109\/TCSII.2018.2865896"},{"key":"23","doi-asserted-by":"crossref","unstructured":"[23] F. Liu, <i>et al.<\/i>: \u201cCASSANN-v2: a high-performance CNN accelerator architecture with on-chip memory self-adaptive tuning,\u201d IEICE Electron. Express <b>19<\/b> (2022) 20220124 (DOI: 10.1587\/elex.19.20220124).","DOI":"10.1587\/elex.19.20220124"},{"key":"24","doi-asserted-by":"crossref","unstructured":"[24] F. Zhang, <i>et al.<\/i>: \u201cHFOD: a hardware-friendly quantization method for object detection on embedded FPGAs,\u201d IEICE Electron. Express <b>19<\/b> (2012) 20220067 (DOI: 10.1587\/elex.19.20220067).","DOI":"10.1587\/elex.19.20220067"},{"key":"25","doi-asserted-by":"crossref","unstructured":"[25] F. Zhang, <i>et al.<\/i>: \u201cHFOD: a hardware-friendly quantization method for object detection on embedded FPGAs,\u201d IEICE Electron. Express <b>19<\/b> (2012) 20220067 (DOI: 10.1587\/elex.19.20220067).","DOI":"10.1587\/elex.19.20220067"},{"key":"26","doi-asserted-by":"crossref","unstructured":"[26] M. Arredondo-Vel\u00e1zquez, <i>et al.<\/i>: \u201cA streaming accelerator of convolutional neural networks for resource-limited applications,\u201d IEICE Electron. Express <b>16<\/b> (2019) 20190633 (DOI: 10.1587\/elex.16.20190633).","DOI":"10.1587\/elex.16.20190633"},{"key":"27","doi-asserted-by":"crossref","unstructured":"[27] H. Jia, <i>et al.<\/i>: \u201cAn FPGA-based accelerator for deep neural network with novel reconfigurable architecture,\u201d IEICE Electron. Express <b>18<\/b> (2021) 20210012 (DOI: 10.1587\/elex.18.20210012).","DOI":"10.1587\/elex.18.20210012"},{"key":"28","doi-asserted-by":"crossref","unstructured":"[28] Y. Huang, <i>et al.<\/i>: \u201cMALMM: a multi-array architecture for large-scale matrix multiplication on FPGA,\u201d IEICE Electron. Express <b>15<\/b> (2021) 20180286 (DOI: 10.1587\/elex.15.20180286).","DOI":"10.1587\/elex.15.20180286"},{"key":"29","doi-asserted-by":"crossref","unstructured":"[29] L. Zong-ling, <i>et al.<\/i>: \u201cThe design of lightweight and multi parallel cnn accelerator based on FPGA,\u201d ITAIC (2019) 1521 (DOI: 10.1109\/ITAIC.2019.8785800).","DOI":"10.1109\/ITAIC.2019.8785800"},{"key":"30","doi-asserted-by":"crossref","unstructured":"[30] N.K. Shaydyuk and E.B. John: \u201cFPGA implementation of MobileNeTv2 CNN model using semi-streaming architecture for low power inference applications,\u201d ISPA (2020) 160 (DOI: 10.1109\/ISPA-BDCloud-SocialCom-SustainCom51426.2020.00046).","DOI":"10.1109\/ISPA-BDCloud-SocialCom-SustainCom51426.2020.00046"},{"key":"31","doi-asserted-by":"crossref","unstructured":"[31] X. Xie, <i>et al.<\/i>: \u201cAn efficient and flexible accelerator design for sparse convolutional neural networks,\u201d IEEE Trans. Circuits Syst. I, Reg. Papers <b>68<\/b> (2021) 2936 (DOI: 10.1109\/TCSI.2021.3074300).","DOI":"10.1109\/TCSI.2021.3074300"}],"container-title":["IEICE Electronics Express"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/elex\/19\/19\/19_19.20220370\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,15]],"date-time":"2022-10-15T03:21:01Z","timestamp":1665804061000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/elex\/19\/19\/19_19.20220370\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,10]]},"references-count":31,"journal-issue":{"issue":"19","published-print":{"date-parts":[[2022]]}},"URL":"https:\/\/doi.org\/10.1587\/elex.19.20220370","relation":{},"ISSN":["1349-2543"],"issn-type":[{"value":"1349-2543","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,10]]},"article-number":"19.20220370"}}