{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T15:00:25Z","timestamp":1773673225589,"version":"3.50.1"},"reference-count":34,"publisher":"MDPI AG","issue":"13","license":[{"start":{"date-parts":[[2021,6,30]],"date-time":"2021-06-30T00:00:00Z","timestamp":1625011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Natural Science Foundation of China","award":["61976098"],"award-info":[{"award-number":["61976098"]}]},{"name":"Technology Development Foundation of Quanzhou City","award":["2020C067"],"award-info":[{"award-number":["2020C067"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Edge-cloud collaborative inference can significantly reduce the delay of a deep neural network (DNN) by dividing the network between mobile edge and cloud. However, the in-layer data size of DNN is usually larger than the original data, so the communication time to send intermediate data to the cloud will also increase end-to-end latency. To cope with these challenges, this paper proposes a novel convolutional neural network structure\u2014BBNet\u2014that accelerates collaborative inference from two levels: (1) through channel-pruning: reducing the number of calculations and parameters of the original network; (2) through compressing the feature map at the split point to further reduce the size of the data transmitted. In addition, This paper implemented the BBNet structure based on NVIDIA Nano and the server. Compared with the original network, BBNet\u2019s FLOPs and parameter achieve up to 5.67\u00d7 and 11.57\u00d7 on the compression rate, respectively. In the best case, the feature compression layer can reach a bit-compression rate of 512\u00d7. Compared with the better bandwidth conditions, BBNet has a more obvious inference delay when the network conditions are poor. For example, when the upload bandwidth is only 20 kb\/s, the end-to-end latency of BBNet is increased by 38.89\u00d7 compared with the cloud-only approach.<\/jats:p>","DOI":"10.3390\/s21134494","type":"journal-article","created":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T02:44:39Z","timestamp":1625107479000},"page":"4494","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":23,"title":["BBNet: A Novel Convolutional Neural Network Structure in Edge-Cloud Collaborative Inference"],"prefix":"10.3390","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7007-9477","authenticated-orcid":false,"given":"Hongbo","family":"Zhou","sequence":"first","affiliation":[{"name":"College of Engineering, Huaqiao University, Quanzhou 362021, China"},{"name":"Fujian Provincial Academic Engineering Research Centre in Industrial Intellectual Techniques and Systems, Quanzhou 362021, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Engineering, Huaqiao University, Quanzhou 362021, China"},{"name":"Fujian Provincial Academic Engineering Research Centre in Industrial Intellectual Techniques and Systems, Quanzhou 362021, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengwei","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Engineering, Huaqiao University, Quanzhou 362021, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Ma","sequence":"additional","affiliation":[{"name":"College of Engineering, Huaqiao University, Quanzhou 362021, China"},{"name":"Fujian Provincial Academic Engineering Research Centre in Industrial Intellectual Techniques and Systems, Quanzhou 362021, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoran","family":"Yu","sequence":"additional","affiliation":[{"name":"College of Engineering, Huaqiao University, Quanzhou 362021, China"},{"name":"Fujian Provincial Academic Engineering Research Centre in Industrial Intellectual Techniques and Systems, Quanzhou 362021, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2021,6,30]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"142","DOI":"10.1109\/TPAMI.2015.2437384","article-title":"Region-Based Convolutional Networks for Accurate Object Detection and Segmentation","volume":"38","author":"Girshick","year":"2016","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"7457","DOI":"10.1109\/JIOT.2020.2984887","article-title":"Edge Intelligence: The Confluence of Edge Computing and Artificial Intelligence","volume":"7","author":"Deng","year":"2020","journal-title":"IEEE Internet Things J."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1738","DOI":"10.1109\/JPROC.2019.2918951","article-title":"Edge Intelligence: Paving the Last Mile of Artificial Intelligence with Edge Computing","volume":"107","author":"Zhou","year":"2019","journal-title":"Proc. IEEE"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"615","DOI":"10.1145\/3093336.3037698","article-title":"Neurosurgeon: Collaborative Intelligence between the Cloud and Mobile Edge","volume":"52","author":"Kang","year":"2017","journal-title":"ACM Sigplan Not."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Choi, H., and Baji\u0107, I.V. (2018, January 29\u201331). Near-Lossless Deep Feature Compression for Collaborative Intelligence. Proceedings of the 2018 IEEE 20th International Workshop on Multimedia Signal Processing (MMSP), Vancouver, BC, Canada.","DOI":"10.1109\/MMSP.2018.8547134"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Li, G., Liu, L., Wang, X., Dong, X., Zhao, P., and Feng, X. (2018, January 4\u20137). Auto-Tuning Neural Network Quantization Framework for Collaborative Inference between the Cloud and Edge. Proceedings of the Artificial Neural Networks and Machine Learning (ICANN 2018), Rhodes, Greece.","DOI":"10.1007\/978-3-030-01418-6_40"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Li, H., Hu, C., Jiang, J., Wang, Z., Wen, Y., and Zhu, W. (2018, January 11\u201313). Jalad: Joint Accuracy-and Latency-Aware Deep Structure Decoupling for Edge-Cloud Execution. Proceedings of the 2018 IEEE 24th International Conference on Parallel and Distributed Systems (ICPADS), Singapore.","DOI":"10.1109\/PADSW.2018.8645013"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"565","DOI":"10.1109\/TMC.2019.2947893","article-title":"Jointdnn: An Efficient Training and Inference Engine for Intelligent Mobile Cloud Computing Services","volume":"20","author":"Eshratifar","year":"2021","journal-title":"IEEE Trans. Mob. Comput."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"447","DOI":"10.1109\/TWC.2019.2946140","article-title":"Edge Ai: On-Demand Accelerating Deep Neural Network Inference Via Edge Computing","volume":"19","author":"Li","year":"2020","journal-title":"IEEE Trans. Wirel. Commun."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Eshratifar, A.E., Esmaili, A., and Pedram, M. (2019, January 29\u201331). Bottlenet: A Deep Learning Architecture for Intelligent Mobile Cloud Computing Services. Proceedings of the 2019 IEEE\/ACM International Symposium on Low Power Electronics and Design (ISLPED), Lausanne, Switzerland.","DOI":"10.1109\/ISLPED.2019.8824955"},{"key":"ref_11","unstructured":"Zhuang, L., Li, J., Shen, Z., Gao, H., and Zhang, C. (2017, January 22\u201329). Learning Efficient Convolutional Networks through Network Slimming. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy."},{"key":"ref_12","unstructured":"Baker, B., Gupta, O., Naik, N., and Raskar, R. (2017). Designing neural network architectures using reinforcement learning. arXiv."},{"key":"ref_13","unstructured":"Han, S., Mao, H., and Dally, W. (2015). Deep Compression: Compressing Deep Neural Network with Pruning, Trained Quantization and Huffman Coding. arXiv."},{"key":"ref_14","unstructured":"Chen, Z., Lin, W., Wang, S., Duan, L.Y., and Kot, A. (2018). Intermediate Deep Feature Compression: The Next Battlefield of Intelligent Sensing. arXiv."},{"key":"ref_15","unstructured":"Sutskever, I., Martens, J., Dahl, G., and Hinton, G. (2013, January 16\u201321). On the Importance of Initialization and Momentum in Deep Learning. Proceedings of the 30th International Conference on Machine Learning, Atlanta, GA, USA."},{"key":"ref_16","first-page":"38","article-title":"Distilling the Knowledge in a Neural Network","volume":"14","author":"Hinton","year":"2015","journal-title":"Comput. Sci."},{"key":"ref_17","unstructured":"Chintala, S. (2020, December 16). Training an Object Classifier in Torch-7 on Multiple gpus over Imagenet. Available online: https:\/\/github.com\/soumith\/imagenet-multiGPU.torch."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Teerapittayanon, S., McDanel, B., and Kung, H.T. (2017, January 5\u20138). Distributed Deep Neural Networks over the Cloud, the Edge and End Devices. Proceedings of the 2017 IEEE 37th International Conference on Distributed Computing Systems (ICDCS), Atlanta, GA, USA.","DOI":"10.1109\/ICDCS.2017.226"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1109\/MNET.001.1800506","article-title":"Boomerang: On-Demand Cooperative Deep Neural Network Inference for Edge Intelligence on the Industrial Internet of Things","volume":"33","author":"Zeng","year":"2019","journal-title":"IEEE Netw."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Zhang, C., Dong, M., and Ota, K. (2020, January 6\u20138). Accelerate Deep Learning in Iot: Human-Interaction Co-Inference Networking System for Edge. Proceedings of the 2020 13th International Conference on Human System Interaction (HSI), Tokyo, Japan.","DOI":"10.1109\/HSI49210.2020.9142631"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"595","DOI":"10.1109\/TNET.2020.3042320","article-title":"Coedge: Cooperative Dnn Inference with Adaptive Workloa d Partitioning over Heterogeneous Edge Devices","volume":"29","author":"Zeng","year":"2021","journal-title":"IEEE\/ACM Trans. Netw."},{"key":"ref_22","unstructured":"Wu, Q., Chen, X., Zhou, Z., and Zhang, J. (2020). Fedhome: Cloud-Edge Based Personalized Federated Learning for in-Home Health Monitoring. IEEE Trans. Mob. Comput."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"102133","DOI":"10.1016\/j.sysarc.2021.102133","article-title":"Dynamic Resource Allocation for Jointing Vehicle-Edge Deep Neural Network Inference","volume":"117","author":"Wang","year":"2021","journal-title":"J. Syst. Archit."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Tishby, N., and Zaslavsky, N. (May, January 26). Deep Learning and the Information Bottleneck Principle. Proceedings of the 2015 IEEE Information Theory Workshop (ITW), Jerusalem, Israel.","DOI":"10.1109\/ITW.2015.7133169"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Luo, S., Yang, Y., Yin, Y., Shen, C., Zhao, Y., and Song, M. (2018, January 13\u201316). Deepsic: Deep Semantic Image Compression. Proceedings of the ICONIP 2018, Siem Reap, Cambodia.","DOI":"10.1007\/978-3-030-04167-0_9"},{"key":"ref_26","unstructured":"Luo, S., Yang, Y., Yin, Y., Shen, C., Zhao, Y., and Song, M. (2019, January 22\u201325). Deepsic: Multi-Task Learning with Compressible Features for Collaborative Intelligence. Proceedings of the 2019 IEEE International Conference on Image Processing (ICIP), Taipei, Taiwan."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"2295","DOI":"10.1109\/JPROC.2017.2761740","article-title":"Efficient Processing of Deep Neural Networks: A Tutorial and Survey","volume":"105","author":"Sze","year":"2017","journal-title":"Proc. IEEE"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Shao, J., and Zhang, J. (2020, January 7\u201311). Bottlenet++: An End-to-End Approach for Feature Compression in Device-Edge Co-Inference Systems. Proceedings of the 2020 IEEE International Conference on Communications Workshops (ICC Workshops), Dublin, Ireland.","DOI":"10.1109\/ICCWorkshops49005.2020.9145068"},{"key":"ref_29","unstructured":"Mulhollon, V. (2021, May 10). Wondershaper. Available online: http:\/\/manpages.ubuntu.com\/manpages\/trusty\/man8\/wondershaper.8.html."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep Residual Learning for Image Recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Los Alamitos, CA, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_31","unstructured":"Gross, S., and Wilber, M. (2020, November 26). cifar.torch. Available online: https:\/\/github.com\/szagoruyko\/cifar.torch."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Huang, G., Sun, Y., Liu, Z., Sedra, D., and Weinberger, K.Q. (2016, January 11\u201314). Deep Networks with Stochastic Depth. Proceedings of the Computer Vision\u2014ECCV 2016, Amsterdam, The Netherlands.","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"ref_33","unstructured":"Lin, M., Chen, Q., and Yan, S. (2014). Network in Network. arXiv."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1109\/MCOM.001.2000373","article-title":"Communication-Computation Trade-Off in Resource-Constrained Edge Inference","volume":"58","author":"Shao","year":"2020","journal-title":"IEEE Commun. Mag."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/13\/4494\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T06:24:22Z","timestamp":1760163862000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/13\/4494"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,30]]},"references-count":34,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2021,7]]}},"alternative-id":["s21134494"],"URL":"https:\/\/doi.org\/10.3390\/s21134494","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,6,30]]}}}