The DOI matches its Crossref record; 515 of the 515 references it cites were found in a registry or an index.
Edge Intelligence: Empowering Intelligence to the Edge of Network
Open accessAbstract
Edge intelligence refers to a set of connected systems and devices for data collection, caching, processing, and analysis proximity to where data are captured based on artificial intelligence. Edge intelligence aims at enhancing data processing and protects the privacy and security of the data and users. Although recently emerged, spanning the period from 2011 to now, this field of research has shown explosive growth over the past five years. In this article, we present a thorough and comprehensive survey of the literature surrounding edge intelligence. We first identify four fundamental components of edge intelligence, i.e., edge caching, edge training, edge inference, and edge offloading based on theoretical and practical results pertaining to proposed and deployed systems. We then aim for a systematic classification of the state of the solutions by examining research results and observations for each of the four components and present a taxonomy that includes practical problems, adopted techniques, and application goals. For each category, we elaborate, compare, and analyze the literature from the perspectives of adopted techniques, objectives, performance, advantages and drawbacks, and so on. This article provides a comprehensive survey of edge intelligence and its application areas. In addition, we summarize the development of the emerging research fields and the current state of the art and discuss the important open issues and possible theoretical and technical directions.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805
You Only Look Once: Unified, Real-Time Object Detection
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.91 · Cited by 53,803
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
Squeeze-and-Excitation Networks
Hu, J., Shen, L., & Sun, G. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00745 · Cited by 35,667
Histograms of Oriented Gradients for Human Detection
Dalal, N., & Triggs, B. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.177 · Cited by 33,584
Rethinking the Inception Architecture for Computer Vision
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.308 · Cited by 32,138
Research works printed but not linked: 67
- han, 2015, Learning both weights and connections for efficient neural network, Proc Adv Neural Inf Process Syst, 1135
- smith, 2017, Federated multi-task learning, Proc Adv Neural Inf Process Syst, 4424
- 10.1109/WACV45572.2020.9093331 · DOI
- 10.1145/3371154 · DOI
- 10.1145/2906388.2906405 · DOI
- tseng, 2017, When cars meet distributed computing: Data storage as an example, arXiv 1711 02014
- 10.1007/978-3-642-38652-7_2 · doi:10.1007/978-3-642-38652-7_2
- 10.1080/03071847.2019.1693801 · doi:10.1080/03071847.2019.1693801
- malki, 2003, CNN image processing on a Xilinx Virtex-II 6000, Proc ECCTD, 3, 261
- morris, 1971, tapered floating point: a new floating-point representation, IEEE Transactions on Computers, c 20, 1578, 10.1109/T-C.1971.223174 · doi:10.1109/t-c.1971.223174
- 10.2196/24207 · doi:10.2196/24207 · Paper page
- drolia, 2017, Precog: Prefetching for image recognition applications at the edge, Proc 2nd ACM/IEEE Symp Edge Comput, 17
- mavromoustakis, 2015, Analysis of vehicular storage and dissemination services based on floating content, Mobile Networks and Management, 141, 387, 10.1007/978-3-319-16292-8_28 · doi:10.1007/978-3-319-16292-8_28
- 10.1109/VNC.2016.7835943 · doi:10.1109/vnc.2016.7835943
- 10.1109/VNC51378.2020.9318400 · doi:10.1109/vnc51378.2020.9318400
- kim, 2015, Compression of deep convolutional neural networks for fast and low power mobile applications, arXiv 1511 06530
- 10.1145/1150402.1150464 · DOI · Paper page
- 2016, Cisco Visual Networking Index Global Mobile Data Traffic Forecast Update
- hu, 2015, Mobile edge computing—A key technology towards 5G, 11, 1
- 10.1109/LCN.2016.039 · doi:10.1109/lcn.2016.039
- 10.1007/s11265-006-4190-4 · doi:10.1007/s11265-006-4190-4
- chen, 2019, FedHealth: A federated transfer learning framework for wearable healthcare, arXiv 1907 09173
- 10.1109/TCOMM.2020.3019527 · doi:10.1109/tcomm.2020.3019527
- 10.1109/GLOBECOM38437.2019.9013821 · doi:10.1109/globecom38437.2019.9013821
- 10.1145/3083187.3084016 · doi:10.1145/3083187.3084016
- 10.1109/WF-IoT.2015.7389148 · doi:10.1109/wf-iot.2015.7389148
- 10.1016/j.compenvurbsys.2017.12.005 · doi:10.1016/j.compenvurbsys.2017.12.005
- 10.1109/JIOT.2021.3049173 · doi:10.1109/jiot.2021.3049173
- 10.1109/ICITBS.2019.00104 · doi:10.1109/icitbs.2019.00104
- 10.1109/TCSI.2020.2966243 · doi:10.1109/tcsi.2020.2966243
- 2019, Microsoft HoloLens
- 2019, Google Street View Image API
- 10.1016/j.ecolind.2020.107124 · doi:10.1016/j.ecolind.2020.107124
- 10.1109/ICSCC.2019.8843640 · doi:10.1109/icscc.2019.8843640
- 2019, Google Glass
- 10.1007/978-981-10-8339-6_6 · doi:10.1007/978-981-10-8339-6_6
- 10.3390/fi9040066 · doi:10.3390/fi9040066
- 10.1016/j.ins.2019.01.014 · doi:10.1016/j.ins.2019.01.014
- 10.1109/TVT.2013.2291811 · doi:10.1109/tvt.2013.2291811
- 10.1109/ACCESS.2019.2951587 · doi:10.1109/access.2019.2951587
- oskouei, 2015, GPU-based acceleration of deep convolutional neural networks on mobile platforms, Distrib Parallel Clust Comput
- 10.1002/wcm.2591 · doi:10.1002/wcm.2591
- 10.1109/INFOCOM.2015.7218644 · doi:10.1109/infocom.2015.7218644
- 10.1007/s00779-016-0932-x · doi:10.1007/s00779-016-0932-x
- 10.1109/JIOT.2016.2579198 · DOI · Paper page
- 10.1109/Oceans-Spain.2011.6003654 · doi:10.1109/oceans-spain.2011.6003654
- 10.1145/3152130.3152135 · doi:10.1145/3152130.3152135
- 10.1109/IUCC/DSCI/SmartCNS.2019.00126 · doi:10.1109/iucc/dsci/smartcns.2019.00126
- 10.1109/MCI.2006.329691 · doi:10.1109/mci.2006.329691 · Paper page
- 10.1109/TITS.2018.2877059 · doi:10.1109/tits.2018.2877059
- 10.1109/ACCESS.2016.2607719 · doi:10.1109/access.2016.2607719
- mazhar, 2019, Mobile crowdsensing application of road condition detection, Urdu News Headline Text Classification by Using Different Machine Learning Algorithms, 25
- 10.1109/COMSNETS.2018.8328270 · doi:10.1109/comsnets.2018.8328270
- 10.1145/2639189.2670273 · doi:10.1145/2639189.2670273
- marjanovi?, 2017, Air and noise pollution monitoring in the city of zagreb by using mobile crowdsensing, Proc 25th Int Conf Softw Telecommun Comput Netw (SoftCOM), 1
- 10.1109/ICSENS.2010.5690033 · doi:10.1109/icsens.2010.5690033
- 10.1145/3196494.3196532 · doi:10.1145/3196494.3196532
- liu, 2020, Scale-out edge storage systems with embedded storage nodes to get better availability and cost-efficiency at the same time, Proc 3rd USENIX Workshop Hot Topics Edge Comput (HotEdge), 1
- 10.1109/ACCESS.2019.2918213 · doi:10.1109/access.2019.2918213
- 10.1016/j.procs.2015.05.043 · doi:10.1016/j.procs.2015.05.043
- chen, 2018, Understanding the limitations of existing energy-efficient design approaches for deep neural networks, Energy, 2, 3l
- 10.1109/ICWS49710.2020.00073 · doi:10.1109/icws49710.2020.00073
- polese, 2020, Machine learning at the edge: A data-driven architecture with applications to 5G cellular networks, IEEE Trans Mobile Comput
- 10.1109/ICCSE.2016.7581655 · doi:10.1109/iccse.2016.7581655
- motamedi, 2016, Fast and energy-efficient CNN inference on IoT devices, arXiv 1611 07151
- 10.1109/TNSE.2020.3033938 · doi:10.1109/tnse.2020.3033938
- 10.1016/j.procs.2015.05.038 · doi:10.1016/j.procs.2015.05.038
Cited by
Efficient Acceleration of Deep Learning Inference on Resource-Constrained Edge Devices: A Review
Shuvo, M. M. H., Islam, S. K., Cheng, J., & Morshed, B. I. (2023) · Proceedings of the IEEE · doi:10.1109/jproc.2022.3226481 · Cited by 436
“3 illustrates the four essential elements of edge-AI [20]: 1) edge caching; 2) edge training; 3) EI; and 4) edge offloading.”
BackgroundEdge ai: leveraging the full potential of deep learning
Shuvo, M. M. H. (2022) · Studies in Computational Intelligence · doi:10.1007/978-3-031-14748-7_2 · Cited by 18
Lightweight Identification of Malicious IoT Traffic via Cross-View Knowledge Distillation
Nie, F., Liu, W., Liu, G., Gao, B., Huang, J., & Yuen, C. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3596167 · Cited by 1
Metadata
- Authors
- Xu, D., Li, T., Li, Y., Su, X., Tarkoma, S., Jiang, T., Crowcroft, J., & Hui, P.
- Venue
- Proceedings of the IEEE
- Published
- 2021-11
- Volume
- 109
- Issue
- 11
- Pages
- 1778-1837
- ISSN
- 0018-9219 (ISSN-L)
- 1558-2256
- OpenAlex
- W3210635777
- Cited by
- 272
- References
- 515
- FWCI
- 15.17
- Type
- journal article
- Language
- en
- Open access
- green
- Licence
- Funders
- National Key Research and Development Program of China (2020YFA0711400, 2020AAA0106000)
- National Natural Science Foundation of China (U1936217, 61971267, 61972223, 61941117, 61861136003)
- Beijing Natural Science Foundation (L182038)
- Beijing National Research Center for Information Science and Technology (20031887521)
- Academy of Finland (319669, 319670, 325570, 326305, 325774, 335934)
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Edge Intelligence: Empowering Intelligence to the Edge of Network. https://app.cochat.ai/papers/10.1109/jproc.2021.3119950
- The paper
- Xu, D., Li, T., Li, Y., Su, X., Tarkoma, S., Jiang, T., Crowcroft, J., & Hui, P. (2021). Edge Intelligence: Empowering Intelligence to the Edge of Network. Proceedings of the IEEE. https://doi.org/10.1109/jproc.2021.3119950
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.