Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Cited by 272

The DOI matches its Crossref record; 518 of the 518 references it cites were found in a registry or an index.

Edge Intelligence: Empowering Intelligence to the Edge of Network

Open access
Xu, Dianlei, Li, Tong, Li, Yong, Su, Xiang, Tarkoma, Sasu, Jiang, Tao, Crowcroft, Jon, Hui, Pan · 2021 · Proceedings of the IEEE

Abstract

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.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/jproc.2021.3119950

Cites

518 of 518 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

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

Items 201–400 of 518

Research works printed but not linked: 66

  1. han, 2015, Learning both weights and connections for efficient neural network, Proc Adv Neural Inf Process Syst, 1135
  2. smith, 2017, Federated multi-task learning, Proc Adv Neural Inf Process Syst, 4424
  3. 10.1109/WACV45572.2020.9093331 · DOI
  4. 10.1145/3371154 · DOI
  5. 10.1145/2906388.2906405 · DOI
  6. tseng, 2017, When cars meet distributed computing: Data storage as an example, arXiv 1711 02014
  7. 10.1007/978-3-642-38652-7_2 · doi:10.1007/978-3-642-38652-7_2
  8. 10.1080/03071847.2019.1693801 · doi:10.1080/03071847.2019.1693801
  9. malki, 2003, CNN image processing on a Xilinx Virtex-II 6000, Proc ECCTD, 3, 261
  10. 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
  11. 10.2196/24207 · doi:10.2196/24207 · Paper page
  12. 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
  13. 10.1109/VNC.2016.7835943 · doi:10.1109/vnc.2016.7835943
  14. 10.1109/VNC51378.2020.9318400 · doi:10.1109/vnc51378.2020.9318400
  15. kim, 2015, Compression of deep convolutional neural networks for fast and low power mobile applications, arXiv 1511 06530
  16. 10.1145/1150402.1150464 · DOI · Paper page
  17. 2016, Cisco Visual Networking Index Global Mobile Data Traffic Forecast Update
  18. hu, 2015, Mobile edge computing—A key technology towards 5G, 11, 1
  19. 10.1109/LCN.2016.039 · doi:10.1109/lcn.2016.039
  20. 10.1007/s11265-006-4190-4 · DOI
  21. chen, 2019, FedHealth: A federated transfer learning framework for wearable healthcare, arXiv 1907 09173
  22. 10.1109/TCOMM.2020.3019527 · doi:10.1109/tcomm.2020.3019527
  23. 10.1109/GLOBECOM38437.2019.9013821 · doi:10.1109/globecom38437.2019.9013821
  24. 10.1145/3083187.3084016 · doi:10.1145/3083187.3084016
  25. 10.1109/WF-IoT.2015.7389148 · doi:10.1109/wf-iot.2015.7389148
  26. 10.1016/j.compenvurbsys.2017.12.005 · doi:10.1016/j.compenvurbsys.2017.12.005
  27. 10.1109/JIOT.2021.3049173 · doi:10.1109/jiot.2021.3049173
  28. 10.1109/ICITBS.2019.00104 · doi:10.1109/icitbs.2019.00104
  29. 10.1109/TCSI.2020.2966243 · doi:10.1109/tcsi.2020.2966243
  30. 2019, Microsoft HoloLens
  31. 2019, Google Street View Image API
  32. 10.1016/j.ecolind.2020.107124 · doi:10.1016/j.ecolind.2020.107124
  33. 10.1109/ICSCC.2019.8843640 · DOI
  34. 2019, Google Glass
  35. 10.1007/978-981-10-8339-6_6 · doi:10.1007/978-981-10-8339-6_6
  36. 10.3390/fi9040066 · doi:10.3390/fi9040066
  37. 10.1016/j.ins.2019.01.014 · doi:10.1016/j.ins.2019.01.014
  38. 10.1109/TVT.2013.2291811 · doi:10.1109/tvt.2013.2291811
  39. 10.1109/ACCESS.2019.2951587 · doi:10.1109/access.2019.2951587
  40. oskouei, 2015, GPU-based acceleration of deep convolutional neural networks on mobile platforms, Distrib Parallel Clust Comput
  41. 10.1002/wcm.2591 · doi:10.1002/wcm.2591
  42. 10.1109/INFOCOM.2015.7218644 · doi:10.1109/infocom.2015.7218644
  43. 10.1007/s00779-016-0932-x · doi:10.1007/s00779-016-0932-x
  44. 10.1109/JIOT.2016.2579198 · DOI · Paper page
  45. 10.1109/Oceans-Spain.2011.6003654 · doi:10.1109/oceans-spain.2011.6003654
  46. 10.1145/3152130.3152135 · doi:10.1145/3152130.3152135
  47. 10.1109/IUCC/DSCI/SmartCNS.2019.00126 · doi:10.1109/iucc/dsci/smartcns.2019.00126
  48. 10.1109/MCI.2006.329691 · doi:10.1109/mci.2006.329691 · Paper page
  49. 10.1109/TITS.2018.2877059 · DOI
  50. 10.1109/ACCESS.2016.2607719 · doi:10.1109/access.2016.2607719
  51. mazhar, 2019, Mobile crowdsensing application of road condition detection, Urdu News Headline Text Classification by Using Different Machine Learning Algorithms, 25
  52. 10.1109/COMSNETS.2018.8328270 · doi:10.1109/comsnets.2018.8328270
  53. 10.1145/2639189.2670273 · doi:10.1145/2639189.2670273
  54. 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
  55. 10.1109/ICSENS.2010.5690033 · doi:10.1109/icsens.2010.5690033
  56. 10.1145/3196494.3196532 · doi:10.1145/3196494.3196532
  57. 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
  58. 10.1109/ACCESS.2019.2918213 · doi:10.1109/access.2019.2918213
  59. 10.1016/j.procs.2015.05.043 · doi:10.1016/j.procs.2015.05.043
  60. chen, 2018, Understanding the limitations of existing energy-efficient design approaches for deep neural networks, Energy, 2, 3l
  61. 10.1109/ICWS49710.2020.00073 · doi:10.1109/icws49710.2020.00073
  62. polese, 2020, Machine learning at the edge: A data-driven architecture with applications to 5G cellular networks, IEEE Trans Mobile Comput
  63. 10.1109/ICCSE.2016.7581655 · doi:10.1109/iccse.2016.7581655
  64. motamedi, 2016, Fast and energy-efficient CNN inference on IoT devices, arXiv 1611 07151
  65. 10.1109/TNSE.2020.3033938 · doi:10.1109/tnse.2020.3033938
  66. 10.1016/j.procs.2015.05.038 · doi:10.1016/j.procs.2015.05.038

Cited by

See all 272

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
518
FWCI
15.17
Type
journal article
Language
en
Open access
green
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

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.