The DOI matches its Crossref record; 140 of the 168 references it cites were found in a registry or an index; 10 of the 54 sources its claims cite were checked for support.
Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing
Open accessAbstract
With the breakthroughs in deep learning, the recent years have witnessed a booming of artificial intelligence (AI) applications and services, spanning from personal assistant to recommendation systems to video/audio surveillance. More recently, with the proliferation of mobile computing and Internet of Things (IoT), billions of mobile and IoT devices are connected to the Internet, generating zillions bytes of data at the network edge. Driving by this trend, there is an urgent need to push the AI frontiers to the network edge so as to fully unleash the potential of the edge big data. To meet this demand, edge computing, an emerging paradigm that pushes computing tasks and services from the network core to the network edge, has been widely recognized as a promising solution. The resulted new interdiscipline, edge AI or edge intelligence (EI), is beginning to receive a tremendous amount of interest. However, research on EI is still in its infancy stage, and a dedicated venue for exchanging the recent advances of EI is highly desired by both the computer system and AI communities. To this end, we conduct a comprehensive survey of the recent research efforts on EI. Specifically, we first review the background and motivation for AI running at the network edge. We then provide an overview of the overarching architectures, frameworks, and emerging key technologies for deep learning model toward training/inference at the network edge. Finally, we discuss future research opportunities on EI. We believe that this survey will elicit escalating attentions, stimulate fruitful discussions, and inspire further research ideas on EI.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
10 of 54 cited sources checked · 4 supported · 0 flagged · accuracy not yet measured
Every source the paper cites for this claim was checked and supports it.
In the paper
“Stamoulis et al. [106] cast the adaptive DNN model selection issue as a hyperparameter optimization problem by taking into account the accuracy and communication constraints imposed by the devices.Then, a Bayesian optimization (BO) is adopted to solve this problem, achieving an improvement by up to 6× in terms of minimum energy per image under accuracy constraints.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > Park et al.
What the sources say
- Supportedcites [106] 106. D. Stamoulis et al., "Designing adaptive neural networks for energy-constrained image classification," in Proc. ACM ICCAD, 2018, Art. no. 23. source
Section 4.1 (p. 4) formulates adaptive CNN design, including network selection, as a hyperparameter optimization problem. Section 4.2 (p. 4) says the authors adapt Bayesian optimization to solve it, and the Conclusion (p. 8) reports up to 6× lower minimum energy per image under accuracy constraints than previously published methods. (LLM, conf=0.94)
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passes- Supported
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“The result varies with architectures and transfer techniques.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 4) DNN Splitting:
What the sources say
- Not checked — no full text of the sourcecites [62] 62. R. Sharma, S. Biookaghazadeh, B. Li, and M. Zhao, "Are existing knowledge transfer techniques effective for deep learning with edge devices?" in Proc. IEEE Int. Conf. Edge Comput. (EDGE), Jul. 2018, pp. 42-49. source
- Could not verifycites [44] 44. Q. Chen, Z. Zheng, C. Hu, D. Wang, and F. Liu, "Data-driven task allocation for multi-task transfer learning on the edge," in Proc. IEEE 39th Int. Conf. Distrib. Comput. Syst. (ICDCS), 2019. sourceExperimental — accuracy not yet measured
Section 5.2.2 (p. 6) reports accuracy for one architecture under different distributed-training conditions, but does not compare architectures or transfer-learning techniques. Section 6 (p. 6) calls studies of other DNN architectures future work. Searches for transfer learning and variation across architectures or transfer techniques found no passage addressing the claim. (LLM, conf=0.76)
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesThe cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“Cachier can increase responsiveness by 3× or more.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 4) Edge Caching:
What the sources say
- Could not verifycites [93] 93. U. Drolia, K. Guo, J. Tan, R. Gandhi, and P. Narasimhan, "Cachier: Edge-caching for recognition applications," in Proc. IEEE ICDCS, Jun. 2017, pp. 276-286. sourceExperimental — accuracy not yet measured
The Results section discusses Edgent’s inference latency, but does not report a result for Cachier. Searches for “Cachier” and “responsiveness three times” found no passage supporting a 3× improvement. (LLM, conf=0.77)
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passes- Could not verify
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Data Generated at the Network Edge Need AI to Fully Unlock Their Potential”
- Also stated in: § A. Motivation and Benefits of Edge Intelligence · boosted
“AI will be functionally necessary due to its ability to quickly analyze those huge data volumes and extract insights from them for high-quality decision making.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > A. Motivation and Benefits of Edge Intelligence
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes- Also stated in: § A. Motivation and Benefits of Edge Intelligence · boosted
In the paper
“Cisco estimates that nearly 850 ZB will be generated by all people, machines, and things at the network edge by 2021 [3].”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > I. I N T R O D U C T I O N
What the sources say
- Not matchedcites [3] 3. Cisco Global Cloud Index: Forecast and Methodology, 2016-2021, White Paper. [Online]. Available: https://www.cisco.com/c/en/us/ solutions/collateral/service-provider/global- cloud-index-gci/white-paper-c11-738085.html
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Strength:hedged· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passes- Not matched
In the paper
“Lin et al. [53] observe that 99.9% of the gradient exchange in distributed SGD (DSGD) are redundant, which demonstrates the power of gradient compression.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 3) Gradient Compression:
What the sources say
- Not checked — no full text of the sourcecites [53] 53. Y. Lin, S. Han, H. Mao, Y. Wang, and W. J. Dally, "Deep gradient compression: Reducing the communication bandwidth for distributed training," 2017, arXiv:1712.01887. [Online]. Available: https://arxiv.org/abs/1712.01887 source
Load-bearingStrength:boosted· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIn the paper
“Specifically, while preserving client's own privacy, the training loss can be reduced by sharing the models among clients, comparing to training solely on their own inputs.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > C. Enabling Technologies
What the sources say
- Not checked — no full text of the sourcecites [46] 46. R. Shokri and V. Shmatikov, "Privacy-preserving deep learning," in Proc. 22nd ACM SIGSAC Conf. Comput. Commun. Secur., 2015, pp. 1310-1321. source
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesA conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Edge Computing Is Able to Prosper AI With Richer Data and Application Scenarios”
- Also stated in: § 2) Edge Computing Is Able to Prosper AI With Richer Data and Application Scenarios: · hedged
“edge computing is proposed to achieve low-latency data processing by sinking the computing capability from the cloud data center to the edge side, i.e., data generation source, which may enable AI processing with high performance.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 2) Edge Computing Is Able to Prosper AI With Richer Data and Application Scenarios:
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes- Also stated in: § 2) Edge Computing Is Able to Prosper AI With Richer Data and Application Scenarios: · hedged
In the paper
“A flaw of [46] is that it does not consider unbalanced and nonindependent identical distribution (non-IID) data.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > C. Enabling Technologies
What the sources say
- Not checked — no full text of the sourcecites [46] 46. R. Shokri and V. Shmatikov, "Privacy-preserving deep learning," in Proc. 22nd ACM SIGSAC Conf. Comput. Commun. Secur., 2015, pp. 1310-1321. source
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIn the paper
“big data have recently gone through a radical shift of data source from the megascale cloud datacenters to the increasingly widespread end devices, e.g., mobile devices and Internetof-Things (IoT) devices.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > I. I N T R O D U C T I O N
What the sources say
- Not matchedcites [3] 3. Cisco Global Cloud Index: Forecast and Methodology, 2016-2021, White Paper. [Online]. Available: https://www.cisco.com/c/en/us/ solutions/collateral/service-provider/global- cloud-index-gci/white-paper-c11-738085.html
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes- Not matched
- Probably not a substantial claim. 28
- It may state two separate claims as one. 27
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“VGG-16 [19] is trained to a deeper structure of 16 layers consisting of 13 convolution layers and three fully connected layers, requiring 138 million weights and 15.5G MACs to classify the image with a size of 224 × 224.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 1) Convolution Neural Network:
What the sources say
- Partly supportedcites [19] 19. K. Simonyan and A. Zisserman, "Very deep convolutional networks for large-scale image recognition," 2014, arXiv:1409.1556. [Online]. Available: https://arxiv.org/abs/1409.1556 sourceExperimental — accuracy not yet measured
Table 1 (p. 3) identifies configuration D as a 16-weight-layer network with a 224 × 224 RGB input, and Table 2 (p. 3) lists 138 million parameters for D. Section 2.1 (p. 2) describes the three fully connected layers. Our copy does not report the claimed 15.5G MACs per image, so that part is unsupported. (LLM, conf=0.88)
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
- Partly supported
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“In particular, an update aggregation protocol named FedCS is developed to allow the centralized server to aggregate as many client updates as possible and to accelerate performance improvement in ML models.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 2) Aggregation Frequency Control:
What the sources say
- Could not verifycites [52] 52. T. Nishio and R. Yonetani, "Client selection for federated learning with heterogeneous resources in mobile edge," 2018, arXiv:1804.08333. [Online]. Available: https://arxiv.org/abs/ 1804.08333 sourceExperimental — accuracy not yet measured
The Introduction (p. 2) describes pruning, quantization, and Huffman coding, while §6.3 (pp. 9–10) discusses inference speedups from compression. Searches for FedCS, client-update aggregation, and federated client selection found no passage addressing the claimed protocol or its effect on model improvement. (LLM, conf=0.76)
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
- Could not verify
Every source the paper cites for this claim was checked and supports it.
In the paper
“The optimization in [45] emphasizes the properties of unbalanced and non-IID since the distributed data may come from various sources.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > C. Enabling Technologies
What the sources say
- Supportedcites [45] 45. H. B. McMahan, E. Moore, D. Ramage, S. Hampson, and B. A. Y. Arcas, "Communication-efficient learning of deep networks from decentralized data," 2016, arXiv:1602.05629. [Online]. Available: https://arxiv.org/abs/1602.05629 source
The Introduction (p. 2) explicitly says the work emphasizes the non-IID and unbalanced properties of federated optimization. It explains that clients’ data reflect different users’ device usage and that users contribute varying amounts of data, supporting the citing sentence’s explanation of why those properties arise. (LLM, conf=0.94)
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
- Supported
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“when moving a tremendous amount of data across the wide area network (WAN), both monetary cost and transmission delay can be prohibitively high, and the privacy leakage can also be a major concern [5].”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > I. I N T R O D U C T I O N
What the sources say
- Could not verifycites [5] 5. Q. Pu et al., "Low latency geo-distributed data analytics," in Proc. ACM SIGCOMM, 2015, pp. 421-434. sourceExperimental — accuracy not yet measured
The Introduction and Section 6 (Advantages and disadvantages; page numbers unavailable) discuss generative models and their computational properties, not transferring large datasets over a WAN. Searches for WAN costs, transmission delay, and privacy leakage found no passage addressing the claim. (LLM, conf=0.75)
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
- Could not verify
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the paper
“the physical proximity between the computing and information-generation sources promises several benefits compared to the traditional cloud-based computing paradigm, including low latency, energy efficiency, privacy protection, reduced bandwidth consumption, on-premises, and context awareness [6], [8].”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > I. I N T R O D U C T I O N
What the sources say
- Not checked — no full text of the sourcecites [6] 6. W. Shi, J. Cao, Q. Zhang, Y. Li, and L. Xu, "Edge computing: Vision and challenges," IEEE Internet Things J., vol. 3, no. 5, pp. 637-646, Oct. 2016. source
- Supportedcites [8] 8. Y. Mao, C. You, J. Zhang, K. Huang, and K. B. Letaief, "A survey on mobile edge computing: The communication perspective," IEEE Commun. Surveys Tuts., vol. 19, no. 4, pp. 2322-2358, 4th Quart., 2017. source
The comparison in “Mobile Edge Computing Versus Mobile Cloud Computing” (p. 3) identifies lower latency, mobile-device energy savings, context awareness, and improved privacy and security as MEC advantages. “Mobile Computing for 5G: From Clouds to Edges” (p. 1) explains that moving traffic toward the edge avoids burdening backhaul networks, while the privacy discussion (p. 3) gives enterprise-managed deployment as an example of keeping data on premises. (LLM, conf=0.88)
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“A good performance improvement is obtained by transferring knowledge from both the intermediate layers and last layer of the teacher to a shallower student while other architectures and transfer techniques do not fare so well and some of them even lead to negative performance impact.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 4) DNN Splitting:
What the sources say
- Not checked — no full text of the sourcecites [62] 62. R. Sharma, S. Biookaghazadeh, B. Li, and M. Zhao, "Are existing knowledge transfer techniques effective for deep learning with edge devices?" in Proc. IEEE Int. Conf. Edge Comput. (EDGE), Jul. 2018, pp. 42-49. source
- Could not verifycites [44] 44. Q. Chen, Z. Zheng, C. Hu, D. Wang, and F. Liu, "Data-driven task allocation for multi-task transfer learning on the edge," in Proc. IEEE 39th Int. Conf. Distrib. Comput. Syst. (ICDCS), 2019. sourceExperimental — accuracy not yet measured
Split into 2 atoms — 0 confirmed, 0 partially supported, 0 disputed, 0 misattributed, 2 unverifiable. Expand the claim to see per-atom verdicts.
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
Every source the paper cites for this claim was checked and supports it.
In the paper
“The early work on random gossip algorithms is gossip averaging [63], which can fast converge toward a consensus among nodes by exchanging information peer to peer.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 4) DNN Splitting:
What the sources say
- Supportedcites [63] 63. S. Boyd, A. Ghosh, B. Prabhakar, and D. Shah, "Randomized gossip algorithms," IEEE Trans. Inf. Theory, vol. 52, no. 6, pp. 2508-2530, Jun. 2006. source
The paper describes gossip averaging as nodes communicating with randomly chosen neighbors (Randomized Gossip Algorithms, p. 1). It studies convergence to the vector of averages and the design of the fastest gossip algorithm (Previous Results, p. 3; Randomized Gossip Algorithms, p. 1), supporting the peer-to-peer consensus paraphrase. (LLM, conf=0.89)
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
- Supported
In the paper
“The algorithm is based on the convergence analysis of distributed gradient descent and can be applied to federated learning in edge computing with provable convergence.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 2) Aggregation Frequency Control:
What the sources say
- Not matchedcites [51] 51. S. Wang et al., "Adaptive federated learning in resource constrained edge computing systems," IEEE J. Sel. Areas Commun., vol. 37, no. 3, pp. 1205-1221, Jun. 2019.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
- Not matched
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“As a result, the transmission latency of data offloading decreases, the data privacy increases, and the WAN bandwidth cost reduces.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 5) Level 4-Cloud-Edge Cotraining and Inference: Train-
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The main challenges of federated learning are optimization and communication.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > C. Enabling Technologies
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“While edge computing and AI complement each other from a technical perspective, their application and popularization are also mutually beneficial.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 2) Edge Computing Is Able to Prosper AI With Richer Data and Application Scenarios:
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesProbably not a substantial claim. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Though the federated learning technique exploits a new decentralized deep learning architecture, it is built upon a central server for aggregating local updates.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > C. Enabling Technologies
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“As forecast by Gartner [33], more than 80% of enterprise IoT projects will include an AI component by 2022, up from only 10% today.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > A. Motivation and Benefits of Edge Intelligence
What the sources say
- Not matchedcites [33] 33. AI Trends for Enterprise Computing. [Online]. Available: https://www.gartner.com/ smarterwithgartner/3-ai-trends-for-enterprise- computing/
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
- Not matched
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This conflict indicates that there is no”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 5) Level 4-Cloud-Edge Cotraining and Inference: Train-
Load-bearingStrength:hedged· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Energy efficiency is mainly affected by the size of the target training model and resources of the used devices.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 6) Energy Efficiency:
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✗ Based: failsProbably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
In the paper
“ResNet [20], the state-of-the-art effort, uses the”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 1) Convolution Neural Network:
What the sources say
- Not checked — no full text of the sourcecites [20] 20. K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," in Proc. IEEE CVPR, Jun. 2016, pp. 770-778. source
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
A claim is checked only against the cited paper’s full text, never its abstract, and none is available for its sources.
In the paper
“real-time video analytics is envisioned to be a killer application for edge computing [12], [37], [38].”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 4) Edge Computing Can Be Popularized With AI Applications:
What the sources say
- Not checked — no full text of the sourcecites [12] 12. G. Ananthanarayanan et al., "Real-time video analytics: The killer app for edge computing," Computer, vol. 50, no. 10, pp. 58-67, 2017. source
- Not checked — no full text of the sourcecites [37] 37. H. Zhang, G. Ananthanarayanan, P. Bodik, M. Philipose, P. Bahl, and M. J. Freedman, "Live video analytics at scale with approximation and delay-tolerance," in Proc. USENIX NSDI, 2017, pp. 377-392.
- Not checked — no full text of the sourcecites [38] 38. C.-C. Hung et al., "VideoEdge: Processing camera streams using hierarchical clusters," in Proc. IEEE/ACM Symp. Edge Comput. (SEC), Oct. 2018, pp. 115-131. source
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“AlexNet requires 61 million weights and 724 million MACs (multiply-add computation) to classify the image with a size of 227 × 227.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 1) Convolution Neural Network:
What the sources say
- Not matchedcites [18] 18. A. Krizhevsky, I. Sutskever, and G. E. Hinton, "Imagenet classification with deep convolutional neural networks," in Proc. NIPS, 2012, pp. 1097-1105.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
- Not matched
In the paper
“However, Gaia focuses on geodistributed datacenters that are capacity-unlimited, making it is not generally applicable to edge computing nodes whose capacity is highly constrained.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 2) Aggregation Frequency Control:
What the sources say
- Not matchedcites [50] 50. K. Hsieh, A. Harlap, N. Vijaykumar, D. Konomis, G. R. Ganger, and P. B. Gibbons, "Gaia: Geo-distributed machine learning approaching LAN speeds," in Proc. NSDI, 2017, pp. 629-647.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
- Not matched
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Under the decentralized training mode, the convergence value depends on the way the gradient is synchronized and updated.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 2) Convergence:
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✗ Based: failsProbably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“When training the DNN model by using the data originated at a massive of end devices, the raw data or intermediate data should be transferred out of the end devices.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 3) Privacy:
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✗ Based: failsProbably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Deep learning represents the state-of-the-art AI technology as well as a highly resource-demanding workload that naturally suits for edge computing.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > B. Deep Learning and Deep Neural Networks
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes? Based: unclearIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“When training the DNN model in a decentralized manner, both the computation and communication processes consume enormous energy.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 6) Energy Efficiency:
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✗ Based: failsProbably not a substantial claim. The paper may give no reason why it holds. It may state two separate claims as one.
- Rests on an assumption: For most end devices, they are energy-constrained.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“However, this is achieved at the cost of increased computational latency and energy consumption.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 5) Level 4-Cloud-Edge Cotraining and Inference: Train-
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
In the paper
“GoogleNet achieves a better accuracy performance than VGG-16, while only requiring seven million weights and 1.43G MACs to process the image with the same size.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 1) Convolution Neural Network:
What the sources say
- Not checked — no full text of the sourcecites [28] 28. C. Szegedy et al., "Going deeper with convolutions," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jun. 2015, pp. 1-9. source
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
In the paper
“MeDNN improves the DNN model inference by 1.86-2.44×with two to four worker nodes and saves 26.5% of additional computing time and 14.2% of extra communication time.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 1) Model Compression:
What the sources say
- Not checked — no full text of the sourcecites [84] 84. J. Mao et al., "MeDNN: A distributed mobile system with enhanced partition and deployment for large-scale DNNs," in Proc. 36th Int. Conf. Comput.-Aided Design, Nov. 2017, pp. 751-756. source
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Communication overhead is affected by the size of the original input data, the way of transmission, and the available bandwidth.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > VII. C O N C L U S I O N
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Due to the combinatorial nature, the high-dimensional configuration problem involves a huge search space of parameters and is very challenging to tackle.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > D. Summary of Existing Systems and Frameworks
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
- Rests on an assumption: Standard performance indicators such as top-k accuracy or mean average precision fail to reflect the runtime performance of DNN model inference on edge devices.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“However, data parallelism may bring heavy overhead of communication, while model parallelism usually leads to severe underutilization of computation resources.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 4) DNN Splitting:
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes? Based: unclearIt may state two separate claims as one.
In the paper
“PipeDream shows the advantage of reducing communication overhead and utilizing computing resource efficiently.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 4) DNN Splitting:
What the sources say
- Not checked — no full text of the sourcecites [61] 61. A. Harlap, D. Narayanan, A. Phanishayee, V. Seshadri, G. R. Ganger, and P. B. Gibbons, "PipeDream: Fast and efficient pipeline parallel DNN training," 2018, arXiv:1806.03377. [Online]. Available: https://arxiv.org/abs/1806.03377 source
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The communication latency may vary from the size of transmitted raw or intermediate data and the bandwidth of network connection.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > VII. C O N C L U S I O N
Strength:hedged· not yet calibratedCausal:conditional· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“By deployment on large-scale systems, Daily et al. [66] show that the trivial gossip-based algorithms at scale lead to a communication imbalance, poor convergence, and heavy communication overhead.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 4) DNN Splitting:
What the sources say
- Not checked — no full text of the sourcecites [66] 66. J. Daily, A. Vishnu, C. Siegel, T. Warfel, and V. Amatya, "GossipGraD: Scalable deep learning using gossip communication based asynchronous gradient descent," 2018, arXiv:1803.05880. [Online]. Available: https://arxiv.org/ abs/1803.05880 source
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
In the paper
“FoggyCache reduces computation latency and energy consumption by a factor of 3× to 10×.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 4) Edge Caching:
What the sources say
- Not checked — no full text of the sourcecites [95] 95. P. Guo, B. Hu, R. Li, and W. Hu, "FoggyCache: Cross-device approximate computation reuse," in Proc. ACM Mobicom, 2018, pp. 19-34. source
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Arguably, latency is one of the most fundamental performance indicators of distributed DNN model training since it directly influences when the trained model is available for use.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > VII. C O N C L U S I O N
Strength:hedged· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“This is based on the important observation that a DNN model can be split inside between two successive layers with two partitions deployed on different locations without losing accuracy.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 4) DNN Splitting:
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✗ Based: failsProbably not a substantial claim. The paper may give no reason why it holds.
In the paper
“the proposed automatic optimization framework AdaDeep [75] systematically formulates the goals and constraints on accuracy, latency, storage, and energy into a unified optimization problem and leverages DRL to effectively find a good combination of compression techniques.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 1) Model Compression:
What the sources say
- Not checked — no full text of the sourcecites [75] 75. S. Liu, Y. Lin, Z. Zhou, K. Nan, H. Liu, and J. Du, "On-demand deep model compression for mobile devices: A usage-driven model selection framework," in Proc. 16th Annu. Int. Conf. Mobile Syst., Appl., Services, 2018, pp. 389-400. source
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The decentralized architecture is naturally friendly to user's privacy, for which the systems that are based on the decentralized architecture such as BlockFL and GossipGraD typically preserve privacy better.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > Table 2 Overview of Systems and Frameworks on EI Model Training
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Intuitively, this communication overhead increases the training latency, energy, and bandwidth consumption.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > VII. C O N C L U S I O N
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
In the paper
“Precog uses predictions of Markov chains to prefetch data onto the mobile device and reach a speedup of 5×.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 4) Edge Caching:
What the sources say
- Not checked — no full text of the sourcecites [94] 94. U. Drolia, K. Guo, and P . Narasimhan, "Precog: Prefetching for image recognition applications at the edge," in Proc. ACM/IEEE Symp. Edge Comput. (SEC), Oct. 2017, p. 17. source
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Compared with the DNN training under the cloud-based framework, the DNN training under edge-based framework pays more attention to protecting users' privacy and training an available deep learning model faster.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > Table 2 Overview of Systems and Frameworks on EI Model Training
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The latency of the distributed training process typically consists of the computation latency and the communication latency.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > VII. C O N C L U S I O N
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
A claim is checked only against the cited paper’s full text, never its abstract, and none is available for its sources.
In the paper
“Both Blot et al. [64] and Jin et al. [65] apply gossip algorithms on the updates of SGD, but neither of them has performance convergence degradation at large scale.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 4) DNN Splitting:
What the sources say
- Not checked — no full text of the sourcecites [64] 64. M. Blot, D. Picard, M. Cord, and N. Thome, "Gossip training for deep learning," 2016, arXiv:1611.09726. [Online]. Available: https://arxiv.org/abs/1611.09726 source
- Not checked — no full text of the sourcecites [65] 65. P. H. Jin, Q. Yuan, F. Iandola, and K. Keutzer, "How to scale distributed deep learning?" 2016, arXiv:1611.04581. [Online]. Available: https://arxiv.org/abs/1611.04581 source
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
In the paper
“ReXCam reduces computation workload by 4.6× and improves DNN model inference accuracy by 27%.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 5) Input Filtering:
What the sources say
- Not checked — no full text of the sourcecites [99] 99. S. Jain, J. Jiang, Y. Shu, G. Ananthanarayanan, and J. Gonzalez, "ReXCam: Resource-efficient, cross-camera video analytics at enterprise scale," 2018, arXiv:1811.01268. [Online]. Available: https://arxiv.org/abs/1811.01268 source
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“For the object recognition application, Huang et al. [120] investigate the influence of the main factors, e.g., number of proposals, input image size, and the selection of feature extractor, on inference speed and accuracy.Based on their experiment results, a new combination of these factors is found to outperform the state-of-the-art method.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > D. Tradeoff Design With Various DNN Performance Metrics
What the sources say
- Not checked — no full text of the sourcecites [120] 120. J. Huang et al., "Speed/accuracy trade-offs for modern convolutional object detectors," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jul. 2017, pp. 7310-7311. source
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
- Rests on an assumption: Standard performance indicators such as top-k accuracy or mean average precision fail to reflect the runtime performance of DNN model inference on edge devices.
In the paper
“Compared to the approach that uploads the entire model, IONN significantly improves query performance and energy consumption during DNN model uploading.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 1) Model Compression:
What the sources say
- Not checked — no full text of the sourcecites [82] 82. H.-J. Jeong, H.-J. Lee, C. H. Shin, and S.-M. Moon, "IONN: Incremental offloading of neural network computations from mobile devices to edge servers," in Proc. ACM Symp. Cloud Comput., 2018, pp. 401-411. source
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The gossip distributed algorithms enjoy the advantage of full asynchronization and total decentralization as they have no requirement on centralized nodes or variables.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 4) DNN Splitting:
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“the cascading network [91] simply adds the MP layer and fully connected layer to the standard DNN model and achieves a speedup of 20%.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > The aggregation methods work when multiple mobile
What the sources say
- Not checked — no full text of the sourcecites [91] 91. S. Leroux et al., "The cascading neural network: Building the Internet of smart things," Knowl. Inf. Syst., vol. 52, no. 3, pp. 791-814, 2017.
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“This process will tend to work if the features are general (i.e., suitable to both base and target tasks) instead of specific to the base task.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 4) DNN Splitting:
Strength:hedged· not yet calibratedCausal:conditional· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✗ Based: failsProbably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
The paper relies on this without support.
There is a lack of a dedicated venue for summarizing, discussing, and disseminating recent advances of edge intelligence in both industry and academia.
“There is, in general, a lack of venue dedicated for summarizing, discussing, and disseminating the recent advances of EI, in both industrial and academia.”
The paper relies on this without support.
Research and practice on edge intelligence are still in a very early stage.
“Notably, research and practice on this emerging interdiscipline-EI-are still in a very early stage.”
The paper relies on this without support.
The edge ecosystem will present many novel application scenarios for AI and fuel the continuous booming of AI.
“Clearly, via bringing the huge volumes of data to AI, the edge ecosystem will present many novel application scenarios for AI and fuel the continuous booming of AI.”
The paper relies on this without support.
For most end devices, they are energy-constrained.
“However, for most end devices, they are energy-constrained.”
The paper relies on this without support.
It is inevitable to deal with privacy issues when raw or intermediate data are transferred out of end devices.
“Obviously, it is inevitable to deal with privacy issues in this scenario.”
The paper relies on this without support.
For some real-time intelligent mobile applications, they usually have stringent deadline requirement such as 100-ms latency.
“For some real-time intelligent mobile applications (e.g., AR/VR mobile gaming and intelligent robots), they usually have stringent deadline requirement such as 100-ms latency.”
The paper relies on this without support.
For some mobile applications requiring high reliability, they demand ultrahigh accuracy on DNN model inference.
“For some mobile applications requiring a high level of reliability, such as self-driving car and face authentication, they demand the ultrahigh accuracy on the DNN model inference.”
The paper relies on this without support.
Most existing efforts use a single compression technique.
“While most existing efforts use a single compression technique, they may not suffice to meet the diverse requirements and constraints on accuracy, latency, storage, and energy imposed by some IoT devices.”
The paper relies on this without support.
Standard performance indicators such as top-k accuracy or mean average precision fail to reflect the runtime performance of DNN model inference on edge devices.
“However, it is difficult for software developers to choose an appropriate DNN model for the EI application because the standard performance indicators such as top-k accuracy or mean average precision fail to reflect the runtime performance of DNN model inference on edge devices.”
The paper relies on this without support.
Most current edge AI programming/software platforms mainly serve as relays for connecting to cloud data centers.
“Nevertheless, currently, most of these platforms mainly serve as relays for connecting to the powerful cloud data centers.”
The paper relies on this without support.
Most deep learning-based AI models are highly resource-intensive.
“Most of the deep learning-based AI models are highly resourceintensive, which means that powerful computing capability supported by abundant hardware resources (e.g., GPU, field-programmable gate array (FPGA), and TPU) is important to boost the performance of these AI models.”
The paper relies on this without support.
For an EI application with a specific mission, there is usually a series of DNN model candidates that are capable of finishing the task.
“For an EI application with a specific mission, there is usually a series of DNN model candidates that are capable of finishing the task.”
The paper relies on this without support.
The service environments for many EI application scenarios are of high dynamics and it is hard to accurately predict future events.
“Since for many EI application scenarios (e.g., smart cities), the service environments are of high dynamics and it is hard to accurately predict future events.”
The paper relies on this without support.
The high-efficiency operation of EI services may require close collaboration and integration across different service providers.
“The high-efficiency operation of EI services may require close collaboration and integration across different service providers, e.g., for implementing expanded resource sharing and smooth service handover.”
The paper relies on this without support.
A user can be a service consumer and, meanwhile, a data generator as well.
“Also, for EI service, a user can be a service consumer and, meanwhile, a data generator as well.”
The paper relies on this without support.
There is a stringent need to push the AI frontier from the cloud to the network edge.
“Driving by flourishing of both AI and IoT, there is a stringent need to pushing the AI frontier from the cloud to the network edge.”
The paper relies on this without support.
Edge computing is widely recognized as a promising solution to support computation-intensive AI applications in resource-constrained environments.
“To fulfill this trend, edge computing has been widely recognized as a promising solution to support computation-intensive AI applications in resource-constrained environments.”
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Additionally, UAVs generate lots of data at the network edge and directly sharing original data sets between many edge nodes has a high risk associated with it [8].”
From A Survey on the Convergence of Edge Computing and AI for UAVs: Opportunities and Challenges (2022) · cites this paper as [8]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Edge Intelligence (EI) Zhou et al. (2019) proposes a new paradigm combining AI and edge computing, with the goal of performing distributed computing of DL models.”
From Deepfakes: current and future trends (2024) · cites this paper as Zhou et al. 2019
The cited source says what the claim attributes to it.
In the citing paper
“This entails some advantages such as low latency, energy and bandwidth efficiency, privacy protection, and context awareness (Zhou et al. 2019).”
From Deepfakes: current and future trends (2024) · cites this paper as Zhou et al. 2019
The cited source says what the claim attributes to it.
In the citing paper
“In the case of training a deep learning model in an edge computing environment, where distributed models are trained locally first and then updates are aggregated centrally (e.g., federated learning), the control of updates aggregation frequency has a significant influence on the communication overhead.”
From A Survey on the Convergence of Edge Computing and AI for UAVs: Opportunities and Challenges (2022) · cites this paper as [8]
In the citing paper
“Edge AI provides a promising solution for connected intelligence by enabling data collection, processing, transmission, and consumption at the network edge [29], [30].”
From Edge artificial intelligence for 6g: vision, enabling technologies, and applications (2022) · cites this paper as [30]
In the citing paper
“All of these reviews only have a small fraction to discuss the edge DNN design which is the key element of edge intelligence systems.”
From Bringing ai to edge: from deep learning’s perspective (2022) · cites this paper as [13]
In the citing paper
“Smart city [113] is another important application scenario for deep-learning-enabled edge computing.”
From Deep learning for edge computing applications: A State-of-the-Art survey (2020) · cites this paper as [113]
In the citing paper
“In the current scenario, Blockchain provides a high degree of privacy for health data [49].”
From 6G Communication Technology: A Vision on Intelligent Healthcare (2021) · cites this paper as [49]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Inference metrics are counted as five but six are listed
MinorThe section introduces five inference metrics, but its numbered list runs from latency through memory footprint and contains six.
“To describe the service quality of the EI model inference, we introduce the following five metrics.”
“## 6) Memory Footprint:”
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 · cited 5×
“GoogleNet achieves a better accuracy performance than VGG-16, while only requiring seven million weights and 1.43G MACs to process the image with the same size.”
BackgroundMethodInfluentialImageNet 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 · cited 7×
“This is because for DNNs as exemplified by AlexNet, the energy of the convolutional layers dominates the total energy cost, while the number in the fully connected layers contributes most of the total number of weights in the DNN.”
BackgroundMethodInfluentialHochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 4×
“4, each neuron in LSTM is called memory cell and includes a multiplicative forget gate, input gate, and output gate.”
BackgroundInfluentialLeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
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 · cited 2×
“GoogleNet achieves a better accuracy performance than VGG-16, while only requiring seven million weights and 1.43G MACs to process the image with the same size.”
MethodLearning representations by back-propagating errors
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986) · Nature · doi:10.1038/323533a0 · Cited by 31,892 · cited 1×
“Leveraging the backpropagation mechanism [26], [27], the error rate is propagated back across the whole neural network, and the weights are updated based on the gradient and the learning rate.”
(2016) · Cited by 31,590
Human-level control through deep reinforcement learning
Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., Graves, A., Riedmiller, M., Fidjeland, A. K., Ostrovski, G., et al. (2015) · Nature · doi:10.1038/nature14236 · Cited by 30,357 · cited 2×
“[32] V.”
Flagged first, then by citations
28 of the 168 references couldn’t be matched to a known paper.
Research works printed but not linked: 11
- 0, 3 AI Trends for Enterprise Computing
- 0, Microsoft Interactive Cloud Gaming
- 0, Democratizing AI
- hsieh, 2017, Gaia: Geo-distributed machine learning approaching LAN speeds, Proc NSDI, 629
- 2018, 5 Trends Emerge in the Gartner Hype Cycle for Emerging Technologies
- 0, Cisco global cloud index Forecast and methodology 2016–2021
- 0, Accelerating AI on the Intelligent Edge
- 2017, IEC White Paper Edge Intelligence
- 0, Edge Intelligence for Industrial Internet of Things
- han, 2015, Learning both weights and connections for efficient neural network, Proc Adv Neural Inf Process Syst, 1135
- 2018, 5 Trends Emerge in the Gartner Hype Cycle for Emerging Technologies
Cited by
Sorted by citations
Items 1,001–1,100 of 2,413
Cost-Efficient Sharing Algorithms for DNN Model Serving in Mobile Edge Networks
Dai, H., Wu, J., Wang, Y., Yen, J., Zhang, Y., & Xu, C. (2023) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2023.3247049 · Cited by 8
“To address the foregoing issues, at present, the mainstream of DNN deployment mode in the edge is so-called In-Cloud Training and In-Edge Co-inference (ICIE), which means the model training is accomplished in the cloud while the model coinference is conducted between the edge and mobile device [10], [14].”
BackgroundMethodAI business models and its impact on business strategic framework
Mishra, S., & Mishra, P. (2023) · International Journal of Financial Engineering · doi:10.1142/s2424786323500019 · Cited by 10
Alnajar, O., & Barnawi, A. (2023) · Computer Networks · doi:10.1016/j.comnet.2023.109712 · Cited by 8
A Lightweight Concept Drift Detection Method for On-Device Learning on Resource-Limited Edge Devices
Yamada, T., & Matsutani, H. (2023) · IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW) · doi:10.1109/ipdpsw59300.2023.00128 · Cited by 8
“In addition, edge intelligence [1] in which some machine learning tasks such as prediction are performed in the edge side is also becoming popular since performance and efficiency of edge devices have been improved significantly.”
BackgroundGRD: An Ultra-Lightweight SAR Ship Detector Based on Global Relationship Distillation
Zhou, Y., Jiang, X., Chen, L., et al. (2023) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2023.3302412 · Cited by 8
Practical Optical Camera Communication Behind Unseen and Complex Backgrounds
Xiao, R., Zhao, L., Qian, F., Yang, L., & Han, J. (2024) · International Conference on Mobile Systems, Applications, and Services · doi:10.1145/3643832.3661866 · Cited by 8
GreenEdge: Greening Edge Datacenters with Energy-Harvesting IoT Devices
Zhou, Z. (2019) · Proceedings/Proceedings - International Conference on Network Protocols · doi:10.1109/icnp.2019.8888103 · Cited by 8
Self-citationA Novel Emotion Control System for Embedded Human–Computer Interaction in Green Iot
Gong, C., Lin, F., & An, X. (2019) · IEEE Access · doi:10.1109/access.2019.2960832 · Cited by 8
“However, with the emergence of edge computing [3] and the rise of green Internet of Things (IoT) technology [4], the core of AI is gradually sinking from the cloud to the user’s closer end [5].”
BackgroundTemporal difference based adaptive object Detection (ToDo) platform at Edge Computing System
Yang, Y., Han, K., Lee, S., et al. (2020) · IEEE Consumer Communications & Networking Conference (CCNC) · doi:10.1109/ccnc46108.2020.9045513 · Cited by 8
“of input data [1].”
A Deep Learning Model for Demand-Driven, Proactive Tasks Management in Pervasive Computing
Kolomvatsos, K., & Anagnostopoulos, C. B. (2020) · IoT · doi:10.3390/iot1020015 · Cited by 8
Tang, S.-N., & Han, Y.-S. (2020) · IEEE Access · doi:10.1109/access.2020.3040366 · Cited by 10
“platform using central processing units (CPUs) or graphical processing units (GPUs) [1], [2].”
BackgroundMethodInfluentialA Flexible In-Memory Computing Architecture for Heterogeneously Quantized CNNs
Ponzina, F., Rios, M. A., Ansaloni, G., Levisse, A., & Atienza, D. (2021) · IEEE Computer Society Annual Symposium on VLSI · doi:10.1109/isvlsi51109.2021.00039 · Cited by 9
“Edge Artificial Intelligence (edgeAI) is fostering a revolution in the computing landscape [1].”
BackgroundBecker, S., Schmidt, F., Thamsen, L., et al. (2021) · IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS) · doi:10.1109/acsos52086.2021.00033 · Cited by 8
“[8], [9], but considers necessary adjustments at runtime in light of the dynamic nature of the IoT in its connectivity, resource availabilities, and connected sensor streams.”
BackgroundDual-Masking Framework against Two-Sided Model Attacks in Federated Learning
Chiu, T.-C., Lin, W.-C., Pang, A., & Cheng, L.-C. (2021) · Globecom · doi:10.1109/globecom46510.2021.9685701 · Cited by 8
A Secure Cloud-Edge Collaborative Logistic Regression Model
Wang, C., Xu, J., & Yin, L. (2021) · 2021 IEEE International Conferences on Internet of Things (iThings) and IEEE Green Computing & Communications (GreenCom) and IEEE Cyber, Physical & Social Computing (CPSCom) and IEEE Smart Data (SmartData) and IEEE Congress on Cybermatics (Cybermatics) · doi:10.1109/ithings-greencom-cpscom-smartdata-cybermatics53846.2021.00049 · Cited by 8
Klippel, E., Oliveira, R., Maslov, D., et al. (2022) · SN Computer Science · doi:10.1007/s42979-022-01169-y · Cited by 8
“In this case, the data is partially transferred to the cloud to perform the inference; Level 2—In-edge coinference and cloud training—training in the cloud and inference performed at the edge of the network on the devices located there, here the data flow is limited to the edge of the network; Level 3—On-device infere…”
MethodEnergy-Efficient Processing and Robust Wireless Cooperative Transmission for Edge InferencePreprint
Yang, K., Shi, Y., Yu, W., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.12475 · Cited by 8
“With the explosion of mobile data and the increasing edge computing capability, there is an emerging trend of edge intelligence [2], [3].”
BackgroundPrivacy For Free: Wireless Federated Learning Via Uncoded Transmission With Adaptive Power ControlPreprint
Liu, D., & Simeone, O. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.05459 · Cited by 8
Wu, Q., Xu, J., Zeng, Y., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.09317 · Cited by 8
“porated into BSs and APs at the network edge, for enabling various intelligent applications (such as autonomous driving and industrial automation) with extensive communication and computation requirements [293], [294].”
BackgroundEdge AI System Using a Thermal Camera for Industrial Anomaly Detection
Oliveira, V. M., & Moreira, A. H. J. (2022) · Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-031-06371-8_12 · Cited by 10
Real-Time Monitoring of Wind Turbine Bearing Using Simple Neural Network on Raspberry Pi
Wang, T. S., Meng, H., Qin, R., Zhang, F., & Nandi, A. K. (2024) · Applied Sciences · doi:10.3390/app14073129 · Cited by 7
“Some studies have attempted to address this issue by training models in the cloud [21] and then transferring them to edge devices.”
BackgroundDesign and Optimization of Hierarchical Gradient Coding for Distributed Learning at Edge Devices
Tang, W., Li, J., Chen, L., & Chen, X. (2024) · IEEE Transactions on Communications · doi:10.1109/tcomm.2024.3418901 · Cited by 7
“To mitigate this side effect, edge computing [6], [7], [8] is applied by exploiting edge nodes (e.g., base stations with MEC servers and smart IoT gateways) located in the proximity of distributed workers for enhancing computation and communication capabilities.”
Self-citationLightweight SAR Ship Detection via Pearson Correlation and Nonlocal Distillation
Zhang, Y., Cai, W., Guo, J., et al. (2025) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2025.3545569 · Cited by 7
Enhancing Clinical Decision-Making and Operational Efficiency in Healthcare Using Edge Computing
Ravikumar, R. N., Aarthi, S., Masharipova, G., Niyazova, N., Salaeva, N., & Buriyeva, D. (2025) · IGI Global eBooks · doi:10.4018/979-8-3373-1147-0.ch008 · Cited by 8
Farrukh, H., Zafar, S., Rehman, Z. U., Shah, A. A., & Alshammry, N. (2025) · Electronics · doi:10.3390/electronics14244952 · Cited by 20
da Luz, G. P. C. P., Sato, G. M., Gonzalez, L. F. G., & Borin, J. F. (2025) · Internet of Things · doi:10.1016/j.iot.2025.101858 · Cited by 31
ResQConnect: An AI-Powered Multi-Agentic Platform for Human-Centered and Resilient Disaster Response
Aththanayake, S., Mallikarachchi, C., Wickramasinghe, J., Kugarajah, S., Meedeniya, D., & Pradhan, B. (2026) · Sustainability · doi:10.3390/su18021014 · Cited by 9
Artificial Intelligence-Enhanced Flexible Sensors for Human Motion and Posture Sensing
Jiang, Y., & He, T. (2026) · Sensors · doi:10.3390/s26051562 · Cited by 9
“In contrast, Edge AI enables on-device data processing, which significantly reduces response time and enhances data security by minimizing external transmissions [98,99].”
A Construction Kit for Efficient Low Power Neural Network Accelerator Designs
Jokic, P., Azarkhish, E., Bonetti, A., Pons, M., Emery, S., & Benini, L. (2022) · ACM Transactions on Embedded Computing Systems · doi:10.1145/3520127 · Cited by 9
“Surveys [9] and [36] present an extended view on edge intelligence, covering pure edge processing and combinations with cloud processing.”
BackgroundMethodOn-Device Deep Multi-Task Inference via Multi-Task Zipping
He, X., Wang, X., Zhou, Z., Wu, J., Yang, Z., & Thiele, L. (2021) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2021.3124306 · Cited by 8
“On the other hand, model compression is preferable over model partition to applications where communication with the edge is prohibited due to data privacy or unreliable network connections [31], [38], [39], [40].”
BackgroundSelf-citationFederated Learning-based Power Control and Computing for Mobile Edge Computing System
Yang, T., Li, X., & Shao, H. (2021) · IEEE Vehicular Technology Conference · doi:10.1109/vtc2021-fall52928.2021.9625545 · Cited by 8
Survey on Edge Intelligence in IoT-Based Computing Platform
Ramya, R., & Ramamoorthy, S. (2022) · Lecture notes in networks and systems · doi:10.1007/978-981-16-7952-0_52 · Cited by 7
Pedestrian and Vehicle Detection Based on Pruning YOLOv4 with Cloud-Edge Collaboration
Wang, H., Mo, R., Chen, Y., Lin, W., Xu, M., & Liu, B. (2023) · Computer Modeling in Engineering & Sciences · doi:10.32604/cmes.2023.026910 · Cited by 7
Internet of Things for Smart Homes and Smart Cities
Kapucu, N., & Bilim, M. (2023) · Power systems · doi:10.1007/978-3-031-38506-3_13 · Cited by 7
Network Simulation Bridge: Bridging Applications to Network Simulators
Kuttivelil, H., Sreenivasamurthy, S., Krishnaswamy, L., Bhatia, N. S., & Obraczka, K. (2023) · ACM Symposium on QoS and Security for Wireless and Mobile Networks (Q2SWinet) · doi:10.1145/3616391.3622771 · Cited by 7
“…two of these applications – collaborative decentralized learning and autonomous vehicle platooning – built with different implementations of NSB. Edge intelligence [21] is an emerging paradigm of artificial intelligence that is situated in the network edge and built on edge computing principles.”
BackgroundEris: An Online Auction for Scheduling Unbiased Distributed Learning Over Edge Networks
Pang, J., Han, Z., Zhou, R., et al. (2023) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2023.3333368 · Cited by 7
Classification of direct optical signal inputs by Ag2S island network reservoir
Matsuo, R., & Hasegawa, T. (2024) · Japanese Journal of Applied Physics · doi:10.35848/1347-4065/ad21bb · Cited by 7
Privacy-Aware Adaptive Model Splitting for Device-Edge Co Inference
Jiang, G., Han, S., Xu, X., et al. (2023) · IEEE Globecom Workshops (GC Wkshps) · doi:10.1109/gcwkshps58843.2023.10464411 · Cited by 7
“By integrating AI with edge computing, edge intelligence (EI) [3] enables the collection, processing, learning, and rapid response to the vast amount of data generated at the edge of the network.”
BackgroundInternet of Things: Architecture, Technologies, Applications, and Challenges
Abdulazeez, S., Nawar, A. K., Hassan, N. B., & Tariq, E. (2024) · Alkadhim journal for computer science. · doi:10.61710/kjcs.v2i1.67 · Cited by 10
AR-Edge: Autonomous and Resilient Edge Computing Architecture for Smart Cities
Xu, R., Nagothu, D., & Chen, Y. (2024) · IntechOpen eBooks · doi:10.5772/intechopen.1005876 · Cited by 10
Wang, Y., Zhao, K., Zhang, X., et al. (2024) · IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS) · doi:10.1109/infocomwkshps61880.2024.10620909 · Cited by 7
“In order to realize the vision of combining SEC and AI (i.e., space edge intelligence) like edge intelligence (EI) [13], multiple companies (e.g., AWS Ground Station [14]) offer “Ground Station as a Service” (GSaaS).”
BackgroundSelf-citationYin, K., Ji, X., Wang, Y., & Wang, Z. (2024) · Defence Technology · doi:10.1016/j.dt.2024.08.015 · Cited by 11
SCL: A sustainable deep learning solution for edge computing ecosystem in smart manufacturing
Gauttam, H., Pattanaik, K. K., Bhadauria, S., & Nain, G. (2024) · Journal of Industrial Information Integration · doi:10.1016/j.jii.2024.100703 · Cited by 8
Mobile Traffic Prediction at the Edge through Distributed and Deep Transfer Learning
Petrella, A., Miozzo, M., & Dini, P. (2024) · IEEE Access · doi:10.1109/access.2024.3518483 · Cited by 8
Making AI available for everyone at anywhere: A Survey about Edge Intelligence
Zhang, Y., Li, B., & Tan, Y. (2021) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1757/1/012076 · Cited by 7
A Review on Edge Intelligence based Collaborative Learning Approaches
Welagedara, L., Harischandra, J., & Jayawardene, N. (2021) · Computing and Communication Workshop and Conference · doi:10.1109/ccwc51732.2021.9376119 · Cited by 8
“With the increasing numbers of mobile computing and IoT products, a huge amount of data is generated in the network edge which results in higher bandwidth requirements [1].”
BackgroundDynamic Computation Offloading Strategy with DNN Partitioning in D2D Multi-Hop Networks
Guo, X., Dong, C., & Wen, W. (2021) · International Conference on Communications and Broadband Networking (ICCBN) · doi:10.1145/3456415.3457224 · Cited by 7
“These works are based on MEC, where mobile devices can partition the DNN model and offload the parts required for more computation resource to edge-cloud.”
BackgroundInfluentialEdge Intelligence for Smart Metro Systems: Architecture and Enabling Technologies
Liu, X., Zhang, M., Zou, C., Yang, J., & Yan, X. (2021) · IEEE Network · doi:10.1109/mnet.211.2100302 · Cited by 7
AI-powered Infrastructures for Intelligence and Automation in Beyond-5G Systems
Militano, L., Zafeiropoulos, A., Fotopoulou, E., et al. (2021) · IEEE Globecom Workshops (GC Wkshps) · doi:10.1109/gcwkshps52748.2021.9682117 · Cited by 7
“It is, therefore, not surprising that pervasive Artificial Intelligence (AI) is deemed to be among the central enabling technologies for beyond 5G networks [2] [4] [5].”
BackgroundOn the Efficiency of Service and Data Handoff Protocols in Edge Computing Systems
Scotece, D., Fiandrino, C., & Foschini, L. (2021) · Globecom · doi:10.1109/globecom46510.2021.9685975 · Cited by 7
“In the recent years, edge computing has gained momentum and attracted the interest of both industry and academia [1], [2].”
BackgroundDynamic Data Collection and Neural Architecture Search for Wireless Edge Intelligence Systems
Yin, B., Chen, Z., & Tao, M. (2022) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2022.3197809 · Cited by 7
“To leverage the abundant data for intelligent applications, edge machine learning [2], [3], [4], [5], [6], [7], [8], [9], [10] is emerging.”
BackgroundAn Optimization Framework for Federated Edge Learning
Li, Y., Cui, Y., & Lau, V. K. N. (2022) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2022.3199564 · Cited by 8
Digital Twin-Assisted Adaptive DNN Inference in Industrial Internet of Things
Hu, S., Li, M., Gao, J., Zhou, C., & Shen, X. (2022) · Globecom · doi:10.1109/globecom48099.2022.10001005 · Cited by 10
“Leveraging edge computing, edge intelligence supports artificial intelligence (AI) applications such as video analytics and production automation in the Industrial Internet of Things (IIoT) [1].”
BackgroundEdge Intelligence-based Obstacle Intrusion Detection in Railway Transportation
Gong, T., & Zhu, L. (2022) · Globecom · doi:10.1109/globecom48099.2022.10001123 · Cited by 7
“Edge intelligence is seen as the future direction of artificial intelligence (AI) [7].”
BackgroundJoint Resource Allocation and Learning Optimization for UAV-Assisted Federated Learning
Liu, C.-Y., & Zhu, Q. (2023) · Applied Sciences · doi:10.3390/app13063771 · Cited by 6
Attribute recognition for person re-identification using federated learning at all-in-edge
Girija, S., Baker, T., Ahmed, N., Khedr, A. M., Aghbari, Z. A., Jha, A., Соболев, К., Ahmadi‐Asl, S., & Phan, A. H. (2023) · Internet of Things · doi:10.1016/j.iot.2023.100793 · Cited by 9
Context-Aware Hybrid Encoding for Privacy-Preserving Computation in IoT Devices
Khalili, H., Chien, H.-J., Hass, A., & Sehatbakhsh, N. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3288523 · Cited by 7
A Low-Cost Neural ODE with Depthwise Separable Convolution for Edge Domain Adaptation on FPGAs
Kawakami, H., WATANABE, H., Sugiura, K., & Matsutani, H. (2023) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2022edp7149 · Cited by 8
“There are several forms of edge training scenarios, as surveyed in [12].”
BackgroundOn the Decentralization of Blockchain-enabled Asynchronous Federated Learning
Wilhelmi, F., Guerra, E., & Dini, P. (2023) · IEEE International Conference on Network Softwarization (NetSoft) · doi:10.1109/netsoft57336.2023.10175411 · Cited by 9
“Edge intelligence, by means of edge computing, is expected to bring artificial intelligence (AI) applications and optimizations closer to users by providing low-latency responses both in training and inference phases [1].”
BackgroundRodríguez, I., Campos, C., & Fdez‐Riverola, F. (2023) · Neurocomputing · doi:10.1016/j.neucom.2023.126835 · Cited by 7
Alanezi, K., & Mishra, S. (2020) · Future Generation Computer Systems · doi:10.1016/j.future.2020.08.001 · Cited by 8
“A recent survey paper underscored the importance of this concept, named edge intelligence [15], and described challenges and future directions to observe it.”
BackgroundIm, D., Park, G., Ryu, J., et al. (2022) · IEEE Journal of Solid-State Circuits · doi:10.1109/jssc.2022.3218278 · Cited by 7
Fog‐cloud distributed intrusion detection and cooperation
Ghribi, S., Meddeb-Makhlouf, A., Zarai, F., et al. (2019) · Transactions on Emerging Telecommunications Technologies · doi:10.1002/ett.3835 · Cited by 7
Latency Guaranteed Edge Inference via Dynamic Compression Ratio Selection
Huang, X., & Zhou, S. (2020) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc45663.2020.9120768 · Cited by 6
“Emerging technology like edge learning [2][3] focuses on deploying machine learning algorithms at the wireless access network edge.”
BackgroundTowards dependable 6G networksPreprint
Ahmad, I., Rodriguez, F., Huusko, J., & Seppänen, K. (2022) · doi:10.36227/techrxiv.20237358 · Cited by 7
Kanagarla, K. P. B. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.5012466 · Cited by 7
Joint Online Optimization of Model Training and Analog Aggregation for Wireless Edge Learning
Wang, J., Liang, B., Dong, M., Boudreau, G., & Abou-Zeid, H. (2023) · IEEE/ACM Transactions on Networking · doi:10.1109/tnet.2023.3318474 · Cited by 7
“This motivates new machine learning technologies at the edge servers and devices, collectively call edge learning [2], [3], [4], [5].”
BackgroundA Secure Authentication Scheme with Local Differential Privacy in Edge Intelligence-Enabled VANET
Kwon, D., Son, S., Park, K., & Park, Y. (2024) · Mathematics · doi:10.3390/math12152383 · Cited by 6
A Comprehensive Survey on Joint Resource Allocation Strategies in Federated Edge Learning
Zhang, J., Wu, Q., Fan, P., & Fan, Q. (2024) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2024.057006 · Cited by 6
“…dynamically adjusts the allocation order of computation tasks according to the real-time situation by means of the ED battery power and the computation load in order to balance the system devices, reduce the waiting time, reduce the energy consumption, and prolong the device's endurance [44].”
BackgroundMethodSelf-citationApplications and Challenges of Radar-Based Human Activity Recognition
Luo, F. (2024) · IEEE International Conference on Smart Internet of Things (SmartIoT) · doi:10.1109/smartiot62235.2024.00040 · Cited by 8
“…challenges, edge computing has recently been proposed, which pushes computation and communication tasks from clouds to the network edges that are in closer proximity to IoT sensors and data sources, in order to avoid unnecessary communication latency and enabling online real-time HAR [59], [60].”
Edge Intelligent Visual Monitoring of Substations Based on Lightweight Object Detection Model
Liu, M., Li, Z., & Sheng, G. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3562970 · Cited by 6
“With the advancement of edge computing [9], substation edge intelligent monitoring has become an emerging substation monitoring mode [10].”
Resource-Efficient Collaborative Edge Transformer Inference With Hybrid Model Parallelism
Ye, S., Ouyang, B., Du, J., Zeng, L., Qian, T., Ou, W., Chu, X., Guo, D., Lu, Y., & Chen, X. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3574695 · Cited by 6
Self-citationYin, Y., Gao, Z., Huang, Y., & Liu, Q. (2025) · Measurement Science and Technology · doi:10.1088/1361-6501/ae0495 · Cited by 6
“Deep learning architectures involve high inference time and energy consumption [32] and are not suitable for edge devices such as drones [33].”
Liu, F., Zhang, Y., Liu, Y., et al. (2025) · Veterinary Sciences · doi:10.3390/vetsci12090906 · Cited by 6
“Relevant studies have explored how to combine TensorFlow Lite with ultra-low power microcontrollers such as Arduino to implement efficient machine learning applications, especially the advantages in handling low-power devices [13,14].”
Mixture-of-Experts for Distributed Edge Computing with Channel-Aware Gating Function
Song, Q., Jing, S., Zhang, S., Zhang, S., & Huang, C. Z. (2025) · IEEE International Conference on Communications workshops · doi:10.1109/iccworkshops67674.2025.11162260 · Cited by 8
“Additionally, the diverse computational capacities and energy constraints across wireless devices heighten the need for load balancing to mitigate bottlenecks and ensure optimal resource utilization [14].”
Energy-Efficient CNN Hardware Accelerator for Real-Time Construction Progress Monitoring
Nardes, G. B., Duarte, L. F. H., Grignani, W., Melo, D. R., & Zeferino, C. A. (2025) · IEEE Access · doi:10.1109/access.2025.3627596 · Cited by 6
Precision decarbonization for clean dairy farming with digital twin and edge intelligence
Feng, C., Reed, K. F., Giordano, J. O., & You, F. (2025) · Nexus · doi:10.1016/j.ynexs.2025.100105 · Cited by 8
Sahu, D. K., Nidhi, N., Prakash, S., Yang, T., Rathore, R. S., Wang, L., Sharma, U., & Alsolbi, I. N. (2025) · Scientific Reports · doi:10.1038/s41598-025-25590-4 · Cited by 16
Task-Oriented Integrated Sensing and Semantic Communications for Multi-Device Video Analytics
He, Y., Li, X., & Luo, J. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3641899 · Cited by 11
FEDGE: FEDerated learning at the EDGE on space platforms using deep neural network architectures
Siddalingappa, R., Deepa, S. M., Mary, P. S., Kalpana, P., & Lakshmi, B. (2025) · International Journal of Information Technology · doi:10.1007/s41870-025-03010-0 · Cited by 7
Zhang, X., Zhao, P., Jaskolka, J., Li, H., & Lu, R. (2026) · Empirical Software Engineering · doi:10.1007/s10664-025-10795-y · Cited by 8
“Edge devices with constrained computational resources present particular challenges for implementing the full SecMLOps framework (Zhou et al. 2019 ).”
Multicore Federated Learning for Mobile-Edge Computing Platforms
Bai, Y., Chen, L., Li, J., Wu, J., Zhou, P., Xu, Z., & Xu, J. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3224239 · Cited by 6
“The CPU frequency of subscribers is randomly sampled from [1, 2, 4] GHz.”
BackgroundFine-grained Cloud Edge Collaborative Dynamic Task Scheduling Based on DNN Layer-Partitioning
Wang, X., Li, X., Wang, N., et al. (2022) · International Conference on Mobility, Sensing and Networking (MSN) · doi:10.1109/msn57253.2022.00037 · Cited by 6
“EI is a new paradigm of the integration of edge computing and AI, aiming to provide high-quality AI services by utilizing edge-size resources [3].”
BackgroundLuo, K., Ouyang, T., Zhou, Z., & Chen, X. (2023) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2023.102968 · Cited by 6
“With the growing demand for intelligent applications at the network edge [62, 63], the elastic Serverless architecture is increasingly being explored in edge computing [64, 65].”
BackgroundSelf-citationFair DNN Model Selection in Edge AI via A Cooperative Game Approach
Xie, J., Zhou, Z., Ouyang, T., Zhang, X., & Chen, X. (2023) · IEEE International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/icdcs57875.2023.00063 · Cited by 6
“As a result of the accelerating convergence of AI and edge computing, edge intelligence effectively paves the last mile delivery of AI [1].”
BackgroundSelf-citationEnd-to-End Learning-Based Wireless Image Recognition Using the PyramidNet in Edge Intelligence
Lee, K., & Yu, N. Y. (2023) · IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC) · doi:10.1109/pimrc56721.2023.10293934 · Cited by 6
“To address the problem, edge intelligence [2], [3] has emerged as a new research paradigm for IoT.”
BackgroundHung, C., Tsai, C.-Y., & Lee, C. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3397008 · Cited by 8
“Strategies include partitioning models based on complexity, leveraging AI-accelerated computing, and refining models for edge deployment [8], [9], [10], [11], [12].”
MethodPerformance Evaluation of Federated Learning in Edge Computing Environment
Kotecha, P., Dhoka, T., Bhatia, J., Kumhar, M., Gupta, R., Tanwar, S., & Jadav, N. K. (2024) · Procedia Computer Science · doi:10.1016/j.procs.2024.04.279 · Cited by 8
Zhang, X., & Zhu, X. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3418463 · Cited by 6
Adaptive Weighting via Federated Evaluation Mechanism for Domain Adaptation with Edge Devices
Zhao, R., Yang, X. W., Zhi, P., et al. (2024) · ACM Transactions on Sensor Networks · doi:10.1145/3669903 · Cited by 6
Model Compression Method for S4 With Diagonal State Space Layers Using Balanced Truncation
Ezoe, H., & Sato, K. (2024) · IEEE Access · doi:10.1109/access.2024.3446642 · Cited by 10
“Let us consider the issues that hinder the application of S4 with DSS layers to EI [17], [18], as explained in Section I.”
BackgroundEnergy efficient spike transformer accelerator at the edge
Du, C., Wen, Q., Wei, Z., & Zhang, H. (2024) · Intelligent Marine Technology and Systems · doi:10.1007/s44295-024-00040-5 · Cited by 7
“Therefore, running LLMs at the edge (Shi et al. 2016; Zhou et al. 2019) or even on the device itself is desirable to meet these requirements.”
Artificial Intelligence of Things: Architectures, Applications, and Challenges
Ahvar, E., Ahvar, S., & Lee, G. M. (2023) · Springer handbooks · doi:10.1007/978-3-031-39650-2_19 · Cited by 9
Over-the-Air Computation Empowered Vertically Split Inference
Yang, P., Wen, D., Zeng, Q., Zhou, Y., Wang, T., Cai, H., & Shi, Y. (2024) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2024.3485678 · Cited by 6
Virtual Power Plants Security Challenges, Solutions, and Emerging Trends: A Review
Rao, S. P., Tiruvalluru, R. S., Balaji, S. R. A., Tomomewo, O. S., & Ranganathan, P. (2024) · Cyber Awareness and Research Symposium (CARS) · doi:10.1109/cars61786.2024.10778817 · Cited by 6
“The privacy problems associated with 5G technologies in a centralized architecture can be mitigated by shifting towards a distributed architecture [101], [102].”
(2025) · doi:10.1016/j.iot.2026.101938 · Cited by 31
Edge Intelligence in Enhancing Last-Mile Delivery Logistics
dos Reis, J. C. G. (2025) · IEEE Access · doi:10.1109/access.2025.3570894 · Cited by 6
“…advancements in Edge AI or Edge Intelligence (EI) have demonstrated substantial potential for The associate editor coordinating the review of this manuscript and approving it for publication was Szidonia Lefkovits . addressing these challenges and optimizing last-mile logistics processes [5].”
InfluentialNair, R. R., Babu, T., Kishore, S. P., et al. (2025) · International Conference on Computing for Sustainable Global Development · doi:10.23919/indiacom66777.2025.11115629 · Cited by 6
“Among these innovations, automated traffic violation detection systems have gained prominence due to their potential to provide continuous, unbiased monitoring and rapid response capabilities [3].”
Sousa, A., Correia, L., & Reis, M. J. C. S. (2025) · Intelligent Cybersecurity Conference (ICSC) · doi:10.1109/icsc65596.2025.11140446 · Cited by 6
“To address this, researchers have developed lightweight neural networks such as TinyML, MobileNet, and pruning-quantization strategies that allow inference directly on edge nodes [10].”
Custom-IP for Gradient Descent Optimization based on Hardware/Software Co-design Paradigm
Shabarinath, B. B., & Muralidhar, P. (2020) · International Symposium on VLSI Design and Test (VDAT) · doi:10.1109/vdat50263.2020.9190560 · Cited by 6
“Z. Zhou demonstrated various advantages of using edge device for computing machine learning algorithms and intimated few architectures and performance metrics for edge computing devices [7].”
Background
Metadata
- Authors
- Zhou, Z., Chen, X., Li, E., Zeng, L., Luo, K., & Zhang, J.
- Affiliations
- Sun Yat-sen University (CN)
- Arizona State University (US)
- Venue
- Proceedings of the IEEE
- Published
- 2019-08
- Volume
- 107
- Issue
- 8
- Pages
- 1738-1762
- ISSN
- 0018-9219 (ISSN-L)
- 1558-2256
- OpenAlex
- W2950865323
- Semantic Scholar
- 928cd808aba140ec298508df87c5579811ff2f41
- Cited by
- 2,455
- References
- 168
- Citations by year
- 2026: 455 · 2025: 352 · 2024: 332 · 2023: 363 · 2022: 370 · 2021: 341 · 2020: 215 · 2019: 26
- FWCI
- 130.23
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- Proceedings of the IEEE (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Basic Research Program of China (2017YFB1001703)
- National Natural Science Foundation of China (U1711265, 61802449)
- Program for Guangdong Introducing Innovative and Entrepreneurial Teams (2017ZT07X355)
- Guangdong Natural Science Funds (2018A030313032)
- Fundamental Research Funds for the Central Universities (17lgjc40)
- Army Research Office (W911NF-16-1-0448)
- Defense Threat Reduction Agency (HDTRA1-13-1-0029)
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Information Systems › Internet of Things and AI
- Keywords
- edge AI, edge computing, edge computing architecture, deep learning training, deep learning inference, Internet of Things, mobile computing
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.
A language model drew the claims from the paper on 2026-10-11, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-11 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
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
