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 501–600 of 2,413
Wu, F., Zhang, X., Zhang, C., et al. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.3004811 · Cited by 27
“Zhou et al. [25] and Wazid et al. [26] introduce edge computing and fog computing to the Internet of Vehicles, employing the computing power of edge nodes in the network to share the pressure of message verification in the VANETs.”
MethodSelf-citationDigital Twin-enabled AI Enhancement in Smart Critical Infrastructures for 5G
Gai, K., Xiao, Q., Qiu, M., Zhang, G., Chen, J., Wei, Y., & Zhang, Y. (2022) · ACM Transactions on Sensor Networks · doi:10.1145/3526195 · Cited by 28
“Unlike running AI algorithms on individual edge devices, edge AI systems facilitate a task allocation to ensure computational tasks are distributed in an optimal mode [47].”
BackgroundWang, F., Cai, S., & Lau, V. K. N. (2022) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2022.3221850 · Cited by 28
“The energy queue dynamics has not been considered in the aforementioned MEC works [10], [11], [12], [13], [14], [15], [16], [17], [18].”
BackgroundSPACE: Segment Prefetching and Caching at the Edge for Adaptive Video Streaming
Aguilar-Armijo, J., Timmerer, C., & Hellwagner, H. (2023) · IEEE Access · doi:10.1109/access.2023.3252365 · Cited by 27
Ouyang, T., Chen, X., Zeng, L., et al. (2019) · Proceedings/Proceedings - Real-Time Systems Symposium · doi:10.1109/rtss46320.2019.00041 · Cited by 27
“And two families of edge devices with [1 , 3] GHz and [0 , 6] GHz computing capacity are considered.”
BackgroundSelf-citationIm, D., Park, G., Li, Z., Ryu, J., & Yoo, H. (2023) · IEEE International Symposium on High-Performance Computer Architecture (HPCA) · doi:10.1109/hpca56546.2023.10071031 · Cited by 27
“D applications such as natural language processing (NLP) [4], [19], photography improvement [15], visual question and answering [40], and AR/VR [43].”
BackgroundJoint DNN partitioning and task offloading in mobile edge computing via deep reinforcement learning
Zhang, J., Shu-fang, M., Yan, Z., & Huang, J. (2023) · Journal of Cloud Computing Advances Systems and Applications · doi:10.1186/s13677-023-00493-9 · Cited by 26
“Although edge intelligence technology has brought many benefits [17], edge-based DNN inference tasks remain heavily reliant on stable and reliable communication conditions between the MD and the edge server [9].”
BackgroundSelf-citationDong, C., Shafiq, M., Dabel, M. M. A., Sun, Y., & Tian, Z. (2023) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2023.3339468 · Cited by 28
“Offloading computation-intensive tasks in the MEC is an efficient method to provide low-latency, high-quality inference services [6], [7].”
MethodImplementation of Big AI Models for Wireless Networks with Collaborative Edge Computing
Zeng, L., Ye, S., Chen, X., & Yang, Y. (2024) · IEEE Wireless Communications · doi:10.1109/mwc.004.2300479 · Cited by 26
“Nevertheless, big AI models, which are elfevident to be large, typically comprised of computation-intensive Transformer blocks in millions and even billions of parameters, posing significant challenges for model training on usually appeal to the powerful cloud, applying a centralized training…”
BackgroundSelf-citationShen, S., Cai, C., Shen, Y., et al. (2025) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2025.3542104 · Cited by 26
Chien, S.-C., Yen, C.-M., Chang, Y., Chen, Y., Liu, C.-C., Hsiao, Y.-P., Yang, P.-Y., Lin, H.-M., Yang, T.-E., Lu, X.-H., et al. (2025) · Journal of Medical Internet Research · doi:10.2196/56692 · Cited by 30
“Regarding EI, Zhou et al [10] explored EI’s potential to enhance real-time decision-making through edge computing, particularly in environments that generate vast amounts of data, such as those supported by IoT devices.”
Adaptive Critical Care Intervention in the Internet of Medical Things
Pazienza, A., Anglani, R., Mallardi, G., Fasciano, C., Noviello, P., Tatulli, C., & Vitulano, F. (2020) · IEEE Conference on Evolving and Adaptive Intelligent Systems (EAIS) · doi:10.1109/eais48028.2020.9122762 · Cited by 27
“Essentially, the physical proximity between the computing and information-generation sources promises several benefits compared to the traditional cloud-based computing paradigm, including energy-efficiency, reduced bandwidth consumption, and context-awareness [2].”
BackgroundLee, C.-S., Hong, S., Hong, S.-B., & Kim, T. (2020) · ETRI Journal · doi:10.4218/etrij.2020-0112 · Cited by 26
“To overcome these challenges, many studies have been conducted that focus on improving the efficiency of DNN inference [6,7].”
BackgroundA Secure and Privacy-Preserving Machine Learning Model Sharing Scheme for Edge-Enabled IoT
Zhou, X., Xu, K., Wang, N., Jiao, J., Dong, N., Han, M., & Xu, H. (2021) · IEEE Access · doi:10.1109/access.2021.3051945 · Cited by 25
“If these huge data are processed by cloud computing, the process of sending them to the cloud will consume a lot of bandwidth resource and bring great computing pressure to the cloud [2].”
BackgroundAdaptive DNN Partition in Edge Computing Environments
Miao, W., Zeng, Z., Wei, L., Li, S., Jiang, C., & Zhang, Z. (2020) · IEEE International Conference on Parallel and Distributed Systems (ICPADS) · doi:10.1109/icpads51040.2020.00097 · Cited by 29
“The speed of getting analysis result depends on the wide area network (WAN) bandwidth to a great extent, yet the conditions of WAN is unpredictable and risky, leading to overtime or privacy leakage [3].”
BackgroundCamera-LiDAR Multi-Level Sensor Fusion for Target Detection at the Network Edge
Mendez, J., Molina, M., Rodríguez, N., et al. (2021) · Sensors · doi:10.3390/s21123992 · Cited by 26
“At the same time, the limitations of the final system in which the models should be integrated must be studied to ensure the suitability of the models for the system regarding memory and computing power requirements due to the specifications of the processing units deployed at the network edge [21,22].”
BackgroundMulti-Exit Semantic Segmentation Networks
Kouris, A., Venieris, S. I., Laskaridis, S., & Lane, N. D. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19803-8_20 · Cited by 36
“However, these solutions [20,24,74] have mainly aimed at image classification so far, leaving challenges in segmentation, such as the design of lightweight exit architectures and exit policies, largely unaddressed.”
BackgroundEnd-to-end predictive intelligence diagnosis in brain tumor using lightweight neural network
Ma, L., & Zhang, F. (2021) · Applied Soft Computing · doi:10.1016/j.asoc.2021.107666 · Cited by 29
Shi, L., Xu, Z., Sun, Y., Shi, Y., Fan, Y., & Ding, X. (2021) · Peer-to-Peer Networking and Applications · doi:10.1007/s12083-021-01223-1 · Cited by 25
Ma, X., Zhao, J.-H., & Gong, Y. (2021) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2021.3107465 · Cited by 22
“It is still highly nontrivial concerning on communication burdens and data security issues at the network edge, especially with the increasing complexity of on-board sensor systems accompanying by a large amount of raw data available for learning [7].”
BackgroundZhang, J., Chen, S., Zhou, X., Wang, X., & Lin, Y. (2022) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2022.3148208 · Cited by 25
“As mentioned in [24], the data owned by the devices participating in distributed machine learning are usually non-i. i.d, which has been considered in several papers on federated learning.”
BackgroundSelf-citationOptimizing Aggregation Frequency for Hierarchical Model Training in Heterogeneous Edge Computing
Yang, L., Gan, Y., Cao, J., & Wang, Z. (2022) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2022.3149584 · Cited by 26
“To address these challenges, edge intelligence [1] has been proposed to perform AI model training and inference in closer proximity to data sources.”
EdgeFaaSBench: Benchmarking Edge Devices Using Serverless Computing
Rajput, K. R., Kulkarni, C. D., Cho, B., Wang, W., & Kim, I. K. (2022) · IEEE International Conference on Edge Computing and Communications (EDGE) · doi:10.1109/edge55608.2022.00024 · Cited by 29
“The applications hosted on edge server layer perform deep learning (DL) inference [7] and big data analytics [56] operations, which tend to require high-performance processors, GPUs, and edge AI accelerators.”
BackgroundNa, J., Zhang, H., Lian, J., & Zhang, B. (2022) · Applied Sciences · doi:10.3390/app122010619 · Cited by 27
Data Integrity Verification in Mobile Edge Computing With Multi-Vendor and Multi-Server
Zhao, Y., Qu, Y., Chen, F., et al. (2023) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2023.3310532 · Cited by 26
An Artificial Intelligence Perspective on Mobile Edge Computing
Chen, Z., He, Q., Liu, L., Lan, D., Chung, H.-M., & Mao, Z. (2019) · IEEE International Conference on Smart Internet of Things (SmartIoT) · doi:10.1109/smartiot.2019.00024 · Cited by 25
“1) Convolution Neural Network: Convolution neural networks (CNNs) are commonly used in computer vision [23].”
BackgroundAn Overview of Data-Importance Aware Radio Resource Management for Edge Machine Learning
Wen, D., Li, X., Zeng, Q., Ren, J., & Huang, K. (2019) · Journal of Communications and Information Networks · doi:10.23919/jcin.2019.9005429 · Cited by 28
Gordienko, Y. G., Kochura, Y., Taran, V., Gordienko, N., Rokovyi, O., Alienin, O., & Stirenko, S. (2020) · Advances in computers · doi:10.1016/bs.adcom.2020.10.003 · Cited by 27
Analysis of Edge-Optimized Deep Learning Classifiers for Radar-Based Gesture Recognition
Chmurski, M., Zubert, M., Bierzynski, K., & Santra, A. (2021) · IEEE Access · doi:10.1109/access.2021.3081353 · Cited by 27
“Deep Learning methods have made distinct breakthroughs in a broad spectrum of fields, including computer vision, speech recognition, natural language processing, medical diagnosis, and board games [3]–[5].”
BackgroundMethodInfluentialGasset, A., G., V. W. J. B., Mirabent, F., Sales‐Vallverdú, A., Garcia‐Ortega, X., Montesinos, J. L. G., Manzano, T., & Valero, F. (2024) · Frontiers in Bioengineering and Biotechnology · doi:10.3389/fbioe.2024.1439638 · Cited by 27
“This requires as much data as possible, to be trained with the aim of achieving accurate and feasible models (Das et al., 2015; Ondracka et al., 2023; Zhou et al., 2019).”
BackgroundRoy, K., Wang, C., Roy, S., Raghunathan, A., Yang, K., & Sengupta, A. (2024) · Nature Reviews Electrical Engineering · doi:10.1038/s44287-024-00107-9 · Cited by 27
“With the proliferation of intelligent devices, including smartphones, the Internet of Things and the relative explosion of digital data, computing platforms across the spectrum increasingly perform brain-like tasks involving recognition, analytics, inference, reasoning and decision making 1,2 .”
Computation-Aware Offloading for DNN Inference Tasks in Semantic Communication Assisted MEC Systems
Zheng, G., Wen, M., Ning, Z., & Ding, Z. (2025) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2024.3523517 · Cited by 31
“A rapid development of artificial intelligence has led to the widespread use of deep neural network (DNN) applications, e.g., image/video analysis and natural language processing, in a broad range of smart mobile devices [1], [2], [3].”
Su, Y., Fan, W., Meng, Q., Chen, P., & Liu, Y. (2025) · IEEE Transactions on Cloud Computing · doi:10.1109/tcc.2025.3530681 · Cited by 29
Li, Y., Zeng, Z., Li, J., et al. (2020) · IEEE Communications Letters · doi:10.1109/lcomm.2020.3041453 · Cited by 25
“More and more enterprises require AI-based applications, including Web search, recommendation systems, and document analysis [1].”
BackgroundSelf-citationVenkatachary, S. K., Alagappan, A., & Andrews, L. J. B. (2021) · Energy Informatics · doi:10.1186/s42162-021-00139-7 · Cited by 30
Blockchain-Enabled Access Management System for Edge Computing
Zhu, Y., Huang, C.-W., Hu, Z., Al-Dhelaan, A., & Al-Dhelaan, M. (2021) · Electronics · doi:10.3390/electronics10091000 · Cited by 17
Collaborative Inference via Ensembles on the Edge
Shlezinger, N., Farhan, E., Morgenstern, H., & Eldar, Y. C. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9414740 · Cited by 27
Kilcioglu, E., Mirghasemi, H., Stupia, I., & Vandendorpe, L. (2021) · IEEE Access · doi:10.1109/access.2021.3084689 · Cited by 26
“Some of the articles [4], [24], [29], [30] survey about deploying deep learning architectures in wireless communication and mobile edge computing perspectives.”
BackgroundSubedi, P., Hao, J., Kim, I. K., & Ramaswamy, L. M. (2021) · IEEE ... International Conference on Cloud Computing · doi:10.1109/cloud53861.2021.00016 · Cited by 25
“Towards addressing the above limitations, researchers have recently been exploring the AI at the edge paradigm [2], [16]–[19], where DL applications are hosted at the edge of the Internet (e.”
BackgroundContext-aware Adaptive Surgery
Wang, H., Guo, B., Liu, J., Liu, S., Wu, Y., & Yu, Z. (2021) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3478073 · Cited by 27
“Edge computing [47] emerges to offload parts of computing tasks from the cloud to end devices, which can reduce the burden of data transmission and energy consumption.”
BackgroundRahman, M. J., Morshed, B. I., Harmon, B. E., & Rahman, M. (2021) · Smart Health · doi:10.1016/j.smhl.2021.100249 · Cited by 25
Liquid Software-Based Edge Intelligence for Future 6G Networks
Yang, T., Qin, M., Cheng, N., et al. (2022) · IEEE Network · doi:10.1109/mnet.011.2000654 · Cited by 25
Trine: Cloud-Edge-Device Cooperated Real-Time Video Analysis for Household Applications
Zhao, Y., Yang, Z., He, X., Cai, X., Miao, X., & Ma, Q. (2022) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2022.3154721 · Cited by 28
“Heterogeneity is one of the most significant characteristics of edge devices [27].”
BackgroundLi, X., Xu, Z., Fang, F., Fan, Q., Wang, X., & Leung, V. C. M. (2022) · IEEE Transactions on Cloud Computing · doi:10.1109/tcc.2022.3177649 · Cited by 25
“Compared with the traditional cloud computing paradigm, the authors in [30] proved that deploying DL models on edge servers could bring significant performance improvements in saving core network resources and reducing inference delays.”
MethodLi, Z., Chen, Z., Wei, X., Gao, S. B., Ren, C., & Quek, T. Q. S. (2022) · IEEE International Conference on Sensing, Communication, and Networking (SECON) · doi:10.1109/secon55815.2022.9918588 · Cited by 30
“With the rapid development of IoT and the massive amount of data generated and collected by IoT devices [1], Machine Learning (ML) technology has been widely applied in urban environmental prediction tasks of smart city applications [2] [3].”
BackgroundLarian, H., & Safi-Esfahani, F. (2025) · Computing · doi:10.1007/s00607-024-01388-6 · Cited by 25
“…closer to data generation and simultaneously enabling cloudbased analytics when neces-3 Figure 1: Machine Leaning Pipeline [14] sary, these systems overcome centralized processing constraints and unlock new possibilities for automation and efficiency in real-time adaptive applications [35, 37].”
Train-to-Edge Cooperative Intelligence for Obstacle Intrusion Detection in Rail Transit
Gong, T., Zhu, L., Yu, F. R., & Tang, T. (2024) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2024.3355230 · Cited by 23
Federated Learning for 6G Networks: Navigating Privacy Benefits and Challenges
Sandeepa, C., Zeydan, E., Samarasinghe, T., & Liyanage, M. (2024) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2024.3513832 · Cited by 33
“One of the strategies to implement this in 6G is by bringing AI closer to the IoT edge [241], [242], where data and decisions are shared within the closer proximity of the data owners or the end users.”
Jin, W., Xu, R., Lim, S., Park, D.-H., Park, C., & Kim, D. (2021) · Sensors · doi:10.3390/s21020630 · Cited by 28
“Additionally, the intelligent services are provided based on the sufficient computational ability of the edge gateway [19].”
BackgroundNew universal sustainability metrics to assess edge intelligence
Lenherr, N., Pawlitzek, R., & Michel, B. (2021) · Sustainable Computing Informatics and Systems · doi:10.1016/j.suscom.2021.100580 · Cited by 24
BBNet: A Novel Convolutional Neural Network Structure in Edge-Cloud Collaborative Inference
Zhou, H., Zhang, W., Wang, C., Ma, X., & Yu, H. (2021) · Sensors · doi:10.3390/s21134494 · Cited by 23
“At present, the most common DNN deployment methods are mobile-only and cloud-only [3].”
BackgroundWang, P., Ouyang, T., Liao, G., Gong, J., Yu, S., & Chen, X. (2022) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2022.102664 · Cited by 26
Self-citationA Hybrid CMOS-Memristor Spiking Neural Network Supporting Multiple Learning Rules
Florini, D., Gandolfi, D., Mapelli, J., Benatti, L., Pavan, P., & Puglisi, F. M. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3202501 · Cited by 25
“This limitation becomes of primary importance if artificial intelligence (AI) algorithms are asked to be solved locally in low-power systems (so-called edge intelligence) since AI algorithms are typically energy-hungry [3].”
BackgroundDevice Scheduling in Over-the-Air Federated Learning Via Matching Pursuit
Bereyhi, A., Vagollari, A., Asaad, S., Müller, R. R., Gerstacker, W., & Poor, H. V. (2023) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2023.3284376 · Cited by 26
“By performing data processing at the edge of networks, several shortcomings of cloud computing, such as long latency and network congestion, can be effectively addressed [6], [7], [8].”
BackgroundRethinking Pruning for Accelerating Deep Inference At the Edge
Gao, D., He, X., Zhou, Z., Tong, Y., Xu, K., & Thiele, L. (2020) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3394486.3403058 · Cited by 23
Self-citationDynamic resource allocation for jointing vehicle-edge deep neural network inference
Wang, Q., Li, Z., Nai, K., et al. (2021) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2021.102133 · Cited by 24
Personalized Federated Learning for Intelligent IoT Applications: A Cloud-Edge based FrameworkPreprint
Wu, Q., He, K., & Chen, X. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.10671 · Cited by 24
“To tackle the high communication and computation cost issues in device heterogeneity, we resort to edge computing which brings the necessary on-demand computing power in the proximity of IoT devices [2].”
BackgroundSelf-citationA Survey on Self-Evolving Autonomous Driving: A Perspective on Data Closed-Loop Technology
Li, X., Wang, Z., Huang, Y., & Chen, H. (2023) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2023.3319689 · Cited by 25
Adaptive and Parallel Split Federated Learning in Vehicular Edge Computing
Qiang, X., Chang, Z., Hu, Y., Liu, L., & Hämäläinen, T. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3479158 · Cited by 32
“Integrating artificial intelligence (AI) technology into vehicular edge computing (VEC) platforms, which provide storage, computing, and networking resources, the full capabilities of VEI can be realized [4].”
Cui, S., Hoang, T., Mechitov, K. A., et al. (2024) · Engineering Structures · doi:10.1016/j.engstruct.2024.119520 · Cited by 23
Collaborative Intelligence: Accelerating Deep Neural Network Inference via Device-Edge Synergy
Shan, N., Ye, Z., & Cui, X. (2020) · Security and Communication Networks · doi:10.1155/2020/8831341 · Cited by 23
“, edge intelligence) [5] to minimize the service latency will be the main consideration in this paper.”
BackgroundShen, T., Gao, C. J., & Xu, D. (2020) · Journal of Real-Time Image Processing · doi:10.1007/s11554-020-01039-x · Cited by 23
Unifying Futures and Spot Market: Overbooking-Enabled Resource Trading in Mobile Edge Networks
Liwang, M., Chen, R., Wang, X., et al. (2022) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2022.3141094 · Cited by 23
Artificial Intelligence for Enhanced Mobility and 5G Connectivity in UAV-Based Critical Missions
Lins, S., Cardoso, K. V., Both, C. B., Mendes, L. L., de Rezende, J. F., da Silveira, A. M., Linder, N., & Junior, A. B. D. R. K. (2021) · IEEE Access · doi:10.1109/access.2021.3103041 · Cited by 24
“Regarding UAVbased computer vision, recent advances included adopting computationally-heavy Deep Neural Network (DNN) models, imposing high throughput between edge and cloud networks [7].”
MethodPreemptive Scheduling for Distributed Machine Learning Jobs in Edge-Cloud Networks
Wang, N., Zhou, R., Jiao, L., Zhang, R., Li, B., & Li, Z. (2022) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2022.3180772 · Cited by 23
“ML model training customarily exploits data parallelism or/and model parallelism [2] [3], in which data parallelism maintains multiple replicas of models among servers, and model parallelism stores copies of datasets.”
BackgroundEdge Computing Solutions for Distributed Machine Learning
Marozzo, F., Orsino, A., Talia, D., & Paolo Trunfio, A. (2022) · IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech) · doi:10.1109/dasc/picom/cbdcom/cy55231.2022.9927824 · Cited by 24
“[5] summarize the main solutions and enabling technologies for model training and inference of deep neural networks on edge devices, both from an application”
BackgroundOpportunistic Digital Twin: an Edge Intelligence enabler for Smart City
Savaglio, C., Barbuto, V., Awan, F. M., Minerva, R., Crespi, N., & Fortino, G. (2023) · ACM Transactions on Sensor Networks · doi:10.1145/3616014 · Cited by 25
“Indeed, in recent years, advanced virtualization techniques and distributed Edge Intelligence (EI) [6, 48] have emerged as key elements to enable the development of the outlined smart cities platforms and related services in a decentralized way and in spite of their inherent complexity.”
BackgroundGibbs, M., & Kanjo, E. (2023) · International Conference on Edge Computing [Services Society] · doi:10.1109/edge60047.2023.00056 · Cited by 18
JAVP: Joint-Aware Video Processing with Edge-Cloud Collaboration for DNN Inference
Yang, Z., Ji, W., Guo, Q., & Wang, Z. (2023) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3581783.3613914 · Cited by 23
“However, edge servers with limited resources can usually only deploy small DNN models [45], which is difficult to meet the accuracy requirements of complex tasks.”
BackgroundEdge-Based Missing Data Imputation in Large-Scale Environments
Guastella, D. A., Marcillaud, G., & Valenti, C. F. (2021) · Information · doi:10.3390/info12050195 · Cited by 23
“Edge Intelligence (EI) meets the need for providing AI techniques in edge computing and is used in a wide spectrum of AI applications, spanning from cognitive assistance to precision agriculture, smart home and industrial IoT [4].”
BackgroundInfluentialMobile Edge Intelligence and Computing for the Internet of VehiclesPreprint
Zhang, J., & Letaief, K. B. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.00400 · Cited by 23
“[37] Z.”
BackgroundSelf-citationReconfigurable Intelligent Surface for Green Edge InferencePreprint
Hua, S., Zhou, Y., Yang, K., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.00820 · Cited by 23
“By leveraging edge computing [11] and deploying DNN models at the edge base stations (BSs) that have strong computational capacity and large storage resources, edge inference stands out as a promising paradigm to provide intelligent services for MDs [12].”
BackgroundBeyond traditional orthopaedic data analysis: AI, multimodal models and continuous monitoring
Oettl, F. C., Zsidai, B., Oeding, J. F., Hirschmann, M. T., FELDT, R. H., Tischer, T., Samuelsson, K., & ESSKA Artificial Intelligence Working Group (2025) · Knee Surgery Sports Traumatology Arthroscopy · doi:10.1002/ksa.12657 · Cited by 29
“Additionally, emerging technologies like edge computing offer promising avenues for enhancing data security by processing sensitive information closer to its source, thereby reducing transmission risks and maintaining patient con fi dentiality [49].”
A Decade of Video Analytics at Edge: Training, Deployment, Orchestration, and Platforms
Bai, T., Zhao, H., Huang, L., Wang, Z., Kim, D. I., & Nallanathan, A. (2025) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2025.3563377 · Cited by 25
“Park et al. [19] and Murshed et al. [26] reviewed research efforts of machine learning for edge computing, while the training and inference of deep learning model at the network edge were focused in [17], [18], [20], [29].”
Huang, J., Zhou, S., Li, G., & Shen, Q. (2025) · Scientific Reports · doi:10.1038/s41598-025-07592-4 · Cited by 30
“Additionally, ensuring the security and privacy of sensitive energy data in a distributed environment poses significant challenges 9,10,13 .”
Data-driven Distributionally Robust Optimization for Edge Intelligence
Zhang, Z., Lin, S., Dedeoğlu, M., Ding, K., & Zhang, J. (2020) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom41043.2020.9155440 · Cited by 22
Self-citationHe, J., Guo, S., Qiao, D., & Lin, Y. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3145360 · Cited by 22
Ghibellini, A., Bononi, L., & Felice, M. D. (2022) · IEEE Consumer Communications & Networking Conference (CCNC) · doi:10.1109/ccnc49033.2022.9700665 · Cited by 22
Fograph: Enabling Real-Time Deep Graph Inference with Fog Computing
Zeng, L., Huang, P., Luo, K., Zhang, X., Zhou, Z., & Chen, X. (2022) · International World Wide Web Conference (WWW) · doi:10.1145/3485447.3511982 · Cited by 23
“To tame such intractability, a promising solution is to exploit available computing resources in proximity to data sources with the emerging fog computing1 paradigm [79].”
MethodSelf-citationPerformance analysis of real-time object detection on Jetson device
Zhu, J., Feng, H., Zhong, S., & Yuan, T. (2022) · IEEE/ACIS International Conference on Computer and Information Science (ICIS) · doi:10.1109/icis54925.2022.9882480 · Cited by 21
“On the other hand, if a large amount of user data is concentrated in the cloud center, it may increase the risk of privacy leakage [3].”
BackgroundOn the Dependability of 6G Networks
Ahmad, I., Yaguache, F. R., Huusko, J., & Seppänen, K. (2023) · Electronics · doi:10.3390/electronics12061472 · Cited by 23
Xie, C., Daghero, F., Chen, Y., Castellano, M., Gandolfi, L., Calimera, A., Macii, E., Poncino, M., & Pagliari, D. J. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3263290 · Cited by 23
“This is beneficial for confidentiality, as it reduces the risk of accidental or malicious leakage of sensitive raw data (e.g., images, audio, video, etc) [1], [6].”
BackgroundA Feedback-Driven DNN Inference Acceleration System for Edge-Assisted Video Analytics
Lv, X., Wang, Q., Chen, Y., & Jin, H. (2023) · IEEE Transactions on Computers · doi:10.1109/tc.2023.3275094 · Cited by 21
“computing has greatly aroused the deployment of video analysis applications [7], [8], [9], [10], [11], [12].”
BackgroundA3D: Adaptive, Accurate, and Autonomous Navigation for Edge-Assisted Drones
Zeng, L., Chen, H., Feng, D., Zhang, X., & Chen, X. (2023) · IEEE/ACM Transactions on Networking · doi:10.1109/tnet.2023.3297876 · Cited by 22
“1(b), A3D eases the drone’s burden by selectively migrating onboard workload to nearby edge servers, targeting reducing inference latency for accurate navigation decisions.”
BackgroundSelf-citationLiu, C., Tang, D., Zhu, H., et al. (2023) · Robotics and Computer-Integrated Manufacturing · doi:10.1016/j.rcim.2023.102638 · Cited by 22
Chen, C., Jiang, B., Liu, S., Li, C., Wu, C., & Yin, R. (2023) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2023.3318080 · Cited by 22
LAMBO: Large AI Model Empowered Edge Intelligence
Li, D., Jiang, F., Peng, Y., Wang, K., Yang, K., Pan, C., & Schober, R. (2024) · IEEE Communications Magazine · doi:10.1109/mcom.001.2400076 · Cited by 31
“1, and described as follows [5]–[9]: 1) Data Collection and Preprocessing: Data collection is crucial for traditional offloading models that use deep learning in edge intelligence systems.”
BackgroundA QoE-Aware Service-Enhancement Strategy for Edge Artificial Intelligence Applications
Xia, J., Cheng, G., Guo, D., & Zhou, X. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.2996422 · Cited by 23
“algorithms are adopted to support those AI applications, which range from computer vision, speech recognition, and natural language processing [1].”
MethodFedViT: Federated continual learning of vision transformer at edge
Zuo, X., Luopan, Y., Han, R., Zhang, Q., Liu, C. H., Wang, G., & Chen, L. Y. (2023) · Future Generation Computer Systems · doi:10.1016/j.future.2023.11.038 · Cited by 22
EdgeCI: Distributed Workload Assignment and Model Partitioning for CNN Inference on Edge Clusters
Chen, Y., Luo, T., Fang, W. W., & Xiong, N. N. (2024) · ACM Transactions on Internet Technology · doi:10.1145/3656041 · Cited by 24
“To alleviate discrepancy between the intensive resource requirements of CNNs and the limited computing powers of IoT devices, many researchers have explored a lot of optimization technologies, including model compression [12, 13], dynamic inference [14, 15], and edge-cloud synergy [16–18].”
BackgroundEnhancing IoT-Edge Computation with Data Forwarding based Decentralized Deep Neural Networks
Prasad, B., Jopate, R., Savita, P., et al. (2023) · International Conference on Image Information Processing (ICIIP) · doi:10.1109/iciip61524.2023.10537705 · Cited by 21
“This makes it possible for older people to receive better care, receive medical assistance more quickly, have regular activity monitored, and have regular check-ups [2].”
BackgroundMethodPrivacy and security vulnerabilities in edge intelligence: An analysis and countermeasures
Shafee, A. A., Hasan, S. R., & Awaad, T. A. (2025) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2025.110146 · Cited by 25
Huang, X., Chen, Y., Liu, Z., Zhao, S., Li, Z., Chen, R., & Guan, Q. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3546304 · Cited by 21
“Various DRL algorithms based on Q-learning, deep Q-network (DQN), and deep deterministic policy gradient (DDPG) are implemented to train and develop optimal models [36].”
Edge AI for Smart Cities: Foundations, Challenges, and Opportunities
Velaga, K. S., Guo, Y., & Yu, W. (2025) · Smart Cities · doi:10.3390/smartcities8060211 · Cited by 38
Multi-user Edge-assisted Video Analytics Task Offloading Game based on Deep Reinforcement Learning
Chen, Y., Zhang, S., Xiao, M., et al. (2020) · IEEE International Conference on Parallel and Distributed Systems (ICPADS) · doi:10.1109/icpads51040.2020.00044 · Cited by 21
“Meanwhile, with the development of deep learning, artifi-cial intelligence (AI) applications and services have boomed in the recent years, including recommendation systems, personal assistant and video surveillance [4], [5].”
BackgroundOptimizing computational resources for edge intelligence through model cascade strategies
Gomez-Carmona, O., Casado-Mansilla, D., Lopez-de-Ipina, D., & Garcia-Zubia, J. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3118845 · Cited by 21
PrivStream: A privacy-preserving inference framework on IoT streaming data at the edge
Wang, D., Ren, J., Wang, Z., Zhang, Y., & Shen, X. (2021) · Information Fusion · doi:10.1016/j.inffus.2021.11.013 · Cited by 23
D’Antoni, F., Petrosino, L., Sgarro, F., Pagano, A., Vollero, L., Piemonte, V., & Merone, M. (2022) · Bioengineering · doi:10.3390/bioengineering9050183 · Cited by 21
“However, the increasing development of new, more powerful, and dedicated hardware, combined with the widespread use of IoT (Internet of Things) tools, enables the emergence of a branch of artificial intelligence known as inference at the edge [25,26].”
6G Communication: A Vision on the Potential Applications
Nayak, S., & Patgiri, R. (2022) · Lecture notes in electrical engineering · doi:10.1007/978-981-19-0019-8_16 · Cited by 40
“Edge Intelligence is combining Edge computing and AI [27].”
Grasso, C., Raftopoulos, R., Schembra, G., & Serrano, S. (2022) · Computer Networks · doi:10.1016/j.comnet.2022.109449 · Cited by 21
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
