CoChat

A Survey on Optimization Techniques for Edge Artificial Intelligence (AI)

Open access

The DOI matches its Crossref record; 101 of the 101 references it cites were found in a registry or an index.

Abstract

Artificial Intelligence (Al) models are being produced and used to solve a variety of current and future business and technical problems. Therefore, AI model engineering processes, platforms, and products are acquiring special significance across industry verticals. For achieving deeper automation, the number of data features being used while generating highly promising and productive AI models is numerous, and hence the resulting AI models are bulky. Such heavyweight models consume a lot of computation, storage, networking, and energy resources. On the other side, increasingly, AI models are being deployed in IoT devices to ensure real-time knowledge discovery and dissemination. Real-time insights are of paramount importance in producing and releasing real-time and intelligent services and applications. Thus, edge intelligence through on-device data processing has laid down a stimulating foundation for real-time intelligent enterprises and environments. With these emerging requirements, the focus turned towards unearthing competent and cognitive techniques for maximally compressing huge AI models without sacrificing AI model performance. Therefore, AI researchers have come up with a number of powerful optimization techniques and tools to optimize AI models. This paper is to dig deep and describe all kinds of model optimization at different levels and layers. Having learned the optimization methods, this work has highlighted the importance of having an enabling AI model optimization framework.

Overview

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

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

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

Integrity signals

Registry

Crossref · 10.3390/s23031279

Cites

101 of 101 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 Block diagram of edge AI-based defect detection.
Figure 1 Block diagram of edge AI-based defect detection.CC BY · PubMed Central
Figure 2 Review method.
Figure 2 Review method.CC BY · PubMed Central
Figure 3 Categories of optimization methods.
Figure 3 Categories of optimization methods.CC BY · PubMed Central
Figure 4 Categories of optimization methods are placed against the inherent technology stack of an AI application.
Figure 4 Categories of optimization methods are placed against the inherent technology stack of an AI application.CC BY · PubMed Central
Figure 5 Graph denoting the major and sub categories of publications.
Figure 5 Graph denoting the major and sub categories of publications.CC BY · PubMed Central
Figure 6 Steps in FPGA.
Figure 6 Steps in FPGA.CC BY · PubMed Central
Figure 7 Concept of federated learning in edge servers (shown with four nodes).
Figure 7 Concept of federated learning in edge servers (shown with four nodes).CC BY · PubMed Central
Figure 8 Federated learning in a peer-to-peer model.
Figure 8 Federated learning in a peer-to-peer model.CC BY · PubMed Central
Figure 9 Deep transfer learning.
Figure 9 Deep transfer learning.CC BY · PubMed Central
Figure 10 Knowledge distillation.
Figure 10 Knowledge distillation.CC BY · PubMed Central
Figure 11 Pruning of connections and neurons.
Figure 11 Pruning of connections and neurons.CC BY · PubMed Central
Figure 12 Filter and channel pruning.
Figure 12 Filter and channel pruning.CC BY · PubMed Central
Figure 13 Post-training quantization and quantization-aware retraining.
Figure 13 Post-training quantization and quantization-aware retraining.CC BY · PubMed Central
Figure 14 Weight sharing.
Figure 14 Weight sharing.CC BY · PubMed Central
Figure 15 Different Hyperparameter tuning methods.
Figure 15 Different Hyperparameter tuning methods.CC BY · PubMed Central

Verification

Claims the paper makes

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

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

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

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?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 101 references

Research works printed but not linked: 9

  1. Hsu, T.M.-H., Qi, H., and Brown, M. (2019). Measuring the effects of nonidentical data distribution for federated visual classification. arXiv.
  2. Li, D., and Wang, J. (2019). FedMD: Heterogenous federated learning via model distillation. arXiv.
  3. Courbariaux, M., Hubara, I., Soudry, D., El-Yaniv, R., and Bengio, Y. (2016). Binarized Neural Networks: Training Neural Networks with Weights and Activations Constrained to +1 or −1. arXiv.
  4. Burges, C.J., Bottou, L., Welling, M., Ghahramani, Z., and Weinberger, K.Q. (2013). Advances in Neural Information Processing Systems 26 (NIPS 2013), Proceedings of the Advances in Neural Information Processing Systems 26 (NIPS 2013), Lake Tahou, NV, USA, 5–10 December 2013, Curran Associates Inc.
  5. Van Leeuwen, J. (1976, January 20–23). On the construction of huffman trees. Proceedings of the Third International Colloquium on Automata, Languages and Programming, Edinburgh, UK.
  6. Sun, X., Wang, N., Chen, C.-y., Ni, J.-M., Agrawal, A., Cui, X., Venkataramani, S., El Maghraoui, K., Srinivasan, V., and Gopalakrishnan, K. (2020, January 6–12). Ultra-low precision 4-bit training of deep neural networks. Proceedings of the 34th International Conference on Neural Information Processing Systems, Vancouver, BC, Canada.
  7. Hutter, F., Kotthoff, L., and Vanschoren, J. (2019). Automated Machine Learning, Springer. · DOI · Paper page
  8. Alkadhmawee, 2016, An energy-efficient heuristic based routing protocol in wireless sensor networks, Int. J. Innov. Res. Inf. Secur., 3, 5
  9. Pleiss, G., Chen, D., Huang, G., Li, T., van der Maaten, L., and Weinberger, Q. (2017). Memory-Efficient Implementation of DenseNets. arXiv.

Cited by

See all 161

Metadata

Authors
Surianarayanan, C., Lawrence, J. J., Chelliah, P. R., Prakash, E., & Hewage, C.
Affiliations
  • Bharathidasan University (IN)
  • Cardiff Metropolitan University (GB)
  • Edge AI Division, Reliance Jio Platforms Ltd., Bangalore 560103, Karnataka, India
  • University for the Creative Arts (GB)
Corresponding author
Surianarayanan, Chellammal
Venue
Sensors
Publisher
MDPI AG
Published
2023-01-22
Volume
23
Issue
3
Pages
1279
ISSN
1424-8220 (ISSN-L)
OpenAlex
W4317727238
Cited by
131
References
95
Citations by year
2026: 46 · 2025: 43 · 2024: 25 · 2023: 17
FWCI
3.40
Type
journal article
Language
en
Open access
Locations
  • Sensors (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
  • Figshare (submittedVersion, cc-by)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
  • Physical Sciences › Computer Science › Information Systems › Internet of Things and AI
Keywords
edge AI, model compression, lightweight AI models, IoT devices, on-device processing, real-time inference, optimization framework, energy efficiency

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: A Survey on Optimization Techniques for Edge Artificial Intelligence (AI). https://app.cochat.ai/papers/10.3390/s23031279
The paper
Surianarayanan, C., Lawrence, J. J., Chelliah, P. R., Prakash, E., & Hewage, C. (2023). A Survey on Optimization Techniques for Edge Artificial Intelligence (AI). Sensors. https://doi.org/10.3390/s23031279

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.