Edge Machine Learning for AI-Enabled IoT Devices: A Review
Open accessThe DOI matches its Crossref record; 162 of the 162 references it cites were found in a registry or an index.
Abstract
In a few years, the world will be populated by billions of connected devices that will be placed in our homes, cities, vehicles, and industries. Devices with limited resources will interact with the surrounding environment and users. Many of these devices will be based on machine learning models to decode meaning and behavior behind sensors’ data, to implement accurate predictions and make decisions. The bottleneck will be the high level of connected things that could congest the network. Hence, the need to incorporate intelligence on end devices using machine learning algorithms. Deploying machine learning on such edge devices improves the network congestion by allowing computations to be performed close to the data sources. The aim of this work is to provide a review of the main techniques that guarantee the execution of machine learning models on hardware with low performances in the Internet of Things paradigm, paving the way to the Internet of Conscious Things. In this work, a detailed review on models, architecture, and requirements on solutions that implement edge machine learning on Internet of Things devices is presented, with the main goal to define the state of the art and envisioning development requirements. Furthermore, an example of edge machine learning implementation on a microcontroller will be provided, commonly regarded as the machine learning “Hello World”.
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.
Integrity signals
Registry
Cites
Statistics
Figures










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.
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
“CNN improved the training accuracy from 97.25% to 99% with ReLu and Sigmoid activation functions.”
From TinyML: Enabling of Inference Deep Learning Models on Ultra-Low-Power IoT Edge Devices for AI Applications (2022) · cites this paper as [25]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“When the data is transmitted to the cloud, it is prone to transmission errors, cyber-attacks e.g., eavesdropping or man-in-the-middle issues. Thereby, the transmitted data may be compromised or lost.”
From TinyML: Enabling of Inference Deep Learning Models on Ultra-Low-Power IoT Edge Devices for AI Applications (2022) · cites this paper as [25]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“In TinyML, data processing is executed locally in the device since the computations are performed in the device. Thus, IoT devices do not suffer from latency. The real-time local processing of data in the devices leads to faster response and rapid analysis in emergency scenarios. Besides this, the burden on the cloud is reduced [24,25].”
From TinyML: Enabling of Inference Deep Learning Models on Ultra-Low-Power IoT Edge Devices for AI Applications (2022) · cites this paper as [25]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The result of the prediction model was 100% accuracy, while the model consumed 135.68 KB of RAM, 668.97 KB of flash memory, and 330 ms computation.”
From TinyML: Enabling of Inference Deep Learning Models on Ultra-Low-Power IoT Edge Devices for AI Applications (2022) · cites this paper as [25]
Experimental — accuracy not yet measured
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
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380
Deep learning in neural networks: an overview
Schmidhuber, J. (2015) · Neural Networks · doi:10.1016/j.neunet.2014.09.003 · Cited by 18,570
The Internet of Things: A survey
Atzori, L., Iera, A., & Morabito, G. (2010) · Computer Networks · doi:10.1016/j.comnet.2010.05.010 · Cited by 15,613
Distilling the Knowledge in a Neural Network
Hinton, G., Vinyals, O., & Dean, J. (2015) · arXiv · doi:10.48550/arxiv.1503.02531 · Cited by 14,204
(2010) · Cited by 14,134
ORB: An efficient alternative to SIFT or SURF
Rublee, E., Rabaud, V., Konolige, K., & Bradski, G. (2011) · 2011 International Conference on Computer Vision · doi:10.1109/iccv.2011.6126544 · Cited by 11,037
Bidirectional recurrent neural networks
Schuster, M., & Paliwal, K. K. (1997) · IEEE Transactions on Signal Processing · doi:10.1109/78.650093 · Cited by 10,172 · cited 1×
“A particular type of NN are the RNNs (recurrent neural networks) [57].”
Background
Research works printed but not linked: 16
- Guestrin, 2006, SVMs, Duality and the Kernel Trick, Mach. Learn., 10701, 15781
- Jordan, M.I., and Bishop, C.M. (2004). Neural networks. Computer Science Handbook, CRC Press. [2nd ed.].
- Viola, P., and Jones, M.J. (2001). Robust Real-Time Object Detection, Cambridge Research Laboratory. Technical Reports.
- Kingma, D.P., and Ba, J.L. (2015, January 7–9). Adam: A method for stochastic optimization. Proceedings of the 3rd International Conference on Learning Representations, ICLR 2015—Conference Track Proceedings, San Diego, CA, USA.
- Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014, January 8–13). Genrative Adversial Nets. Proceedings of the 27th International Conference on Neural Information Processing Systems–Volume 2, Montreal, QC, Canada.
- Gupta, C., Suggala, A.S., Goyal, A., Simhadri, H.V., Paranjape, B., Kumar, A., Goya, S., Udupa, R., Varma, M., and Jain, P. (2017, January 6–11). ProtoNN: Compressed and accurate kNN for resource-scarce devices. Proceedings of the 34th International Conference on Machine Learning ICML, Sydney, Australia.
- Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. (2017). MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. arXiv.
- Han, S., Mao, H., and Dally, W.J. (2015). Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding. arXiv.
- Molchanov, P., Tyree, S., Karras, T., Aila, T., and Kautz, J. (2016). Pruning Convolutional Neural Networks for Resource Efficient Inference. arXiv.
- Guo, Y., Yao, A., and Chen, Y. Dynamic network surgery for efficient DNNs. Proceedings of the 30th International Conference on Neural Information Processing Systems (NIPS’16).
- Yu-han, T., Ravindranath, L., Deng, S., and Chen, T.Y. Continuous, Real-Time Object Recognition on Mobile Devices Categories and Subject Descriptors. Proceedings of the 13th ACM Conference on Embedded Networked Sensor Systems (SenSys ‘15). Association for Computing Machinery, New York, NY, USA.
- (2020, March 11). 802.15.4v-2017—IEEE Standard for Low-Rate Wireless Networks—Amendment 5: Enabling/Updating the Use of Regional Sub-GHz Bands. Available online: https://standards.ieee.org/standard/802_15_4v-2017.html.
- Patil, 2018, Survey on Creating ZigBee Chain Reaction Using IoT, Int. J. Sci. Res. Comput. Sci. Eng. Inf. Technol., 3, 545
- Dowlin, 2016, CryptoNets: Applying neural networks to Encrypted data with high throughput and accuracy—Microsoft research, Microsoft Res. Tech. Rep., 48, 1
- Tao, Z., and Li, Q. (2018, January 10). eSGD: Communication efficient distributed deep learning on the edge. Proceedings of the USENIX Workshop on Hot Topics in Edge Computing, HotEdge 2018, Co-Located with USENIX ATC 2018, Boston, MA, USA.
- Cong, 2014, Minimizing in Convolutional Neural Networks, Int. Conf. Artif. Neural Networks, 8681, 281
Cited by
AI for next generation computing: Emerging trends and future directions
Gill, S. S., Xu, M., Ottaviani, C., Patros, P., Bahsoon, R., Shaghaghi, A., Golec, M., Stankovski, V., Wu, H., Abraham, A., et al. (2022) · Internet of Things · doi:10.1016/j.iot.2022.100514 · Cited by 686
Fraga-Lamas, P., Lopes, S. I., & Fernández-Caramés, T. M. (2021) · Sensors · doi:10.3390/s21175745 · Cited by 405
Machine Learning for Healthcare Wearable Devices: The Big Picture
Sabry, F., Eltaras, T., Labda, W., Alzoubi, K., & Malluhi, Q. (2022) · Journal of Healthcare Engineering · doi:10.1155/2022/4653923 · Cited by 321
Rahman, M. A., Hossain, M. S., Islam, M. S., Alrajeh, N. A., & Muhammad, G. (2020) · IEEE Access · doi:10.1109/access.2020.3037474 · Cited by 299
Edge Computing on IoT for Machine Signal Processing and Fault Diagnosis: A Review
Lu, S., Lu, J., An, K., Wang, X., & He, Q. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3239944 · Cited by 295
Towards edge computing in intelligent manufacturing: Past, present and future
Nain, G., Pattanaik, K. K., & Sharma, G. K. (2022) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2022.01.010 · Cited by 283
AI-based fog and edge computing: A systematic review, taxonomy and future directions
Iftikhar, S., Gill, S. S., Song, C., Xu, M., Aslanpour, M. S., Toosi, A. N., Du, J., Wu, H., Ghosh, S., Chowdhury, D., et al. (2023) · Internet of Things · doi:10.1016/j.iot.2022.100674 · Cited by 260
Alajlan, N. N., & Ibrahim, D. M. (2022) · Micromachines · doi:10.3390/mi13060851 · Cited by 224
“[25] Handwritten Digits Handwritten digit images from (0 to 9) 70,000 images 60,000 10,000”
BackgroundMethodInfluentialA survey on optimization techniques for edge artificial intelligence (ai)
Surianarayanan, C., Lawrence, J. J., Chelliah, P. R., Prakash, E., & Hewage, C. (2023) · Sensors · doi:10.3390/s23031279 · Cited by 131
Artificial Intelligence in the IoT Era: A Review of Edge AI Hardware and Software
Sipola, T., Alatalo, J., Kokkonen, T., & Rantonen, M. (2022) · 2022 31st Conference of Open Innovations Association (FRUCT) · doi:10.23919/fruct54823.2022.9770931 · Cited by 100
Shumba, A.-T., Montanaro, T., Sergi, I., Bramanti, A., Ciccarelli, M., Rispoli, A., Carrizzo, A., De Vittorio, M., & Patrono, L. (2023) · Sensors · doi:10.3390/s23156896 · Cited by 74
A collective AI via lifelong learning and sharing at the edge
Soltoggio, A., Ben-Iwhiwhu, E., Braverman, V., Eaton, E., Epstein, B., Ge, Y., Halperin, L., How, J., Itti, L., Jacobs, M. A., et al. (2024) · Nature Machine Intelligence · doi:10.1038/s42256-024-00800-2 · Cited by 51
Exploring Edge TPU for Network Intrusion Detection in IoT
Hosseininoorbin, S., Layeghy, S., Sarhan, M., Jurdak, R., & Portmann, M. (2021) · arXiv · doi:10.48550/arxiv.2103.16295 · Cited by 45
Survey of Deep Learning Accelerators for Edge and Emerging Computing
Alam, S., Yakopcic, C., Wu, Q., Barnell, M., Khan, S., & Taha, T. M. (2024) · Electronics · doi:10.3390/electronics13152988 · Cited by 38
DNN is not all you need: Parallelizing Non-Neural ML Algorithms on Ultra-Low-Power IoT Processors
Tabanelli, E., Tagliavini, G., & Benini, L. (2021) · arXiv · doi:10.48550/arxiv.2107.09448 · Cited by 36
Oscillatory neural networks for edge ai computing
Delacour, C., Carapezzi, S., Abernot, M., Boschetto, G., Azemard, N., Salles, J., Gil, T., & Todri-Sanial, A. (2021) · 2021 IEEE Computer Society Annual Symposium on VLSI (ISVLSI) · doi:10.1109/isvlsi51109.2021.00066 · Cited by 28
Larian, H., & Safi-Esfahani, F. (2025) · Computing · doi:10.1007/s00607-024-01388-6 · Cited by 25
Toma, C., Popa, M., Iancu, B., Doinea, M., Pascu, A., & Ioan-Dutescu, F. (2022) · Electronics · doi:10.3390/electronics11213507 · Cited by 22
Loukatos, D., Lygkoura, K.-A., Maraveas, C., & Arvanitis, K. G. (2022) · Sensors · doi:10.3390/s22134874 · Cited by 21
Benchmarking TensorFlow Lite Quantization Algorithms for Deep Neural Networks
Orasan, I. L., Seiculescu, C., & Caleanu, C. D. (2022) · 2022 IEEE 16th International Symposium on Applied Computational Intelligence and Informatics (SACI) · doi:10.1109/saci55618.2022.9919465 · Cited by 18
Makina, H., & Ben Letaifa, A. (2023) · International Journal of Communication Systems · doi:10.1002/dac.5484 · Cited by 16
Smart Anomaly Detection Using Data-Driven Techniques in IoT Edge: A Survey
Manokaran, J., & Vairavel, G. (2022) · Lecture Notes in Electrical Engineering · doi:10.1007/978-981-16-8862-1_45 · Cited by 13
Mallick, N., Nanda, H., Sahu, S., Pattnayak, P., Mohanty, A., & Das, T. (2026) · 2026 IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI) · doi:10.1109/iatmsi68868.2026.11466166
Metadata
- Authors
- Merenda, M., Porcaro, C., & Iero, D.
- Affiliations
- University of Reggio Calabria (IT)
- Corresponding author
- Merenda, Massimo
- Venue
- Sensors
- Publisher
- MDPI AG
- Published
- 2020-04-29
- Volume
- 20
- Issue
- 9
- Pages
- 2533
- ISSN
- 1424-8220 (ISSN-L)
- PMC
- PMC7273223
- OpenAlex
- W3023935494
- Cited by
- 523
- References
- 162
- Citations by year
- 2026: 79 · 2025: 111 · 2024: 92 · 2023: 90 · 2022: 91 · 2021: 52 · 2020: 8
- FWCI
- 9.92
- Type
- journal article
- Language
- en
- Open access
- gold
- dx.doi.org
- Licence
- Locations
- Sensors (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Physical Sciences › Computer Science › Information Systems › Internet of Things and AI
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- edge machine learning, Internet of Things, resource-constrained devices, network congestion, low-power electronics, microcontroller, edge computing architecture, sensor data processing
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.