Edge Artificial Intelligence for Industrial Internet of Things Applications: An Industrial Edge Intelligence Solution
The DOI matches its Crossref record; 28 of the 28 references it cites were found in a registry or an index.
Abstract
In this article, we study edge artificial intelligence (AI) for industrial Internet of Things (IIoT) applications. We discuss edge AI technology, which is considered the combination of AI with edge computing, and provide an overview of edge AI applications for IIoT networks, where the following three challenges are important to address: 1) personalization, 2) responsiveness, and 3) privacy preservation. To this end, we propose a federated active transfer learning (FATL) model, which through training and testing is able to address those open challenges. Details about the training and testing of the proposed FATL global model are given, including the corresponding simulation setup. This work concludes with a discussion and comparison of the obtained simulation results with existing edge AI training solutions, which provide useful insights about the proposed FATL model. The simulation results highlight how the FATL global model can efficiently address the open challenges of edge AI for future IIoT applications.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“By 2025, Gartner expects 75% of enterprise-generated data will be created and processed outside of the conventional data centre or cloud, thanks to the expansion of the IoT [73].”
From Edge AI: A survey (2023) · cites this paper as [73]
In the citing paper
“For instance, edge computing devices can need specific AI libraries and frameworks that are tailored to function with a constrained set of computer resources [73].”
From Edge AI: A survey (2023) · cites this paper as [73]
Citations
Cites
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805 · cited 1×
“To benchmark the proposed FATL model, we utilized the MNIST data set [22] and Google’s Inception V3 DNN [23].”
MethodImageNet 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
Rethinking the Inception Architecture for Computer Vision
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.308 · Cited by 32,138
Pan, S. J., & Yang, Q. (2010) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2009.191 · Cited by 23,387 · cited 2×
“Our model also utilizes a learning setting similar to multitask learning, as stated in [20], as the source task contains labeled data, and, thus, no self-learning procedure takes place.”
MethodFederated Machine Learning: Concept and Applications
Yang, Q., Liu, Y., Chen, T., & Tong, Y. (2019) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3298981 · Cited by 6,322
How transferable are features in deep neural networks?
Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2014) · arXiv · doi:10.48550/arxiv.1411.1792 · Cited by 6,061 · cited 1×
“We To avoid over fitting, we also froze the last layers of the Inception V3 neural network, where specific features were extracted, as discussed in [24].”
MethodEdge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing
Zhou, Z., Chen, X., Li, E., Zeng, L., Luo, K., & Zhang, J. (2019) · Proceedings of the IEEE · doi:10.1109/jproc.2019.2918951 · Cited by 2,455 · cited 4×
“Different types of enabling techniques have been proposed for training and inference to tackle the design requirements in the IoT domain [3].”
BackgroundMethodInfluentialWollschlaeger, M., Sauter, T., & Jasperneite, J. (2017) · IEEE Industrial Electronics Magazine · doi:10.1109/mie.2017.2649104 · Cited by 1,726 · cited 2×
“Such an IIoT application will be able to collect data from all over the shop floor that can be aggregated to the edge of the network [1].”
BackgroundLearning IoT in Edge: Deep Learning for the Internet of Things with Edge Computing
Li, H., Ota, K., & Dong, M. (2018) · IEEE Network · doi:10.1109/mnet.2018.1700202 · Cited by 1,566 · cited 2×
“Finally, [11] provides an edge training model that is able to manage the network traffic requirements in IoT applications.”
BackgroundEdge AI: On-Demand Accelerating Deep Neural Network Inference via Edge Computing
Li, E., Zeng, L., Zhou, Z., & Chen, X. (2020) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2019.2946140 · Cited by 929
Cited by
Singh, R., & Gill, S. S. (2023) · Internet of Things and Cyber-Physical Systems · doi:10.1016/j.iotcps.2023.02.004 · Cited by 572
Mansour, M., Gamal, A., Ahmed, A., Said, L. A., Elbaz, A., Herencsár, N., & Soltan, A. (2023) · Energies · doi:10.3390/en16083465 · Cited by 261
Artificial intelligence Internet of Things: A new paradigm of distributed sensor networks
Seng, K. P., Ang, L.-M., & Ngharamike, E. (2022) · International Journal of Distributed Sensor Networks · doi:10.1177/15501477211062835 · Cited by 133
Industrial Internet of Things for Safety Management Applications: A Survey
Misra, S., Roy, C., Sauter, T., Mukherjee, A., & Maiti, J. (2022) · IEEE Access · doi:10.1109/access.2022.3194166 · Cited by 104
A Survey of Industrial AIoT: Opportunities, Challenges, and Directions
Awaisi, K. S., Ye, Q., & Sampalli, S. (2024) · IEEE Access · doi:10.1109/access.2024.3426279 · Cited by 109
A Survey on the Applications of Cloud Computing in the Industrial Internet of Things
Dritsas, E., & Τρίγκα, Μ. (2025) · Big Data and Cognitive Computing · doi:10.3390/bdcc9020044 · Cited by 131
A Low-Cost AI Buoy System for Monitoring Water Quality at Offshore Aquaculture Cages
Lu, H., Cheng, C., Cheng, S., Cheng, Y.-H., Lo, W.-C., Jiang, W., Nan, F., Chang, S., & Ubina, N. A. (2022) · Sensors · doi:10.3390/s22114078 · Cited by 70
“In this paper, the author proposes a low-cost buoy system with AI integration [34,39] to monitor the water quality of offshore cages.”
BackgroundKey Considerations for Real-Time Object Recognition on Edge Computing Devices
Surantha, N., & Sutisna, N. (2025) · Applied Sciences · doi:10.3390/app15137533 · Cited by 64
Application and Research of IoT Architecture for End-Net-Cloud Edge Computing
Zhang, Y., Yu, H., Zhou, W., & Man, M. (2022) · Electronics · doi:10.3390/electronics12010001 · Cited by 50
Artificial Intelligence (AI) and Machine Learning for Multimedia and Edge Information Processing
Seng, J. K. P., Ang, K. L.-M., Peter, E., & Mmonyi, A. C. (2022) · Electronics · doi:10.3390/electronics11142239 · Cited by 55
Edge artificial intelligence for big data: a systematic review
Hemmati, A., Raoufi, P., & Rahmani, A. M. (2024) · Neural Computing and Applications · doi:10.1007/s00521-024-09723-w · Cited by 51
“…Latency and energy cost minimization[37] Manufacturing Edge server resource allocation[39] Condition monitoring for vibration[40] Edge AI training[41, 43–45] iRobot-factory, cognitive manufacturing[42] Computation offloading decisions[46] A real-world scenario of K-12 learners and FL[14] AI…”
InfluentialIntegrating IoT and 6G: Applications of Edge Intelligence, Challenges, and Future Directions
He, Q., Lin, J., Fang, H., Wang, X., Huang, M., Yi, X., & Yu, K. (2025) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2025.3586152 · Cited by 58
Edge Intelligence for Industrial IoT: Opportunities and Limitations
Savaglio, C., Mazzei, P., & Fortino, G. (2024) · Procedia Computer Science · doi:10.1016/j.procs.2024.01.039 · Cited by 55
Bhadra, P., Chakraborty, S., & Saha, S. (2023) · Smart innovation, systems and technologies · doi:10.1007/978-981-19-8296-5_15 · Cited by 48
Energy-Efficient Edge Inference in Integrated Sensing, Communication, and Computation Networks
Yao, J., Xu, W., Zhu, G., Huang, K., & Cui, S. R. (2025) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2025.3574612 · Cited by 51
“In particular, edge inference, a key area in edge intelligence, concerns real-time inference and decision-making using a well-trained edge-deployed AI model, providing a platform for intelligent control in ICPS [16].”
A secure and flexible edge computing scheme for AI-driven industrial IoT
Zhao, Y. L., Hu, N., Zhao, Y., & Zhu, Z. (2021) · Cluster Computing · doi:10.1007/s10586-021-03400-6 · Cited by 33
“Moreover, it also alleviates the bottleneck of the industrial core network, as the on-site data can be refined or processed at the edge of networks to facilitate AI model training [9].”
BackgroundJosbert, N. N., Wei, M., Wang, P., & Rafiq, A. (2024) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2024.102069 · Cited by 35
“Besides, there is considerable articles on AI and ML, which remarkably optimize the performance of SDN-IIoT (Lv et al., 2020; Foukalas and Tziouvaras, 2021).”
Gebbran, D., Barragán-Moreno, A., Gómez, P. I., Subroto, R. K., Mardani, M. M., López, M. E., Quiroz, J., & Dragičević, T. (2022) · IEEE Industrial Electronics Magazine · doi:10.1109/mie.2022.3211125 · Cited by 29
“2) The microprocessors of PECs are prime candidates for becoming edge devices as the core of the integration of DERs in the power grid and are already equipped with strong data processing capabilities [20].”
BackgroundChen, H., Han, X., & Zhang, Y. (2023) · Tsinghua Science & Technology · doi:10.26599/tst.2023.9010034 · Cited by 23
Zhao, H., Tan, Y., Guo, K., Xia, W., Xu, B., & Quek, T. Q. S. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3354914 · Cited by 24
Yu, D.-S., Liu, X.-H., Ning, J., Wang, S.-Y., Zhu, C.-L., & Zhao, W.-D. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3620126 · Cited by 13
“By enabling large-scale data acquisition, cloud–edge collaboration, and coordinated resource allocation, IIoT supports the deployment, training, and optimization of AI models with low latency and high e ffi ciency [4].”
Federated transfer learning for intrusion detection system in industrial iot 4.0
Malathy, N. R., Shree Harish Kumar, G., Sriram, R., & Jebocen Immanuel Raj, N. R. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-18379-6 · Cited by 23
“The collaboration between FTL and IoT security is further evidenced by the work of Fotis Foukalas et al. [36], who proposed an ensemble FTL-based technique for IoT network threat detection and categorization.”
Resource Allocation for Task-Oriented Generative Artificial Intelligence in Internet of Things
Feng, J., Huang, X., Liu, L., Yang, M., Pei, Q., & Shee, Y. G. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3542473 · Cited by 15
Hamood, M., Albaseer, A. M., Abdallah, M. M., & Al‐Fuqaha, A. (2023) · IEEE Internet of Things Magazine · doi:10.1109/iotm.001.2300054 · Cited by 12
“Additionally, AI can be used to develop self-configuring autonomic systems that can adapt to different services and communication protocols, reducing the need for manual intervention [4].”
BIRP: Batch-aware Inference Workload Redistribution and Parallel Scheme for Edge Collaboration
Sun, H., Chen, X., Qian, Z., Li, Z., Chen, N., Cao, T., Xu, S., & Zhou, Y.-T. (2023) · Proceedings of the International Conference on Parallel Processing · doi:10.1145/3605573.3605615 · Cited by 10
Hirsi, A., Audah, L., Salh, A., Alhartomi, M. A., Sun, Z., Hammoodi, A. T., & Ahmed, S. (2025) · Physical Communication · doi:10.1016/j.phycom.2025.102712 · Cited by 12
Powroźnik, P., Szcześniak, P., & Piotrowski, K. (2021) · Energies · doi:10.3390/en15010109 · Cited by 11
Ma, M., Gong, C., Wu, L., & Yang, Y. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3222295 · Cited by 8
AI-Based Temperature Monitoring System for Hydro Generators
Milić, S., & Kožicić, M. (2024) · International Symposium INFOTEH-JAHORINA (INFOTEH) · doi:10.1109/infoteh60418.2024.10496027 · Cited by 7
“The necessity of AI in IIoT applications [ 3, 4 ] is discussed in this paper.”
BackgroundWang, Y., Hu, B., Feng, Y., Li, Z., Feng, Y., & Tan, J. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3237727 · Cited by 5
“In IIoT applications, the computing task processing usually is more time-consuming [51].”
BackgroundAssessment of Innovative Architectures, Challenges and Solutions of Edge Intelligence
Siltanen, H., & Vlrtanen, L. (2022) · Journal of Machine and Computing · doi:10.53759/7669/jmc202202020 · Cited by 4
“Foukalas and Tziouvaras [1] have employed smartphones and edge servers to build an application for face recognition.”
BackgroundEdge Intelligence Based Garbage Classification Detection Method
Zhu, R., Liu, Y., Gao, Y., Shi, Y., & Peng, X. (2023) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-031-28990-3_10 · Cited by 4
Putra, M. A. P., Karna, N. B. A., Zainudin, A., Kim, D., & Lee, J. (2024) · Internet of Things · doi:10.1016/j.iot.2024.101287 · Cited by 4
SRT: A Skip-Range Transformer for Detecting Anomalies in Multiattribute Industrial Time Series Data
Gao, H., Jiang, W., Ran, Q., Wang, K., Ma, X., & Xu, Y. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3565669 · Cited by 3
Decentralized semi-federated learning in digital twin-empowered industrial IoT
Chen, F., Wu, X., & Tang, J. (2026) · Digital Communications and Networks · doi:10.1016/j.dcan.2026.04.003 · Cited by 3
Smart Shopping Cart for Self-Service Checkout Based on IoT Technologies
Batool, S. F., Ambreen, H., Waqar, K., Imran, M., Ali, S., & Maqbool, A. (2023) · International Bhurban Conference on Applied Sciences and Technology (IBCAST) · doi:10.1109/ibcast59916.2023.10712891 · Cited by 2
“Edge computing and AI can be used to provide solutions for industrial edge intelligence [20].”
BackgroundLakhan, A. R., & Grønli, T. (2025) · Elsevier eBooks · doi:10.1016/b978-0-443-34160-1.00005-5 · Cited by 2
Smart Home Powered by New Energy: Energy Management Systems (EMS) Technologies and Future Prospects
Chen, X. (2023) · Highlights in Science Engineering and Technology · doi:10.54097/m24n9691 · Cited by 1
“We anticipate that this paper will inform readers on EMS technology and its use in smart homes and pique their interest in further study.”
BackgroundAn Adaptive Compression Method for Lightweight AI Models of Edge Nodes in Customized Production
Jiang, C. S., Hou, M., & Wang, H. (2026) · Sensors · doi:10.3390/s26020383 · Cited by 3
“Under such dynamic and heterogeneous conditions, static compression schemes frequently fail to achieve optimal performance, resulting in unacceptable accuracy degradation, excessive inference latency, or unstable runtime behavior [9,10].”
Thakur, V., More, V. N., & Bhatt, A. (2026) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2026.103940 · Cited by 1
EDGE Intelligent for Smart Factory Application
Ahmed, K., Jia, G., Chen, Y., Ding, C., Wen, Z., & Mei, S. (2022) · International Conference on Computer, Control and Robotics (ICCCR) · doi:10.1109/icccr54399.2022.9790194 · Cited by 1
Jamming-Resilient Over-the-Air Computation for Federated Learning in Edge Intelligence
Zou, Y., Xu, M., Li, H., Hu, Q., Deng, X., Yu, D., & Cheng, X. (2022) · IEEE Smart World Congress (SWC) · doi:10.1109/smartworld-uic-atc-scalcom-digitaltwin-pricomp-metaverse56740.2022.00038 · Cited by 2
“For example, the authors in [3] show how to utilize AI in edge service optimization in the intelligent transportation systems; an industrial edge intelligence solution is given in [4] for various industrial Internet-of-Things applications; A distributed cloud-edge-aided LSTM model and its optimization method are propo…”
BackgroundAn Efficient and Reliable I/O Mapping Protocol for Industrial Cyber-Physical Systems
Liu, S., Shi, L., & Liu, Z. (2023) · International Conference on Computing, Networks and Internet of Things (CNIOT) · doi:10.1145/3603781.3603883
“Another issue is how to ensure the real-time transmission[5, 11, 14].”
BackgroundClient Scheduling for Unreliable Semi-Decentralized Federated Learning
Tan, Y., Zhao, H., Xia, W., Wang, Q., Guo, K., Xu, B., & Quek, T. Q. S. (2023) · IEEE International Conference on Communication Technology (ICCT) · doi:10.1109/icct59356.2023.10419833
“In this way, large number of IIoT end devices can collaboratively train AI models through the edge network, to provide smart applications and services that satisfy ultra-reliable and low-latency requirements [4].”
BackgroundDesign and Development of a Low-Cost Communication-Based Protection System for Fishermen
Sivakumar, S., Arthi, T. S., Premkumar, S., & Thillaieaswaran, B. (2023) · International Conference on Optimization Techniques for Learning (ICOTL) · doi:10.1109/icotl59758.2023.10435276
“A riverine ontology was developed in response to these challenges to enable visualization and proactive decisions to be made in real-time [29].”
BackgroundChen, Y., Yu, Z., Leng, J., Hu, X. P., Zou, Z., & Zheng, L. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3515214
Cloud-Enabled IoT Systems for Real-Time Manufacturing Service Optimization
Rani, D. S., Sasikaran, S., Tharun, D. V. S., & Siva, L. (2025) · International Conference on Electronics and Sustainable Communication Systems (ICESC) · doi:10.1109/icesc65114.2025.11212463
“Foukalas and Tziouvaras [4] demonstrate that edge artificial intelligence significantly enhances Industrial Internet of Things applications.”
Gamified Edge-AI Interfaces for Smart Retail
Misara, R., Mishra, S., & Singh, V. (2025) · IEEE Conference on Information and Communication Technology (CICT) · doi:10.1109/cict67193.2025.11398895
“The practical advantages of this change are as follows: less latency, superior data security, decreased bandwidth consumption, and real-time responsiveness [5].”
Edge Training of Lightweight Bearing Fault Diagnosis Model via Dataset Distillation
Li, Y., Liu, Y. Z., Wang, X., Liu, B., Zhang, K. H. L., & Lu, H. (2025) · Global Reliability and Prognostics and Health Management Conference (PHM) · doi:10.1109/phm-xian66756.2025.11427452
“Such extensive data requirements make it almost impossible to train these complex models directly on resource-constrained edge AI devices [10,11].”
A Tiki-Taka-Inspired SOT-MRAM In-Memory Computing Architecture for Long-Term Edge Learning
Li, Y., Dong, F., & Xing, G. (2026) · Applied Sciences · doi:10.3390/app16094326
A Comprehensive Survey on Embedded Deep Learning Algorithms for Smart IoT Monitoring Systems
Alalwany, W. S. H., & Fahim, A. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-25568-6_9
LIPS: Latency-Aware Incentive Design for Personalized SplitFed Learning
Ren, K., & Cheung, M. H. (2026) · IEEE International Mediterranean Conference on Communications and Networking (MeditCom) · doi:10.1109/meditcom67211.2026.11641103
“The rapid advances of Edge Artificial Intelligence (AI) have brought AI applications directly to domains like health-care [1] and the Internet of Things [2].”
Wang, B. (2026) · Procedia Computer Science · doi:10.1016/j.procs.2026.09.056
Zhang, Y., & Wang, X. (2026) · Research Square · doi:10.21203/rs.3.rs-11183677/v1
Metadata
- Authors
- Foukalas, F., & Tziouvaras, A.
- Affiliations
- University College London (GB)
- University of Thessaly (GR)
- Venue
- IEEE Industrial Electronics Magazine
- Published
- 2021-06
- Volume
- 15
- Issue
- 2
- Pages
- 28-36
- ISSN
- 1932-4529 (ISSN-L)
- 1941-0115
- OpenAlex
- W3135486588
- Cited by
- 54
- References
- 27
- Citations by year
- 2026: 8 · 2025: 12 · 2024: 9 · 2023: 13 · 2022: 10 · 2021: 2
- FWCI
- 3.81
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Industrial Electronics Magazine (publishedVersion)
- University of Thessaly Institutional Repository (University of Thessaly) (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Information Systems › Internet of Things and AI
- Keywords
- edge AI, Industrial Internet of Things, edge computing, federated learning, personalization, responsiveness, privacy preservation
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.