Real-Time AI and Deep Learning–Driven Data Analytics for Networked Cyber-Physical Systems Using Edge Sensor Hardware
DOI:
https://doi.org/10.63503/j.ijaimd.2026.261Keywords:
cyber-physical systems · edge intelligence · temporal convolutional networks · transformer encoders · real-time anomaly detection · remaining-useful-life estimation · distributed inference orchestrationAbstract
Cyber-physical systems being utilized in industrial transportation and critical-infrastructure environments produce heterogeneous sensor streams that require sub-20 ms analytical latency and classification fidelity is not compromised. In this paper, a layered edge-intelligence system that combines temporal convolutional networks with lightweight transformer encoders to deliver real-time anomaly detection and predictive control on edge sensor hardware is introduced. An edge-cloud orchestration protocol is a dynamically partitioned, distributed edge-cloud architecture whose inference is latency-sensitive and that offloads heavy retraining workloads to cloud accelerators. Performances on the Edge-IIoTset dataset, which is further extended to a distributed cyber-physical system design, i.e. 48 heterogeneous sensor nodes connected in a 5G mesh, show an end-to-end inference latency of 17.3 ms, fault-classification accuracy of 96.4%, and an average absolute error of 2.8 cycles to estimate the remaining-use The suggested architecture lowers the bandwidth usage by 61.2% in comparison with cloud-focused baselines and can maintain the performance at the loss rates of packets as high as 18 percent. These findings serve as a benchmark that can be reproduced to enable latency-constrained deep analytics in safety-critical cyber-physical systems.
References
[1] Gushev, M. (2020). Dew computing architecture for cyber-physical systems and IoT. Internet of things, 11, 100186. https://doi.org/10.1016/j.iot.2020.100186
[2] Mondal, M. K., Mandal, R., Banerjee, S., Biswas, U., Chatterjee, P., & Alnumay, W. (2022). A CPS based social distancing measuring model using edge and fog computing. Computer Communications, 194, 378-386. https://doi.org/10.1016/j.comcom.2022.07.029
[3] Yu, Q., Ren, J., Zhou, H., & Zhang, W. (2020, March). A cybertwin based network architecture for 6G. In 2020 2nd 6G Wireless Summit (6G SUMMIT) (pp. 1-5). IEEE. doi: 10.1109/6GSUMMIT49458.2020.9083808.
[4] Li, K., Wang, X., He, Q., Wang, J., Li, J., Zhan, S., ... & Dustdar, S. (2024). Computation offloading in resource-constrained multi-access edge computing. IEEE Transactions on Mobile Computing, 23(11), 10665-10677. doi: 10.1109/TMC.2024.3383041.
[5] Li, G., & Jung, J. J. (2023). Deep learning for anomaly detection in multivariate time series: Approaches, applications, and challenges. Information Fusion, 91, 93-102. Li, G., & Jung, J. J. (2023). Deep learning for anomaly detection in multivariate time series: Approaches, applications, and challenges. Information Fusion, 91, 93-102.
[6] Dong, L., Xu, S., & Xu, B. (2018, April). Speech-transformer: a no-recurrence sequence-to-sequence model for speech recognition. In 2018 IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 5884-5888). IEEE. doi: 10.1109/ICASSP.2018.8462506.
[7] Bibi, U., Mazhar, M., Sabir, D., Butt, M. F. U., Hassan, A., Ghazanfar, M. A., ... & Abdul, W. (2024). Advances in pruning and quantization for natural language processing. IEEE access, 12, 139113-139128. doi: 10.1109/ACCESS.2024.3465631.
[8] Mittal, P. (2024). A comprehensive survey of deep learning-based lightweight object detection models for edge devices. Artificial Intelligence Review, 57(9), 242. https://doi.org/10.1007/s10462-024-10877-1
[9] Shan, D., Yao, K., & Zhang, X. (2023). Sequential learning network with residual blocks: Incorporating temporal convolutional information into recurrent neural networks. IEEE Transactions on Cognitive and Developmental Systems, 16(1), 396-401. doi: 10.1109/TCDS.2023.3325358.
[10] Yu, J., & Zhang, Y. (2023). Challenges and opportunities of deep learning-based process fault detection and diagnosis: a review. Neural Computing and Applications, 35(1), 211-252. https://doi.org/10.1007/s00521-022-08017-3
[11] Liu, J., Du, Y., Yang, K., Wu, J., Wang, Y., Hu, X., ... & Leung, V. C. (2026). Edge-cloud collaborative computing on distributed intelligence and model optimization: A survey. IEEE Communications Surveys & Tutorials. doi: 10.1109/COMST.2026.3669216.
[12] Chiang, Y., Hsu, C. H., Chen, G. H., & Wei, H. Y. (2022). Deep Q-learning-based dynamic network slicing and task offloading in edge network. IEEE Transactions on Network and Service Management, 20(1), 369-384. doi: 10.1109/TNSM.2022.3208776.
[13] Taşcı, B., Omar, A., & Ayvaz, S. (2023). Remaining useful lifetime prediction for predictive maintenance in manufacturing. Computers & Industrial Engineering, 184, 109566. https://doi.org/10.1016/j.cie.2023.109566
[14] McMahon, E., Patton, M., Samtani, S., & Chen, H. (2018, November). Benchmarking vulnerability assessment tools for enhanced cyber-physical system (CPS) resiliency. In 2018 IEEE International Conference on Intelligence and Security Informatics (ISI) (pp. 100-105). IEEE. doi: 10.1109/ISI.2018.8587353.
[15] Akkad, G., Mansour, A., & Inaty, E. (2023). Embedded deep learning accelerators: A survey on recent advances. IEEE Transactions on Artificial Intelligence, 5(5), 1954-1972. doi: 10.1109/TAI.2023.3311776.
[16] Tabani, H., Balasubramaniam, A., Marzban, S., Arani, E., & Zonooz, B. (2021, September). Improving the efficiency of transformers for resource-constrained devices. In 2021 24th Euromicro Conference on Digital System Design (DSD) (pp. 449-456). IEEE. doi: 10.1109/DSD53832.2021.00074.
[17] https://www.kaggle.com/datasets/mohamedamineferrag/edgeiiotset-cyber-security-dataset-of-iot-iiot?
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 International Journal on Engineering Artificial Intelligence Management, Decision Support, and Policies
This work is licensed under a Creative Commons Attribution 4.0 International License.
