Real-Time Data Analytics in AI-Driven IoT Ecosystems: Leveraging Edge AI for Processing Massive Data Streams from Smart Devices, Enabling Applications in Healthcare Monitoring and Industrial Automation
DOI:
https://doi.org/10.63282/3050-9246.IJETCSIT-V5I4P115Keywords:
Edge AI, IoT Analytics, Real-Time Data Processing, Healthcare Monitoring, Industrial Automation, Machine Learning, Stream ProcessingAbstract
The Internet of Things (IoT) devices have been extensively spread, which has led to an enormous influx of real-time data streams that need to be processed instantly to facilitate actionable data. Conventional cloud-based data processing solutions are also not usually adequate because of lag issues, bandwidth, and confidentiality. The Edge Artificial Intelligence (Edge AI) offers a new paradigm with the ability of making computational work nearer to the data sources to minimize latency and improve the performance of real-time analytics. The present paper explores the implementation of Edge AI into the IoT ecosystems, with healthcare monitoring and industrial automation as the applications. There are techniques, like stream processing, lightweight machine learning models and distributed resource management, which are examined. The paper further discusses such challenges as device heterogeneity, privacy, and reliability and examines the existing solutions such as federated learning and model compression. The architectural frameworks and implementations application-specific are explained through comparative analyses with using tables and conceptual figures. The paper proves that the Edge AI-based IoT systems are much more efficient in terms of performance, responsiveness, and operational efficiency, which preconditions the future studies and applications in the critical fields.
Downloads
References
[1] F. Bonomi, R. Milito, J. Zhu, and S. Addepalli, “Fog computing and its role in the Internet of Things,” Proc. MCC’12, pp. 13–16, 2012.
[2] M. Satyanarayanan, “The emergence of edge computing,” Computer, vol. 50, no. 1, pp. 30–39, 2017.
[3] W. Shi, J. Cao, Q. Zhang, Y. Li, and L. Xu, “Edge computing: Vision and challenges,” IEEE Internet of Things J., vol. 3, no. 5, pp. 637–646, 2016.
[4] Y. Xiao, M. Wen, and R. Lu, “Security and privacy in edge computing paradigms: A survey,” IEEE Commun. Surveys Tuts., vol. 20, no. 4, pp. 2958–2990, 2018.
[5] A. Alrawais, A. Alhothaily, C. Hu, and X. Cheng, “Fog computing for the Internet of Things: Security issues and challenges,” IEEE Commun. Surveys Tuts., vol. 20, no. 4, pp. 2707–2735, 2018.
[6] J. Ren, G. Yu, Y. Cai, and Y. He, “When edge meets learning: Adaptive control for resource-constrained edge AI,” IEEE Trans. Wireless Commun., vol. 20, no. 1, pp. 29–38, 2021.
[7] T. H. Luan et al., “Fog computing: Focusing on mobile users at the edge,” Proc. IEEE ICC, 2015, pp. 915–920.
[8] M. Aazam and E. N. Huh, “Fog computing micro datacenter based dynamic resource estimation and pricing model for IoT,” Proc. IEEE/IFIP NOMS, 2014, pp. 1–9.
[9] J. Gubbi, R. Buyya, S. Marusic, and M. Palaniswami, “Internet of Things (IoT): A vision, architectural elements, and future directions,” Future Gener. Comput. Syst., vol. 29, no. 7, pp. 1645–1660, 2013.
[10] L. Atzori, A. Iera, and G. Morabito, “The Internet of Things: A survey,” Comput. Netw., vol. 54, no. 15, pp. 2787–2805, 2010.
[11] Z. Zhou, X. Chen, E. Li, L. Zeng, K. Luo, and J. Zhang, “Edge intelligence: Paving the last mile of artificial intelligence with edge computing,” Proc. IEEE, vol. 107, no. 8, pp. 1738–1762, 2019.
[12] S. Wang, R. Urgaonkar, T. He, M. Zafer, K. Chan, and K. K. Leung, “Dynamic service placement for mobile micro-clouds with predicted future costs,” IEEE Trans. Parallel Distrib. Syst., vol. 28, no. 4, pp. 1002–1016, 2017.
[13] 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, 2017.
[14] N. Fernando, S. W. Loke, and W. Rahayu, “Mobile cloud computing: A survey,” Future Gener. Comput. Syst., vol. 29, no. 1, pp. 84–106, 2013.
[15] T. D. Nguyen and P. M. Costa, “Machine learning in edge computing: Techniques and applications,” IEEE Access, vol. 9, pp. 143593–143624, 2021.
[16] X. Xu, W. Sun, Y. Liu, and Y. Huang, “A survey of edge computing based solutions for industrial IoT,” IEEE Trans. Industrial Informatics, vol. 15, no. 12, pp. 6522–6531, 2019.
[17] Y. Liu, S. Huang, S. Spadaro, and M. P. Mimoso, “Deep learning at the edge: A review of network compression, acceleration and deployment,” IEEE Trans. Neural Netw. Learn. Syst., vol. 31, no. 12, pp. 6213–6229, 2020.
[18] P. Mach and Z. Becvar, “Mobile edge computing: A survey on architecture and computation offloading,” IEEE Commun. Surveys Tuts., vol. 19, no. 3, pp. 1628–1656, 2017.
[19] F. B. Islam et al., “Edge machine learning and its applications: A review,” IEEE Access, vol. 8, pp. 96754–96772, 2020.
[20] M. Chen, Y. Hao, Y. Li, C. Lai, and D. Wu, “Edge cognitive computing for Internet of Things: Theoretical foundation and challenges,” IEEE Netw., vol. 33, no. 3, pp. 45–51, 2019.
[21] N. Taimoor and S. Rehman, “Reliable and resilient AI and IoT based personalized healthcare services: A survey,” arXiv, 2022.
[22] R. Buyya et al., “Quality of service (QoS) driven edge computing and smart hospitals,” arXiv, 2023.
[23] A. A. Hossain, “Edge computing in healthcare: Opportunities and challenges,” Future Internet, 2021.
[24] Z. Zhang et al., “IoT enabled smart healthcare monitoring system,” IEEE Access, vol. 7, pp. 136988–136999, 2019.
[25] H. Park et al., “Real time patient monitoring system based on IoT,” IEEE Sensors J., vol. 20, no. 9, pp. 4512–4522, 2020.
[26] S. M. Riazul Islam et al., “The Internet of Things for health care: A comprehensive survey,” IEEE Access, vol. 3, pp. 678–708, 2015.
[27] M. Hossain, M. Fotouhi, and R. Hasan, “Towards an analysis of security issues, challenges, and open problems in the Internet of Medical Things (IoMT),” IEEE Internet Things J., vol. 3, no. 6, pp. 827–834, 2016.
[28] G. Fortino, W. Russo, and A. Savaglio, “Wearable health monitoring systems,” IEEE Pervasive Comput., vol. 17, no. 1, pp. 65–67, 2018.
[29] T. H. Daji et al., “Cloud-based asset monitoring and predictive maintenance in IIoT,” Proc. INCET 2020, IEEE.
[30] Y. Pejić Bach et al., “Predictive maintenance in Industry 4.0 for SMEs,” Designs, vol. 7, 2023.
[31] Z. Fila, M. E. Khaili, and M. Mestari, “Cloud computing for industrial predictive maintenance,” Proc. Procedia Comput. Sci., vol. 177, 2020.
[32] R.-I. Chang et al., “Cloud-based analytics module for predictive maintenance,” Appl. Sci., 2021.
[33] K. Teoh, S. S. Gill, and A. K. Parlikad, “IoT and fog computing based predictive maintenance model,” IEEE IoT J., vol. 8, no. 10, 2021.
[34] D. Dalzochio et al., “Machine learning and reasoning for predictive maintenance in Industry 4.0,” Comput. Ind., vol. 123, 2020.
[35] M. Riccio et al., “A new framework for predictive maintenance,” Machines, 2024 (pre-2023 cited works).
[36] P. Prieto et al., “From sensors to data intelligence: Leveraging IoT, cloud, and edge technologies,” PMC, 2025 (cites prior studies).
[37] B. Liu et al., “Deep anomaly detection for time series data in IIoT: On-device federated learning,” arXiv, 2020.
[38] A. Malhotra et al., “Efficient on-edge machine learning models for IoT,” IEEE Trans. Mobile Comput., vol. 19, no. 10, pp. 2206–2219, 2020.
[39] F. Chollet, Deep Learning with Python, 2nd Ed., 2021.
[40] I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning, MIT Press, 2016.
[41] M. Chen et al., “Edge computing for the Internet of Things: A survey,” IEEE Internet Things J., vol. 5, no. 1, 2018.
[42] K. Zhang et al., “Energy-efficient edge computing for industrial IoT,” IEEE Trans. Green Commun. Netw., vol. 5, no. 3, pp. 1193–1204, 2021.
[43] S. Y. Wang, “Latency reduction techniques in edge IoT analytics,” IEEE Commun. Mag., 2022.
[44] J. Ma et al., “Fog enabled real-time processing for IoT,” IEEE Trans. Ind. Informatics, 2018.
[45] X. Song et al., “Lightweight machine learning models for IoT edge devices,” IEEE IoT J., 2022.
[46] M. A. Kabir et al., “Resource management for edge-based IoT applications,” IEEE Access, 2021.
[47] S. Raza et al., “Secure and privacy-preserving IoT architectures,” IEEE Internet Things J., 2020.
[48] A. Ahmed et al., “Real-time anomaly detection for IoT data streams,” IEEE Trans. Big Data, 2019.
[49] T. Hu et al., “Adaptive workload scheduling in edge AI,” IEEE Trans. Parallel Distrib. Syst., 2020.
[50] Y. Liang et al., “Real-time stream processing for edge IoT,” IEEE Access, 2022.
[51] H. Zhang et al., “Lightweight neural networks for edge AI,” IEEE Trans. Neural Netw. Learn. Syst., 2021.
[52] F. Tao et al., “Digital twin and edge analytics for smart manufacturing,” IEEE Trans. Ind. Informatics, 2020.
[53] D. Li et al., “Fog/edge analytics for smart grids,” IEEE Trans. Smart Grid, 2021.
[54] X. Wang et al., “Machine learning models for edge IoT,” IEEE Access, 2020.
[55] S. K. Singh et al., “Edge computing service models for IoT systems,” IEEE Commun. Surveys Tuts., 2022.
[56] A. Gupta and A. J. Jara, “IoT security and edge intelligence,” IEEE Consumer Electron. Mag., 2019.
[57] M. Ray, “Machine learning workloads in edge devices,” IEEE Internet Things J., 2021.
[58] Q. Liu et al., “Continuous data analytics at the IoT edge,” IEEE Trans. Big Data, 2022.
[59] P. Patel and S. Chilamkurti, “Deep learning on edge for IoT,” IEEE Access, 2021.
[60] B. Kang et al., “Edge AI model compression techniques,” IEEE Access, 2021.
[61] M. Sarker et al., “Federated learning for privacy-preserving edge analytics,” IEEE Commun. Mag., 2020.
