Edge AI Deploying Artificial Intelligence Models on Edge Devices for Real-Time Analytics

Edge AI Deploying Artificial Intelligence Models on Edge Devices for Real-Time Analytics Sagar Choudhary Vijitha S Dokku Durga Bhavani Bhuvaneswari N Mohit Tiwari Subburam S S. Kannadhasan P. Sivakumar T. Saravanan S. Senthil Kumar

Because of its on-the-go nature, edge AI has gained popularity, allowing for realtime analytics by deploying artificial intelligence models onto edge devices. Despite the promise of Edge AI evidenced by existing research, there are still significant barriers to widespread adoption with issues such as scalability, energy efficiency, security, and reduced model explainability representing common challenges. Hence, while this paper solves the Edge AI in a number of ways, with real use case of a deployment, modular adaptability, and dynamic AI model specialization. Our paradigm achieves low latency, better security and energy efficiency using light-weight AI models, federated learning, Explainable AI (XAI) and smart edge-cloud orchestration. This framework could enable generic AI beyond specific applications that depend on multi-modal data processing, which contributes to the generalization of applications across various industries such as healthcare, autonomous systems, smart cities, and cybersecurity. Moreover, this work will help deploy sustainable AI by employing green computing techniques to detect anomalies in near real-time in various critical domains helping to ease challenges of the modern world.
03 25 2025 2025 01009 itmconf_icsice2025_01009 https://creativecommons.org/licenses/by/4.0/ 10.1051/itmconf/20257601009 https://www.itm-conferences.org/10.1051/itmconf/20257601009 https://www.itm-conferences.org/10.1051/itmconf/20257601009/pdf IEEE Transactions on Industrial Informatics Li 19 3 2541 2023 10.1109/TII.2022.3177726 Journal of Systems Architecture Patel 130 102635 2022 IEEE Internet of Things Journal Zhao 11 2 1895 2024 10.1109/JIOT.2023.3296613 International Journal of Scientific Research and Management (IJSRM) Arjunan 11 6 944 2023 10.18535/ijsrm/v11i06.ec2 International Journal of Science and Research (IJSR) Gujar 13 10 577 2024 10.21275/SR241006200634 IEEE Internet Computing Mohan 28 4 49 2024 10.1109/MIC.2024.3383758 Singh J., Adams B., & Hassan A. E. (2024). On the impact of black-box deployment strategies for Edge AI on latency and model performance. arXiv preprint arXiv:2403.17154. 10.1109/iThings-GreenCom-CPSCom-SmartData-Cybermatics60724.2023.00064 Chen X., Zhu W., Chen J., Zhang T., Yi C., & Cai J. (2024). Edge computing enabled real-time video analysis via adaptive spatial-temporal semantic filtering. arXiv preprint arXiv:2402.18927. 10.1109/ICMLA58977.2023.00233 Smith H., Seekings J., Mohammadi M., & Zand R. (2024). Realtime facial expression recognition: Neuromorphic hardware vs. Edge AI accelerators. arXiv preprint arXiv:2403.08792. 10.1007/s10586-024-04686-y Gill S. S., Golec M., Hu J., Xu M., Du J., Wu H., & Uhlig S. (2024). Edge AI: A taxonomy, systematic review and future directions. arXiv preprint arXiv:2407.04053. Anonymous. (2024). Generative AI on the Edge: Architecture and performance evaluation. arXiv preprint arXiv:2411.17712. 10.1016/j.future.2022.07.023 Wang X., Khan A., Wang J., Gangopadhyay A., Busart C. E., & Freeman J. (2022). An edge-cloud integrated framework for flexible and dynamic stream analytics. arXiv preprint arXiv:2205.04622. 10.1016/j.future.2022.03.039 Rivas D., Guim F., Polo J., Silva P. M., Berral J. Ll., & Carrera D. (2021). Towards automatic model specialization for edge video analytics. arXiv preprint arXiv:2104.06826. Gao G., Dong Y., Wang R., & Zhou X. (2022). EdgeVision: Towards collaborative video analytics on distributed edges for performance maximization. arXiv preprint arXiv:2211.03102. King J., & Lee Y. C. (2022). Distributed edge-based video analytics on the move. arXiv preprint arXiv:2206.14414.