• Shruti Pravin Bokare

Edge AI integrates artificial intelligence (AI) with edge computing, enabling localized data processing and decision-making directly on devices at the network's edge. This paradigm shifts AI processing from centralized cloud systems to distributed, resource-constrained edge devices, significantly reducing latency, bandwidth usage, and enhancing data privacy. As IoT devices proliferate, Edge AI addresses the demand for real-time, scalable, and efficient solutions across industries such as healthcare, autonomous vehicles, and smart cities. This paper introduces a novel Adaptive Modular Edge AI Framework (AMEAF) that optimizes the deployment of Edge AI by improving system resilience, scalability, and interoperability. We explore the evolution of Edge AI, propose a unique architecture to support dynamic resource allocation, and highlight its future potential to revolutionize data processing in real-time applications.

Edge AI, Real-time processing, Edge computing, IoT, Privacy, Latency, Scalability

" Adaptive Modular Frameworks for Edge AI : Challenges and Future Horizons", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 12, page no.b652-b659, December-2024, Available :http://www.jetir.org/papers/JETIR2412165.pdf

" Adaptive Modular Frameworks for Edge AI : Challenges and Future Horizons", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 12, page no. ppb652-b659, December-2024, Available at : http://www.jetir.org/papers/JETIR2412165.pdf