INTELLIGENT EDGE: A SURVEY OF ARTIFICIAL INTELLIGENCE INTEGRATION IN ELECTRONIC EMBEDDED SYSTEMS
DOI: https://doi.org/10.xxxxxx

JOURNAL OF RESEARCH PERSPECTIVES IN MULTIDISCIPLINARY SCIENCE, EDUCATION AND TECHNOLOGY (RPSET)
Volume 1 Issue 1, Jan – March 2026

Abstract
The convergence of Artificial Intelligence (AI) and Electronic Embedded Systems (EES) is driving a paradigm shift towards intelligent, autonomous, and adaptive edge computing. This survey paper provides a comprehensive examination of the integration of machine learning, particularly deep learning, into resource-constrained embedded platforms. We analyze the evolution from traditional, rule-based embedded systems to contemporary AI-enabled systems
capable of perception, reasoning, and decision-making at the network edge. The paper systematically reviews key architectural innovations, including hardware accelerators, algorithmic optimizations, and novel design methodologies that enable efficient AI inference and lightweight training on embedded devices. Furthermore, we identify persistent challenges such as energy efficiency, real-time performance, security, and model maintainability in dynamic environments. By synthesizing findings from over a decade of research, this survey outlines the current state-of-the-art, delineates critical problem spaces, and projects future trajectories for intelligent embedded systems across diverse application domains including autonomous systems, industrial IoT, and wearable healthcare. The synthesis aims to serve as a foundational reference for researchers and engineers navigating the intersection of embedded systems design and artificial intelligence..

Authors: Dr. B. Asraf Yasmin

Keywords: Embedded Artificial Intelligence, TinyML, Edge Computing, Hardware Acceleration, Model Optimization, Autonomous Systems