AI and machine learning in antenna-enabled sensors

Abstract

Antenna-enabled sensors represent a unique class of sensing technologies that principally employ electromagnetic (EM) theory and principles to facilitate contactless, wireless and energy-efficient sensing and detection. Due to their sensitivity to changes in permittivity, geometry and surrounding media, antenna-enabled sensors are increasingly utilised in various applications, including biomedical monitoring, environmental diagnostics, structural health assessment and food and beverage quality inspection. This chapter provides a review of the theoretical underpinnings and practical applications of antenna-based sensing, with a particular focus on resonant behaviour, impedance characteristics and radiation interactions. Additionally, it explores the growing integration of artificial intelligence (AI) and machine learning (ML) in the design and deployment of antenna-enabled sensors. By facilitating predictive modelling, adaptive calibration and intelligent signal processing, AI and ML techniques are significantly improving the performance, scalability and robustness of antenna-enabled wireless sensing and communication systems. The discussion in this chapter also briefly extends to state-of-the-art developments, key challenges and prospects for intelligent antenna-enabled sensors in next-generation wireless sensing technologies.