A Machine Learning Driven Computationally Efficient Horse Shoe Shaped Antenna Design for Wearable Internet of Medical Things

With bio-medical wearables or sensors becoming an essential part of future generations for monitoring the health of workers and others in industrial and other environments. Computationally efficient Antenna as sensors or radiating interface being an indispensable part of such wearables. In this paper a novel Horse shoe shaped antenna (HSPA) meant for such wearables is presented in this work. Inspired by the artificial intelligence, a regression-based Machine learning (ML) techniques are used to facilitate the design of Horse shoe shaped patch antenna to predict the various on body measuring parameters. The ML models so developed are used to predict the desired responses of antenna for given physical and geometrical parameters of the design. This helps us to design an optimized antenna design while efficiently using the available resources. The optimized HSPA designed has a footprint area of 0.272 λ 0 x 0.224 λ 0 and resonates at 2.45 GHz in the frequency band of 1.9–3.05 GHz with SAR of 1.89 W/kg for an input power of 16.98 dBm, peak gain of 1.91 dBi and radiation efficiency of 62.07% when mounted on the human body. Further, a detailed comparison of the five regression-based ML algorithms is also presented and proved more efficient.