Non-contact Blood Pressure Estimation By Microwave Reflection Employing Machine Learning

Hinako Ochi, Jiang Liu, Shigeru Shimamoto

Abstract: In recent years, hypertension has become a leading cause of diseases worldwide. Despite the recommendation from medical experts to measure blood pressure on a daily basis, only a small few do so. The main reason for this is that the typical measurement method using a cuff is physiologically stressful for many, especially for physically handicapped people, and the elderly. In order to eliminate the burden during measurement, a non-contact method for monitoring blood pressure is necessary. This paper proposes a non-contact method to detect the human pulse and in turn, estimate blood pressure. In the experiment, 2.4GHz microwave signals were transmitted against, and reflected from the body, upon which the time-varying reflection intensity was acquired. Pulse rates are first estimated via post-processing of acquired raw data. Blood pressure is then estimated via Machine Learning (ML) methods with parameter values derived from the detected pulse waveform. Experiments indicate that our proposed method is practical and has great potential for future smart health solutions.