Human respiration feature extraction in personal emergency response systems and methods

Abstract

A non-wearable Personal Emergency Response System (PERS) architecture is provided, implementing RF interferometry using synthetic aperture antenna arrays to derive ultra-wideband echo signals which are analyzed and then processed by a two-stage human state classifier and abnormal states pattern recognition. Systems and methods transmit ultra-wide band radio frequency signals at, and receive echo signals from, the environment, process the received echo signals to yield a range-bin-based slow signal that is spatially characterized over a plurality of spatial range bins, and estimate respiration parameter(s) of the human(s) by analyzing the slow signal. The antennas may be arranged in several linear baselines, implement virtual displacements, and may be set into multiple communicating sub-arrays. A classifier uses respiration and other derived features to classify the state of the human(s). A decision process is carried out based on the instantaneous human state (local decision) followed by abnormal states patterns recognition (global decision).