Real-time detection of apnea via signal processing of time-series properties of RFID-based smart garments

Signal processing of time-series properties of Radio Frequency Identification (RFID) tags and novel work in textile knitted antennas for garment devices have enabled real-time detection of motion-based artifacts through unobtrusive, wireless, wearable devices. Capturing the Received Signal Strength Indicator (RSSI) as a time-series signal, we classify whether the subject is breathing or not, estimate the rate at which the subject is breathing, and classify whether the tag is moving in a linear, non-stretched fashion. We improve upon previous efforts to classify subject state from RSSI signals by eliminating the need to train the classifier with both breathing and non-breathing sample data (which is biologically infeasible). To test our approach, we use a programmable breathing infant mannequin yielding accurate detection of cessation of respiratory activity within 5 seconds, and a maximum root-mean-square error of 7 per minute when computing the respiratory rate.