TagBreathe: Monitor Breathing with Commodity RFID Systems

Abstract

Breath monitoring helps assess the general personal health and gives clues to chronic diseases. Yet current breath monitoring technologies are inconvenient and intrusive. For instance, typical breath monitoring devices need to attach nasal probes or chest bands to users. Wireless sensing technologies have been applied to monitor breathing using radio waves without physical contact. Those wireless sensing technologies however require customized radios which are not readily available. More importantly, due to interference, such technologies do not work well with multiple users. With multiple users in presence, the detection accuracy of existing systems decreases dramatically. In this paper, we propose to monitor users' breathing using commercial-off-the-shelf (COTS) RFID systems. In our system, passive lightweight RFID tags are attached to users' clothes and backscatter radio waves, and commodity RFID readers report low level data (e.g., phase values). We reliably detect the effective human respiration corresponded signal and track periodic body movement due to inhaling and exhaling by analyzing the low level data reported by commodity readers. To enhance the measurement robustness, we synthesize data streams from an array of multiple tags to improve the monitoring accuracy. Our design follows the standard EPC protocol which arbitrates collisions in the presence of multiple tags. We implement a prototype the breath monitoring system with commodity RFID systems. The experiment results show that the prototype system can simultaneously monitor breathing with high accuracy even with the presence of multiple users.

Unsupervised Detection of Apnea Using Commodity RFID Tags With a Recurrent Variational Autoencoder

“…Although WiFi based techniques can measure human vital signs with off-the-shelf WiFi devices, the accuracy is easily affected by the surrounding environment, because of broadcasting nature and long range of WiFi transmissions. To address this issue, some RFID based systems like TagBreathe are developed to track human respiration by analyzing the RFID response data collected at an RFID reader [19]. Since the passive UHF RFID tags are low-cost and are easily attachable to human body, the RFID system can monitor human vital signs at a low cost and is resilient to interference from the unstable environment.…”

“…The main challenge for extracting the breathing signal from the RFID phase measurements is how to mitigate the discontinuity in phase data, which is caused by channel hopping. One way to eliminate the channel hopping influence, as proposed for the TagBreathe system [19], is to group the signals collected from the same channel and to use the estimated displacement in each channel to track the breathing signal. As discussed earlier, this method may not work well for RFID systems in the US, since the reader must hop among 50 different frequencies, following the FCC requirement.…”

“…Some RFID based systems are proposed to achieve low cost as well as reducing the influence of unstable surroundings. Multiple RFID based techniques have been developed for object tracking [14], orientation estimation [15], drones [16]- [18], and especially, for respiration monitoring [19]. Such existing works mainly make use of the RFID phase information collected from the RFID reader on different channels.…”

“…Such existing works mainly make use of the RFID phase information collected from the RFID reader on different channels. One such typical techniques for smart healthcare is called TagBreathe, which monitors the respiration signal of a patient by grouping the RFID responses collected from the same channel and using a estimated displacement in each channel [19]. This method may not be well suited for operation with Ultra High Frequency (UHF) RFID devices in the US, which all adopt frequency hopping over 50 channels, 200 ms per channel, according to FCC requirements.…”

RFID Based Non-Contact Human Activity Detection Exploiting Cross Polarization

“…Human activity detection is a crucial part in human activity monitoring. Traditionally, camera systems or on-body sensors, such infrared sensors or accelerometer/gyroscopes, and FMCW radar [1]- [4], have been utilized to detect human activity, however, these methods comes with drawbacks [5]- [8]. For video monitoring, extensive amount of computational power is required to process the video received, and cameras have security and privacy concerns…”