Passive RFID for Object and Use Detection during Trauma Resuscitation

Abstract

We evaluated passive radio-frequency identification (RFID) technology for detecting the use of objects and related activities during trauma resuscitation. Our system consisted of RFID tags and antennas, optimally placed for object detection, as well as algorithms for processing the RFID data to infer object use. To evaluate our approach, we tagged 81 objects in the resuscitation room and recorded RFID signal strength during 32 simulated resuscitations performed by trauma teams. We then analyzed RFID data to identify cues for recognizing resuscitation activities. Using these cues, we extracted descriptive features and applied machine-learning techniques to monitor interactions with objects. Our results show that an instance of a used object can be detected with accuracy rates greater than 90 percent in a crowded and fast-paced medical setting using off-the-shelf RFID equipment, and the time and duration of use can be identified with up to 83 percent accuracy. Our results also offer insights into the limitations of passive RFID and areas in which it needs to be complemented with other sensing technologies.

Deep Learning for RFID-Based Activity Recognition

“…In addition to the 10 activities we monitored, tens of other activities occur during trauma resuscitation that we did not monitor, which we labeled as “other activity.” We did not manually remove their corresponding data from our testing set as has been done in other research [12,16], but these “extraneous” data may cause false predictions because in some cases an object may be used in the labeled activities as well as in “other activities.” Because Precision = TP / ( TP + FP ), where TP denotes true positives and FP denotes false positives, if TP is smaller than FP then the precision is significantly influenced by the FP , and if TP is greater than FP the precision is significantly influenced by TP . For short activities (e.g.…”

“…The system was able to achieve satisfactory performance for phase recognition, but wearing the antennas requires user participation and may interfere with work in fast-paced medical settings. Recent research demonstrated that the status of object manipulation can be estimated using passive RFID tags and fixed antennas based on manufactured features extracted from received signal strength indicator (RSSI) [16]. The use of specialized objects to perform complex activities provided the basis for activity recognition [6].…”

Activity Recognition Using RFID Phase Profiling in Smart Library

“…This inspires us to infer the activity by monitoring the transformation of the phase value. Although there are some applications based on RFID phase applied to areas, such as object use detection [14], [15], gesture recognition [7], and indoor localization [8], this study is the first to involve activity recognition in the library according to the intensity of the variation of phase. Details of our system are expounded in the next section.…”

Activity recognition for medical teamwork based on passive RFID

“…Wearing and configuring wearable sensors, however, can be time consuming and inconvenient. Object-use detection and activity recognition have been evaluated in simulated trauma resuscitations using passive RFID tags and fixed antennas[9][10]. The advantages of ultra-high frequency (UHF) passive RFID systems include the use of fixed antennas and small size, battery-free tags that do not hinder work, capacity for use in dynamic environments, and cost efficiency.…”