Detecting Object Motion Using Passive RFID: A Trauma Resuscitation Case Study

Abstract

Abstract-We studied object motion detection in an indoor environment using RFID technology. Unlike prior work, we focus on dynamic scenarios, such as emergency medical situations, subject to signal interference by people and many RFID tags. We build a realistic trauma resuscitation setting and record a dataset of around 14 000 detection instances. We find that factors affecting radio signal, such as tag motion, have different statistical fingerprints, making them discernible using statistical methods. Our method for object motion detection extracts descriptive features of the received signal strength and classifies them using machine-learning techniques. We report experimental results obtained with several statistical features and classifiers, and provide guidelines for feature and classifier selection in different environments. Experimental results show that object motion could be detected with an accuracy of 80% in complex scenarios and 90% on average. The motion type, on the other hand, could not be identified with such high accuracy using currently available passive RFID technology.

Passive RFID for Object and Use Detection during Trauma Resuscitation

“…We built a system for detecting the use of these objects based on their motion and location, which achieved an average precision rate of 63.8% and a recall rate of 90.6% [23]. We then used these data to experiment with various feature sets and classifiers for detecting whether an object is in motion from passive RFID data [22]. While this previous work provided insights into object use detection from RSSI data [22][23], the setups used were simpler than the realistic experimental setup achieved in this paper.…”

“…We then used these data to experiment with various feature sets and classifiers for detecting whether an object is in motion from passive RFID data [22]. While this previous work provided insights into object use detection from RSSI data [22][23], the setups used were simpler than the realistic experimental setup achieved in this paper. Finally, the same laboratory setting was used to analyze the performance of RFID antennas and tags placement [21].…”

“…2) Motion: Movement of a used object (and its attached tag) causes fluctuations in RSSI, which can be detected by quantifying the variability in the current window. Our previous work showed the feasibility of this approach in a crowded laboratory setting [22]. To quantify this variability, we divided a time window into left (L) and right (R) sub-windows, and computed statistics to quantify the dissimilarity between them (Table II).…”

A System Model for Cooperative RFID Readpoints

“…11. Combined detection probability of the RFID system with N ∈ [1,4]. Whereas individual readpoints suffer from performance dips, the fusion of readevents provides a robust and reliable detection.…”

“…From the viewpoint of the RFID system, there are two possible types of errors: missing a tag in a particular packaging unit and false positive reads from other tags in close vicinity. The latter phenomenon is caused by the lack of a well-defined interrogation zone [1] and requires a filtering or classification step [2]- [4]. A simple calculation example demonstrates that even small error rates cause a considerable work load for manual correction.…”