Active RFID attached object clustering method based on RSSI series for finding lost objects

An active radio frequency identifier (RFID) tag that can communicate with smartphones using Bluetooth Low Energy technology has recently received widespread attention. Indeed, many products have been released that aim to find lost objects using the received signal strength indication (RSSI). However, these products do not provide sufficiently accurate location information to find objects. In this paper, we propose an active RFID attached object clustering method based on RSSI series for finding lost objects. This approach to find lost objects does not execute existing localization methods. We hypothesize that users can deduce the location of a lost object from information about surrounding objects in an environment where RFID tags are attached to all personal belongings. To help find lost objects from the proximity between RFID tags, the system calculates the proximity between a pair of RFID tags from the RSSI series, and estimates the groups of objects in the neighborhood. We present a method for calculating the proximity of the lost object to those around it using a distance function between RSSI series and estimating the group by hierarchical clustering. We confirm the validity of the proposed method, and determine the most appropriate pairs of four distance functions and four clustering algorithms. From the experimental results, it is apparent that our method provides a clear advantage in finding lost objects at low financial and installation cost, and can estimate groups accurately even if the smartphone or RSSI sensor is moving quickly.