EM-ID tag-less identification via electromagnetic emissions (novel sensing, Sample).
A technique for identifying individual instances of electronic devices. This is done by using a basic RFID reader to read the RF emissions from the electronic device to obtain an emitted electromagnetic spectrum and compare it to a library of emitted electromagnetic spectrums of different instances of that type of electronic device and, based on that comparison, finding a best match and identifying the electronic device as being a particular instance of that type of electronic device. This comparison may be made by computing Euclidean distances between vectors that are based on the measured electromagnetic spectrums.
BACKGROUND(1) The five-cent RFID tag was famously claimed to be the tipping point for the RFID industry that would lead to widespread adoption of the technology. While many of the innovations in cost reduction outlined in 2001 have come to pass, the five-cent price point has remained elusive at any quantity. Presently, EPC Gen2 tags (ISO-18000-6c) can be readily purchased individually for ninety-cents online and industry trade magazines report that, in large volumes, tags can be purchased in the seven- to fifteen-cent range. While both academia and industry continue to make strides to reduce the cost of traditional UHF RFID tags, the reality is that due to inflationary forces the opportunity for a five-cent tag may have already passed us by.(2) In an effort to further reduce cost and tag complexity, researchers are focusing on developing chip-less and antenna-less RFID tags. The general rule of thumb being that—a third of the cost of the tag is the integrated circuit (IC), the second third is the antenna inlay, and the final third represents the cost of bonding the two elements together. Therefore, by eliminating one of these elements, it should be possible to further reduce the cost of RFID tags.(3) However, all of these RF methods of uniquely identifying an object rely on adding some form of tag. For many applications, RFID is simply dismissed as being too expensive compared to the alternative of using optical identification in the form of printed barcodes or QR codes. Whil
1. A method for identifying a particular instance of an electronic device, the method comprising: receiving a spectrum of electromagnetic signals emitted by an electronic device under examination; after the receiving, determining a category classification of the electronic device based on the received spectrum of electromagnetic signals; after the determining, comparing the received spectrum of electromagnetic signals to a library of spectrums of electromagnetic signals for electronic devices belonging to the category classification, each of the spectrums of electromagnetic signals in the library representing the spectrum of electromagnetic signals produced by a particular instance of an electronic device belonging to the category classification; finding a best match of the received spectrum of electromagnetic signals to one of the spectrums of electromagnetic signals in the library; and identifying the electronic device under examination as the electronic device in the library that produces the spectrum of electromagnetic signals to which the best match was made. |
18. A method comprising: separately for each of a group of electronic devices of the same type, receiving the spectrum of electromagnetic signals emitted by each electronic device in the group; creating a library of the received spectrums, including an indication of which electromagnetic device in the group produced each spectrum; after the creating of the library, receiving a spectrum of electromagnetic signals emitted by an electronic device that is powered on; comparing the received spectrum of electromagnetic signals to the library of spectrums of electromagnetic signals using a cosine similarity function; finding a best match of the received spectrum of electromagnetic signals to one of the spectrums of electromagnetic signals in the library based on rankings from the cosine similarity function; and identifying the electronic device under examination as the electronic device in the library that produces the spectrum of electromagnetic signals to which the best match was made. |
30. A method for identifying a particular instance of an electronic device, the method comprising: receiving an electromagnetic signal emitted by an electronic device whenever the electronic device is powered on; after the receiving, determining a category classification of the electronic device based on the received electromagnetic signal by using a cosine similarity function to score comparisons of the received electromagnetic signals and representations of electromagnetic signals stored in two or more databases; after the determining, finding a highest probability match by comparing the received electromagnetic signal to one of the databases matching the category classification, wherein the finding the highest probability match comprises using a cosine similarity function to rank similarity between the received electromagnetic signal and the representations of the electromagnetic signals in the one of the databases; and identifying the electronic device as the particular instance using the highest probability match.