Learning Material Properties Using Radio Signals

Non-Exclusively Licensed

A system may sense the contents of a closed container, by analyzing a wireless signal that reflects from an RFID tag on the outside of the container. The frequency response of the tag's antenna may be affected by the relative permittivity of the contents and by the tag's environment. The frequency response may be measured in a line-of-sight environment and in a multipath environment. Channel estimates may be calculated, based on the measurements. Channel ratios may be calculated by dividing line-of-sight channel estimates by multipath channel estimates. The resulting channel ratios may be fed into a variational autoencoder, which in turn generates synthetic data that contains information about multipath environments but not the contents. The output of the variational autoencoder may be converted into synthetic channel estimates, which may in turn be employed for anomaly detection, or to train a classifier to classify contents of the container.

Researchers

Fadel Adib / Alaa Khaddaj / Zexuan Zhong / Junshan Leng / Unsoo Ha / Tzu Ming Hsu / Yunfei Ma

Departments: Program in Media Arts and Sciences
Technology Areas: Artificial Intelligence (AI) and Machine Learning (ML) / Sensing & Imaging: Chemical & Radiation Sensing
Impact Areas: Healthy Living

  • learning material properties using radio signals
    United States of America | Granted | 11,308,291
  • methods and apparatus for radio frequency sensing in diverse environments
    United States of America | Granted | 10,872,209

License this technology

Interested in this technology? Connect with our experienced licensing team to initiate the process.

Sign up for technology updates

Sign up now to receive the latest updates on cutting-edge technologies and innovations.