Abstract: A system and method for detecting a suspicious object, including a wireless signal transmitter with first and second transmitter antennas, a first wireless signal receiver on an opposite side of the object from the transmitter having first and second receiver antennas, and a second wireless signal receiver on a same side of the object as the transmitter having a third receiver antenna. The transmitter may emit wireless signals from each of the transmitter antennas. The signals emitted by the first transmitter antenna may be received at the first and second receiver antennas. The signals emitted by both transmitter antennas may be received at the third receiver antenna. The object's material type may be determined based on channel state information of the wireless signals received at first receiver. A size of the object may be determined based on channel state information of the wireless signals received at the second receiver.
Type:
Application
Filed:
March 31, 2020
Publication date:
October 8, 2020
Applicants:
Rutgers, The State University of New Jersey; Office of Research Commercialization, The Trustees of Indiana University, The Research Foundation for The State University of New York
Inventors:
Yingying Chen, Chen Wang, Jian Liu, Hongbo Liu, Yan Wang
Abstract: A method of generating a set of examples for explaining decisions made by a machine learning program, involving receiving a set of training data for training the program, and for given subsets of the training data, determining each of (a) a probability of a user correctly inferring a future decision of the program after observing the respective decisions of the program for the given subset of the training data, (b) a suitability of a size of the given subset, and (c) an average probability of the user correctly inferring a future decision of the program after observing the respective decisions of the program for an unspecified subset of the training data. The determinations (a), (b) and (c) are used to score each of the given subsets of training data, and a subset of training data is selected as the generated set of examples based on the scores.
Type:
Application
Filed:
November 27, 2019
Publication date:
June 4, 2020
Applicant:
Rutgers, The State University of New Jersey; Office of Research Commercialization
Inventors:
Patrick Shafto, Scott Cheng-Hsin Yang, Wai Keen Vong, Ravi Sojitra