Media.Player

Method to identify particular signatures in mixed signals using only one sensor

Detailed Technology Description

None

Others

*Abstract

University of MissouriOffice of Technology Management & Industry RelationsNon-Confidential Abstract of InventionUM Disclosure No. 12UMC052Method to identify particular signatures in mixed signals using only one sensorPattern recognition is the assignment of a label to a given input value. In typical problems involving pattern recognition, the challenge lies in selecting a good set of features and in devising a reliable algorithm to recognize any particular vector of such features. In general, even when noise is present in the feature vectors, a single pattern naturally emerges from the domain, and the goal becomes to find the class of patterns that most resemble the observed vector. In many other cases, however, various patterns emerge at the same time, and the complexity of the problem increases since the patterns must now be separated before they can be classified. University of Missouri researchers have invented a method for recognizing patterns in mixed signals. The method is not only capable of dealing with mixed signals, but it also requires a single measurement to do so. Traditional techniques for signal separation require the number of measurements to equal the number of sources. This new method requires one single measurement to handle multiple patterns mixed within the measurement. POTENTIAL AREAS OF APPLICATIONS:• IED Detectors• Airport Scanners• Robotic Assistive Technology Systems• Human-Machine Interfaces MAIN ADVANTAGES OF INVENTION:• Fewer sensors and features reduce system’s complexity• Less complexity lowers system’s expenseSTATE OF DEVELOPMENT:• Prototype completeFURTHER R&D REQUIRED• Further testing in other application areasLICENSING POTENTIAL:• University seeks licensee with the potential to commercializeINVENTOR(S):• Guilherme DeSouza• Luis Alberto RiveraCONTACT INFO: Office of Technology Management & Industry Relations Wayne C. McDaniel, Ph.D. Senior Licensing & Business Development Associate – Engineering and Physical Sciences Email: McDanielwc@missouri.edu Phone: 573-884-3302

*Principal Investigator

Name: Guilherme DeSouza, Assistant Professor - ViGIR - Dept of Electrical & Computer Engineering

Department:

Name: Luis Rivera

Department:

Country/Region

USA