Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
PATTERN DETECTION AT LOW SIGNAL-TO-NOISE RATIO WITH MULTIPLE DATA CAPTURE REGIMES
Document Type and Number:
WIPO Patent Application WO/2019/140430
Kind Code:
A1
Abstract:
Methods and systems for detecting and characterizing a pattern (or patterns) of interest in a low signal-to-noise ratio (SNR) data set are disclosed. One method is a two-stage Likelihood pipeline analysis for detecting patterns of interest captured with multiple data capture regimes that takes advantage of the benefits of a full Likelihood analysis while providing computational tractability. The two-stage pipeline may include a first stage including the application of approximate Likelihood functions. At the first stage, the effects of penetrance of each pattern of interest into each data capture regime may be accounted for. The second stage may include a full Likelihood analysis.

Inventors:
KLECKNER NANCY E (US)
CHANG FREDERICK S (US)
Application Number:
PCT/US2019/013605
Publication Date:
July 18, 2019
Filing Date:
January 15, 2019
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
HARVARD COLLEGE (US)
International Classes:
G06K9/00; G06K9/36; G06K9/62; G06T7/77
Domestic Patent References:
WO2017040669A12017-03-09
Foreign References:
US20050050129A12005-03-03
US8166064B22012-04-24
US7340257B22008-03-04
Attorney, Agent or Firm:
DYKEMAN, David J. et al. (US)
Download PDF: