About
Experience & Education
Licenses & Certifications
Volunteer Experience
-
MIT Alumni Mentor
Virtual
- Present 24 years 8 months
Help Aero/Astro students as well as mathematical students decide about career paths, Grad School and doing PhDs, options for internships and introductions to other professional friends.
Publications
-
Online Variational Approximations to non-Exponential Family Change Point Models: With Application to Radar Tracking
Neural Information Processing Systems (NIPS) 2013
The Bayesian online change point detection (BOCPD) algorithm provides an efficient way to do exact inference when the parameters of an underlying model may suddenly change over time. BOCPD requires computation of the underlying model’s posterior predictives, which can only be computed online in O(1)
time and memory for exponential family models. We develop variational approximations to the posterior on change point times (formulated as run lengths) for efficient inference when the underlying…The Bayesian online change point detection (BOCPD) algorithm provides an efficient way to do exact inference when the parameters of an underlying model may suddenly change over time. BOCPD requires computation of the underlying model’s posterior predictives, which can only be computed online in O(1)
time and memory for exponential family models. We develop variational approximations to the posterior on change point times (formulated as run lengths) for efficient inference when the underlying model is not in the exponential family, and does not have tractable posterior predictive distributions. In doing so, we develop
improvements to online variational inference. We apply our methodology to a tracking problem using radar data with a signal-to-noise feature that is Rice distributed. We also develop a variational method for inferring the parameters of the (non-exponential family) Rice distribution.Other authors
Patents
-
Methods and arrangements to enhance correlatio
Issued US 7050652B2
Optical Correlation and Target Tracking
-
Methods and arrangements to enhance gridlocking
Issued US 6922493B2
The present invention is in the area of gridlocking or sensor registration. Embodiments encompass systems of process and/or equipment to format tracks from more than one sensor to be compared or correlated by statistical and/or optical correlation techniques to provide coordinate transformations between one or more of the sensors based upon the objects or a subset of the objects tracked by each sensor. Embodiments may take into account determinations or calculations regarding tracks describing…
The present invention is in the area of gridlocking or sensor registration. Embodiments encompass systems of process and/or equipment to format tracks from more than one sensor to be compared or correlated by statistical and/or optical correlation techniques to provide coordinate transformations between one or more of the sensors based upon the objects or a subset of the objects tracked by each sensor. Embodiments may take into account determinations or calculations regarding tracks describing the same object by different sensors and may take into account errors in those determinations by comparing pairs of tracks
-
Image compression to enhance optical correlation
Issued US 6909808B2
The present invention is in the area of optical correlation. Embodiments of the invention encompass systems of process and/or equipment to compress images for optical correlation. Further embodiments of the invention may compress images to correlate objects and gridlock sensors with images based upon track data from sensors. In many of the embodiments of the invention, the sensors may comprise radars, global positioning systems, laser target designators, seismic sensors or systems of seismic…
The present invention is in the area of optical correlation. Embodiments of the invention encompass systems of process and/or equipment to compress images for optical correlation. Further embodiments of the invention may compress images to correlate objects and gridlock sensors with images based upon track data from sensors. In many of the embodiments of the invention, the sensors may comprise radars, global positioning systems, laser target designators, seismic sensors or systems of seismic sensors comprising hydrophones and geophones, and other similar systems.
-
Gridlocking and correlation methods and arrangements
Issued US 6803997B2
The present invention is in the area of tracking objects with systems such as correlation, gridlocking, optical correlation, and combinations thereof. Embodiments encompass systems of process and/or equipment to correlate objects and gridlock sensors with images based upon track data from sensors. In many of the embodiments the sensors may comprise radars, global positioning systems, laser target designators, seismic sensors or systems of seismic sensors comprising hydrophones and geophones…
The present invention is in the area of tracking objects with systems such as correlation, gridlocking, optical correlation, and combinations thereof. Embodiments encompass systems of process and/or equipment to correlate objects and gridlock sensors with images based upon track data from sensors. In many of the embodiments the sensors may comprise radars, global positioning systems, laser target designators, seismic sensors or systems of seismic sensors comprising hydrophones and geophones, and other similar systems. While embodiments may comprise an optical correlator, many embodiments perform one or more analyzes statistically.
Languages
-
English
-
Organizations
-
IEEE
IEEE Distinguished Member
- Present
Other similar profiles
-
Sudhakar Rao
Connect -
Moses Chan
Technical Fellow at Lockheed Martin
Connect -
Butler Lampson
Technical Fellow at Microsoft
Connect -
Carl Nardell
Connect -
Doug Burger
Connect -
Johannes Gehrke
Connect -
Don Shafer
Connect -
Rohit Namjoshi, Ph.D.
Connect -
Jeffrey Hunt
Senior Technical Fellow at The Boeing Company
Connect -
Michael Shaughnessy
Connect
Explore collaborative articles
We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.
Explore MoreOthers named Clay Stanek in United States
8 others named Clay Stanek in United States are on LinkedIn
See others named Clay Stanek