Piotr Mirowski

US Patent:

7630517, Dec 8, 2009

Filed:

Jul 13, 2005

Appl. No.:

11/180191

Inventors:

Piotr Mirowski - New York NY, US
Daniel Tetzlaff - Houston TX, US
David McCormick - Acton MA, US
Nneka Williams - Boston MA, US
Claude Signer - Somerville MA, US

Assignee:

Schlumberger Technology Corporation - Ridgefield CT

International Classification:

G06K 9/00
G06G 7/48
G01V 1/40
G01V 3/18
G01V 5/04
G01V 9/00
G06F 17/18
G06F 19/00

US Classification:

382109, 702 6, 702179, 703 10

Abstract:

A computer-implemented method is provided that automatically characterizes and verifies stationarity of a training image for use in multipoint geostatistical analysis. The stationarity is preferably characterized by statistical measures of orientation stationarity, scale stationarity, and category distribution stationarity.

US Patent:

8463291, Jun 11, 2013

Filed:

Sep 30, 2011

Appl. No.:

13/249895

Inventors:

Piotr Mirowski - New York NY, US
Harald Steck - New Providence NJ, US
Philip A. Whiting - New Providence NJ, US
Ravishankar Palaniappan - Jersey City NJ, US
William Michael MacDonald - Bridgewater NJ, US
Tin Kam Ho - Millburn NJ, US

Assignee:

Alcatel Lucent - Paris

International Classification:

H04W 24/00

US Classification:

4554561, 455457

Abstract:

Embodiments are directed to mobile localization, and more specifically, but not exclusively, to tracking mobile devices. Embodiments include methods that consider probability kernels with distance-like metrics between distributions. Also described are probabilistic kernels that can be used for a regression of location, which can achieve up to about inn accuracy in an office environment.

US Patent:

20060074825, Apr 6, 2006

Filed:

Jan 26, 2004

Appl. No.:

10/538961

Inventors:

Piotr Mirowski - New York NY, US

International Classification:

G06F 15/18
G06E 1/00
G06E 3/00
G06G 7/00

US Classification:

706020000

Abstract:

A system for inferring geological classes from oilfield well input data is described using a neural network for inferring class probabilities and class sequencing knowledge and optimising the class probabilities according to the sequencing knowledge.

US Patent:

20110218950, Sep 8, 2011

Filed:

Jun 2, 2009

Appl. No.:

12/995925

Inventors:

Piotr W. Mirowski - New York NY, US
Deepak Madhavan - Omaha NE, US
Yann Lecun - Lincroft NJ, US
Ruben Kuzniecky - Englewood CA, US

Assignee:

New York University - New York NY

International Classification:

G06N 5/02
G06F 15/18

US Classification:

706 12, 706 58

Abstract:

An exemplary methodology, procedure, system, method and computer-accessible medium can be provided for receiving physiological data for the subject, extracting one or more patterns of features from the physiological data, and classifying the at least one state of the subject using a spatial structure and a temporal structure of the one or more patterns of features, wherein at least one of the at least one state is an ictal state.

US Patent:

20120150532, Jun 14, 2012

Filed:

Dec 8, 2010

Appl. No.:

12/963161

Inventors:

Piotr Wojciech Mirowski - New York NY, US
Srinivas Banglore - Morristown NJ, US
Suhrid Balakrishnan - Scotch Plains NJ, US
Sumit Chopra - Jersey City NJ, US

Assignee:

AT&T Intellectual Property I, L.P. - Reno NV

International Classification:

G06F 17/27

US Classification:

704 9, 704E11001

Abstract:

Disclosed herein are systems, methods, and non-transitory computer-readable storage media for predicting probabilities of words for a language model. An exemplary system configured to practice the method receives a sequence of words and external data associated with the sequence of words and maps the sequence of words to an X-dimensional vector, corresponding to a vocabulary size. Then the system processes each X-dimensional vector, based on the external data, to generate respective Y-dimensional vectors, wherein each Y-dimensional vector represents a dense continuous space, and outputs at least one next word predicted to follow the sequence of words based on the respective Y-dimensional vectors. The X-dimensional vector, which is a binary sparse representation, can be higher dimensional than the Y-dimensional vector, which is a dense continuous space. The external data can include part-of-speech tags, topic information, word similarity, word relationships, a particular topic, and succeeding parts of speech in a given history.

US Patent:

20150198443, Jul 16, 2015

Filed:

Jan 10, 2014

Appl. No.:

14/152209

Inventors:

- Murray Hill NJ, US
Piotr Mirowski - New York NY, US
Tin Ho - Millburn NJ, US

Assignee:

Alcatel-Lucent USA Inc. - Murray Hill NJ

International Classification:

G01C 5/06
G01P 15/14
G06N 99/00
G01C 19/00

Abstract:

A system and method for providing multi-floor activity classification for a mobile device within a multi-floor environment includes an activity recognition module receiving inertial readings and pressure readings from the mobile device. The activity recognition module classifies activities for the mobile device from the inertial readings and the pressure readings.

US Patent:

20150198447, Jul 16, 2015

Filed:

Jan 10, 2014

Appl. No.:

14/152437

Inventors:

- Murray Hill NJ, US
Amy Ortega - Succasunna NJ, US
Tin Ho - Millburn NJ, US
Piotr Mirowski - New York NY, US

Assignee:

Alcatel-Lucent USA Inc. - Murray Hill NJ

International Classification:

G01C 21/16

Abstract:

A system and method for position tagging within an environment includes at least one mobile electronic device adapted to be moved within the environment and a pedestrian dead reckoning module. The at least one mobile electronic device includes an inertial measurement unit and at least one of a near field communication chip, barcode scanner, global positioning system, Bluetooth receiver or WiFi receiver. The pedestrian dead reckoning module is adapted to query and record time stamped readings from the inertial measurement unit and the at least one of the near field communication chip, barcode scanner, global positioning system, Bluetooth receiver or WiFi receiver. The system and method may generate one or more spatial maps of the environment through the collection of radio frequency signal data along with the time stamped readings.

US Patent:

20140315570, Oct 23, 2014

Filed:

Apr 22, 2013

Appl. No.:

13/867420

Inventors:

- Murray Hill NJ, US
Piotr W. Mirowski - New York NY, US
Hyunseok Chang - Holmdel NJ, US
T. V. Lakshman - Morganville NJ, US

Assignee:

Alcatel-Lucent USA Inc. - Murray Hill NJ

International Classification:

H04W 4/04

US Classification:

4554561

Abstract:

A system and method for providing localization of a mobile electronic device within an environment includes at least one server in communication with the mobile electronic device. The at least one server is adapted to receive at least one picture and at least one accelerometer measurement from the mobile electronic device. The at least one server includes a localization module that provides localization to the mobile electronic device based on the at least one picture, the at least one accelerometer measurement and on at least one 3-dimensional map of the environment.