Matthew C Reynolds

US Patent:

8094034, Jan 10, 2012

Filed:

Sep 16, 2008

Appl. No.:

12/283869

Inventors:

Shwetak N. Patel - Atlanta GA, US
Thomas M. Robertson - Atlanta GA, US
Gregory D. Abowd - Atlanta GA, US
Matthew S. Reynolds - Durham NC, US

Assignee:

Georgia Tech Research Corporation - Atlanta GA

International Classification:

G08B 21/00

US Classification:

340657, 34031011, 340644

Abstract:

Activity sensing in the home has a variety of important applications, including healthcare, entertainment, home automation, energy monitoring and post-occupancy research studies. Many existing systems for detecting occupant activity require large numbers of sensors, invasive vision systems, or extensive installation procedures. Disclosed is an approach that uses a single plug-in sensor to detect a variety of electrical events throughout the home. This sensor detects the electrical noise on residential power lines created by the abrupt switching of electrical devices and the noise created by certain devices while in operation. Machine learning techniques are used to recognize electrically noisy events such as turning on or off a particular light switch, a television set, or an electric stove. The system has been tested to evaluate system performance over time and in different types of houses. Results indicate that various electrical events can be learned and classified with accuracies ranging from 85-90%.

US Patent:

8392107, Mar 5, 2013

Filed:

Jun 28, 2007

Appl. No.:

11/824204

Inventors:

Shwetak N. Patel - Atlanta GA, US
Khai N. Truong - Atlanta GA, US
Gregory D. Abowd - Atlanta GA, US
Thomas Robertson - Atlanta GA, US
Matthew S. Reynolds - Atlanta GA, US

Assignee:

Georgia Tech Research Corporation - Atlanta GA

International Classification:

G01C 21/30
G01C 21/00
G06F 17/00
G01S 1/24

US Classification:

701409, 701434, 342450, 342463, 34053914

Abstract:

Disclosed is an indoor location system that uses an electrical power line, power line signal injection devices, and portable position receivers (tags) to generate location data relating to positions of the tags in a structure such as a residence or business. The indoor location system fingerprinting of multiple signals transmitted along the power line to achieve sub-room-level localization of the positioning receivers. Details regarding power line positioning are described along with how it compares favorably to other fingerprinting techniques.

US Patent:

8494762, Jul 23, 2013

Filed:

Sep 15, 2009

Appl. No.:

12/560099

Inventors:

Shwetak N. Patel - Atlanta GA, US
Gregory D. Abowd - Atlanta GA, US
Matthew S. Reynolds - Atlanta GA, US
Thomas Robertson - Atlanta GA, US
Erich Stuntebeck - Atlanta GA, US

Assignee:

Georgia Tech Research Corporation - Atlanta GA

International Classification:

G08B 1/08
G06F 19/00
G01C 21/00
G01S 3/02

US Classification:

701408, 701434, 701300, 342450, 342463, 34053911, 34053913

Abstract:

An indoor location system uses an electrical power line, power line signal injection devices, and portable position receivers (tags) to generate location data relating to positions of the tags in a structure such as a residence or business. The indoor location system fingerprinting of multiple signals transmitted along the power line to achieve sub-room-level localization of the positioning receivers. In one embodiment, the fingerprinting techniques utilizes wideband power line positioning (WPLP) that injects up to 44 different frequencies into the power line infrastructure of a structure. The WPLP technique improves upon overall positioning accuracy, improved temporal stability and may be implemented in commercial indoor spaces.

US Patent:

20190195929, Jun 27, 2019

Filed:

Feb 27, 2019

Appl. No.:

16/287517

Inventors:

- Atlanta GA, US
Thomas M. Robertson - Atlanta GA, US
Gregory D. Abowd - Atlanta GA, US
Matthew S. Reynolds - Seattle WA, US

Assignee:

Georgia Tech Research Corporation - Atlanta GA

International Classification:

G01R 29/26
H04B 3/54
G06F 17/00
G01R 21/00

Abstract:

Activity sensing in the home has a variety of important applications, including healthcare, entertainment, home automation, energy monitoring and post-occupancy research studies. Many existing systems for detecting occupant activity require large numbers of sensors, invasive vision systems, or extensive installation procedures. Disclosed is an approach that uses a single plug-in sensor to detect a variety of electrical events throughout the home. This sensor detects the electrical noise on residential power tines created by the abrupt switching of electrical devices and the noise created by certain devices while in operation. Machine learning techniques are used to recognize electrically noisy events such as turning on or off a particular light switch, a television set, or an electric stove. The system has been tested to evaluate system performance over time and in different types of houses. Results indicate that various electrical events can be learned and classified with accuracies ranging from 85-90%.

US Patent:

20160154043, Jun 2, 2016

Filed:

Feb 1, 2016

Appl. No.:

15/012780

Inventors:

- Atlanta GA, US
Thomas M. Robertson - Atlanta GA, US
Gregory D. Abowd - Atlanta GA, US
Matthew S. Reynolds - Seattle WA, US

Assignee:

Georgia Tech Research Corporation - Atlanta GA

International Classification:

G01R 29/26

Abstract:

Activity sensing in the home has a variety of important applications, including healthcare, entertainment, home automation, energy monitoring and post-occupancy research studies. Many existing systems for detecting occupant activity require large numbers of sensors, invasive vision systems, or extensive installation procedures. Disclosed is an approach that uses a single plug-in sensor to detect a variety of electrical events throughout the home. This sensor detects the electrical noise on residential power tines created by the abrupt switching of electrical devices and the noise created by certain devices while in operation. Machine learning techniques are used to recognize electrically noisy events such as turning on or off a particular light switch, a television set, or an electric stove. The system has been tested to evaluate system performance over time and in different types of houses. Results indicate that various electrical events can be learned and classified with accuracies ranging from 85-90%.