Robert J Jannarone

US Patent:

7127439, Oct 24, 2006

Filed:

Jun 7, 2002

Appl. No.:

10/165232

Inventors:

Robert Jannarone - San Diego CA, US
David Homoki - Marietta GA, US
Amanda Rasmussen - Atlanta GA, US

Assignee:

Netuitive, Inc. - Reston VA

International Classification:

G06F 17/17
G06F 17/18
G05B 19/418

US Classification:

706 25, 706 17, 706 23

Abstract:

This invention specifies analyzers to be run in conjunction with computer estimation systems, which may be applied to performance monitoring (APM) services. A semi-automated analyzer may be used by a human analyst to periodically evaluate available historical data for establishing a desired set of input measurements, model parameters, and reporting criteria, collectively called configuration parameters, to be used by an estimation system. In addition, a fully automated analyzer may periodically and automatically reevaluate such configuration parameters and automatically reconfigure the estimation system accordingly. For both types of analyzer, the active set of input measurements for the computerized estimation system can be initially established or periodically updated to perform any variety of configuration tuning operations, including the following: removing linearly redundant variables; removing inputs showing no variation; removing unnecessary or non-estimable inputs; tuning estimation system operating parameters that govern learning rates and the use of recent trends; occasional model accuracy assessment; and tuning monitoring alarm thresholds.

US Patent:

7280988, Oct 9, 2007

Filed:

Dec 19, 2002

Appl. No.:

10/324641

Inventors:

David Helsper - Marietta GA, US
Jean-Francois Huard - New York NY, US
David Homoki - Marietta GA, US
Amanda Rasmussen - Atlanta GA, US
Robert Jannarone - San Diego CA, US

Assignee:

Netuitive, Inc. - Reston VA

International Classification:

G06E 1/00

US Classification:

706 26, 706 22, 706 21, 709224, 702182, 702186

Abstract:

A monitoring system including a baseline model that automatically captures and models normal system behavior, a correlation model that employs multivariate autoregression analysis to detect abnormal system behavior, and an alarm service that weights and scores a variety of alerts to determine an alarm status and implement appropriate response actions. The baseline model decomposes the input variables into a number of components representing relatively predictable behaviors so that the erratic component e(t) may be isolated for further processing. These components include a global trend component, a cyclical component, and a seasonal component. Modeling and continually updating these components separately permits a more accurate identification of the erratic component of the input variable, which typically reflects abnormal patterns when they occur.

US Patent:

7529721, May 5, 2009

Filed:

Jul 10, 2006

Appl. No.:

11/484874

Inventors:

Robert J. Jannarone - San Diego CA, US
J. Tyler Tatum - Atlanta GA, US
Jennifer A. Gibson - Atlanta GA, US

Assignee:

Brainlike, Inc. - San Diego CA

International Classification:

G06F 17/15
G06F 17/16
G06F 17/18
G05B 15/00

US Classification:

706 52, 706 14, 706 23

Abstract:

Feature values, which may be multi-dimensional, collected over successive time slices, are efficiently processed for use, for example, in known adaptive learning functions and event detection. A Markov chain in a recursive function to calculate imputed values for data points by use of a “nearest neighbor” matrix. Only data for the time slices currently required to perform computations must be stored. Earlier data need not be retained. A data selector, referred to herein for convenience as a window driver, selects successive cells of appropriate adjacent values in one or more dimensions to comprise an estimation set. The window driver effectively indexes tables of data to efficiently deliver input data to the matrix. In one form, feature inputs are divided into subgroups for parallel, pipelined processing.

US Patent:

7877337, Jan 25, 2011

Filed:

Oct 10, 2007

Appl. No.:

11/907259

Inventors:

Robert J. Jannarone - San Diego CA, US
J. Tyler Tatum - Atlanta GA, US
Jennifer A. Gibson - Atlanta GA, US

Assignee:

Brainlike, Inc. - San Diego CA

International Classification:

G06F 15/18
G06G 7/22

US Classification:

706 14, 706 21, 706 28

Abstract:

In an auto-adaptive system, efficient processing generates predicted values in an estimation set in at least one dimension for a dependent data location. The estimation set comprises values for a dependent data point and a preselected number of spatial nearest neighbor values surrounding the dependent data point in a current time slice; The prediction may be made for time slices, seconds, hours or days into the future, for example. Imputed values may also be generated. A mean value sum of squares and cross product MVSCP matrix, inverse, and other learned parameters are used. The present embodiments require updating only one MVSCP matrix and its inverse per time slice. A processing unit may be embodied with selected modules each calculating a component function of feature value generation. Individual modules can be placed in various orders. More than one of each type of module may be provided.

US Patent:

8069132, Nov 29, 2011

Filed:

Apr 29, 2009

Appl. No.:

12/432514

Inventors:

Robert John Jannarone - San Diego CA, US
John Tyler Tatum - Atlanta GA, US
Jennifer A. Gibson - Atlanta GA, US

Assignee:

Brainlike, Inc. - Atlanta GA

International Classification:

G06F 9/44

US Classification:

706 52, 706 14, 706 23

Abstract:

Feature values, which may be multi-dimensional, collected over successive time slices, are efficiently processed for use, for example, in known adaptive learning functions and event detection. A Markov chain in a recursive function to calculate imputed values for data points by use of a “nearest neighbor” matrix. Only data for the time slices currently required to perform computations must be stored. Earlier data need not be retained. A data selector, referred to herein for convenience as a window driver, selects successive cells of appropriate adjacent values in one or more dimensions to comprise an estimation set. The window driver effectively indexes tables of data to efficiently deliver input data to the matrix. In one form, feature inputs are divided into subgroups for parallel, pipelined processing.

US Patent:

8229879, Jul 24, 2012

Filed:

Mar 27, 2009

Appl. No.:

12/412680

Inventors:

Robert J. Jannarone - San Diego CA, US
John Tyler Tatum - Atlanta GA, US
Thuy Xuan Cox - Suwanee GA, US
Leronzo Lidell Tatum - College Park GA, US

Assignee:

Brainlike, Inc. - Atlanta GA

International Classification:

G06F 15/18
G06K 9/62
G06N 5/04

US Classification:

706 61, 706 20, 706 21, 706 22

Abstract:

An auto-adaptive system is provided that includes a template builder that allows weighted templates to be created for computing auto-adaptive features, an auto-adaptive event locator that analyzes a data set to identify events, an event extractor that locates and extracts identified events and provides events for review by an event analyzer (operator or programmed module) to distinguish clutter data from target data, and an auto-adaptive risk analyzer that processes data related to hit rates, false alarm rates, alarm costs, and risk factors to determine return on investment information and receiver operator characteristic curves.

US Patent:

20110257978, Oct 20, 2011

Filed:

Oct 21, 2010

Appl. No.:

12/909633

Inventors:

Robert J. Jannarone - San Diego CA, US
John T. Tatum - Atlanta GA, US
Leronzo Lidell Tatum - College Park GA, US
David J. Cohen - Ann Arbor MI, US

Assignee:

BRAINLIKE, INC. - Atlanta GA

International Classification:

G10L 19/00

US Classification:

704500, 704E19001

Abstract:

A computer implemented method for processing audio data communicated between a first device and a second device over a data communication network, where one or more processors are programmed to perform steps include at a first device: receiving time series audio data comprising audio data over a time period; partitioning the audio data in a plurality of time segments; transforming the audio data in the plurality of time segments into a plurality of feature values; transmitting a subset of plurality of feature values over a data communication network; and at a second device: receiving the transmitted plurality of feature values from the data communication network; and transforming the feature values into the time domain to reproduce the time series audio data.