Sense Networks, Inc.

David Rosenberg

Tony Jebara

Blake Shaw

Markus Loecher

Joseph Mattiello

Christine Lemke

Girish Rao

Greg Skibiski

Jason Uechi

Alex (Sandy) Pentland

A method of detecting an event anomaly includes receiving one or more data points, in which each data point represents a spatial or temporal event; associating a unique identifier with each of the one or more data points to obtain one or more individualized data points; distributing the one or more individualized data points across a grid, in which the grid includes one or more cells; determining an event likelihood ratio for one or more of the grid cells; identifying one or more event clusters, in which each event cluster includes one or more of the grid cells; and storing in a data repository an event cluster having a significance level above a threshold significance level.

Event identification in sensor analytics

Systems and computer-implemented methods are provided for comparing, associating and deriving associations between two or more spatial temporal data trails. One or more spatial-temporal data trails comprising one or more places are received at a processor. Each place is identified by a spatial temporal data point. And each spatial-temporal data trail is associated with an individual. The similarity between pairs of places is determined to establish one or more groups of places or one or more groups of individuals. Similarity and/groups can be determined based on demographics associated with the place or individual.

Comparing spatial-temporal trails in location analytics

Growing community of inventors

Scotch Plains, NJ, United States of America

David Rosenberg