Walter Woodson Borden, 55Bethesda, MD

2004011, Jun 10, 2004

Jun 25, 2003

10/606517

Walter Borden - New York NY, US
Alexander Abrams - New York NY, US
Dana Spiegel - New York NY, US

G06F015/16

709/206000, 709/203000

A method and system for on-line monitoring of electronic communications include automatically monitoring text-based communications of one or more chat room or instant messaging participants to determine if a monitoring event has occurred. A monitoring event can be, for example, the combined existence of certain defined factors associated with a particular exchange relating to, for example, the exchange's participants, content, recent history, and/or tone. The existence of a monitoring event can result in one or more predetermined actions being taken by the system. In an exemplary embodiment of the present invention, on-line communications are continually monitored and input to a number of pattern recognizing modules, preferably working in parallel. Using known pattern-recognition techniques, each pattern recognizing module can analyze an aspect of such communications by implementing certain algorithms and, as appropriate, set, increase or decrease the values of one or more state variables descriptive of one or more defined attributes of the online communications. Such state variables can reflect, for example, emotional levels, participant turnover frequencies, use of suspicious word patterns, and other metrics regarding the on-line communications. State variables out put form the various pattern recognizing modules can be simultaneously input to a decision module which can launch one or more decision algorithms. The decision module can then output one or more predetermined actions as determined by the decision algorithms.

2007003, Feb 8, 2007

Jul 18, 2006

11/458259

Walter Borden - Bethesda MD, US
Naveen Agnihotri - New York NY, US

H04L 12/66

370352000, 370250000

A system is claimed that deploys a multi-layer neural network for analyzing, categorizing and organizing conversations and video conferencing on Voice over Internet Protocol (VoIP), The parallel architecture of this implementation is an artificial neural network which allows it to process very large amounts of voice data very efficiently, both in dealing with large, continuous streams of information in real time as well as on voice data archives This invention uses its neural network to operate considerably faster than its linear counterparts as found ill current VoIP message and call management software.

2008015, Jul 3, 2008

Dec 10, 2007

12/000153

Naveen Agnihotri - Brooklyn NY, US
Walter Borden - Bethesda MD, US
David Schieffelin - Waterbury CT, US

The Nexus Holdings Group, LLC - Garden City NY

G06K 9/62

382157, 382156

A computer-readable medium for performing target object recognition in images and video includes instructions for receiving target image data including a target object, applying non-negative matrix factorization with enforced sparseness to the target image data to generate target extracted image feature data, training a neural network to identify the target object using the target extracted image feature data to obtain a trained neural network, receiving object image data, applying non-negative matrix factorization with enforced sparseness to the object image data to generate object extracted image feature data, analyzing the object extracted image feature data with the trained neural network to obtain a result indicating whether the presence of the target object is identified in the object image data, and storing the result of analyzing the object extracted image feature data.