Personal identification system using multiple parameters having low cross-correlation

Claim 1

A detection system for analyzing personal behavioral traits and matching such traits with known trait profiles, comprising: a plurality of sensors, each monitoring a respective condition, having sensor output signals, each said output signal indicative of a subject criteria; a sensor reading repository connected to said plurality of sensors for storing a plurality of said sensor output signals; a profile generator, connected to said sensor reading repository, receiving said sensor output signals and generating a subject profile from said plurality of sensor output signals; an accepted profile repository for storing a plurality of accepted subject profiles; a profile verifier for receiving said subject profiles for comparing said subject profile to said plurality of accepted profiles, and for generating profile output signals in response to said comparing.

Claim 13

A method of matching patterns indicative of personal characteristic traits, comprising the steps of: reading a plurality of sensors each monitoring a respective condition; determining at least one criteria value from each said reading by a processor in communication with said plurality of sensors; storing said at least one criteria value in a sensor reading database associated with said processor; building a subject profile by said processor from said at least one criteria value; storing a plurality of accepted subject profiles in an accepted profile database; and comparing said subject profile to said plurality of accepted subject profiles in said accepted profile database.

Claim 14

A method of matching patterns indicative of personal characteristic traits, comprising the steps of: reading a plurality of sensors each monitoring a respective condition; determining at least one criteria value from each said reading by a processor in communication with said plurality of sensors; storing said at least one criteria value in a sensor reading database associated with said processor; building a subject profile by said processor from said at least one criteria value; storing a plurality of accepted subject profiles in an accepted profile database; and comparing said subject profile to said plurality of accepted subject profiles in said accepted profile database.

Claim 27

A method of matching patterns indicative of personal characteristic traits, comprising the steps of: reading at least one sensor and calculating a time stamp for said reading; determining at least one criteria value including handwriting height, width, pressure, duration and saturation from said reading by a processor in communication with said at least one sensor by calculating a bin value, wherein said bin value denotes a subrange of values for said criteria; storing said at least one criteria value and said time stamp in a sensor reading database associated with said processor; building a subject profile comprised of a series of said bin values for said at least one criteria value by said processor from said at least one criteria value; storing an accepted subject profile by updating a previously stored accepted subject profile as a function of said readings stored in said sensor reading database, said at least one criteria value, and a previously stored accepted subject profile in a plurality of accepted subject profiles in an accepted profile database; comparing said subject profile to said plurality of accepted subject profiles in said accepted profile database; and calculating a match value from said subject profile and said accepted profile database, comprising comparing said series of bin values for each of said at least one criteria to said series of accepted subject profiles in said accepted profile database, said calculating said match value is computed as a function of said bin values differing from said accepted profile database by a tolerance threshold.

Claim 28

A method of matching patterns indicative of personal characteristic traits, comprising the steps of: reading at least one sensor and calculating a time stamp for said reading; determining at least one criteria value including handwriting height, width, pressure, duration and saturation from said reading by a processor in communication with said at least one sensor by calculating a bin value, wherein said bin value denotes a subrange of values for said criteria; storing said at least one criteria value and said time stamp in a sensor reading database associated with said processor; building a subject profile comprised of a series of said bin values for said at least one criteria value by said processor from said at least one criteria value; storing an accepted subject profile by updating a previously stored accepted subject profile as a function of said readings stored in said sensor reading database, said at least one criteria value, and a previously stored accepted subject profile in a plurality of accepted subject profiles in an accepted profile database; comparing said subject profile to said plurality of accepted subject profiles in said accepted profile database; and calculating a match value from said subject profile and said accepted profile database, comprising comparing said series of bin values for each of said at least one criteria to said series of accepted subject profiles in said accepted profile database, said calculating said match value is computed as a function of said bin values differing from said accepted profile database by a tolerance threshold.