System and Method for Auto-Adaptive Network
AssigneeBrainlike Surveillance Research, Inc.
InventorsRobert J. Jannarone, John Tyler Tatum, Thuy Xuan Cox, Leronzo Lidell Tatum
Life of this patent
Estimating the term…
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.
Claims21
A computer implemented method for processing a data set collected through a sensor array over successive time slices comprising:
- locating an event in the data set, the event having a plurality of data points;
- extracting the event from the data set;
- defining a number of dimensions for each data point in the event, wherein at least one dimension has a dependent data location for which a value will be imputed;
- imputing a value to the dependent data point in accordance with an estimation function;
- and
- analyzing the data set including the imputed value of the dependent data point to categorize the event as a hit or a false alarm.
A computer readable medium having stored thereon one or more sequences of instructions for causing one or more microprocessors to perform the steps for processing a data set collected through a sensor array over successive time slices, the steps comprising:
- locating an event in the data set, the event having a plurality of data points;
- extracting the event from the data set;
- defining a number of dimensions for each data point in the event, wherein at least one dimension has a dependent data location for which a value will be imputed;
- imputing a value to the dependent data point in accordance with an estimation function;
- and
- analyzing the data set including the imputed value of the dependent data point to categorize the event as a hit or a false alarm.
A system for processing a data set collected through a sensor array over successive time slices comprising:
- a data storage area storing the data set;
- a processing unit communicatively coupled with said data storage area and configured to execute a plurality of auto-adaptive modules;
- an event locator module configured to be executed by said processing unit to locate an event in the data set, the event having a plurality of data points;
- an event extractor module configured to be executed by said processing unit to extract the event from the data set;
- an arithmetic unit configured to be executed by said processing unit, said arithmetic unit configured to define a number of dimensions for each data point in the event, wherein at least one dimension has a dependent data location for which a value will be imputed by the arithmetic unit;
- and
- an output module configured to be executed by said processing unit, said output module configured to analyze the data set including the imputed value of the dependent data point to categorize the event as a hit or a false alarm.
Dependencies are inferred from the claim text.