System and method for tagging signals of interest in time variant data

A signal tagging system, comprising:

• a processor;
• a classifier module configured to control the processor to accept an input data signal wherein the classifier module classifies the input data signal into one of at least two classifications available comprising a first classification of the data as having no identified outputs and a second classification of the data as at least one potential signal of interest, wherein the short-term classifier also is configured to bypass data that is known to be of no interest;
• a collapser module further configured to control the processor to collapse the input data that is classified as having no identified outputs, thereby creating time-variant data;
• and
• a signal tagger configured to control the processor to tag known signals of interest within the time-variant data classified as having at least one potential signal of interest.

A computer-readable storage medium storing a computer program having instructions for controlling a computing device to tag known signals of interest, the instructions causing the computing device to perform the steps comprising:

• classifying data from an input signal using a short-term classifier, wherein there are at least two classifications available comprising a first classification of the data as having no identified outputs and a second classification of the data as at least one potential signal of interest, wherein the short-term classifier also bypasses data that is known to be of no interest;
• collapsing the input data in the short-term classifier that is classified as having no identified outputs, thereby creating time-variant data;
• and
• tagging a known signal of interest in the time-variant data that was classified as having at least one potential signal of interest.