Method for localization of atypical sequences in big data

One characteristic of the information age is the exponential growth of information, and the ready availability of this information through networks. The question is what to do with this enormous amount of information. One possibility is to characterize it through statistical averages, but UH researchers have taken the opposite tack and developed a system that posits that most of the value in the information is in the parts that deviate from the average: that are unusual or atypical. Their invention uses information and coding theory to locate the most interesting, atypical data.

 

Applications

The invention has a very large number of application areas. Including medical applications such as genomic sequence interpretation and analysis of physiographic data. Other applications include ocean acoustic monitoring, industrial process control, forensic accounting, power grid monitoring, fraud prevention.

 

Main Advantages

Allows identification information of interest in large data sets that could not be recognized through existing methods.

 

Patent Information: