
Dartmouth College engineers George Cybenko and Vincent Berk believe that process query systems (PQS) will help to make sense of the fast growing volumes of digital data currently being generated.
The pair presented their case in a paper published in this month's IEEE Computer, the magazine of the Institute of Electrical and Electronics Engineers Computer Society.
"PQS closes the gap between gathering a tremendous amount of valuable data and figuring out what the data means," said Cybenko, the Dorothy and Walter Gramm professor of engineering at Dartmouth's Thayer School of Engineering.
Engineers have been investigating the potential of PQS as an evolving algorithmic and software framework for the past few years, and Cybenko and Berk believe that the system could be a useful and powerful tool in a variety of fields.
Applications could include analysing credit reports for identity theft, discovering attacks on computer networks, and measuring activity at national borders, car parks or wildlife refuges.
"PQS can do for discrete, categorical data analysis problems what classical times series analysis did for finance and control systems where the data is numerical," said Professor Cybenko.
The technique is based on the premise that sensed environments, be they computer networks, email traffic or high-security buildings, all consist of processes with distinct states, dynamics and observables.
PQS works to detect and understand the changes or irregularities in these processes.
"I think the most interesting application of PQS is in network security monitoring," said Berk, research associate and lecturer at Thayer School of Engineering.
"Network administrators have many options when it comes to monitoring tools, but none of them are integrated. And, while all of them produce useful information, it is often in hugely impractical quantities.
"PQS brings the information together, and effectively focuses on the most important issues first. To my knowledge there has not been a new software technology that is this versatile since the introduction of relational databases."