SMARTER STRATEGIES

A Stream of Better Information

Dennis McCafferty | Date: 03-03-10 | Comments

Better stock forecasting, health-care providing for infants and even outer-space monitoring are all possible via a new "stream computing" software product.

The price of a stock can turn on a dime�influenced by factors as disparate as a commodity price swing, a currency shift or even a snowstorm. The long-term health of a sick infant can depend upon genetics, heart rate and respiratory function. And scientists who are now studying the intriguing world of "space weather" are constantly monitoring the state of sunspot activity, electromagnetic storms and other forms of solar activity.

Typically, this kind of data crunching plays out in piecemeal fashion, with separate devices and software programs monitoring the information. But Armonk, N.Y.-based IBM is positioning itself to change all that with its "stream computing" IBM InfoSphere Streams software. The product analyzes massive amounts of data in real time to deliver faster, more accurate conclusions. Via perpetual analytics, InfoSphere Streams combines streaming architecture and mathematical algorithms to create a forward-looking analysis of data from any source�narrowing down precisely what users are looking for and continuously refining the answer as additional data is made available.

For the stockbroker, that means inventory data, retail sales, weather reports and even the latest global taxation/import regulations can be analyzed at once to come up with an on-the-money forecast. And there are two uses of the product that are expected to improve the state of health care and science:
- In Sweden, researchers are using InfoSphere Streams to better understand �space weather,� which can influence satellite operations, energy transmission over power lines, communications via radio and TV signals, and airline and space travel. By using the LOIS Space Center radio facility in Sweden to analyze radio emissions from space in three dimensions, scientists from Uppsala University use this technology to compile large amounts of data and extract predictions on activities in space. Since researchers need to measure signals from space over large time spans, the raw data generated by even one antenna quickly becomes too large to handle or store. InfoSphere Streams analyzes the data immediately as it streams from sensors. Over the next year or so, the project is expected to perform analytics at no less than 6 gigabytes per second, or 21,600 gigabytes per hour�the equivalent of all the Web pages on the Internet.
- IBM and the University of Ontario Institute of Technology (UOIT) are using the product to help doctors detect subtle changes in the condition of critically ill premature babies. The software ingests a constant stream of biomedical data, such as heart rate and respiration, along with clinical information about the babies. Monitoring these babies as a patient group is especially important as certain life-threatening conditions such as infection may be detected up to 24 hours in advance by observing changes in physiological data streams. Currently, physicians monitoring preemies rely on a paper-based process that involves manually looking at the readings from various monitors and getting feedback from the nurses providing care.
�This research has the potential to really impact neonatal care through reduced mortality and morbidity rates and overall health care costs,� says Dr. Carolyn McGregor, an associate professor at UOIT and a lead researcher on the product testing effort. �By merging our research and technology, we�re able to collect more detailed patient data in a systematic manner, do online health analysis and decision support, and get advanced early warning of emerging patterns that could predict a medical event.�