Database Reference
In-Depth Information
Take, for example, a typical oil drilling platform that can have 20,000 to
40,000 sensors on board. All of these sensors are streaming data about the health
of the oil rig, quality of operations, and so on. Not every sensor is actively
broadcasting at all times, but some are reporting back many times per second.
Now take a guess at what percentage of those sensors are actively utilized. If
you're thinking in the 10 percent range (or even 5 percent), you're either a
great guesser or you're getting the recurring theme for Big Data that spans
industry and use cases: clients aren't using all of the data that's available to
them in their decision-making process. Of course, when it comes to energy
data (or any data for that matter) collection rates, it really begs the question:
“If you've bothered to instrument the user, device, or rig, in theory, you've
done it on purpose, so why are you not capturing and leveraging the infor-
mation you are collecting?”
In this usage pattern, it's about applying the analytics you harvested at
rest and getting them applied in motion, to better understand the domain.
The University of Ontario Institute of Technology (UOIT) lead researcher (Dr.
Carolyn McGregor) partnered with The Hospital for Sick Children, Toronto,
to find a better way to predict the onset of a specific hospital-borne illness
affecting newborn babies. You can imagine these fragile babies are connected
to machines that continually collect data. Some hospitals record hourly or
half hourly spot readings and discard it after 72 hours or so; thereby missing
the ability to discover trends at rest and apply analytics in motion at a more
granular level. UOIT's lead research, Dr. Carolyn McGregor, leveraged IBM's
Streams technology to create an in-motion analytics platform that analyzes
over 1,000 pieces of unique medical diagnostic information per second.
Imagine the amount of sensor data for 120 babies; that's 120,000 messages
per second, 178.8 million messages per day, analyzed! You can find more
details on this wonderful success story on the Web (search for “IBM data
baby”). Now consider expanding this approach to outpatients hooked up
to a sensor who are free to go about their daily activities, or monitoring
people at risk of chronic disease states. Quite simply, Big Data has the poten-
tial to be a game changer and a life saver.
Sensor data—it's amazing to see how many things the world has instru-
mented (electrical grids, oil rigs, traffic flows, toll routes, and more), which
means their intention was to collect data: Big Data now lets you do some-
thing with it.
