Realizing the Potential of Sensors

E-mail Tom Kevan

The proliferation of sensors is producing a wealth of information, which when used properly can optimize manufacturing processes, deliver greater performance in motor vehicles and aircraft, and enhance all types of operations, from medical facilities to warehouses to logistical services. The catch is whether you have the IT tools to extract actionable information from the glut of data provided by these technologies.

Working with More Data
The past 20 years have witnessed an explosion in the use of sensors. Led by automotive manufacturers, industrial and building automation providers have increasingly turned to sensors to enable greater control and efficiency. More and more, the health care industry uses these devices to expand its capabilities. And this trend is going to continue to grow.

Support for this assumption can be found in a survey conducted by the Institute for the Future (IFTF) and IEEE Spectrum magazine this month, which suggests the impact of science and technology over the next 50 years. According to an article in Spectrum summarizing the views of the leading technology professionals polled in the survey, "Tiny smart sensors will increasingly be embedded in everyday objects and places, forming the basis for a sensory infrastructure." The article also says that the technologists foresee the growing use of RFID-enabled devices and "the widespread diffusion of smart dust-tiny wireless sensors that self-organize into ad hoc networks."

These observations indicate that the mass of data that you have to wade through to find usable information is only going to grow—and become more overwhelming. Unless, you can find a way to extract what you need, the value of the sensors and RFID tags becomes questionable.

Converting Data to Information
Problems, solutions, and benefits in the technology arena tend to result from the convergence of developments rather than from the emergence of any one engineering breakthrough. And this is particularly true of sensory technology.

The mechanism that will enable you to deal with the glut of sensory data is identified by the same IFTF survey. The Spectrum article observes that the technology professionals point to the decentralization of computing power, which occurred in the 1980s with the shift from mainframes to PCs. As this trend evolves, computing and processing will increasingly move from the desktop to sensors and sensor networks. This on-site processing power will enable you to perform deep data mining "to seek out patterns in vast amounts of data and to construct models and simulations of increasingly complex phenomena."

Combine the rich data provided by a growing sensory infrastructure with distributed processing power residing with the sensors, and you overcome the problem of data glut and move closer to realizing the potential of sensors.