Startup receives $150,000 grant from NSF

WEST LAFAYETTE, USA:High-tech companies that manufacture and integrate sensor networks for electronic systems could benefit from a Purdue University technology developed by a startup that received National Science Foundation funding.

SensorHound Innovations LLC was awarded a six-month SBIR Phase I grant from the NSF, scheduled for Jan. 1 through June 30. The company's software solutions are based on research from Purdue University's School of Electrical and Computer Engineering and Department of Computer Science.

The company is developing software products and services that could reduce the cost of developing, deploying and operating networked embedded systems. These systems act as sensors, gathering data from an environment and sharing it electronically.

Co-founder Patrick Eugster, an associate professor of computer science, said sensors will be used in the future to control the power grid and other systems. Improving how they communicate could diminish the possibility of events like power outages.

"SensorHound Innovations specializes in making these sensor networks reliable through our pure software solutions," he said. "Our specialized software can be loaded onto sensors by the manufacturers. It provides information to a developer or system administrator while monitoring the sensors, and it can raise an alarm should something go wrong."

The company has developed laboratory-tested prototypes, and the NSF SBIR grant will help in creating commercial prototypes of the flagship product, adding new features to the original research. Commercial versions could be created by mid-2014.

Co-founder Vinai Sundaram, the principal investigator of the SBIR grant, said the company's solutions stem from research that he, Eugster and co-founder Matthew Tan Creti conducted with the help of other faculty and students from the Department of Computer Science and the School of Electrical and Computer Engineering. Sundaram earned his doctorate degree from Purdue's School of Electrical and Computer Engineering, and Tan Creti is a doctoral candidate.

"The motivation for our research came from personal experience in trying to build network systems," Sundaram said. "We expected information to come in from the sensors, but when data didn't arrive we realized a diagnosis tool was needed for people who develop these systems."