"As a university, Georgia Tech is uniquely positioned to take this white hat role in between industry and government," said Andrew Howard, a GTRI research scientist who is part of the Titan project. "We want to bring communities together to break down the walls between industry and government to provide a trusted, sharing platform."
Researchers from the University of Notre Dame, MIT and the University of Memphis are working on educational software that can respond to students' cognitive and emotional states, and deliver the appropriate content based on how knowledgeable a student is about a subject, or even how bored he or she is with it.
AutoTutor and Affective AutoTutor get a feel for students' mood and capabilities based on their responses to questions, including their facial expressions, speech patterns and hand movements.
"Most of the 20th-century systems required humans to communicate with computers through windows, icons, menus and pointing devices," says Notre Dame Assistant Professor of Psychology Sidney D'Mello, an expert in human-computer interaction and AI in education. "But humans have always communicated with each other through speech and a host of nonverbal cues such as facial expressions, eye contact, posture and gesture. In addition to enhancing the content of the message, the new technology provides information regarding the cognitive states, motivation levels and social dynamics of the students."
Mobile nets on the move
For emergency responders and others who need to take their mobile networks with them, even in fast-moving vehicles, data transmission quality can be problematic. North Carolina State University researchers say they've come up with a way to improve the quality of these Mobile ad hoc networks (MANET).
"Our goal was to get the highest data rate possible, without compromising the fidelity of the signal," says Alexandra Duel-Hallen, a professor of electrical and computer engineering at NC State whose work is outlined in the paper "Enabling Adaptive Rate and Relay Selection for 802.11 Mobile Ad Hoc Networks."
The challenge is that fast moving wireless nodes make it difficult for relay paths to be identified by the network, as channel power tends to fluctuate much more in fast-moving vehicles. The researchers have come up with an algorithm for nodes to choose the best data relay and transmission paths, based on their experience with recent transmissions.~~
Tweet the Street