Technology Could Enable Computers to ‘Read the Minds’ of Users
Computers capable of responding to users’ emotional states could be facilitated by methods developed by Tufts University researchers through the novel application of non-invasive and easily portable imaging technology. “Measuring mental workload, frustration and distraction is typically limited to qualitatively observing computer users or to administering surveys after completion of a task, potentially missing valuable insight into the users’ changing experiences,” says Tufts computer science professor Robert Jacob. His human-computer interaction group is collaborating with biomedical engineering professor Sergio Fantini in an analysis of functional near-infrared spectroscopy (fNIRS) technology that monitors blood oxygenation levels in the brain as a proxy for workload stress a user may undergo when executing a task of increasing difficulty. School of Engineering researcher Erin Solovey says, “fNIRS, like MRI, uses the idea that blood flow changes to compensate for the increased metabolic demands of the area of the brain that’s being used.” Fantini says the specific area of the brain where the change in blood flow transpires should yield clues about the brain’s metabolic changes and workload, which could act as a surrogate for frustration and similar emotions. A $445,000 National Science Foundation grant will let the researchers incorporate real-time biomedical data with machine learning to generate a computer user experience that is more in tune with users’ mental load. The initial results of the team’s experiments to detect the user workload experience with fNIRS will be presented at the ACM symposium on user interface software and technology, which takes place Oct. 7-10, in Newport, R.I. For more information on the ACM UIST Conference, visit http://www.acm.org/uist/uist2007/
Tufts University (10/01/07) Thurler, Kim
