Andrew Kun

Two weeks ago my student Alex Shyrokov defended his PhD dissertation. Alex was interested in human-computer interaction for cases when the human is engaged in a manual-visual task. In such situations a speech interface appears to be a natural way to communicate with a computer. Alex was especially interested in multi-threaded spoken HCI. In multi-threaded dialogues the conversants switch back and forth between multiple topics.

How should we design a speech interface that will support multi-threaded human-computer dialogues when the human is engaged in a manual-visual task? In order to begin answering this question Alex explored spoken dialogues between two human conversants. The hypothesis is that a successful HCI design can mimic some aspects of human-human interaction.

In Alex’s experiments one of the conversants (the driver) operated a simulated vehicle while the other (an assistant) was only engaged in the spoken dialogue. The conversants were engaged in an ongoing and in an interrupting spoken task. Alex’s dissertation discusses several interesting findings, one of which is that driving performance is worse during and after the interrupting task. Alex proposes that this is due to a shift in the driver’s attention away from driving and to the spoken tasks. The shift in turn is due to the perceived urgency of the spoken tasks - as the perceived urgency increases the driver is more likely to shift her attention away from driving. The lesson for HCI design is to be very careful in managing the driver’s perceived urgency when interacting with devices in the car.

Alex benefited tremendously from the help of my collaborator on this research Peter Heeman. Peter provided excellent guidance throughout Alex’s PhD studies for which I am grateful. Peter and I plan to continue working with Alex’s data. The data includes transcribed dialogues, videos, driving performance as well as eye tracker data. I am especially interested in using the eye tracker’s pupil diameter measurements to estimate cognitive load as we have done in work lead by Oskar Palinko [1].

References

[1] Oskar Palinko, Andrew L. Kun, Alexander Shyrokov, Peter Heeman, “Estimating Cognitive Load Using Remote Eye Tracking in a Driving Simulator,” ETRA 2010

In an effort to promote the CEPS-BUTE exchange program I gave the following presentation to two similar audiences here at UNH. Last Monday Kent Chamberlin hosted me in his ECE 401 class (the introductory ECE course) and I had a chance to talk to about 75 ECE freshmen. Today I gave the presentation to Bob Henry’s TECH 400 students (TECH 400 introduces the CEPS majors to CEPS undeclared students).

My main point was this: spending a semester abroad gives students a competitive advantage because it proves that they can adapt to change. Of course spending a semester in Europe allows students to travel and I spent some time promoting my favorite travel guide author, Rick Steves :)

On Thursday I participated in a Phase II National Science Foundation Small Business Innovation Research (NSF SBIR) panel. While I’ve been to Phase I panels before, this was my first Phase II panel. In Phase I companies can request up to $150,000 for 6 months to a year. A company that receives a Phase I award, and successfully delivers on its grant, is eligible to compete in Phase II with a proposal for up to $500,000 for two years. 

The one thing that always strikes me at the SBIR panels is that proposals have to make a good business case. Panels include both technical experts and business experts and a proposal has to clear the bar with both sets in order to be recommended for funding. I’ve always taken it for granted that an NSF proposal (SBIR or scientific) should make a good argument for why the technology or scientific innovation is worth funding. However, before my involvement in the SBIR review process, I didn’t really think much about the business case to be made when requesting funding for a business venture. In this respect I’m hardly alone: engineers usually don’t spend much time exploring the business side of running a business. At the UNH ECE department we’re looking into alleviating this problem through the involvement of Brad Gillespie in our senior project courses. Brad is a UNH ECE alumnus, Microsoft veteran and business strategy consultant. Read about Brad’s last visit to UNH ECE and check back for more on this in a future post.

So, if you’re a technical person planning to submit an SBIR proposal (note that many federal agencies run SBIR programs, not just the NSF), my advice is this: bring in people who can help you think through (and coherently present in the proposal) a business plan for your venture. Without a compelling business plan your proposal will not be funded.