Unformatted text preview: to his cell phone — unless his calendar and other evidence suggest that he is in a meeting. Most large companies already use computerized phone systems and standard calendar and contact management software, so tapping into those “sensors” should be straightforward. Not all employees will like the idea of having a microphone on all the time in their ofﬁce, however, nor will everyone want to expose their datebook to some program they do not ultimately control. Moreover, some managers might be tempted to equate a “state of low attention” with “goofing off” and punish those who seem insufﬁciently busy. The researchers seem to appreciate these risks. Hudson argues that an attentive system should not record audio, keystrokes or the like but simply analyze the data streams and discard them after logging “conversation in progress,” “typing detected,” and so on. “We built a pri- vacy tool into Bestcom from the beginning,” Horvitz emphasizes, “so users can control who is allowed to see the various kinds of information it collects about them.” Watching the Watcher
a s dig i t a l c a m e r a s fall in price, that information may come to include video. With a simple $20 webcam, Horvitz’s software can tell when a person is in view and whether she is alone or in a meeting. Fancier cameras can use the eyes as a window to the mind and perhaps extend the reach of considerate computers into the home. Vertegaal has ﬁlled the Human Media Lab at Queen’s University with everyday appliances that know when you are looking at them. “When I say ‘on,’ the lamp over there doesn’t do anyJANUARY 2005 58 SCIENTIFIC A MERIC A N COPYRIGHT 2004 SCIENTIFIC AMERICAN, INC. K C A R M S T R O N G ( p h o to g r a p h s) ; P E T E R H O E Y (s c e n a r i o s) ; J E N C H R I S T I A N S E N (d i a g r a m) SCENARIO 1 Monday, 10:07 A.M. SCENARIO 2 Tuesday, 9:00 A.M. SCENARIO 3 Wednesday, 6:15 A.M. Camera Microphone Task completion Ambient acoustics URGENCY CLASSIFIER
c onsults its database to determine the relationship between the sender and recipient and their communication history. A linguistic analyzer scans the text for times, dates and key words. The classiﬁer “stamps” the message with a dollar value that can fall as the communication grows stale. Deadline status Interaction with computer Date and time Focus of attention Conversation in progress Schedule Location Gaze direction BAYESIAN STATISTICAL MODEL
f uses information from many sources (highlighted objects) to infer Alice’s current focus of attention.
SCENARIO 1 SCENARIO 2 8 Cost ($) Cost ($) 4 0 0 10 20 30 40 50 60 Delay (minutes) 8 4 0 0 10 20 30 40 50 60 Delay (minutes) Wireless signal SCENARIO 3 The system also estimates the cost of interrupting Alice now and in the near future. It alerts her to the message only when the cost of a distraction falls below the value of a notiﬁcation (arrows). 8 Cost ($) 4 0 0 10 20 30 40 50 60 Delay (minutes) Focus of attention User preferences Value of notification Notification method Cost of notification DECISION MODEL surveys the devices available to Ali...
View Full Document
- SCIENTIFIC AMERICAN, Horvitz, Eric Horvitz, Attentive user interface