Info iconThis preview shows page 1. Sign up to view the full content.

View Full Document Right Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: ce and performs a cost-benefi t analysis to determine if, when and how to signal her that this message has arrived. SCENARIO 1 The Notification Platform adds the e-mail from Alice’s boss to her inbox but does not notify her about the message until one hour later, after her appointment with the job candidate has ended. Predicted usefulness SCENARIO 2 The system senses that Alice is at her PC and is composing an e-mail. It waits for her to finish writing, then chimes and displays a small alert box in the corner of the screen, notifying her about the message from her boss. SCENARIO 3 The system matches the subject of the e-mail to an entry in Alice’s schedule for today and assigns it highest priority. The e-mail is forwarded to her “considerate” cell phone, which signals her with an urgent ring tone. C OPYRIGHT 2004 SCIENTIFIC AMERICAN, INC. WATCHING THE EYES TO FOLLOW THE MIND Roel Vertegaal (left) and his students at Queen’s University in Kingston, Ontario, have been enhancing televisions, phones, computers and video-conferencing systems with the ability to sense human eye contact. They have also put the technology to artistic use in AuraMirror (right). Hidden infrared lights, cameras and a computer transform a large monitor into a virtual magic mirror that superimposes nebulous “auras” over the images of people in front of it. The blobs extend outward and merge when two observers look at each other, giving visible form to an intangible human connection ( far right). ! thing,” Vertegaal says, pointing over his shoulder. He turns to face the object. “On,” he says. LEDs mounted on a small circuit board stuck to the lamp shoot invisible infrared light into his pupils. The light reflects off his retinas, and an infrared camera on the board picks up two bright spots in the image, one from each eye. A processor does some quick pattern and speech recognition, and the lamp switches on. Gaze detection can endow quotidian machines with seemingly magical behavior. Vertegaal answers a ringing telephone by looking at it and saying “Hello.” When he stops talking and turns away from the phone, it hangs up. The TV in the lab pauses a DVD or mutes the sound on a broadcast show whenever it notices that there are no longer any eyes watching it. Some of Vertegaal’s students walk around with eye-contact sensors on their hat or glasses. When the wearer enters a conversation, the sensor passes “Eye contact is the most accurate measure of attention that we have. But it’s not perfect by any means.” particular piece of information. Both approaches must face the bugbear of complexity. If the system is limited to following a few rules, users can predict exactly how it will treat a given message. Many e-mail programs, for example, manage spam by maintaining lists of known spammers and of legitimate contacts. When each e-mail arrives, its sender is compared against both lists and either deleted or delivered. Such systems are simple and clear— but infamously inaccurate. Spam fi lters and network fi rewalls improved significantly when they began to rely on statistical models, called Bayesian networks, that are built by machinel...
View Full Document

This note was uploaded on 02/24/2010 for the course COMM 4400 at Cornell University (Engineering School).

Ask a homework question - tutors are online