Bpra1751

STUDENT RESEARCHPRESENTATION:

AFFECTIVE COMPUTINGBY BUSYAIRI PRABU (ERIC)

#308303458

Table of Contents:- Introduction- Refection on 3 Publications- Conclusion

Affective Computing:Affective computing is computing that deals with the attempt tomake machines which can detect and respond to human emotion.

The term "Affective Computing" was the title of an article by Professor Rosalind Picard at the MIT Media Lab in 1995

Reference: http://www.nationmaster.com/encyclopedia/Affective-computing

Academic Paper One:Affective Computing: ChallengesRosalind W. PicardMIT Media Laboratory, Room E15-020G, 20 Ames Street, Cambridge, MA 02139-4307, USAReceived 17 January 2003; accepted 5 February 2003

Say Hello to

SPOCK:Half-Vulcan/half-humanVery intelligentHighly rational&

Highly unemotional

When someone never expresses Emotion, it is tempting to think that Emotion is not there.

Machines:Example: Macintosh has been displaying a smile for years when successful boot-up.

People tend to confuse the smile asAn emotional expression.

Machines can fake the appearanceOf an emotion, without having anySimilar to those we have.

Rosalind W. PicardExplains:

“Machines that might actually “have” Feelings is the key area of Affective Computing.”

In this paper: She addresses and respondsTo the criticisms and challenges which haveArisen in affective computing explainingWhy it might be more valuable thanPreviously expected.

Published books:Affective Computing, Picard 1997 & 2003

Biometric Surveillance:Face recognition using biometrics

Criticism:The range of mean and modalities of emotion expression is so broad, with many ofThese modalities being inaccessible (e.g., blood chemistry, brain activity, Neurotransmitters), and many others being too non-differentiated. This makes it Unlikely that collecting the necessary data will be possible or feasible in the Near future.

Criticism 2:

The sine qua non of emotion expression is the physical body. To the extent that computers do not have physical bodies, they cannot reliably and believably express emotion. Existing attempts at expressingemotions in robots which are at times referred to as embodied, are unrealistic and therefore unconvincing, and unable to Generate the type of affective responsiveness characterising human-human interaction.

Coco – the interactive monitor:Ability to move its monitor, expressing ways that respond to and encourage its user’s own postural movements.

Zizi the affectionate coach:Home of tomorrowZizi growls when sat upon, purrs when touched and groans with delight when you stroke her fur. If left alone, she mews for attention.

Academic Paper Two:Evaluating Affective Interactions: Alternatives to asking what users feelRosalind W. Picard, Shaundra Bryant DailyMIT Media Laboratory, Room E15-020G, 20 Ames Street, Cambridge, MA 02139-4307, USA2005 paper

Classical methods:Such as –Questionnaires: asking you what you feel nowInterviews: with a video set up, recalling what happen earlier in the task

These methods are valuable and are still used today, this paper will highlightSome alternatives to self-report of feelings.

The Paper:Divided into two categories:

Body Measures (e.g. Change in muscle activity)

&

Task measures(e.g. Better ability to a solve a creativeProblem)

Body Measures of Affect:With computers having abilities affective perceptual abilities such as;- body-worn accelerometers- rubber and fabric electrodes- miniature cameras & microphonesetc

Biggest advantage is that body measurements can be taken parallel with the interaction rather than interrupting the user or asking him after the task.

Wearable Earring:Sense emotional status using blood volume pressure.

Task Measures of Affect:

Findings show ways that affective states tend to influence various behaviours during different tasks.

Within different situations can change the outcome of an individualsInteraction changing their behaviours.

Emotional Bottles:Bottles when open expresses an emotional state of;- Sad- Happy &- Angry

Academic Paper Three:Ambient Display using Musical EffectsLuke Barrington, Michael J. Lyons, Dominique Diegmann, Shinji AbeUniversity of California, San Diego2006

The PaperExamine the communication of information about human affect, and constructA functioning prototype which captures behavioural activity level from the face and maps it to musical affects.

QUESTIONS...?