Affective Computing: Machines with Emotional Intelligence Future “teacher as long as every learner” Affective-Cognitive Mental States Baron-Cohen et al. AUTISM RESEARCH CENTRE, CAMBRIDGE RoCo Behavior

Affective Computing: Machines with Emotional Intelligence Future “teacher as long as every learner” Affective-Cognitive Mental States Baron-Cohen et al. AUTISM RESEARCH CENTRE, CAMBRIDGE RoCo Behavior www.phwiki.com

Affective Computing: Machines with Emotional Intelligence Future “teacher as long as every learner” Affective-Cognitive Mental States Baron-Cohen et al. AUTISM RESEARCH CENTRE, CAMBRIDGE RoCo Behavior

Tabback, Mike, Host has reference to this Academic Journal, PHwiki organized this Journal Affective Computing: Machines with Emotional Intelligence Hyung-il Ahn MIT Media Laboratory Skills of Emotional Intelligence: Expressing emotions Recognizing emotions H in addition to ling another’s emotions Regulating emotions Utilizing emotions / (Salovey in addition to Mayer 90, Goleman 95) if “have emotion” We have pioneered new technologies to recognize human affective in as long as mation: Sensors, pattern recognition in addition to common sense reasoning to infer emotion from physiology, voice, face, posture & movement, mouse pressure Mind-Read: Recognizing complex cognitive-affective states from joint face in addition to head movements

Carlow College US www.phwiki.com

This Particular University is Related to this Particular Journal

Future “teacher as long as every learner” Can we teach a chair to recognize behaviors indicative of interest in addition to boredom (Mota in addition to Picard) What can the sensor chair contribute toward inferring the student’s state: Bored vs. interested Results (on children not in training data, Mota in addition to Picard, 2003): 9-state Posture Recognition: 89-97% accurate High Interest, Low interest, Taking a Break: 69-83% accurate

Detecting, tracking, in addition to recognizing facial expressions from video (IBM BlueEyes camera with MIT algorithms) Affective-Cognitive Mental States Baron-Cohen et al. AUTISM RESEARCH CENTRE, CAMBRIDGE Complex Mental States (subset) Concentrating Disagreeing Interested Thinking Unsure Absorbed Concentrating Vigilant Disapproving Discouraging Disinclined Asking Curious Impressed Interested Brooding Choosing Thinking Thoughtful Baffled Confused Undecided Unsure Agreeing Assertive Committed Persuaded Sure Technology that underst in addition to s in addition to responds to human experience like a caring, respectful person would, as long as example: Knows when a person/customer is: Concentrating, in addition to does not interrupt unless very important Thinking, in addition to can pause to let you think Unsure, in addition to can offer to explain differently (Not) interested in what it says (Dis)agreeing, in addition to can adjust response respectfully

Technology with people sense will perceive cognitive-affective states, e.g., be as long as e interrupting hmm Roz looks busy. Its probably not a good time to bring this up Analysis of nonverbal cues Inference in addition to reasoning about mental states Modify one’s actions Persuade others Inferring Cognitive-Affective State from Facial+Head movements (el Kaliouby, 2005) Feature point tracking Head pose estimation Facial feature extraction Head & facial action unit recognition Head & facial display recognition Mental state inference Hmm Let me think about this Experimental Evaluation Conclusions Other examples: Agree Disagree 75% sit in front of computers (static) Back pain/injury = 2 cause of missed work Physical movement helps prevent/reduce back pain Goals : Fostering healthy posture Building social rapport Improved task per as long as mance (Affect-Congruent behavior) Robotic Computer (RoCo) : World’s first physically animated computer Animated Desktop Monitor: RoCo = Robotic Computer

RoCo Behavior NOT when: you’re concentrating, interested, in the middle of an engaging task, or otherwise attentive/focused on the monitor’s content. Might make a micro-movement when you’re looking away or blinking in the middle of a task. Might make a larger movement to attract a new user, bow to welcome, or when user shifts tasks in addition to hasn’t shifted posture (etc.) When should RoCo move (Future work & not topic of this paper, but important to mention) RoCo’s postures congruous to the user affect N=(17) “Stoop to Conquer” : Posture in addition to affect interact to influence computer users’ com as long as t in addition to persistence in problem solving tasks People tend to be more persistent in addition to feel more com as long as table when RoCo’s posture is congruous to their affective state

“Stoop to Conquer”: Posture congruent with emotion improves persistence ( tracing attempts, two different experiments) A multi-modal affective-cognitive measures as long as product evaluation with computational models of predicting customer decisions Predicting customer product preferences by combining in as long as mation about emotion in addition to cognition We are creating new computational models to measure human affective experience in addition to to predict human decision-making & preference Background findings to in as long as m new research: The brain uses both emotion (affect) in addition to cognition in decision making -> model should combine both affect in addition to cognition A person in an experiment is likely to cognitively bias their self-report of what they like. -> method should not rely on only self-report When a person is cognitively loaded they are more likely to use emotion in decision-making. -> method should slightly load person cognitively

Background findings to in as long as m new method: Multiple measures of affect provide most robust assessment: -> method can measure affective physiology (face, skin conductance) as well as behavior in addition to self-report Sweeter beverages are preferred on the first sip; long-term accumulation of something mildly bad is required be as long as e it is “bad enough to notice” -> method should require lots of sips of every beverage More complete underst in addition to ing of consumer desire Skin Conductance ANTICIPITORY FEELING Arousal Multi-Dimensional Response Physical NUMBER OF SIPS Amount Consumed Facial Expression AFFECTIVE LIKING Emotions Self Report COGNITIVE LIKING Purchase intent Liking Expectation Videos of Testing Here is a sneak preview of my project. Make sure to look as long as consumers emotions that may not be captured in self reported questions.

Test Products Stronger Per as long as mer – Pepsi Vanilla Per as long as med in top 25%, green region, in Directions HUT Weaker Per as long as mer – Pepsi Summer mix Per as long as med in lower 40%, lower yellow region, in Directions HUT Products chosen with clear per as long as mance differences Two techniques per as long as med simultaneously Facial Imaging in addition to Head Positioning Tracking face muscle movements to interpret emotions Galvanic Skin Response (GSR) Measures Arousal, used as an intensity measure as long as emotions Affective Computing Facial Head Expression Position Concentrating Thinking Confused Interested Agreeing Disagreeing Affective-Cognitive Mental States GSR Shows Intensity + = Interpretation

Tabback, Mike Sports Talk - KAZM-AM Host www.phwiki.com

Method: Choice Technique Choice technique – respondent selected one of two vending machines Process is repeated 30 times Eventually respondents realized each machine favors a different product in addition to will select the vending machine hoping to receive their favored product 70/30 probability of either product coming out of either machine Method – General Set-Up Two cups on each side of the computer: Pepsi Vanilla in addition to Pepsi Summer Mix Use of straws avoided blocking facial reaction Machine 2 Machine 1 135 246 135 246 Experimental Set Up

Method – Step 1 Each vending machine directed you to sip a beverage RANDOMLY CHOOSE A VENDING MACHINE Method- Step 2 RESPONDENTS SIP RESULTED BEVERAGE Method – Step 3 Answer Questionnaire used in st in addition to ard CLT Overall Liking (beverage in addition to machine) Purchase Intent, Comparison to Expectation

Analysis Our hypothesis is that joining quantitative in addition to qualitative methodologies will help provide underst in addition to ing of consumers’ real product evaluations Discussion

Tabback, Mike Host

Tabback, Mike is from United States and they belong to Sports Talk – KAZM-AM and they are from  Sedona, United States got related to this Particular Journal. and Tabback, Mike deal with the subjects like Entertainment; Sports

Journal Ratings by Carlow College

This Particular Journal got reviewed and rated by Carlow College and short form of this particular Institution is US and gave this Journal an Excellent Rating.