Picard, R. (1997). Affective computing. Cambridge, MA: MIT Press.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....a more ambitious and challenging stage of development. Although the study of emotion in the realm of Artificial Intelligence is not totally new (Simon [14] Minsky [8] and Sloman and Croucher [15] much more attention has been recently devoted to this subject by several researchers (Picard [12], Velasquez [18] Wright [20] This renewed effort is being motivated by trends in neuroscience (Damsio [3] LeDoux [7] that are helping to clarify and to establish new connections between high level cognitive processes, such as memory and reasoning, and emotional processes. These recent ....

....for hardware and software Agents. We hope to develop more flexible Agent Architectures capable of dealing with highly complex, rapidly changing and uncertain environments. However, there are other reasons why studying emotion can be important from a computer science or engineering point of view [12]. One of many examples is automatic recognition of user emotional state in order to produce more efficient and intelligent Human Computer interface system. Since our work is mainly oriented towards decision making processes we will not explore these other possible paths. In a certain way, we are ....

R. Picard. Affective Computing. The MIT Press, 1997

....to date they have not considered hierarchies of plans and goals or user errors. Media lab projects specific to problems of the elderly include wearable medical monitors [129] and Memory Glasses [37] Some of these systems will be tested at The Center for Future Health [128] Affective Computing [121, 82] studies how a computer can recognize a person s emotional state based on various kinds of sensor readings. Such work could be applied to Assisted Cognition systems as a way to help determine if a patient is becoming agitated. The Nursebot Project at CMU [10] aims at developing personal robots to ....

R. W. Picard. Affective Computing. MIT Press, Cambridge, 1997.

.... and by the player s personality [2] The formalization includes a theory of how the players emotions can be detected, based on current research on how to measure emotional reactions through bodily expressions such as facial expressions, vocal intonation, galvanic skin response and heart rate [16]. 3.3 Action Generators The action generator for each SIA in the game relies on a decision theoretic model of decision making predicting that agents act so as to maximize the expected utility of their actions [10] Other researchers have started adopting a decision theoretic approach to regulate ....

R. Picard. Affective Computing. M.I.T. Press, Cambridge, Massachusetts, 1997.

....management module. Some of our agents are conceived as embodied human like agents. In order to build believable agents it is not sufficient to endow them with intelligence that enables them to solve complex problems. They should also be provided with a personality, moods and emotions ( 3] [17]) In [7] we present a hybrid architecture, including neural networks, for a cognitive model of agents in which emotions play a role. The system implements an appraisal model of emotions based on the theory proposed by Ortony, Clore and Collins ( 15] A gridworld has been created in which ....

Picard, R. (1997). Affective Computing. MIT Press.

.... devise intelligent interfaces began to realize the importance of emotions in attention, planning, learning, memory, and decision making, there has been increasing interest in building emotionally intelligent interactive systems that can express emotions and respond intelligently to human emotions [18]. One of the challenges in building emotionally intelligent systems is recognizing user emotional states. Humans use different sources of information to assess a person s emotions, including causal information on both context and the person s relevant traits, as well as symptomatic information on ....

Picard, R., Affective Computing. 1997, Boston: MIT Press.

....important than verbal information [2] particularly in respect of the communicating of changing moods and emotional states. Recent findings in psychology and neurology also suggest that emotions are an important factor in decision making, problem solving, cognition and intelligence in general [3][4][5] As socially active humans, we usually have an informal understanding of what emotion is and what different emotions there are. There is also a formal research tradition, which has investigated the nature of emotion systematically. Major figures in scientific research have contributed, most ....

Picard R., Affective Computing, MIT Press (1997)

....Typical context variables in Ubiquitous Computing are: user location, attention focus, physical activity (sitting, driving. emotional state (relaxed, working, in distress. privacy (who else is in the vicinity) etc. There is a considerable body of work in observing context variables [6,23,32,37]. There are also numerous experiments in building context aware applications for Ubiquitous Computing environments [11,22,45] Typically, these either represent context awareness as collection of clauses of the form if context then action , or embed ad hoc context awareness in the application s ....

R. Picard, Affective Computing. MIT Press, Cambridge, Massachusetts. 1997.

....notion with the observation that a computer s capacity for affective interaction plays a vital role in making agents believable. 1] Researchers like Picard have recognized the potential and importance of affect to human computer interaction, dubbing work in this field as affective computing. [13]. In order for intelligent user interfaces to make use of user affect, the user s affective state must invariably first be recognized or sensed. Researchers have tried detecting the user s affective state in many ways, such as, inter alia, through facial expressions, speech, physiological ....

....user interfaces to make use of user affect, the user s affective state must invariably first be recognized or sensed. Researchers have tried detecting the user s affective state in many ways, such as, inter alia, through facial expressions, speech, physiological phenomena, and text. see [13] for a survey of the literature) We believe that text is a particularly important modality for sensing affect because the bulk of computer user interfaces today are textually based. It follows that the development of robust textual affect sensing technologies can have a substantial impact in ....

Picard, R. W., Affective Computing, The MIT Press, Mass., 1997.

....a set of signals, generated by its sensors, resulting from the interaction with the user. The acquisition module transforms these signals, so they can be easily interpreted and consequently used to infer the underlying action or emotion. RELATED WORK ON AFFECTIVE INPUT Affective computing [13] is a growing research area where recently there have been some developments in the area of affective input. There are basically two lines of work on affective input: inferring users real emotional states, and allowing users to manipulate the emotional state of their representation (be it an ....

Picard, R. Affective Computing, MIT Press, 1997.

....sets of capabilities, states and processes, and these different clusters characterise different concepts. For instance, the fullest instantiations of the CogAff schema account for at least three classes of emotions: primary, secondary and tertiary emotions, extending previous classifications. [6, 14, 23, 28]. An architecture based analysis can lead to further refinements in the classification of affective states. 25] Likewise, different concepts of seeing relate to visual pathways through different subsystems in a larger architecture. Blindsight [31] could arise from damage to connections ....

R. Picard. Affective Computing. MIT Press, Cambridge, Mass, London, England, 1997.

....a pressure sensor, and an infrared (IR) sensor for motion detection. The use of biometric sensors with wearable computers is discussed by Picard and Healey [7] Such sensors allow for new interactions between the wearable and the wearer based upon affect detection, prediction, and synthesis [6]. Biometric monitoring for personal health in a wearable is described by Mann, using commercial sensors and algorithms such as signalling danger when the ratio of heart rate and walking speed goes outside a certain range, 3] Here we describe wearable hard and soft sensors. Other wearable ....

R.W. Picard, Affective Computing, MIT Press, Cambridge, MA, 1997.

....supported in part bytheAFOSR and ONR These are not the only important aspects of embodiment, nor even the only ones relevanttoagency. Emotion and mood come immediately to mind as further aspects of embodied agents whichmust be considered for any fully realistic model of human agency. See [45,13] Indeed, we believeattention paid to these issues can be used to improveinteractive systems more generally. See, e.g. 9, 10,11,31,32, 40, 49] as an opportunity to access and utilize resources which can dramatically improve a system s power and performance. In general, as Ismail and Shapiro ....

R. Picard. Affective Computing. MIT Press, Cambridge, MA, 1998.

....methodologies [78] direct manipulation and intelligent agents (also known as delegation) These approaches can be contrasted as the computer sitting passively waiting for input from the human versus the computer taking over from the human. Another dimension for HCI is that of affective computing [67]. Affective computing is concerned with the means to recognize emotional intelligence. Whereas emotional intelligence includes both bodily (physical) and mental (cognitive) events, affective computing presently focuses mainly on the apparent characteristics of verbal and nonverbal communication, ....

....intelligence. Whereas emotional intelligence includes both bodily (physical) and mental (cognitive) events, affective computing presently focuses mainly on the apparent characteristics of verbal and nonverbal communication, as most HCI studies elicit emotions in relatively simple settings [67]. Specifically, recognition of affective states focuses on their physical form (e.g. blinking or face distortions underlying human emotions) rather than implicit behavior and function (their impact on how the user employs the interface) In contrast to the established paradigms of direct ....

R. Picard, Affective Computing. Cambridge, MA:MIT Press, 1998.

....evaluation criteria. 1. INTRODUCTION The effort to create an embodied conversational agent is, by its very nature, multidisciplinary. Creating a fully realized agent requires the application of diverse disciplines ranging from agent systems [4,5,6,13,17,22,28,29] models of emotion [7,8,27] graphics [2,25] and interface design [18,30] to sociology and psychology [9,16,23,24,35] and even art, drama, and animation techniques [17, 33] The practitioners of these disciplines do not share a common language, even when describing components of the common goal; the criteria for critical ....

Picard, R. Affective Computing. MIT Press, Boston MA, 1997.

....and correspond to broad classes of basic emotions, but disagree and are unclear when one looks at the differences between the acoustic correlates of for instance fear and surprise or boredom and sadness. Indeed, certain emotional states are often correlated with particular physiological states ([6] which in turn have quite mechanical and thus predictable effects on speech, especially on pitch, fundamental frequency F0) timing and voice quality. 3. The recognition of emotions in human speech 3.1. Goal As interesting interactions need to be 2 ways, it is necessary that robotic pets can ....

.... but rather were searching for general qualitative acoustic correlates of emotion in speech (for example: happiness tends to make the mean pitch of utterances higher than in calm sentences) More recently, the increasing awareness that affective computing had an important industrial potential ([6]) pushed research towards the quest of performance in automatic recognition of emotions in speech. Unfortunately, to our knowledge, no large scale study using the modern tools developped in the machine learning community have been conducted. Indeed, most often, either only one or two learning ....

Picard R. 1997. Affective Computing, MIT Press.

....emotions, but disagree and are unclear when one looks at the differences between the acoustic www.csl.sony.fr py production.html correlates of for instance fear and surprise or boredom and sadness. Indeed, certain emotional states are often correlated with particular physiological states ([8]) which in turn have quite mechanical and thus predictable effects on speech, especially on pitch, fundamental frequency F0) timing and voice quality. For instance, when one is in a state of anger, fear or joy, the sympathetic nervous system is aroused, the heart rate and blood pressure increase, ....

Picard R. 1997. Affective Computing, MIT Press.

....[14] Ekman s model provided the basis for an implementation by Velasquez [38] others (e.g. 16] have also implemented categorical models. For a far more comprehensive discussion of emotional models in computational systems, the reader is directed to Rosalind Picard s book, Affective Computing [27]. A dimensional approach better captured the range of emotional phenomena that we wanted our wolves to display. Our emotion model is based most directly on the PleasureArousal Dominance model presented by Mehrabian and Russell [24] At each moment, a wolf has three continuous ....

Picard, R.: Affective Computing. Cambridge, MA: MIT Press. (1998)

....design of the Affective Space is such that any quantitative appraisal theory could be implemented. Smith and Ellsworth s model was chosen as the discrete values for the appraisal dimensions had been gather through human experimentation and were readily available. For further appraisal theories see [7]. Fig. 3. A Conceptual Graph Representation of an Abstract Event Definition: A Goal Hierarchy is a partially ordered set G whose elements are called goals. Each goal in G is specified as abstract or primitive. Considering that the sym bol vqvph#r . qr. vt hq g and h are goals, G is such ....

Picard, R. (1997). "Affective Computing". The MIT Press, London.

....sets of capabilities, states and processes, and these different clusters characterise different concepts. For instance, the fullest instantiations of the CogAff schema account for at least three classes of emotions: primary, secondary and tertiary emotions, extending previous classifications. [6, 14, 23, 28]. Likewise, different concepts of seeing relate to visual pathways through different subsystems in a larger architecture. Blindsight [31] is explained by damage to connections between meta management and intermediate high level perceptual buffers, while lower level pathways remain intact. ....

R. Picard. Affective Computing. MIT Press, Cambridge, Mass, London, England, 1997.

No context found.

Picard, R. (1997). Affective computing. Cambridge, MA: MIT Press.

No context found.

Rosalind W. Picard. Affective Computing. The MIT Press, 1997.

No context found.

Picard, R.W., "Affective Computing", MIT Press, Cambridge

No context found.

Picard, R. W. (1997) Affective computing. MIT Press: Cambridge, MA.

No context found.

R.W. Picard. Affective Computing. The MIT Press, Cambridge, MA, 1997.

No context found.

R. Picard. Affective Computing. The MIT Press, Cambridge, Massachusetts, 2000.

No context found.

Picard R., W., Affective Computing, MIT Press, Cambridge, 1997

No context found.

Picard, R. W., Affective Computing, MIT Press, Cambridge, MA,

No context found.

Picard, R. (1997). Affective computing. Cambridge, MA: MIT Press.

No context found.

Picard, R.W., "Affective Computing", MIT Press, Cambridge

No context found.

Picard,R., Affective Computing. 1997, Boston: MIT Press.

No context found.

Rosalind W. Picard. Affective Computing. MIT Press, 1997.

No context found.

R. Picard, Affective Computing. Cambridge, MA: MIT Press, 1997.

No context found.

Picard R.W., "Affective Computing", MIT Press, 2000

No context found.

Picard , R. Affective Computing..MIT Press, 1997.

No context found.

Picard, R. W. Affective Computing. The MIT Press, Cambridge, MA, 1998.

No context found.

R. Picard, Affective Computing, The MIT Press, 1997.

No context found.

R. Picard. Affective Computing. MIT Press, Cambridge, 1997.

No context found.

Picard, "Affective Computing" MIT Press, 1998.

No context found.

Picard, R. Affective Computing. MIT Press, Cambridge MA, 2000.

No context found.

Picard, R.W.: Affective Computing. MIT Press, Cambridge, MA (1997)

No context found.

R. Picard, Affective Computing. Cambridge, MA: MIT Press, 1997.

No context found.

Picard R. Affective Computing. MIT Press 1997

No context found.

R. Picard, Affective Computing, MIT Press, 1997.

No context found.

R.W. Picard, Affective Computing, The MIT Press, Cambridge, MA, 1997.

No context found.

R. W. Picard, Affective Computing. Cambridge, MA: MIT Press, 1997.

No context found.

R. Picard. Affective Computing. MIT Press, 1997.

No context found.

R. W. Picard. Affective Computing. MIT Press, 1997.

No context found.

Picard, R., Affective Computing. MIT Press, Cambridge, MA, 1997.

No context found.

Rosalind W. Picard. Affective Computing. The MIT Press, 1997.

No context found.

Picard, R. (1997). Affective Computing. MIT Press.

First 50 documents  Next 50

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC