@media screen\n{\n\nbody {\n font: 13px/125% "Lucida Grande", "Trebuchet MS", "Bitstream Vera Sans", Verdana, Helvetica, sans-serif;\n}\n\n}\n\n@media print\n{\n\nbody {\n font-size: 6.2pt;\n font-family: "Lucida Grande", "Bitstream Vera Sans", Helvetica, Verdana, Arial, sans-serif;\n}\n\n}

Rana el Kaliouby | MIT Media Lab

Rana el Kaliouby is a Research Scientist at MIT Media Lab, inventing technologies that sense and have a commonsense understanding of people’s affective and cognitive experiences. El Kaliouby holds a B.Sc and M.Sc in Computer Science from the American University in Cairo and a Ph.D. in Computer Science from the Computer Laboratory, University of Cambridge. Her doctoral dissertation, which has been nominated to the British Computer Society Distinguished Dissertation Award, broke new ground in advancing the nascent ability of machines to infer cognitive-affective mental states in real time from nonverbal expressions of people. \n\n El Kaliouby did her post-doctoral training at MIT with Professor Rosalind W. Picard, where she worked on extending her doctoral work to measuring user experiences, human-computer interaction, personal robotics, as well as in learning contexts. Her post-doc research---developing the first in the world suite of social-emotional wearables for autism spectrum disorders---was rated among the top 100 innovations of the year 2006 by New York Times. She played a key role in launching the autism technology initiative at MIT Media Lab, with three autism-related projects underway (funded by NSF and NLMFF) and co-taught the first in the world Autism Theory and Technology course with Rosalind Picard, Cynthia Breazeal and Sherry Turkle. El Kaliouby works closely with sponsors of the Media Lab, including Google, Microsoft, Pepsico, Intuit, Samsung and others and continues to build collaborations within MIT and other institutions, sponsors and foundations locally and internationally. \n\n El Kaliouby is the 2006 recipient of the Higher Education and Learning Institutes Gold Award from the Global Women and Inventors Network. She exhibits her work regularly to engage the public in the research and to encourage more under-represented individuals to pursue a career in technology innovation. She has been invited to present her work at Google, Royal Society and others, and her work has been featured in NewScientist, Reuters, CNET, Wired, the Boston Globe, New York Times, Slashdot and BoingBoing. She has lived on four continents: Africa (Egypt), Middle East (Kuwait and the United Arab Emirates), Europe (UK) and the United States. She is most proud of her husband and her five year-old daughter. \n\n [[Cirriculum Vitae|cv.html]] or in [[pdf|Rana_el_Kaliouby_cv.pdf]]

This site was developed by [[Rana el Kaliouby]] using a ~JavaScript application called ~TiddlyWiki, and is primarily based on Andres Monroy Hernandez's webpage.

For as long as I remember, I have been fascinated by people’s ability to sense and make sense of themselves and others, and the important role this plays in how we connect to and communicate with others (across and inspite of distance, cultural and religious differences, and even in the absence of language). I am also interested in how the social and affective aspects of our life experiences influences our memories, how and what we learn, and eventually how the dots in our life connect. \n\n Thus, my research is about inventing new computational models and technologies that sense and have a commonsense understanding of people’s mental states, behaviors and experiences. My goal? (1) empower people to capture, learn from and share their social, affective and memorable experiences and ulimately connect in a fundamentally better way; (2) address open research questions regarding how our people sensing abilities shape our behaviour, memories and connections with others.

My current research projects: \n# [[Facial Analysis API|API.html]] for real-time analysis of affective and cognitive states \n# Detection and Analytsis of Hand over face gestures \n# [[Social-emotional toolkit for autism spectrum disorders|http://affect.media.mit.edu/projectpages/esp]] \n# Devise new computational models of people’s experiences (e.g., customer delight, memorable experiences) \n# Analysis of customer preferences \n# Sensor-toys for children, including those on the autism spectrum, that will help them navigate the world around them in richer and more memorable ways.

\n* Identification of people's nonverbal behaviour \n* Identification of people's actions and gestures \n* Inference and attribution of complex mental states \n* Mental state reasoning \n* Incorporation of context cues for mental state attribution \n* Inference of intention \n* Mind-reading and Decision-making \n* Applications of mind-reading to Autism Spectrum Disorders ([[ESP project|http://affect.media.mit.edu/projectpages/esp]]) \n* Prosthetics \n* Detection of driver mental states (in collaboration with University of Cambridge and Toyota Corporation)

My current research involves developing real-time vision and sensor models/systems for sensing people. Sensing channels include observable ones (e.g., face, hand-over-face gestures) as well as ones that are up-close (e.g., skin conductance, accelerometers, EEG). People sensors can also be embedded in everyday objects, such as toys or pens. I have used Dynamic Bayesian Networks to model affective (e.g., like and dislike) as well as cognitive (e.g., confusion) states of people. I would like to extend this model to include creativity (can we predict or influence people’s level of creativity) and memory (can we predict and influence what experiences people will find memorable). I am also working on extending the models to sense a variety of “people” including children and large audiences. \n # Real-Time Inference of Affective and Cognitive Mental states from Video \n # Detection and Localization of Hand-over-Face Gestures from Video (with Marwa Mahmoud)

Social communication and emotion regulation difficulties, lie at the core of Autism Spectrum Disorders, making interpersonal interactions overwhelming, frustrating and stressful. Often, these difficulties portray that persons on the autism spectrum are "choosing" to be disengaged from social interactions due to a lack of interest or desire, even when that is not the case. To the contrary, many persons on the autism spectrum who are now able to communicate, write about their persistent attempts to seek interaction with others using unconventional nonverbal cues that were either misinterpreted or simply unnoticed by family members and others. Communication difficulties combined with atypical visual and auditory perception in ASD makes traditional learning challenging, and suggests that independent, spontaneous and sensory-based learning comes more naturally to persons with ASD. \n\n In collaboration with the Groden Center, we are developing novel wearable, in situ social-emotional technology that helps individuals with ASD acquire an affinity for the social domain and improve their overall social communication abilities. We are also developing technologies that build on the nonverbal communication that individuals on the autism spectrum are already using to express themselves socially and emotionally, to help families, educators and other persons who deal with autism spectrum disorders to better understand these alternative means of nonverbal communication. Our work leverages the advances in affect sensing and perception to (1) develop technologies that are sensitive to people's affective-cognitive states; (2) advance autism research and (3) create new technologies that enhance the social-emotional intelligence of people diagnosed with autism, as well as those who are not. Several other projects are also underway, including autism and emotion regulation, sensor and toy technologies for monitoring children.

\n* Co-taught MAS.962: Autism Theory and Technology course during Spring 2006 with Rosalind Picard, Cynthia Breazeal and Sherry Turkle. \n* As an Adjunct Faculty member for Fall 2005, I taught Introduction to Computer Science using C++ at the [[Computer Science Department|http:\\www.cs.aucegypt.edu/index.jsp]] at the [[American University in Cairo (AUC)|http:\\www.aucegypt.edu]], where I've also worked as a Teaching Assistant between 1995 and 2001. At the Computer Laboratory in Cambridge I supervised several courses, graduation projects and internships. At the [[Academic Computing Services|http:\\www.aucegypt.edu/acs]] at AUC, I was responsible for training faculty, staff and students. I introduced and designed the content of two news tracks of courses and delivered the first online course at AUC. I have also collaborated with faculty members on integrating technology in their curricula.

\n!Book Chapters \n# Rana el Kaliouby and Peter Robinson. ~Real-Time Vision for HCI, chapter ~Real-time Inference of Complex Mental States from Facial Expressions and Head Gestures, pages 181200. ~Spring-Verlag, 2005. \n# Rana el Kaliouby and Peter Robinson. Designing a More Inclusive World, chapter The Emotional Hearing Aid: An Assistive Tool for Children with Asperger Syndrome, pages 163172. London: ~Springer-Verlag, 2004. \n\n \n!Journal Articles \n# Rana el Kaliouby and Peter Robinson. Prosthetic versus Therapeutic Assistive Technologies: The Case of Autism. Assistive Technology. Under review. \n# Rana el Kaliouby and Peter Robinson. The Emotional Hearing Aid: An Assistive Tool for Children with Asperger Syndrome. Universal Access in the Information Society 4(2), 2005. \n\n \n!Conference Proceedings \n# Rana el Kaliouby and Peter Robinson. Generalization of a Computational Model of ~Mind-Reading. In Proceedings of First International Conference on Affective Computing and Intelligent Interfaces, pp 582-589, 2005. \n# Rana el Kaliouby and Peter Robinson. Mind Reading Machines: Automated Inference of Cognitive Mental States from Video. In Proceedings of The IEEE International Conference on Systems, Man and Cybernetics, 2004. \n# Rana el Kaliouby and Peter Robinson. ~Real-Time Inference of Complex Mental States from Facial Expressions and Head Gestures. In the IEEE International Workshop on Real Time Computer Vision for Human Computer Interaction at el Kaliouby, CVPR, 2004. \n# Tal Sobol Shikler, Rana el Kaliouby and Peter Robinson. Design Challenges in Multi-modal Inference Systems for ~Human-Computer Interaction. In Proceedings of International Workshop on Universal Access and Assistive Technology, 2004. \n# Rana el Kaliouby and Peter Robinson. FAIM: Integrating Automated Facial Affect Analysis in Instant Messaging. In Proceedings of ACM International Conference on Intelligent User Interfaces (IUI), pages 244-246, 2004. \n# Rana el Kaliouby and Peter Robinson. ~Real-Time Inference of Complex Mental States from Facial Expressions and Head Gestures. In IEEE Workshop on ~Real-Time Vision for ~Human-Computer Interaction at the CVPR Conference, 2004. Won Best Paper Award by the Cambridge Computer Lab Ring. \n# Rana el Kaliouby and Peter Robinson. ~Real-Time Head Gesture Recognition in Affective Interfaces. In Proceedings of the 9th IFIP International Conference on ~Human-Computer Interaction (INTERACT), pages 950953, 2003. \n# Rana el Kaliouby, Peter Robinson and Simeon Keates. Temporal Context and the Recognition of Emotion from Facial Expression. In Proceedings of the 10th International Conference on ~Human-Computer Interaction (HCII): ~Human-Computer Interaction, Theory and Practice, volume 2, pages 631-635. Lawrence Erlbaum Associates, 2003. \n# Rana el Kaliouby and Peter Robinson. The Emotional Hearing Aid: An Assistive Tool for Autism. In Proceedings of the 10th International Conference on ~Human-Computer Interaction (HCII): Universal Access in HCI, volume 4, pages 68-72. Lawrence Erlbaum Associates, 2003. \n# Philipp Michel and Rana el Kaliouby. Facial Expression Recognition using Support Vector Machines. In Poster Proceedings of HCI International Conference, 2003. \n# Philipp Michel and Rana el Kaliouby. Emotion Recognition using Support Vector Machines. In Proceedings of International Conference on Multimodal Interfaces, 2003. \n# Amr Goneid and Rana el Kaliouby. Facial Feature Analysis of Spontaneous Facial Expression. In Proceedings of the 10th International AI Applications Conference, 2002. \n# Amr Goneid and Rana el Kaliouby. Enhanced Facial Feature Tracking of Spontaneous and Continuous Tracking. In Proceedings of HCI International Conference, 2002. \n\n \n!Dissertations \n# Rana el Kaliouby. Mind-reading Machines: the automated inference of complex mental states from video. Ph.D. Dissertation, Computer Laboratory, University of Cambridge. 2005. \n# Rana el Kaliouby. Enhanced Facial Feature Tracking of Spontaneous Facial Expression. M.Sc. Dissertation, Computer Science Department, American University in Cairo. 2000.

\n* IIT Techfast, Bombay, Jan 2007 \n* Royal Society Summer Science Exhibition, London, July 2006 \n* Royal Society Science Exhibition, Glasgow, September 2006 \n* IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) in Washington DC, July 2004 \n* The Royal Institution of Great Britain, Feb. 2004 \n* Kettle's Yard, Cambridge UK Oct 19th - Nov 3rd 2002

kaliouby AT media.mit.edu

\n\n[[MIT|http://www.mit.edu/]] [[Media Lab|http://www.media.mit.edu/]]

[[Biography]] [[Research Interests]] [[Research Projects]] [[Teaching]] [[Contact]]

[img[Rana el Kaliouby| images/RanaelKaliouby.jpg]] [[Biography]] [[Research Interests]] [[Research Projects]] [[Publications]] [[Exhibitions]] [[Teaching]] [[Contact]]

ESP: Social Emotional Intelligence at the MIT Media Lab