Emotion Technology, Wearables, and Surprises

Abstract – More than fifteen years ago I set out to build the first computational systems to recognize and respond intelligently to emotion. My team and I created and tested the world’s first wearable sensors for processing emotion. We developed pattern analysis, machine learning, and signal processing algorithms for working with speech, physiology, facial expressions, and more. Today this work has spawned two start-up companies, collected more than seven billion facial emotion points from viewers who opted-in online to turn on their cameras, and is leading to a new sensor that can issue potentially life-saving alerts for people who have seizures. In this talk I will tell stories that highlight several surprising findings. These findings include discerning frustrated smiles from happy ones, discovering that regular cameras could compute heart rate and respiration, finding electrical signals on the wrist that respond to deep brain activity, discovering connections to memory consolidation during sleep, and learning of surprising implications of wearable sensing for autism, anxiety, epilepsy, and more.

Biography – Professor Rosalind W. Picard, Sc.D. is founder and director of the Affective Computing Research Group at the Massachusetts Institute of Technology (MIT) Media Lab and co-director of the Things That Think Consortium, the largest industrial sponsorship organization at the lab. She has co-founded two businesses, Empatica, Inc. creating wearable sensors and analytics to improve health, and Affectiva, Inc. delivering technology to help measure and communicate emotion.

Picard holds a bachelor’s degree in electrical engineering with highest honors from the Georgia Institute of Technology, and master’s and doctorate degrees, both in electrical engineering and computer science, from MIT. She started her career as a member of the technical staff at AT&T Bell Laboratories designing VLSI chips for digital signal processing and developing new algorithms for image compression. In 1991 she joined the MIT Media Lab faculty. She became internationally known for constructing mathematical texture models for content-based retrieval of images and for pioneering methods of automated search and annotation in digital video including the Photobook system. The year before she was up for tenure she took a risk and published the book Affective Computing, which became instrumental in starting a new field by that name. Today that field has its own journal, international conference, and professional society. Picard was also a founding member of the IEEE Technical Committee on Wearable Information Systems in 1998, helping launch the field of wearable computing.

Picard has authored or co-authored over two hundred scientific articles and chapters spanning computer vision, pattern recognition, machine learning, human-computer interaction, wearable sensors and affective computing. She is a recipient of several best paper prizes, including work on machine learning with multiple models (with Minka, 1998), a best theory paper prize for affect in human learning (with Kort and Reilly, 2001) a best Face and Gesture paper prize for work with facial expressions (with McDuff, Kaliouby and Demirdjian, 2013) and a best UBICOMP paper for an automated conversation coach (with Hoque et al, 2013). Her paper (with Healey, 2005) measuring Boston driver stress won best paper of the decade 2000-2009 for IEEE Intelligent Transportation Systems.

Picard is an active inventor with multiple patents, including wearable and non-contact sensors, algorithms, and systems for sensing, recognizing, and responding respectfully to human affective information. Her inventions have applications in autism, epilepsy, sleep, stress, autonomic nervous system disorders, human and machine learning, health behavior change, market research, customer service, and human-computer interaction. In 2005 she was named a Fellow of the IEEE for contributions to image and video analysis and affective computing. Picard has been honored with dozens of distinguished and named lectureships and other international awards. She is a popular speaker and has given over 100 keynote talks.

Picard has served on numerous international and national science and engineering program committees, editorial boards, and review panels, including the Advisory Committee for the National Science Foundation’s (NSF’s) division of Computers in Science and Engineering (CISE), the Advisory Board for the Georgia Tech College of Computing, and the Editorial Board of User Modeling and User-Adapted Interaction: The Journal of Personalization Research.

Picard interacts regularly with industry and has consulted for many companies including Apple, AT&T, BT, HP, i.Robot, Merck, Motorola, and Samsung. Her group’s achievements have been featured in forums for the general public such as The New York Times, The London Independent, National Public Radio, Scientific American Frontiers, ABC’s Nightline and World News Tonight, Time, Vogue, Wired, Voice of America Radio, New Scientist, and BBC programs such as “hard Talk” and BBC Horizon with Michael Mosley. Picard lives in Newton, Massachusetts with her amazing husband and three energetic sons.