Scientists at the MIT Media Lab are studying how computing influences emotions or other affective phenomena. The field of Affective Computing is defined as computing that relates to or arises from or deliberately influences emotion or other affective phenomena.
The field combines engineering, computer science with psychology, cognitive science, neuroscience, sociology, education, psychophysiology, value-centered design, ethics, and more. The scientists aim to restore a proper balance between emotion and cognition in designing technologies needed to address human needs.
The MIT research has helped to find new ways for people to communicate affective-states, especially through creation of novel wearable sensors and new machine learning algorithms that jointly analyze multimodal channels of information.
Some of the MIT ongoing projects include research on:
- Developing comfortable and wearable biosensors able to measure stress in real-life environments
- Developing Cardiocam, a low-cost, non-contact technology to measure physiological signals using a basic digital imaging device
- Harnessing the power of large, distributed online communities to solve artificial intelligence problems that might otherwise be intractable
- Designing new software to work with individuals diagnosed with Autism Spectrum Disorder with intense focused interests that will embed them seamlessly into flash-based computer programs
- Developing a computational model that enables real-time analysis, tagging, and interference of cognitive-affective mental states from facial videos
- Developing social signals puzzle games for children with autism to help them recognize social-emotional cues from information surrounding the eyes
- Introducing a digital stethoscope device that is easy to use, low cost, and open source that can be connected to the internet for streaming the physiological data to remote clinicians
- Developing comfortable, safe, attractive physiological sensors that infants can wear around the clock to wirelessly communicate their internal physiological state changes
- Developing computers that will be able to make rapid and accurate inferences from multiple modes of data to determine a person’s affective state using multiple sensors
- Developing a mobile phone-based platform to assist people with chronic diseases, panic anxiety disorders, or addictions using wearable wireless biosensors. Mobile phones will use pattern analysis and machine learning algorithms to detect specific physiological states and use automatic interventions in the form of text/images
