Research — MIT Media Lab

Affective Computing

Advancing human wellbeing by developing new ways to communicate, understand, and respond to emotion

Fluid Interfaces

Designing Systems for Cognitive Support

Archived

UncNet: Modeling uncertainty in deep learning for inherently subjective tasks

Automatic emotion recognition has become a well-established machine learning task in recent years. The sensitive and subjective nature of...

Archived

PAL: Project on Affinities + Language

The Project on Affinities and Language (PAL) is designed to help us understand what happens in a child’s brain when they engage with thei...

Archived

Learning via Social Awareness: Improving sketch representations with facial feedback

In the quest towards general artificial intelligence (AI), researchers have explored developing loss functions that act as intrinsic moti...

Archived

Improving Wellbeing for Office Workers

Excessive stress can decrease office workers' productivity and negatively impact overall health. This project aims to predict office work...

Archived

BrainBeat: Breath-based music therapy

Can we sonfiy calming breathing and passively influence a state of calm?Deep breathing has been scientifically proven to affect the heart...

Archived

Personalized Machine Learning for Future Health

The view on Alzheimer’s Disease (AD) diagnosis has shifted towards a more dynamic process in which clinical and pathological markers evo...

Archived

WorldBeat: Hearing the world differently

Can we modulate the way we hear the world around us to make it more calming or to induce focus? While technology is usually associated wi...

Archived

Personalized Animated Movies

Storytelling is a fundamental way in which human beings understand the world. Imagine watching a movie telling the story of your life, ho...

Archived

Machine Learning for Pain Measurement

Pain is a subjective experience commonly measured through patients' self reports. Unfortunately, self-report measures only work when...

Archived

Behavioral Indications of Depression Severity

In collaboration with Massachusetts General Hospital, we are conducting a clinical trial exploring objective methods for assessing depres...

Archived

Personalized Machine Learning for Autism Therapy

EngageME: Personalized machine learning and humanoid robots for measuring affect and engagement of children with autismEngageME is a proj...

Archived

Modulating peripheral and cortical arousal using a musical motor response task

We are conducting EEG studies to identify the musical features and musical interaction patterns that universally impact measures of arous...

Archived

SPRING: A Smart Platform for Research, Intervention, and Neurodevelopmental Growth

SPRING is a custom-built hardware and software platform for children with neuro-differences. The system automates data acquisition, optim...

Archived

Predicting students' wellbeing from physiology, phone, mobility, and behavioral data

The goal of this project is to apply machine learning methods to model the wellbeing of MIT undergraduate students. Extensive data is obt...

Archived

An EEG and motion-capture based expressive music interface for affective neurofeedback

This project examines how the expression granted by new musical interfaces can be harnessed to create positive changes in health and well...

Archived

MIT Chalk Radio: AI Literacy for All with Prof. Cynthia Breazeal

Social robotics pioneer Prof. Cynthia Breazeal discusses artificial intelligence in our lives, digital citizenship, and AI education for all

Post Research

Picard, Choudhoury, and Schiele Named 2021 ACM Fellows

Fellowship program honors ACM members whose specific accomplishments drive innovation and make broader advances possible.

Deploying machine learning to improve mental health

MIT scientist Rosalind Picard collaborates with clinicians to develop tools for mental health care delivery.

Opera of the Future

Extending expression, learning, and health through innovations in musical composition, performance, and participation

Personalized Multitask Learning for Predicting Tomorrow's Mood, Stress, and Health

Taylor, S.*, Jaques, N.*, Nosakhare, E., Sano, A. and Picard, R., "Personalized Multitask Learning for Predicting Tomorrow's Mood, Stress, and Health," in IEEE Transactions on Affective Computing, vol. PP, no. 99, pp. 1-1. doi: 10.1109/TAFFC.2017.2784832 *Both authors contributed equally. WINNER: BEST OF COLLECTION

Personal Robots

Building intelligent personified technologies that collaborate with people to help them learn, thrive, and flourish.

Project Us

“Us” aims to help people develop their sense of empathy. It uses machine learning to analyze interlocutors’ signals (e.g., tone of voice,...

Emotion Navigation

Before automobiles were invented and widely adopted, animals like horses were the most common mode of transportation. While this change b...

Archived

QuantifyMe

Unlike traditional randomized controlled trials that generalize relationships in large groups of people, single-case experiments seek to ...

Archived

ELSA: Empathy learning, socially-aware agents

What is ELSA?ELSA is an AI-powered chatbot that acts as an empathetic companion, encouraging users to talk about their day through a form...

Archived

When AI Recognizes Emotion, with Rosalind Picard

John Ellis talks to Affective Computing head Rosalind Picard about making AI and computers more emotionally intelligent.

Privacy-Preserving Depressive Symptoms Estimation

The goal of this project is to develop techniques to remove identifying information from wearable and phone data to protect patients’ pri...

aSpire: Clippable, Mobile Pneumatic-Haptic Device for Breathing Rate Regulation via Personalizable Tactile Feedback

We introduce–aSpire–a clippable, mobile pneumatic-haptic device designed to help users regulate their breathing rate via subtle tactile f...

iNonymize: Empathetic Anonymity in Tele-Mental Health Using AI Generated Avatars

This project was selected to represent MIT at the Microsoft Design Expo 2020 on ‘Healthier Futures.’ iNonymizeA tele-mental health p...

Essence Wearables: Biometric Olfactory Interfaces for Day and Night

Human-computer interaction (HCI) has traditionally focused on designing and investigating interfaces that provide explicit visual, audito...

dementAI

dementAI is an open-source platform for modeling risk stratification of Alzheimer's dementia using spontaneous speech through ...

Leveraging artificial intelligence for the assessment of severity of depressive symptoms

This project is supported by the Abdul Latif Jameel Clinic for Machine Learning in Health (J-Clinic), the National Institutes of Hea...

Multimodal Inductive Transfer Learning for Detection of Alzheimer's Dementia and its Severity

@article{sarawgi2020multimodal, title={Multimodal Inductive Transfer Learning for Detection of Alzheimer's Dementia and its Severity}, author={Sarawgi, Utkarsh and Zulfikar, Wazeer and Soliman, Nouran and Maes, Pattie}, journal={arXiv preprint arXiv:2009.00700}, year={2020} }

Uncertainty-Aware Multi-Modal Ensembling for Severity Prediction of Alzheimer's Dementia

@misc{sarawgi2020uncertaintyaware, title={Uncertainty-Aware Multi-Modal Ensembling for Severity Prediction of Alzheimer's Dementia}, author={Utkarsh Sarawgi and Wazeer Zulfikar and Rishab Khincha and Pattie Maes}, year={2020}, eprint={2010.01440}, archivePrefix={arXiv}, primaryClass={cs.LG} }

Embracing neurodiversity to better understand autism

Using personalized, naturalistic experiments, the Gabrieli lab is pioneering new approaches to neurodevelopmental differences.

Affective Robotic Ring

An affective robotic ring which allows users to interact with multiple robots using finger gestures.- Runs on Robotic Operating System (R...

Digital Life

Archived

BioEssence

A wearable olfactory display that monitors cardio-respiratory information with the aspiration to support mental wellbeing.BioEssence is a...

Characterizing Sources of Uncertainty to Proxy Calibration and Disambiguate Annotator and Data Bias

Ghandeharioun, A., Eoff, B., Jou, B., & Picard, R. W. (2019). Characterizing Sources of Uncertainty to Proxy Calibration and Disambiguate Annotator and Data Bias. arXiv preprint arXiv:1909.09285.

AMAI: Adaptive Music for Affect Improvement

Su, D., Picard, R., Liu, Y. "AMAI: Adaptive Music for Affect Improvement." Proceedings of the 44th International Computer Music Conference (ICMC), Daegu, Korea, August 2018.

Archived

Predicting Trust Between People

Machine learning model outperforms human judgementOur computational trust model is capable of predicting—above human accuracy—the degree ...

Archived

Intentional Inference of Emotions

Emotion recognition modeled as a goal-directed process!

Archived

Human-Robot Trust

Unconventional mixing of research fields introduces a new method to study human behavior using social robots.

Archived

Artificial listener with social intelligence

A social robot modifies its behavior to change what you think about it!

Archived

Advancing Wellbeing

Adaptive Music for Affect Improvement

Adaptive Music for Affect Improvement (AMAI) is a music generation and playback system with the goal of steering the listener toward a st...

Rosalind Picard: Affective Computing, Emotion, Privacy, and Health | Artificial Intelligence Podcast

In an interview with MIT research scientist Lex Fridman, Rosalind Picard discusses affective computing, privacy, diversity in tech, and more

Post Research

Affective Computing researchers win Best Paper Award at IEEE BHI 2019

"Improving Students' Daily Life Stress Forecasting using LSTM Neural Networks," by Terumi Umematsu, Akane Sano, Sara Taylor, an...

Improving wellbeing prediction performance using temporal machine learning models

This project aims to improve the prediction accuracy of wellbeing (stress, mood, and health levels) using temporal machine learning model...

SNAPSHOT Study

The SNAPSHOT study seeks to measure Sleep, Networks, Affect, Performance, Stress, and Health using Objective Techniques. It is an NIH-fun...

Computing Careers: Advice from Rosalind Picard on succeeding in the fast-growing field of "affective computing"

Affective Computing head Rosalind Picard talks to IEEE Computer Society for their series on careers in computing.

Archived

MACH: My Automated Conversation coacH

MACH, My Automated Conversation coacH, is a system for people to practice social interactions in face-to-face scenarios. MACH consists of...

Archived

BrightBeat: Effortlessly influencing breathing for cultivating calmness and focus

The relationship between breathing and self-reported stress is bidirectional. Respiration pattern is an indicator of stress, but it can a...

Emotion AI, explained

Senior leaders should consider how emotion AI could change their industries and play a critical role in their firms.

Six MIT researchers elected to the National Academy of Engineering for 2019

Six MIT researchers are among the 86 new members and 18 foreign associates elected to the National Academy of Engineering.

Personalized Machine Learning for Robot Perception of Affect and Engagement in Autism Therapy

Rudovic, O., Lee, J., Dai, M., Schuller, B. , Picard, R. W., " Personalized machine learning for robot perception of affect and engagement in autism therapy," Science Robotics, June 2018.

Emotional Beasts: Visually Expressing Emotions through Avatars in VR

Bernal, Guillermo, and Pattie Maes. "Emotional Beasts: Visually Expressing Emotions through Avatars in VR." Proceedings of the 2017 CHI Conference Extended Abstracts on Human Factors in Computing Systems. ACM, 2017.

Image Sentiment Analysis

In this project we explore how to recognize and localize affect in images.

Archived

Masque

When the body senses itself internally and localizes its actions, it provides the basis for a material sense of self-existence. At ...

Archived

Tech community wrestles over working with government

Hiawatha Bray reports on the unrest bubbling up in the tech industry.

Personalized “deep learning” equips robots for autism therapy

Machine learning network offers personalized estimates of children’s behavior.

Wearable ESM: Comparing the Wearable Experience Sampling Method across Wearable Devices

Hernandez, J., McDuff, D., Infante, C., Maes, P., Quigley, K., and Picard, R. W. "Wearable ESM: Comparing the Wearable Experience Sampling Method across Wearable Devices," In Proceedings of Mobile Human Computer Interaction, Florence, Italy, September 2016.

Can AI Learn to Understand Emotions?

Rana el Kaliouby is now helping AI understand human emotion. Rosalind Picard pioneered the field of affective computing.

Learning via social awareness: improving sketch representations with facial feedback

Jaques, N., Engel, J., Ha, D., Bertsch, F., Picard, R., and Eck, D. "Learning via social awareness: improving sketch representations with facial feedback." International Conference on Learning Representations (ICLR) Workshop, Vancouver, Canada, April 2018.