The Social Intelligence and Multi-Sensing group is part of the Computer Science department of the University of Geneva and the INIT institute (Data science and computational intelligence center) from HEPIA. This collaboration allows to facilitate the transfert of fundamental research to the market. We are also members of the Swiss Center for Affective Sciences.

Research interests

Multi-Sensing

We sense human by combining several sources of information (Brain and physiological signals, facial expressions, eye-tracking…)

Artificial intelligence and statistics

We apply machine learning, deep learning and hypothesis testing

Social and emotional

We interpret signals to asses people’s emotional states and social behaviors (but not only !)

In the wild

We aim at measuring people in their ecological environment

Human-computer interaction

We enhance interaction

Fun

We love games, entertainment and want to promote fun

Projects

AI-powered wound care monitoring and assessment

In this project, we propose AI-based and serious-game based solutions to provide guidance and training to HCPs to document precisely the characteristics, treatment and evolution of wounds.

Emotions for game streaming

The broadcasting of original media through online platforms like YouTube or Twitch, referred to as “streaming”, is today more popular than traditional TV.

Impressions

In any encounter the first moments are critical and the impressions that we form of others matter.

Emotional and aesthetic highlights detection in movies

Affective computing is now an important research area of computer science with existing ties with the humanities as is demonstrated by the activities in text sentiment analysis and affective tagging of movies.

EATMINT

The project “Affective computing and emotion awareness in computer-mediated interaction” aims at developing emotion awareness tools (EAT) to improve the collaborative processes and outcomes of people working together through computers.

Resources

*
AMuCS database
The AMuCS database contains multi-modal and multi-user recordings of physiological signals and behaviors in an e-sport setting where participants played a 1v1 or 2v2 first person shooter game.
E-Sport LSL Data Platform
This is a collection of LSL modules which we developed/adapted and used for the AMuCS database.
EATMINT database
The EATMINT database contains multi-modal and multi-user recordings of affect and social behaviors in a collaborative setting.
TEAPhysio
TEAPhysio, the Toolbox for Emotion Analysis using Physiological signals, is a Matlab (fully Octave compliant) toolbox that aims to reduce code dispersing and duplication across your research projects.
GamEMO
GamEMO is an automatic emotion assessment installation used for game’s dynamic difficulty adjustment.

Meet the Team

Researchers

Avatar

Dr. Guillaume Chanel

Head of the SIMS group

Avatar

Dr. Rania Niri

Post-Doctoral researcher

Avatar

Kaushal Sharma

Doctoral student

Avatar

Yann Frachi

Doctoral student @QMUL

Former members

Avatar

Dr. Marios Fanourakis

Post-Doctoral researcher

Contact