Affective Sensing

Cognitive Sensor Technology for Improved Healtcare and Quality of Life

One of the core subjects in the area of “Smart Sensing and Electronics“ is the machine recognition, interpretation, and processing of human emotions and affects. For many years we have been working on developing networked sensor solutions, emotion-adaptive technologies, and perception-based user interfaces. Our contribution to human-machine communication in this area is significant. 

Call for Machine Learning Challenge

UbiTtention Cognitive Load Machine Learning Challenge

On behalf of the organizing team we are happy to invite you to the UbiTtention Cognitive Load Machine Learning Challenge!

To prevent undesirable effects of attention grabbing at times when a user is occupied with a difficult task, ubiquitous computing devices should be aware of the user’s cognitive load.

To advance the field of cognitive load inference in ubiquitous  computing, we organize a public machine learning challenge in which competitors have to infer cognitive load from sensor data. The goal of this machine learning challenge is to recognize 2 levels of cognitive load from the sensor data of a wearable wrist-band (Microsoft Band 2). The participants will have to develop a machine-learning pipeline that will process the sensor data, create models and output the recognized cognitive load.

The best three teams will also receive prizes!

Results will be presented at UbiTtention 2020, a workshop to be held in conjunction with UbiComp 2020 Cancún, México in September 12-13. (Note: of course, conference organizers are aware of the ongoing developments with COVID-19 and will announce any necessary changes on the respective websites!)

We would be happy if you would participate!

Emotion-sensitive robots as physical interaction partners and development tools

Some things that most people do entirely at the unconscious level pose enormous challenges for autistic children: correctly recognizing and interpreting the emotions of the person they are interacting with and responding accordingly.

The joint ERIK project therefore aims to develop a robotic platform that addresses new interaction strategies in treatments for children with impaired socioemotional functioning, such as children with autism.  

Hot Topics


KI2020 – 43rd German Conference on Artificial Intelligence

September 21-25, 2020, Bamberg, Germany


Vortrag Dr.-Ing. Jens Garbas

AI gets emotional – Technology learns to feel

Dr. Jens-Uwe Garbas (Fraunhofer IIS) talks at the annual international science and technology conference FUTURAS IN RES about AI and empathy & Human-Machine-Interaction.



TraMeExCo (Transparent Medical Expert Companion) is a project funded by Germany’s Federal Ministry of Education and Research (BMBF). Its purpose is to investigate and develop suitable new methods to enable robust and explainable machine learning in complementary applications (digital pathology, pain analysis, cardiology) in the field of medical engineering.