Brain-computer interface to improve interaction with technology through emotion recognition
May 27, 2015
In the EMOIO project launched at the beginning of the year, Fraunhofer IAO is working with partners from research and industry to study how they might record and classify the emotional experiences that take place when a human being interacts with a technical product. The goal is to develop emotion-sensitive assistance systems that adapt to the mood and personal needs of users.
Assistance systems have great potential to help users in a wide variety of situations. When they access external user information to do so, however, things often become problematical. With the objective of removing these barriers to usage, Fraunhofer IAO is working with research and industrial partners in the EMOIO project to develop a neuroadaptive system that will measure the users’ brain activity to determine whether they are pleased or displeased with a system-initiated assistive action.
From neuroscientific basic research to mobile application
As a first step, different neuroscientific methods are being investigated regarding their potential for real-time measurement in natural interaction scenarios. Subsequently, algorithms for real-time emotion recognition and classification will be developed. On this basis, a brain-computer interface will be created that is capable of recording and evaluating users’ subjective feelings (approval/rejection) as to the appropriateness of system-initiated behaviors and feed this information back to an adaptive assistance system. In this way, the brain-computer interface enables assistance systems to adapt their behavior precisely to users’ individual preferences and needs. Using neurophysiological feedback for the developed system does not require direct, active feedback, hence the users are not interrupted during the interaction process. Once developed, the system will be tested in three different fields of application, whereby it will be integrated into an adaptive web interface, a driver assistance system, and a system for human-robot cooperation.
NeuroLab measures brain activity during human-technology interaction
Launched in January, the EMOIO project will run until the end of 2017. The project scientists are using Fraunhofer IAO’s new NeuroLab to evaluate different neuroscientific methods (electroencephalography and functional near infrared spectroscopy) to determine their potential for measuring emotions. The work in the NeuroLab will be mainly focused on the question of how far a combination of the two methods can improve the accuracy of the classification algorithms. Moreover, the scientists will deal with the challenge to realize emotion recognition in real time and during the interaction process.