Elsanussi Mneina, one of our Research Assistants, is presently investigating the possibilities of interpreting electroencephalographic (EEG) data. The starting point of this project is using the DEAP dataset collected by the School of Electronic Engineering and Computer Science, at Queen Mary University of London. DEAP is a Database for Emotion Analysis using Physiological Signals, a dataset that was collected using EEG where participants watched music videos and rated their feelings about each one.

This project presents its own challenges, not only is EEG data notoriously difficult to interpret, but there are more than 20 different signals that vary over time in many different ways.

By using machine learning algorithms on the EEG data, we intend to be able to predict feelings from the EEG data. In order to do so, much work must be done wading through the data and deciding which parts of the data are relevant to predicting feelings. Different ways of transforming the data, and summarizing the data must be tried before a machine learning algorithm can be used to make predictions.

The knowledge gained by building a successful algorithm could be used to more accurately gage a person’s feelings: using a computer; watching a movie; or reacting to commercials. This may have practical applications in consumer focus groups or even in the field of psychiatry.

To find out more about DEAP, their dataset can be found at the following link: http://www.eecs.qmul.ac.uk/mmv/datasets/deap/