System could allow PCs to read emotions in real time

A computer science PhD student at Bangor University is hoping to develop a system that will enable computers to read and interpret emotions and moods in real time.

’I am particularly interested in developing a real-time ’mood sensing’ device. It will combine already existing biometric detection devices into a lightweight portable system that will be able to perceive and indicate a person’s mood, and level of stress and anxiety,’ said researcher Tom Christy.

To do so, Christy plans to collect brain-wave information collected from a single electrode that sits on the forehead as part of a ’headset’, a skin-conductance response (that will detect tiny changes in perspiration as first indicators of stress) and a pulse signal, reflecting the wearer’s heart rate.

This information will then be fed into a so-called classifier ensemble set − a group of programmes that will be independently able to analyse the data and decide which emotion a person is experiencing.

Christy is aiming to pioneer the classification software techniques that will allow players’ emotions to be identified within the gaming environment. It is believed that this could open up new and exciting markets for the gaming industry where players would need to control their feelings in advance within a virtual environment.

There are many other possible applications for the technology − it could be used in marketing to determine customer preferences and brand effectiveness or to monitor anxiety levels of prospective soldiers during military training.

Christy is collaborating with the Bangor University’s Schools of Electronic Engineering and Psychology, and has had talks with Massachusetts Institute of Technology (MIT) in Boston. He is also looking for industrial collaborators and innovators who might be interested in working with him.