Using Technology to Recognise Emotions in Autistic People

This graduation report approaches the application of emotion recognition technology for autistic people from a different angle. In this research the technology focussed on the situation where the emotions from the autistic person are measured instead of the emotions from a typically developed person. Autistic people express their emotions differently, which makes it hard for others to interpret the emotions correctly. This is especially troublesome for autistic children, whose parents have difficulty reading their emotions. The different expression of emotions by autistic people influences affective signals, which makes technology based on facial recognition, body language or voice intonation unreliable. Therefore physiological signals should be used as input for the emotion recognition. Sensors for these physiological signals can be placed in a variety of products, but these products should adhere to specific design guidelines based on user requirements of the target group. These design guidelines are necessary because the target group is sensitive to stimuli and has difficulty adapting. User requirements were investigated using an online survey and semi-structured interviews. A smartwatch, a patch and an infrared camera were evaluated as possible designs. The evaluation of these designs led to the guidelines. The smartwartch was the preferred design, followed by the patch. An infrared camera is not a suitable design. The guidelines can be used when designing a wearable that measures physiological signals of autistic children.