Measuring cognitive state from physiological signals in user interface research
Loading...
URL
Journal Title
Journal ISSN
Volume Title
Perustieteiden korkeakoulu |
Master's thesis
Unless otherwise stated, all rights belong to the author. You may download, display and print this publication for Your own personal use. Commercial use is prohibited.
Authors
Date
2018-02-12
Department
Major/Subject
Human Neuroscience and Technology
Mcode
SCI3601
Degree programme
Master’s Programme in Life Science Technologies
Language
en
Pages
46+4
Series
Abstract
The purpose of this Thesis is to investigate how modern technology can be used for evaluating human cognitive state in the context of human-computer interaction, namely user interface (UI) research. In this work two types of physiological data were collected to measure cognitive load during a task which requires some degree of human-computer interaction. A near-infrared spectroscopy device and eye tacker were used to evaluate cognitive load level during the task and provide an insight into how these data might be used in an adaptive real-time system. A mental calculation task was used as the cognitively demanding learning task, which challenges working memory. Additional difficulty was added using the task presentation: mathematical expressions were either static or moving from the top to the bottom of the screen. Results indicate that tasks of different mental complexity elicit different cognitive responses. With careful interpretation this information can be used in designing environments, suitable for the user. This work have shown that in designing the systems which use physiological measurements, it is crucial to know the possible sources of the noise. For example, in pupillary measurements it is important to control for luminance and physiological changes which affect pupil size along with cognitive load, or to develop methods which discriminate between task-evoked pupil response from other responses. For any real-time system it is necessary to develop the fast and efficient algorithms which produce reliable results with minimal training of the models.Description
Supervisor
Oulasvirta, AnttiThesis advisor
Nissilä, IlkkaKeywords
cognitive load, hemodynamic brain imaging, task-evoked pupillary response, user interfaces