Developing measurement set-up for assessing cognitive workload with consumer-based EEG-device
Vikström, Thomas (2022)
Vikström, Thomas
2022
All rights reserved. This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:amk-2022090219806
https://urn.fi/URN:NBN:fi:amk-2022090219806
Tiivistelmä
A research study was conducted to find out if and how it might be possible to assess increased cognitive workload using a consumer-based EEG-device. Earlier research has established that it is possible to assess cognitive workload by using clinical or professional EEG-devices.
To reach the objectives of the study, a computer game was developed in Python using an iterative and incremental software development method. The game increases a user’s cognitive workload or working memory by an adaptation of the well-known n-back psychological test. The developed game was successfully tested in a small experiment, using a consumer-based EEG-device, to be able to validate the functionality and usability of the game, and to collect EEG-data for further analysis. Data was processed, analyzed and visualized with spectrograms and a machine learning tool.
The study resulted in a versatile, configurable, and well-documented open-source n-back game which can be used as such or developed further by other Python-developers. Furthermore, the results from the experiment revealed that there are differences in the collected EEG-data between periods of rest and periods of higher cognitive workload. Identified limitations of the study as well as recommendations for further game improvements and research are included.
As a conclusion, based on the results of this study, it is possible to differentiate data from a consumer-based EEG-device between periods of rest and periods of higher cognitive workload.
To reach the objectives of the study, a computer game was developed in Python using an iterative and incremental software development method. The game increases a user’s cognitive workload or working memory by an adaptation of the well-known n-back psychological test. The developed game was successfully tested in a small experiment, using a consumer-based EEG-device, to be able to validate the functionality and usability of the game, and to collect EEG-data for further analysis. Data was processed, analyzed and visualized with spectrograms and a machine learning tool.
The study resulted in a versatile, configurable, and well-documented open-source n-back game which can be used as such or developed further by other Python-developers. Furthermore, the results from the experiment revealed that there are differences in the collected EEG-data between periods of rest and periods of higher cognitive workload. Identified limitations of the study as well as recommendations for further game improvements and research are included.
As a conclusion, based on the results of this study, it is possible to differentiate data from a consumer-based EEG-device between periods of rest and periods of higher cognitive workload.