Comparison of Brainwave Sensors and Mental State Classifiers

Comparison of Brainwave Sensors and Mental State Classifiers

Hironori Hiraishi
Copyright: © 2022 |Pages: 13
DOI: 10.4018/IJAIML.310933
Article PDF Download
Open access articles are freely available for download

Abstract

Brain-computer interfaces (BCIs) have been attracting attention as a research topic. BCI has various applications, such as at home and in the medical sector. BCI is an interconnection between the human brain and a computer, which is a communication pathway between external peripheral devices. Brainwave sensors play a significant role when applying BCIs in practice. In this study, data from such sensors are analyzed to classify the mental states of users. This study used two different brainwave sensors: Neurosky MindWave Mobile and Emotiv EPOC+. Several types of machine-learning techniques (support vector machine, random forest, and long short-term memory) have been applied to classify brainwave data. This study aimed to compare the accuracy of the two sensors, analyze data, and identify the most accurate machine-learning method. Finally, a BCI toy with MaBeee, which is a battery-type internet-of-things device, was designed as a BCI application that reflected the analysis results.
Article Preview
Top

2. Brainwave Sensors

Figure 1 shows the two brainwave sensors adopted in this study, namely MindWave Mobile from NeuroSky Inc. (on the left) and EPOC+ from Emotiv Inc. (on the right), both of which are EEG sensors.

Figure 1.

MindWave Mobile (left) and EPOC+ (right)

IJAIML.310933.f01

EEG scans are performed by placing small metal disks—known as EEG electrodes—on the scalp. These electrodes identify and record electrical activity in the brain. The obtained EEG signals are amplified, digitized, and then sent to a computer or mobile device for storage and data processing.

Complete Article List

Search this Journal:
Reset
Volume 13: 1 Issue (2024)
Volume 12: 2 Issues (2022)
Volume 11: 2 Issues (2021)
Volume 10: 2 Issues (2020)
Volume 9: 2 Issues (2019)
View Complete Journal Contents Listing