Next Article in Journal
Capacitively-Coupled ECG and Respiration for Sleep–Wake Prediction and Risk Detection in Sleep Apnea Patients
Next Article in Special Issue
Effective Connectivity for Decoding Electroencephalographic Motor Imagery Using a Probabilistic Neural Network
Previous Article in Journal
Adaptive Navigation Algorithm with Deep Learning for Autonomous Underwater Vehicle
Previous Article in Special Issue
IndoorCare: Low-Cost Elderly Activity Monitoring System through Image Processing
Article

Comparing Methods of Feature Extraction of Brain Activities for Octave Illusion Classification Using Machine Learning

1
Graduate School of Advanced Science and Technology, Tokyo Denki University, Hiki-gun, Saitama 350-0394, Japan
2
Graduate School of Science and Engineering, Tokyo Denki University, Hiki-gun, Saitama 350-0394, Japan
*
Author to whom correspondence should be addressed.
Academic Editor: Manuel José Cabral dos Santos Reis
Sensors 2021, 21(19), 6407; https://doi.org/10.3390/s21196407
Received: 31 August 2021 / Revised: 21 September 2021 / Accepted: 22 September 2021 / Published: 25 September 2021
(This article belongs to the Special Issue Data, Signal and Image Processing and Applications in Sensors II)
The aim of this study was to find an efficient method to determine features that characterize octave illusion data. Specifically, this study compared the efficiency of several automatic feature selection methods for automatic feature extraction of the auditory steady-state responses (ASSR) data in brain activities to distinguish auditory octave illusion and nonillusion groups by the difference in ASSR amplitudes using machine learning. We compared univariate selection, recursive feature elimination, principal component analysis, and feature importance by testifying the results of feature selection methods by using several machine learning algorithms: linear regression, random forest, and support vector machine. The univariate selection with the SVM as the classification method showed the highest accuracy result, 75%, compared to 66.6% without using feature selection. The received results will be used for future work on the explanation of the mechanism behind the octave illusion phenomenon and creating an algorithm for automatic octave illusion classification. View Full-Text
Keywords: feature selection; machine learning; octave illusion; auditory illusion; MEG feature selection; machine learning; octave illusion; auditory illusion; MEG
Show Figures

Figure 1

MDPI and ACS Style

Pilyugina, N.; Tsukahara, A.; Tanaka, K. Comparing Methods of Feature Extraction of Brain Activities for Octave Illusion Classification Using Machine Learning. Sensors 2021, 21, 6407. https://doi.org/10.3390/s21196407

AMA Style

Pilyugina N, Tsukahara A, Tanaka K. Comparing Methods of Feature Extraction of Brain Activities for Octave Illusion Classification Using Machine Learning. Sensors. 2021; 21(19):6407. https://doi.org/10.3390/s21196407

Chicago/Turabian Style

Pilyugina, Nina, Akihiko Tsukahara, and Keita Tanaka. 2021. "Comparing Methods of Feature Extraction of Brain Activities for Octave Illusion Classification Using Machine Learning" Sensors 21, no. 19: 6407. https://doi.org/10.3390/s21196407

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop