Fusion of Deep Features from 2D-DOST of fNIRS Signals for Subject-Independent Classification of Motor Execution Tasks

Functional near-infrared spectroscopy (fNIRS) is a low-cost and noninvasive method to measure the hemodynamic responses of cortical brain activities and has received great attention in brain-computer interface (BCI) applications. In this paper, we present a method based on deep learning and the time...

Full description

Saved in:
Bibliographic Details
Published in:International journal of intelligent systems 2023-12, Vol.2023, p.1-17
Main Authors: Khani, Pouya, Solouk, Vahid, Kalbkhani, Hashem, Ahmadi, Farid
Format: Article
Language:English
Subjects:
Accuracy
Artificial neural networks
Brain research
Classification
Data augmentation
Datasets
Decomposition
Deep learning
Discriminant analysis
Electroencephalography
Fourier transforms
Generative adversarial networks
Hemodynamic responses
Hemodynamics
Hemoglobin
Human-computer interface
Infrared spectra
Machine learning
Medical imaging
Near infrared radiation
Neural networks
Neurosciences
Signal classification
Signal processing
Support vector machines
Wavelet transforms
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Functional near-infrared spectroscopy (fNIRS) is a low-cost and noninvasive method to measure the hemodynamic responses of cortical brain activities and has received great attention in brain-computer interface (BCI) applications. In this paper, we present a method based on deep learning and the time-frequency map (TFM) of fNIRS signals to classify the three motor execution tasks including right-hand tapping, left-hand tapping, and foot tapping. To simultaneously obtain the TFM and consider the correlation among channels, we propose to utilize the two-dimensional discrete orthonormal Stockwell transform (2D-DOST). The TFMs for oxygenated hemoglobin (HbO), reduced hemoglobin (HbR), and two linear combinations of them are obtained and then we propose three fusion schemes for combining their deep information extracted by the convolutional neural network (CNN). Two CNNs, LeNet and MobileNet, are considered and their structures are modified to maximize the accuracy. Due to the lack of enough signals for training CNNs, data augmentation based on the Wasserstein generative adversarial network (WGAN) is performed. Several simulations are performed to assess the performance of the proposed method in three-class and binary scenarios. The results present the efficiency of the proposed method in different scenarios. Also, the proposed method outperforms the recently introduced methods.
ISSN:0884-8173
1098-111X
DOI:10.1155/2023/3178284