Convolutional neural network for high-accuracy functional near-infrared spectroscopy in a brain–computer interface: three-class classification of rest, right-, and left-hand motor execution

Abstract

"Convolutional neural network for high-accuracy functional near-infrared spectroscopy in a braincomputer interface: three-class classification of rest, right-, and left-hand motor execution," Neurophoton. 5(1), 011008 (2017), doi: 10.1117/1.NPh.5.1.011008. Abstract. The aim of this work is to develop an effective brain-computer interface (BCI) method based on functional near-infrared spectroscopy (fNIRS). In order to improve the performance of the BCI system in terms of accuracy, the ability to discriminate features from input signals and proper classification are desired. Previous studies have mainly extracted features from the signal manually, but proper features need to be selected carefully. To avoid performance degradation caused by manual feature selection, we applied convolutional neural networks (CNNs) as the automatic feature extractor and classifier for fNIRS-based BCI. In this study, the hemodynamic responses evoked by performing rest, right-, and left-hand motor execution tasks were measured on eight healthy subjects to compare performances. Our CNN-based method provided improvements in classification accuracy over conventional methods employing the most commonly used features of mean, peak, slope, variance, kurtosis, and skewness, classified by support vector machine (SVM) and artificial neural network (ANN). Specifically, up to 6.49% and 3.33% improvement in classification accuracy was achieved by CNN compared with SVM and ANN, respectively.

Feature Extraction and Classification Methods for Hybrid fNIRS-EEG Brain-Computer Interfaces

“…The conventional classifiers may not be effective for identification of neuro-plasticity from brain images. So far, only one fNIRS study has used deep learning approach for BCI (Trakoolwilaiwan et al, 2017 ). As described in the study, a Convolutional Neural Network (CNN) can be effective for classification of multiple brain activities from a brain image.…”

Enhanced Accuracy for Multiclass Mental Workload Detection Using Long Short-Term Memory for Brain–Computer Interface

“…In these studies, the most important objective is to improve classification accuracies, which lead to the exploitation of appropriate classifiers using different machine learning (ML) techniques. The challenging part in these conventional ML classification methods is feature engineering, involving feature extraction, a large number of possible features, feature selection, their combinations, and dimensionality reduction from a relatively small amount of data, which leads to overfitting and biasness (Trakoolwilaiwan et al, 2017;Wang et al, 2019). These intrinsic limitations make researchers tweak around and hence results in a lot of time consumed in data mining and preprocessing.…”

Deep learning a boon for biophotonics?

“…It is thus advantageous to apply deep neural networks for the analysis of vibrational spectra, which are a complex superposition of all vibrational information within the sample. Applications of deep learning were reported for both infrared and Raman spectroscopy in order to achieve tasks like brain function investigations , biological diagnostics , cytopathology , microbial identification , pathogenic bacteria identification , food science investigations , tobacco leaves characterization and mineral analysis . Furthermore, it was reported in references that deep learning can perform better than classical machine learning methods .…”