scholarly journals Deep Learning-Based Classification of Fine Hand Movements from Low Frequency EEG

2021 ◽  
Vol 13 (5) ◽  
pp. 103
Author(s):  
Giulia Bressan ◽  
Giulia Cisotto ◽  
Gernot R. Müller-Putz ◽  
Selina Christin Wriessnegger
Keyword(s):  
Low Frequency ◽  
Classification Performance ◽  
Hand Movements ◽  
Eeg Signals ◽  
Low Frequencies ◽  
Linear Discriminant ◽  
Comparable Performance ◽  
Research Challenge ◽  
Electroencephalogram Eeg

The classification of different fine hand movements from electroencephalogram (EEG) signals represents a relevant research challenge, e.g., in BCI applications for motor rehabilitation. Here, we analyzed two different datasets where fine hand movements (touch, grasp, palmar, and lateral grasp) were performed in a self-paced modality. We trained and tested a newly proposed CNN, and we compared its classification performance with two well-established machine learning models, namely, shrinkage-linear discriminant analysis (LDA) and Random Forest (RF). Compared to previous literature, we included neuroscientific evidence, and we trained our Convolutional Neural Network (CNN) model on the so-called movement-related cortical potentials (MRCPs). They are EEG amplitude modulations at low frequencies, i.e., (0.3,3) Hz that have been proved to encode several properties of the movements, e.g., type of grasp, force level, and speed. We showed that CNN achieved good performance in both datasets (accuracy of 0.70±0.11 and 0.64±0.10, for the two datasets, respectively), and they were similar or superior to the baseline models (accuracy of 0.68±0.10 and 0.62±0.07 with sLDA; accuracy of 0.70±0.15 and 0.61±0.07 with RF, with comparable performance in precision and recall). In addition, compared to the baseline, our CNN requires a faster pre-processing procedure, paving the way for its possible use in online BCI applications.

EEG Classification for BCI Based on CSP and SVM-GA

2013 ◽  
Vol 459 ◽  
pp. 228-231 ◽  
Author(s):  
Hao Yang ◽  
Song Wu
Keyword(s):  
Classification Performance ◽  
Computer Interface ◽  
Support Vector ◽  
Eeg Signals ◽  
Common Spatial Pattern ◽  
Data Set ◽  
Linear Discriminant ◽  
Brain Signals ◽  
Electroencephalogram Eeg ◽  
The Brain

Electroencephalogram (EEG) is generally used in Brain-Computer Interface (BCI) applications to measure the brain signals. However, the multichannel EEG signals characterized by unrelated and redundant features will deteriorate the classification accuracy. This paper presents a method based on common spatial pattern (CSP) for feature extraction and support vector machine with genetic algorithm (SVM-GA) as a classifier, the GA is used to optimize the kernel parameters setting. The proposed algorithm is performed on data set Iva of BCI Competition III. Results show that the proposed method outperforms the conventional linear discriminant analysis (LDA) in average classification performance.

scholarly journals Classification of Drowsiness Levels Based on a Deep Spatio-Temporal Convolutional Bidirectional LSTM Network Using Electroencephalography Signals

2019 ◽  
Vol 9 (12) ◽  
pp. 348 ◽  
Author(s):  
Ji-Hoon Jeong ◽  
Baek-Woon Yu ◽  
Dae-Hyeok Lee ◽  
Seong-Whan Lee
Keyword(s):  
Short Term Memory ◽  
Mental States ◽  
Critical Issue ◽  
High Accuracy ◽  
Classification Performance ◽  
Eeg Signals ◽  
Aviation Accidents ◽  
Spatio Temporal ◽  
Lstm Network

Non-invasive brain-computer interfaces (BCI) have been developed for recognizing human mental states with high accuracy and for decoding various types of mental conditions. In particular, accurately decoding a pilot’s mental state is a critical issue as more than 70% of aviation accidents are caused by human factors, such as fatigue or drowsiness. In this study, we report the classification of not only two mental states (i.e., alert and drowsy states) but also five drowsiness levels from electroencephalogram (EEG) signals. To the best of our knowledge, this approach is the first to classify drowsiness levels in detail using only EEG signals. We acquired EEG data from ten pilots in a simulated night flight environment. For accurate detection, we proposed a deep spatio-temporal convolutional bidirectional long short-term memory network (DSTCLN) model. We evaluated the classification performance using Karolinska sleepiness scale (KSS) values for two mental states and five drowsiness levels. The grand-averaged classification accuracies were 0.87 (±0.01) and 0.69 (±0.02), respectively. Hence, we demonstrated the feasibility of classifying five drowsiness levels with high accuracy using deep learning.

Study of quadrature FIR filters for extraction of low-frequency instantaneous information in biophysical signals

2017 ◽  
Vol 28 (05) ◽  
pp. 1750065
Author(s):  
Valdemar E. Arce-Guevara ◽  
Alfonso Alba-Cadena ◽  
Martín O. Mendez
Keyword(s):  
Filter Design ◽  
Narrow Band ◽  
Bandwidth Selection ◽  
Low Frequency ◽  
Qualitative Evaluation ◽  
Eeg Signals ◽  
Electrophysiological Signals ◽  
Selection For ◽  
Null Response ◽  
Electroencephalogram Eeg

Quadrature bandpass filters take a real-valued signal and output an analytic signal from which the instantaneous amplitude and phase can be computed. For this reason, they represent a useful tool to extract time-varying, narrow-band information from electrophysiological signals such as electroencephalogram (EEG) or electrocardiogram. One of the defining characteristics of quadrature filters is its null response to negative frequencies. However, when the frequency band of interest is close to 0 Hz, a careless filter design could let through negative frequencies, producing distortions in the amplitude and phase of the output. In this work, three types of quadrature filters (Ideal, Gabor and Sinusoidal) have been evaluated using both artificial and real EEG signals. For the artificial signals, the performance of each filter was measured in terms of the distortion in amplitude and phase, and sensitivity to noise and bandwidth selection. For the real EEG signals, a qualitative evaluation of the dynamics of the synchronization between two EEG channels was performed. The results suggest that, while all filters under study behave similarly under noise, they differ in terms of their sensitivity to bandwidth choice. In this study, the Sinusoidal filter showed clear advantages for the estimation of low-frequency EEG synchronization.

FEATURES EXTRACTION METHOD FOR BRAIN-MACHINE COMMUNICATION BASED ON THE EMPIRICAL MODE DECOMPOSITION

2013 ◽  
Vol 25 (06) ◽  
pp. 1350058 ◽  
Author(s):  
Pablo F. Diez ◽  
Vicente A. Mut ◽  
Eric Laciar ◽  
Abel Torres ◽  
Enrique M. Avila Perona
Keyword(s):  
Empirical Mode Decomposition ◽  
Communication System ◽  
Brain Activity ◽  
Features Extraction ◽  
Eeg Signals ◽  
Linear Discriminant ◽  
Mode Decomposition ◽  
Machine Communication ◽  
Mental Tasks

A brain-machine interface (BMI) is a communication system that translates human brain activity into commands, and then these commands are conveyed to a machine or a computer. It is proposes a technique for features extraction from electroencephalographic (EEG) signals and afterward, their classification on different mental tasks. The empirical mode decomposition (EMD) is a method capable of processing non-stationary and nonlinear signals, as the EEG. The EMD was applied on EEG signals of seven subjects performing five mental tasks. Six features were computed, namely, root mean square (RMS), variance, Shannon entropy, Lempel–Ziv complexity value, and central and maximum frequencies. In order to reduce the dimensionality of the feature vector, the Wilks' lambda (WL) parameter was used for the selection of the most important variables. The classification of mental tasks was performed using linear discriminant analysis (LDA) and neural networks (NN). Using this method, the average classification over all subjects in database is 91 ± 5% and 87 ± 5% using LDA and NN, respectively. Bit rate was ranging from 0.24 bits/trial up to 0.84 bits/trial. The proposed method allows achieving higher performances in the classification of mental tasks than other traditional methods using the same database. This represents an improvement in the brain-machine communication system.

scholarly journals An Optimized Channel Selection Method Based on Multifrequency CSP-Rank for Motor Imagery-Based BCI System

2019 ◽  
Vol 2019 ◽  
pp. 1-10 ◽  
Author(s):  
Jian Kui Feng ◽  
Jing Jin ◽  
Ian Daly ◽  
Jiale Zhou ◽  
Yugang Niu ◽  
...  
Keyword(s):  
Motor Imagery ◽  
Classification Accuracy ◽  
Channel Selection ◽  
Selection Method ◽  
Selection Methods ◽  
Eeg Signals ◽  
Common Spatial Pattern ◽  
Linear Discriminant ◽  
Novel Method ◽  
Electroencephalogram Eeg

Background. Due to the redundant information contained in multichannel electroencephalogram (EEG) signals, the classification accuracy of brain-computer interface (BCI) systems may deteriorate to a large extent. Channel selection methods can help to remove task-independent electroencephalogram (EEG) signals and hence improve the performance of BCI systems. However, in different frequency bands, brain areas associated with motor imagery are not exactly the same, which will result in the inability of traditional channel selection methods to extract effective EEG features. New Method. To address the above problem, this paper proposes a novel method based on common spatial pattern- (CSP-) rank channel selection for multifrequency band EEG (CSP-R-MF). It combines the multiband signal decomposition filtering and the CSP-rank channel selection methods to select significant channels, and then linear discriminant analysis (LDA) was used to calculate the classification accuracy. Results. The results showed that our proposed CSP-R-MF method could significantly improve the average classification accuracy compared with the CSP-rank channel selection method.

scholarly journals Motor Imagery EEG Classification Using Capsule Networks

Sensors ◽  
2019 ◽  
Vol 19 (13) ◽  
pp. 2854 ◽  
Author(s):  
Kwon-Woo Ha ◽  
Jin-Woo Jeong
Keyword(s):  
Motor Imagery ◽  
Learning Approaches ◽  
Eeg Signals ◽  
Left Hand ◽  
Computer Interfaces ◽  
Conventional Machine ◽  
Short Time ◽  
Electroencephalogram Eeg ◽  
Target Data

Various convolutional neural network (CNN)-based approaches have been recently proposed to improve the performance of motor imagery based-brain-computer interfaces (BCIs). However, the classification accuracy of CNNs is compromised when target data are distorted. Specifically for motor imagery electroencephalogram (EEG), the measured signals, even from the same person, are not consistent and can be significantly distorted. To overcome these limitations, we propose to apply a capsule network (CapsNet) for learning various properties of EEG signals, thereby achieving better and more robust performance than previous CNN methods. The proposed CapsNet-based framework classifies the two-class motor imagery, namely right-hand and left-hand movements. The motor imagery EEG signals are first transformed into 2D images using the short-time Fourier transform (STFT) algorithm and then used for training and testing the capsule network. The performance of the proposed framework was evaluated on the BCI competition IV 2b dataset. The proposed framework outperformed state-of-the-art CNN-based methods and various conventional machine learning approaches. The experimental results demonstrate the feasibility of the proposed approach for classification of motor imagery EEG signals.

scholarly journals Classification of Multi-Frequency Polarimetric SAR Images Based on Multi-Linear Subspace Learning of Tensor Objects

2015 ◽  
Vol 7 (7) ◽  
pp. 9253-9268 ◽  
Author(s):  
Chun Liu ◽  
Junjun Yin ◽  
Jian Yang ◽  
Wei Gao
Keyword(s):  
Linear Subspace ◽  
Principal Component ◽  
Subspace Learning ◽  
Classification Performance ◽  
Polarimetric Sar ◽  
Third Order ◽  
Sar Images ◽  
Linear Discriminant ◽  
Multi Band

One key problem for the classification of multi-frequency polarimetric SAR images is to extract target features simultaneously in the aspects of frequency, polarization and spatial texture. This paper proposes a new classification method for multi-frequency polarimetric SAR data based on tensor representation and multi-linear subspace learning (MLS). Firstly, each cell of the SAR images is represented by a third-order tensor in the frequency, polarization and spatial domains, with each order of tensor corresponding to one domain. Then, two main MLS methods, i.e., multi-linear principal component analysis (MPCA) and multi-linear extension of linear discriminant analysis (MLDA), are used to learn the third-order tensors. MPCA is used to analyze the principal component of the tensors. MLDA is applied to improve the discrimination between different land covers. Finally, the lower dimension subtensor features extracted by the MPCA and MLDA algorithms are classified with a neural network (NN) classifier. The classification scheme is accessed using multi-band polarimetric SAR images (C-, L- and P-band) acquired by the Airborne Synthetic Aperture Radar (AIRSAR) sensor of the Jet Propulsion Laboratory (JPL) over the Flevoland area. Experimental results demonstrate that the proposed method has good classification performance in comparison with the classic multi-band Wishart classifier. The overall classification accuracy is close to 99%, even when the number of training samples is small.

scholarly journals Continuous Classification of Locomotion in Response to Task Complexity and Anticipatory State

2021 ◽  
Vol 9 ◽  
Author(s):  
Mahdieh Kazemimoghadam ◽  
Nicholas P. Fey
Keyword(s):  
Task Complexity ◽  
Window Size ◽  
Classification Performance ◽  
Training Data ◽  
Intent Recognition ◽  
Linear Discriminant ◽  
Classification Schemes ◽  
Target Task ◽  
Straight Line

ObjectiveIntent recognition in lower-extremity assistive devices (e.g., prostheses and exoskeletons) is typically limited to either recognition of steady-state locomotion or changes of terrain (e.g., level ground to stair) occurring in a straight-line path and under anticipated condition. Stability is highly affected during non-steady changes of direction such as cuts especially when they are unanticipated, posing high risk of fall-related injuries. Here, we studied the influence of changes of direction and user anticipation on task recognition, and accordingly introduced classification schemes accommodating such effects.MethodsA linear discriminant analysis (LDA) classifier continuously classified straight-line walking, sidestep/crossover cuts (single transitions), and cuts-to-stair locomotion (mixed transitions) performed under varied task anticipatory conditions. Training paradigms with varying levels of anticipated/unanticipated exposures and analysis windows of size 100–600 ms were examined.ResultsMore accurate classification of anticipated relative to unanticipated tasks was observed. Including bouts of target task in the training data was necessary to improve generalization to unanticipated locomotion. Only up to two bouts of target task were sufficient to reduce errors to <20% in unanticipated mixed transitions, whereas, in single transitions and straight walking, substantial unanticipated information (i.e., five bouts) was necessary to achieve similar outcomes. Window size modifications did not have a significant influence on classification performance.ConclusionAdjusting the training paradigm helps to achieve classification schemes capable of adapting to changes of direction and task anticipatory state.SignificanceThe findings could provide insight into developing classification schemes that can adapt to changes of direction and user anticipation. They could inform intent recognition strategies for controlling lower-limb assistive to robustly handle “unknown” circumstances, and thus deliver increased level of reliability and safety.

scholarly journals Electroencephalogram-Based Motor Imagery Classification Using Deep Residual Convolutional Networks

2021 ◽  
Vol 15 ◽  
Author(s):  
Jing-Shan Huang ◽  
Wan-Shan Liu ◽  
Bin Yao ◽  
Zhan-Xiang Wang ◽  
Si-Fang Chen ◽  
...  
Keyword(s):  
Motor Imagery ◽  
Recognition Accuracy ◽  
Wavelet Packet ◽  
Eeg Signals ◽  
Convolutional Networks ◽  
Learning Classifier ◽  
Signal Features ◽  
Electroencephalogram Eeg ◽  
Bci System

The classification of electroencephalogram (EEG) signals is of significant importance in brain-computer interface (BCI) systems. Aiming to achieve intelligent classification of motor imagery EEG types with high accuracy, a classification methodology using the wavelet packet decomposition (WPD) and the proposed deep residual convolutional networks (DRes-CNN) is proposed. Firstly, EEG waveforms are segmented into sub-signals. Then the EEG signal features are obtained through the WPD algorithm, and some selected wavelet coefficients are retained and reconstructed into EEG signals in their respective frequency bands. Subsequently, the reconstructed EEG signals were utilized as input of the proposed deep residual convolutional networks to classify EEG signals. Finally, EEG types of motor imagination are classified by the DRes-CNN classifier intelligently. The datasets from BCI Competition were used to test the performance of the proposed deep learning classifier. Classification experiments show that the average recognition accuracy of this method reaches 98.76%. The proposed method can be further applied to the BCI system of motor imagination control.

Sign in / Sign up

Export Citation Format

Share Document