Online EEG Classification of Covert Speech for Brain–Computer Interfacing

2017 ◽  
Vol 27 (08) ◽  
pp. 1750033 ◽  
Author(s):  
Alborz Rezazadeh Sereshkeh ◽  
Robert Trott ◽  
Aurélien Bricout ◽  
Tom Chau
Keyword(s):  
Chance Level ◽  
Support Vector ◽  
Eeg Classification ◽  
Time Frequency ◽  
Computer Interfaces ◽  
Online Classification ◽  
Average Accuracy ◽  
Gamma Power ◽  
Brain Computer Interfacing

Brain–computer interfaces (BCIs) for communication can be nonintuitive, often requiring the performance of hand motor imagery or some other conversation-irrelevant task. In this paper, electroencephalography (EEG) was used to develop two intuitive online BCIs based solely on covert speech. The goal of the first BCI was to differentiate between 10[Formula: see text]s of mental repetitions of the word “no” and an equivalent duration of unconstrained rest. The second BCI was designed to discern between 10[Formula: see text]s each of covert repetition of the words “yes” and “no”. Twelve participants used these two BCIs to answer yes or no questions. Each participant completed four sessions, comprising two offline training sessions and two online sessions, one for testing each of the BCIs. With a support vector machine and a combination of spectral and time-frequency features, an average accuracy of [Formula: see text] was reached across participants in the online classification of no versus rest, with 10 out of 12 participants surpassing the chance level (60.0% for [Formula: see text]). The online classification of yes versus no yielded an average accuracy of [Formula: see text], with eight participants exceeding the chance level. Task-specific changes in EEG beta and gamma power in language-related brain areas tended to provide discriminatory information. To our knowledge, this is the first report of online EEG classification of covert speech. Our findings support further study of covert speech as a BCI activation task, potentially leading to the development of more intuitive BCIs for communication.

scholarly journals Classification of Relaxation and Concentration Mental States with EEG

Information ◽  
2021 ◽  
Vol 12 (5) ◽  
pp. 187
Author(s):  
Shingchern D. You
Keyword(s):  
Mental States ◽  
Support Vector ◽  
Svm Classifier ◽  
Eeg Signals ◽  
Consumer Market ◽  
Time Frequency ◽  
Average Accuracy ◽  
Spectral Components ◽  
Machine Interface

In this paper, we study the use of EEG (Electroencephalography) to classify between concentrated and relaxed mental states. In the literature, most EEG recording systems are expensive, medical-graded devices. The expensive devices limit the availability in a consumer market. The EEG signals are obtained from a toy-grade EEG device with one channel of output data. The experiments are conducted in two runs, with 7 and 10 subjects, respectively. Each subject is asked to silently recite a five-digit number backwards given by the tester. The recorded EEG signals are converted to time-frequency representations by the software accompanying the device. A simple average is used to aggregate multiple spectral components into EEG bands, such as α, β, and γ bands. The chosen classifiers are SVM (support vector machine) and multi-layer feedforward network trained individually for each subject. Experimental results show that features, with α+β+γ bands and bandwidth 4 Hz, the average accuracy over all subjects in both runs can reach more than 80% and some subjects up to 90+% with the SVM classifier. The results suggest that a brain machine interface could be implemented based on the mental states of the user even with the use of a cheap EEG device.

scholarly journals Open Software/Hardware Platform for Human-Computer Interface Based on Electrooculography (EOG) Signal Classification

Sensors ◽  
2020 ◽  
Vol 20 (9) ◽  
pp. 2443
Author(s):  
Jayro Martínez-Cerveró ◽  
Majid Khalili Ardali ◽  
Andres Jaramillo-Gonzalez ◽  
Shizhe Wu ◽  
Alessandro Tonin ◽  
...  
Keyword(s):  
Open Source ◽  
Raspberry Pi ◽  
Support Vector ◽  
Svm Classifier ◽  
Computer Interfaces ◽  
Human Computer Interfaces ◽  
Online Classification ◽  
Acquisition Device ◽  
Maximum Minimum

Electrooculography (EOG) signals have been widely used in Human-Computer Interfaces (HCI). The HCI systems proposed in the literature make use of self-designed or closed environments, which restrict the number of potential users and applications. Here, we present a system for classifying four directions of eye movements employing EOG signals. The system is based on open source ecosystems, the Raspberry Pi single-board computer, the OpenBCI biosignal acquisition device, and an open-source python library. The designed system provides a cheap, compact, and easy to carry system that can be replicated or modified. We used Maximum, Minimum, and Median trial values as features to create a Support Vector Machine (SVM) classifier. A mean of 90% accuracy was obtained from 7 out of 10 subjects for online classification of Up, Down, Left, and Right movements. This classification system can be used as an input for an HCI, i.e., for assisted communication in paralyzed people.

scholarly journals Research on GA-SVM Based Head-Motion Classification via Mechanomyography Feature Analysis

Sensors ◽  
2019 ◽  
Vol 19 (9) ◽  
pp. 1986 ◽  
Author(s):  
Yue Zhang ◽  
Jing Yu ◽  
Chunming Xia ◽  
Ke Yang ◽  
Heng Cao ◽  
...  
Keyword(s):  
Classification Accuracy ◽  
Kernel Functions ◽  
Support Vector ◽  
Motion Classification ◽  
Time Frequency ◽  
Feature Sets ◽  
Average Accuracy ◽  
Training Samples ◽  
And Training

This study investigated classification of six types of head motions using mechanomyography (MMG) signals. An unequal segmenting algorithm was adopted to segment the MMG signals generated by head motions. Three types of features (time domain, time-frequency domain and nonlinear dynamics) were extracted to construct five feature sets as candidate datasets for classification analysis. Genetic algorithm optimized support vector machine (GA-SVM) was used to classify the MMG signals. Three different kernel functions, different combinations of feature sets, different number of signal channels and training samples were selected for comparative analysis to evaluate the classification accuracy. Experimental results showed that the classifier had the best overall classification accuracy when using the radial basis function (RBF). Any combination of three different types of feature sets guaranteed an average accuracy of over 80%. In the case of the best combination (feature set 2 + 3 + 5), the classification accuracy was up to 88.2%. Using four channels to acquire MMG signal and no less than 60 training samples can assure a satisfactory classification accuracy.

scholarly journals Performance of channel selection used for Multi-class EEG signal classification of motor imagery

2019 ◽  
Vol 15 (3) ◽  
pp. 1305
Author(s):  
Djelloul Kheira ◽  
M. Beladgham
Keyword(s):  
Support Vector ◽  
Eeg Signal ◽  
K Nearest Neighbors ◽  
Linear Discriminant ◽  
Left Hand ◽  
Time Frequency ◽  
Non Invasive ◽  
Average Accuracy ◽  
Motor Activities

<p>In this paper, a study of a non-invasive brain-machine interfaces for the classification of 4 imaginary are presented. Performance comparisons using time-frequency analysis between the Linear Discriminant Analysis motor activities (left hand, right hand, foot, tongue) with the BCI competition III dataset IIIa is (LDA), the Support Vector Machine (SVM) and the K-Nearest Neighbors (KNN) algorithms have been carried. The number and position of electrodes for each subject were investigated to provide an improvement for the classification accuracy of the algorithm. Results show that the electrode positions varied from subject to subject; moreover , using one subset of the channels enhanced the classification performances compared to literature data. an average accuracy of 86.06% was observed among all 3 subjects.<strong></strong></p>

scholarly journals Severity Classification of Multiple Sclerosis Disease: A Rough Set-Based Method

2019 ◽  
Vol 8 (9S) ◽  
pp. 307-314
Keyword(s):  
Multiple Sclerosis ◽  
Random Forest ◽  
Rough Set ◽  
Weighted Average ◽  
Support Vector ◽  
Neurologic Disorder ◽  
Severity Classification ◽  
Average Accuracy ◽  
Multiple Sclerosis Disease

Multiple sclerosis (MS) is among the world’s most common neurologic disorder. Severity classification of MS disease is necessary for treatment and medication dosage decisions and to understand the disease progression. To the best of authors’ knowledge, this is the first study for the severity classification of MS disease. In this study, Rough set (RS) approach is applied to discern the three classes (mild, moderate, and severe) of the severity of MS disease. Furthermore, the performance of the RS approach is compared with Machine learning (ML) classifiers namely, random forest, K-nearest neighbour, and support vector machine. The performance is evaluated on the dataset acquired from Multiple sclerosis outcome assessments consortium (MSOAC), Arizona, US. The weighted average accuracy, precision, recall, and specificity values for the RS approach are found to be 84.04%, 76.99%, 76.75%, and 83.84% respectively. However, among the ML classifiers, the performance of random forest classifier is found best for which the weighted average accuracy, precision, recall, and specificity values are 62.19 %, 52.65 %, 56.84 %, and 59.87 % respectively. The RS approach is found much superior to ML classifiers and may be used for MS disease severity classification. This study may be helpful for the clinicians to assess the severity of the MS patients and to take medication and dosage decisions.

Epileptic EEG Identification via LBP Operators on Wavelet Coefficients

2018 ◽  
Vol 28 (08) ◽  
pp. 1850010 ◽  
Author(s):  
Qi Yuan ◽  
Weidong Zhou ◽  
Fangzhou Xu ◽  
Yan Leng ◽  
Dongmei Wei
Keyword(s):  
Recognition System ◽  
Support Vector ◽  
Svm Classifier ◽  
Automatic Identification ◽  
Wavelet Coefficients ◽  
Eeg Signals ◽  
Eeg Classification ◽  
Time Frequency ◽  
Ictal Eeg ◽  
Uniform Lbp

The automatic identification of epileptic electroencephalogram (EEG) signals can give assistance to doctors in diagnosis of epilepsy, and provide the higher security and quality of life for people with epilepsy. Feature extraction of EEG signals determines the performance of the whole recognition system. In this paper, a novel method using the local binary pattern (LBP) based on the wavelet transform (WT) is proposed to characterize the behavior of EEG activities. First, the WT is employed for time–frequency decomposition of EEG signals. After that, the “uniform” LBP operator is carried out on the wavelet-based time–frequency representation. And the generated histogram is regarded as EEG feature vector for the quantification of the textural information of its wavelet coefficients. The LBP features coupled with the support vector machine (SVM) classifier can yield the satisfactory recognition accuracies of 98.88% for interictal and ictal EEG classification and 98.92% for normal, interictal and ictal EEG classification on the publicly available EEG dataset. Moreover, the numerical results on another large size EEG dataset demonstrate that the proposed method can also effectively detect seizure events from multi-channel raw EEG data. Compared with the standard LBP, the “uniform” LBP can obtain the much shorter histogram which greatly reduces the computational burden of classification and enables it to detect ictal EEG signals in real time.

scholarly journals Extracting Time-Frequency Features of Images for Robust LSTM-based Classification of H&E Stained Tissue

2020 ◽  
Author(s):  
Tuan Pham
Keyword(s):  
Short Term Memory ◽  
Digital Pathology ◽  
Support Vector ◽  
Automated Classification ◽  
Time Frequency ◽  
Statistical Measures ◽  
Vector Machines ◽  
Histopathological Images ◽  
Frequency Features

The importance of automated classification of histopathological images has been increasingly recognized for effective processing of large volumes of data in the era of digital pathology for new discovery of disease mechanism. This paper presents a deep-learning approach that extracts time-frequency features of H&E stained tissue images for classification by long short-term memory networks. Using two large public databases of colorectal-cancer and heart-failure H&E stained tissue images, the proposed approach outperforms several state-of-the-art benchmark classification methods, including support vector machines and convolutional neural networks in terms of several statistical measures.

Sign in / Sign up

Export Citation Format

Share Document