Motor imaginary task classification using statistically significant time-domain EEG features

Degirmenci, Murside; Yüce, Yılmaz Kemal; İşler, Yalçın

doi:10.1109/siu55565.2022.9864745

Cited by 5 publications

(13 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study for differentiation of FM imageries, the provided ITD-based EEG features have been evaluated using eight well-known machine learning algorithms, such as Decision Tree (Tzallas et al, 2009 ; Sharma et al, 2022 ), Discriminant Analysis (Hart et al, 2000 ; Chakrabarti et al, 2003 ; Lotte et al, 2018 ), Naive Bayes (Hart et al, 2000 ; Miao et al, 2017 ), Support Vector Machine (Vapnik, 1999 ; Hart et al, 2000 ; Bascil et al, 2016 ), k -Nearest Neighbor (Hart et al, 2000 ; Isler, 2009 ; Tzallas et al, 2009 ), Ensemble Learning (Sayilgan et al, 2019 , 2020 , 2021a , b , 2022 ; Degirmenci et al, 2022b , c ; Karabiber Cura et al, 2023 ), Neural Networks (Richard and Lippmann, 1991 ; Pan et al, 2012 ; Narin and Isler, 2021 ; Ozdemir et al, 2021 ; Degirmenci et al, 2022a ), and Kernel Approximation (Maji et al, 2008 ; Lei et al, 2019 ). The classifiers and corresponding algorithms that were adopted in this study are listed below in Table 1 .…”

Section: Methodsmentioning

confidence: 99%

EEG-based finger movement classification with intrinsic time-scale decomposition

Degirmenci,

Yuce,

Perc

et al. 2024

Front. Hum. Neurosci.

Self Cite

View full text Add to dashboard Cite

IntroductionBrain-computer interfaces (BCIs) are systems that acquire the brain's electrical activity and provide control of external devices. Since electroencephalography (EEG) is the simplest non-invasive method to capture the brain's electrical activity, EEG-based BCIs are very popular designs. Aside from classifying the extremity movements, recent BCI studies have focused on the accurate coding of the finger movements on the same hand through their classification by employing machine learning techniques. State-of-the-art studies were interested in coding five finger movements by neglecting the brain's idle case (i.e., the state that brain is not performing any mental tasks). This may easily cause more false positives and degrade the classification performances dramatically, thus, the performance of BCIs. This study aims to propose a more realistic system to decode the movements of five fingers and the no mental task (NoMT) case from EEG signals.MethodsIn this study, a novel praxis for feature extraction is utilized. Using Proper Rotational Components (PRCs) computed through Intrinsic Time Scale Decomposition (ITD), which has been successfully applied in different biomedical signals recently, features for classification are extracted. Subsequently, these features were applied to the inputs of well-known classifiers and their different implementations to discriminate between these six classes. The highest classifier performances obtained in both subject-independent and subject-dependent cases were reported. In addition, the ANOVA-based feature selection was examined to determine whether statistically significant features have an impact on the classifier performances or not.ResultsAs a result, the Ensemble Learning classifier achieved the highest accuracy of 55.0% among the tested classifiers, and ANOVA-based feature selection increases the performance of classifiers on five-finger movement determination in EEG-based BCI systems.DiscussionWhen compared with similar studies, proposed praxis achieved a modest yet significant improvement in classification performance although the number of classes was incremented by one (i.e., NoMT).

show abstract

Section: Methodsmentioning

confidence: 99%

EEG-based finger movement classification with intrinsic time-scale decomposition

Degirmenci,

Yuce,

Perc

et al. 2024

Front. Hum. Neurosci.

Self Cite

View full text Add to dashboard Cite

show abstract

“…These are signal preprocessing, feature extraction, feature selection, and classification. Among these steps, the feature extraction and selection processes play an important role in EEG-based studies (Degirmenci et al, 2022b ). The preprocessing step includes different and significant operations such as signal filtering, signal normalization, artifact removal, and signal segmentation (Altaheri et al, 2021 ).…”

Section: Introductionmentioning

confidence: 99%

“…Temporal features are supplied from the time domain of signals using time points or different time segments and include features such as mean value, kurtosis, variance, skewness, root mean square value, and Hjorth parameters (Pawar and Dhage, 2020 ; Degirmenci et al, 2022b ). Spectral features contain both frequency domain features such as power spectral density and fast Fourier transform (Djamal et al, 2017 ; Degirmenci et al, 2022c ) and time-frequency domain features such as short-time Fourier transform (Ha and Jeong, 2019 ) and Wavelet transform (Chaudhary et al, 2020 ).…”

Section: Introductionmentioning

confidence: 99%

Statistically significant features improve binary and multiple Motor Imagery task predictions from EEGs

Degirmenci

Yüce²,

Perc

et al. 2023

Front. Hum. Neurosci.

View full text Add to dashboard Cite

In recent studies, in the field of Brain-Computer Interface (BCI), researchers have focused on Motor Imagery tasks. Motor Imagery-based electroencephalogram (EEG) signals provide the interaction and communication between the paralyzed patients and the outside world for moving and controlling external devices such as wheelchair and moving cursors. However, current approaches in the Motor Imagery-BCI system design require effective feature extraction methods and classification algorithms to acquire discriminative features from EEG signals due to the non-linear and non-stationary structure of EEG signals. This study investigates the effect of statistical significance-based feature selection on binary and multi-class Motor Imagery EEG signal classifications. In the feature extraction process performed 24 different time-domain features, 15 different frequency-domain features which are energy, variance, and entropy of Fourier transform within five EEG frequency subbands, 15 different time-frequency domain features which are energy, variance, and entropy of Wavelet transform based on five EEG frequency subbands, and 4 different Poincare plot-based non-linear parameters are extracted from each EEG channel. A total of 1,364 Motor Imagery EEG features are supplied from 22 channel EEG signals for each input EEG data. In the statistical significance-based feature selection process, the best one among all possible combinations of these features is tried to be determined using the independent t-test and one-way analysis of variance (ANOVA) test on binary and multi-class Motor Imagery EEG signal classifications, respectively. The whole extracted feature set and the feature set that contain statistically significant features only are classified in this study. We implemented 6 and 7 different classifiers in multi-class and binary (two-class) classification tasks, respectively. The classification process is evaluated using the five-fold cross-validation method, and each classification algorithm is tested 10 times. These repeated tests provide to check the repeatability of the results. The maximum of 61.86 and 47.36% for the two-class and four-class scenarios, respectively, are obtained with Ensemble Subspace Discriminant among all these classifiers using selected features including only statistically significant features. The results reveal that the introduced statistical significance-based feature selection approach improves the classifier performances by achieving higher classifier performances with fewer relevant components in Motor Imagery task classification. In conclusion, the main contribution of the presented study is two-fold evaluation of non-linear parameters as an alternative to the commonly used features and the prediction of multiple Motor Imagery tasks using statistically significant features.

show abstract

“…In last decades, traditional machine learning based approaches have been commonly used to classify MI EEG data. The processing of MI EEG signals in traditional methods consists of three main phase: preprocessing of signals, feature extraction, and classification [15]. The preprocessing phase includes some definite and significant processes of channel selection, signal filtering, signal normalization, and artifact removal.…”

Section: Introductionmentioning

confidence: 99%

“…These features were separated in three main groups based on their processing domain: temporal features, spectral features and spatial features. Temporal features are generated from time-domain utilizing time segments and time points of EEG signals such as mean value, skewness, kurtosis, variance, Hjorth parameters and root mean square value [15]. Spectral features categorized as frequency-domain based features which are power spectrum density (PSD) and Fast Fourier transform (FFT) [16], or timefrequency domain features which are Wavelet Transform (WT) [17] and short-time Fourier transform (STFT) [18].…”

Section: Introductionmentioning

confidence: 99%

Classification of Multi-Class Motor Imaginary Tasks using Poincare Measurements Extracted from EEG Signals

Degirmenci

Yüce²,

İşler

2022

J Intell Syst Appl

View full text Add to dashboard Cite

Motor Imaginary (MI) electroencephalography (EEG) signals are generated with the recording of brain activities when a participant imagines a movement without physically performing it. The correct decoding of MI signals have been became an important task due to the application of these signals in the rehabilitation process of paralyzed patients in recent studies. However, the decoding of the these signals is still an evolving challenge in the design of a brain-computer interface (BCI) system. In this study, a machine learning based approach using Poincare measurements from non-linear measurements of MI EEG signals is proposed for classification of four-class MI tasks. The m-lagged Poincare plots were used to extract non-linear features and m is set to be values from 1 to 10. The performances of feature vectors which are extracted from 10 lag values and feature vector which is the combinations of these vectors were investigated separately in experimental evaluation section. The 24 different typical classification algorithms were tested in differentiating MI tasks using 5-fold cross-validation. Each of the these algorithms tested 10 times to analyzed the repeatability of the experimental results. The highest classifier performance of 47.08% among these 11 feature vectors was achieved over the combination feature vector that includes all lag values features using Quadratic Support Vector Machine (SVM). According to average accuracy value of 24 classifiers in 11 feature vector, the most discriminative feature set is 9th vector that consists of features extracted when lag value defined as 9. As a result, the innovative aspect of this study is the application of Poincare plots, one of the nonlinear feature extraction methods, in motor imaginary task classification.

show abstract

Motor imaginary task classification using statistically significant time-domain EEG features

Cited by 5 publications

References 0 publications

EEG-based finger movement classification with intrinsic time-scale decomposition

EEG-based finger movement classification with intrinsic time-scale decomposition

Statistically significant features improve binary and multiple Motor Imagery task predictions from EEGs

Classification of Multi-Class Motor Imaginary Tasks using Poincare Measurements Extracted from EEG Signals

Contact Info

Product

Resources

About