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

Frontiers in Human Neuroscience, Год журнала: 2023, Номер 17

Опубликована: Июль 11, 2023

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

Язык: Английский

---

Multiclass classification of motor imagery tasks based on multi-branch convolutional neural network and temporal convolutional network model

Cerebral Cortex, Год журнала: 2024, Номер 34(2)

Опубликована: Янв. 5, 2024

Abstract Motor imagery (MI) is a cognitive process wherein an individual mentally rehearses specific movement without physically executing it. Recently, MI-based brain–computer interface (BCI) has attracted widespread attention. However, accurate decoding of MI and understanding neural mechanisms still face huge challenges. These seriously hinder the clinical application development BCI systems based on MI. Thus, it very necessary to develop new methods decode tasks. In this work, we propose multi-branch convolutional network (MBCNN) with temporal (TCN), end-to-end deep learning framework multi-class We first used MBCNN capture electroencephalography signals information spectral domains through different kernels. Then, introduce TCN extract more discriminative features. The within-subject cross-session strategy validate classification performance dataset Competition IV-2a. results showed that achieved 75.08% average accuracy for 4-class task classification, outperforming several state-of-the-art approaches. proposed MBCNN-TCN-Net successfully captures features decodes tasks effectively, improving MI-BCIs. Our findings could provide significant potential systems.

Язык: Английский

---

NF-EEG: A generalized CNN model for multi class EEG motor imagery classification without signal preprocessing for brain computer interfaces

Biomedical Signal Processing and Control, Год журнала: 2024, Номер 92, С. 106081 - 106081

Опубликована: Фев. 8, 2024

Язык: Английский

---

Classification of EEG Signal Using Deep Learning Architectures Based Motor-Imagery for an Upper-Limb Rehabilitation Exoskeleton

SN Computer Science, Год журнала: 2025, Номер 6(3)

Опубликована: Фев. 18, 2025

Язык: Английский

---

A parallel multi-scale time-frequency block convolutional neural network based on channel attention module for motor imagery classification

Biomedical Signal Processing and Control, Год журнала: 2022, Номер 79, С. 104066 - 104066

Опубликована: Авг. 13, 2022

Язык: Английский

---

Enhanced grasshopper optimization algorithm with extreme learning machines for motor‐imagery classification

Asian Journal of Control, Год журнала: 2022, Номер 25(4), С. 3015 - 3028

Опубликована: Ноя. 28, 2022

Abstract In Brain Computer Interface (BCI), achieving a reliable motor‐imagery classification is challenging task. The set of discriminative and relevant feature vectors plays crucial role in classification. this article, an enhanced optimization technique implemented for selecting active to enhance using Electroencephalography (EEG) signals. After collecting the input EEG signals from BCI competition III‐4a IV‐2a databases, 6th‐order butter‐worth filter employed eliminating base‐line wander noise raw Further, Variational Mode Decomposition applied separating important signal components composite signals, then, Higher Order Statistic, kurtosis, skewness, standard deviation, entropy are utilized extraction. high‐dimensional values given Enhanced Grasshopper Optimization Algorithm optimum selection, which Extreme Learning Machines (ELM) classifier Finally, resulting section, optimized ELM model achieved 99.48% 99.12% accuracy on where results maximum compared traditional deep learning models.

Язык: Английский

---

A novel multi-branch hybrid neural network for motor imagery EEG signal classification

Biomedical Signal Processing and Control, Год журнала: 2022, Номер 77, С. 103718 - 103718

Опубликована: Апрель 28, 2022

Язык: Английский

---

Exploring Digital Biomarkers of Illness Activity in Mood Episodes: Hypotheses Generating and Model Development Study

JMIR mhealth and uhealth, Год журнала: 2023, Номер 11, С. e45405 - e45405

Опубликована: Март 20, 2023

Depressive and manic episodes within bipolar disorder (BD) major depressive (MDD) involve altered mood, sleep, activity, alongside physiological alterations wearables can capture. Firstly, we explored whether wearable data could predict (aim 1) the severity of an acute affective episode at intra-individual level 2) polarity euthymia among different individuals. Secondarily, which were related to prior predictions, generalization across patients, associations between symptoms data. We conducted a prospective exploratory observational study including patients with BD MDD on (manic, depressed, mixed) whose recorded using research-grade (Empatica E4) 3 consecutive time points (acute, response, remission episode). Euthymic healthy controls during single session (approximately 48 h). Manic assessed standardized psychometric scales. Physiological included following channels: acceleration (ACC), skin temperature, blood volume pulse, heart rate (HR), electrodermal activity (EDA). Invalid removed rule-based filter, channels aligned 1-second units segmented window lengths 32 seconds, as best-performing parameters. developed deep learning predictive models, channels' individual contribution permutation feature importance analysis, computed scales' items normalized mutual information (NMI). present novel, fully automated method for preprocessing analysis from device, viable supervised pipeline time-series analyses. Overall, 35 sessions (1512 hours) 12 mixed, euthymic) 7 (mean age 39.7, SD 12.6 years; 6/19, 32% female) analyzed. The mood was predicted moderate (62%-85%) accuracies 1), their (70%) accuracy 2). most relevant features former tasks ACC, EDA, HR. There fair agreement in classification (Kendall W=0.383). Generalization models unseen overall low accuracy, except models. ACC associated "increased motor activity" (NMI>0.55), "insomnia" (NMI=0.6), "motor inhibition" (NMI=0.75). EDA "aggressive behavior" (NMI=1.0) "psychic anxiety" (NMI=0.52). show potential identify specific mania depression quantitatively, both MDD. Motor stress-related (EDA HR) stand out digital biomarkers predicting depression, respectively. These findings represent promising pathway toward personalized psychiatry, allow early identification intervention episodes.

Язык: Английский

---

EEG motor imagery classification using deep learning approaches in naïve BCI users

Biomedical Physics & Engineering Express, Год журнала: 2023, Номер 9(4), С. 045029 - 045029

Опубликована: Июнь 15, 2023

Abstract Motor Imagery (MI)-Brain Computer-Interfaces (BCI) illiteracy defines that not all subjects can achieve a good performance in MI-BCI systems due to different factors related the fatigue, substance consumption, concentration, and experience use. To reduce effects of lack use BCI (naïve users), this paper presents implementation three Deep Learning (DL) methods with hypothesis could be improved compared baseline evaluation naïve users. The proposed here are based on Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM)/Bidirectional (BiLSTM), combination CNN LSTM used for upper limb MI signal discrimination dataset 25 results were widely Common Spatial Pattern (CSP), Filter Bank (FBCSP), Spatial-Spectral (FBCSSP), temporal window configurations. As results, LSTM-BiLSTM-based approach presented best performance, according metrics Accuracy, F-score, Recall, Specificity, Precision, ITR, mean 80% (maximum 95%) ITR 10 bits/min using 1.5 s. DL Methods represent significant increase 32% ( p < 0.05). Thus, outcomes study, it is expected controllability, usability, reliability robotic devices

Язык: Английский

---

Motor imagery electroencephalography channel selection based on deep learning: A shallow convolutional neural network

Engineering Applications of Artificial Intelligence, Год журнала: 2024, Номер 136, С. 108879 - 108879

Опубликована: Июнь 27, 2024

Язык: Английский

---