KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Search Results

Now showing 1 - 7 of 7

Some of the metrics are blocked by your
consent settings
PSD-EEGRepNet: A CNN Architecture with Multi-Branch RepBlocks for Power Spectral Density-Based Motor Imagery EEG Classification in BCI
(2025-01-01)
Thangthong, Kantham
;
Asadi, Fawad
;
Tungjitkusolmun, Supan
Motor Imagery (MI) based Brain-Computer Interfaces (BCIs) utilizing electroencephalography (EEG) offer significant potential, yet progress can be hindered by the computational demands of deep learning classifiers. This study introduces and evaluates a novel lightweight, multi-branch Convolutional Neural Network (CNN), inspired by efficient design principles, specifically for classifying MI tasks from Power Spectral Density (PSD) EEG features. Our objective was to achieve strong classification performance coupled with favorable development phase computational characteristics. Evaluated on 10 subjects from a public PhysioNet dataset using 5-fold cross-validation and two data overlap conditions (80%, 90%), the proposed model (~6.32M parameters, ~20 MFLOPs) demonstrated high mean classification accuracies (80.38% for 80% overlap, 85.69% for 90% overlap) and efficient training times (avg. 8.8s and 20.4s per fold, respectively). While performance scaled positively with data augmentation, inter-subject variability was noted. We conclude that the proposed architecture effectively balances high accuracy with significant offline computational efficiency offering a valuable tool for BCI research and a promising foundation for developing practical MI-BCI systems.
Some of the metrics are blocked by your
consent settings
Alleviating Chronic Stress in University Students: An EEG Analysis of Binaural Beat Therapy
(2025-01-01)
Aunchit, Sasithon
;
Angsuwatanakul, Thanate
;
Phairot, Ekkapon
;
Jinawan, Chulikon
;
Sirirattanapan, Boonrut
The COVID-19 pandemic has significantly elevated chronic stress levels, especially among university students. This study examined the effectiveness of binaural beat auditory stimulation in reducing chronic stress, using both the DASS-21 questionnaire and electroencephalography (EEG) as measurement tools. Six students identified with high stress were randomly assigned to one of three four-week interventions: alpha binaural beat music, beta binaural beat music, or non-binaural beat control music. EEG analysis revealed a general increase in power spectrum across all groups, indicating changes in brainwave activity. Notably, a significant increase in sample entropy—a measure of neural complexity—was observed exclusively in the alpha binaural beat group by week four. Correspondingly, this group showed the greatest reduction in self-reported DASS-21 stress scores. These findings suggest that alpha binaural beat stimulation promotes effective neural entrainment and is more successful than beta or non-binaural beat stimuli in alleviating chronic stress among university students. This study highlights the potential of binaural beat auditory stimulation as a non-invasive tool for improving mental health.
Some of the metrics are blocked by your
consent settings
Common Spatial Pattern Variants for Feature Extraction in Multi-Class Motor Imagery BCI
(2025-01-01)
Asadi, Fawad
;
Thangthong, Kantham
;
Tungjitkusolmun, Supan
Brain-Computer Interfaces (BCIs) based on Motor Imagery (MI) offer intuitive control but face challenges due to noisy electroencephalography (EEG) signals that often contain artifacts, necessitating effective feature extraction. Common Spatial Pattern (CSP) is a standard technique, yet its limitations in multi-class MI scenarios motivate various extensions. This paper investigates the classification performance, computational cost, and the crucial performance versus cost trade-off inherent in practical BCI applications of five prominent CSP variants, including standard CSP, Regularized CSP (RCSP), Filter Bank CSP (FBCSP), Sparse CSP, and Kernel CSP, when applied to multi-class MI classification. Using the PhysioNet MI dataset, we employed a consistent preprocessing pipeline (18 sensorimotor channels, filtering, epoching) and evaluated each variant by feeding extracted features into a Support Vector Machine (SVM) classifier with an RBF kernel. The evaluation revealed that standard CSP and RCSP achieved the highest peak average accuracy (~97.8%) with near-efficient computational cost. FBCSP yielded high accuracy (~96.7%) but incurred the highest computational cost. Sparse CSP was computationally efficient but achieved lower peak accuracy (~95.3%), while Kernel CSP showed the lowest peak accuracy (~92.8%) at moderate cost. The findings highlight the performance profiles and efficiency of these CSP methods for this multi-class MI task, indicating that standard CSP and RCSP offer a particularly effective combination of high accuracy and manageable computational load under the evaluated conditions.
Some of the metrics are blocked by your
consent settings
Localized estimation of event-related neural source activity from simultaneous MEG-EEG with a recurrent neural network
(2024-12-01)
O'Reilly, Jamie A.
;
Zhu, Judy D.
;
Sowman, Paul F.
Estimating intracranial current sources underlying the electromagnetic signals observed from extracranial sensors is a perennial challenge in non-invasive neuroimaging. Established solutions to this inverse problem treat time samples independently without considering the temporal dynamics of event-related brain processes. This paper describes current source estimation from simultaneously recorded magneto- and electro-encephalography (MEEG) using a recurrent neural network (RNN) that learns sequential relationships from neural data. The RNN was trained in two phases: (1) pre-training and (2) transfer learning with L1 regularization applied to the source estimation layer. Performance of using scaled labels derived from MEEG, magnetoencephalography (MEG), or electroencephalography (EEG) were compared, as were results from volumetric source space with free dipole orientation and surface source space with fixed dipole orientation. Exact low-resolution electromagnetic tomography (eLORETA) and mixed-norm L1/L2 (MxNE) source estimation methods were also applied to these data for comparison with the RNN method. The RNN approach outperformed other methods in terms of output signal-to-noise ratio, correlation and mean-squared error metrics evaluated against reference event-related field (ERF) and event-related potential (ERP) waveforms. Using MEEG labels with fixed-orientation surface sources produced the most consistent estimates. To estimate sources of ERF and ERP waveforms, the RNN generates temporal dynamics within its internal computational units, driven by sequential structure in neural data used as training labels. It thus provides a data-driven model of computational transformations from psychophysiological events into corresponding event-related neural signals, which is unique among MEEG source reconstruction solutions.
Some of the metrics are blocked by your
consent settings
Brain Function Analysis Using EEG Evidence: New Insights into English Paper-Based Versus Computer-Based Tests
(2024-01-01)
Khemanuwong, Thapanee
;
Angsuwatanakul, Thanate
;
Phairot, Ekkapon
;
Iramina, Keiji
;
Puttasakul, Tasawan
In today's disruptive era, where digital systems and the internet are central, assessment methods are transitioning from paper-based to computer-based tests. As digital technology becomes more accessible, there is growing interest in determining whether these new formats provide more effective means of evaluating learning outcomes. To investigate this, we examined performance and objective measures of brain function during both computer-based and paper-based reading comprehension tests. This study focuses on brain function analysis of computer-based and paper-based tests measured by EEG signals. Five healthy students at the Bl CEFR level voluntarily participated in two experimental conditions: paper-based testing (PBT) and computer-based testing (CBT). During the tests, EEG signals were recorded and analyzed using MATLAB to identify various features of brain activity. The results indicate that participants who performed better on paper-based tests showed greater familiarity with the test format. The power spectral density of EEG recordings, along with the average frequency of alpha and beta waves, were positively correlated with test familiarity. Specifically, the correlation coefficients were as follows: CBT-difficult (r=0.82, p < 0.05), CBT -easy (r=0.82,p < 0.05), PBT -difficult (r=0.82, p < 0.05), and PBT -easy (r=0.65,p < 0.05).
Some of the metrics are blocked by your
consent settings
DETECTION OF DRIVER DROWSINESS FROM EEG SIGNALS USING WEARABLE BRAIN SENSING HEADBAND
(2021-05-31)
Chan, Khune Satt Nyein
;
Srisurangkul, C.
;
Depaiwa, N.
;
Pangkreung, S.
Driver drowsiness detection plays an important role in the field of road safety and advanced driver assistance system. Electroencephalogram (EEG) signals are one of the most accurate and reliable indicators of fatigue and drowsiness but in the case of detecting drowsiness, its medical graded measuring system can be intrusive to the driver. The purpose of this research is to test the feasibility and usability of the consumer graded EEG sensor to use in a driver drowsiness detection system. The experiment was carried out by using MUSE S brain sensing headband. Fast Fourier Transform (FFT) method was used to extract features from EEG signals. The extracted feature data are then used to build two classification model, the Support Vector Machine (SVM) and Artificial Neural Network (ANN). The detection of drowsiness is the binary classification task which is to classify between drowsy epochs and alert epochs. In the case of detecting only drowsy epochs, the SVM model detected 82.7% of the drowsy epochs which was better than the ANN model which can only detect 81.25% of the drowsy epochs. But in the detection of both drowsy and alert epochs, the ANN model performed better than that of SVM. The SVM model was tested with different kernel function and Fine Gaussian SVM model showed the highest accuracy of 87.8%. The ANN model performed slightly higher than the SVM model with an accuracy of 87.9%. The ability of consumer graded EEG sensor to use in drowsiness detection system was validated in this research.
Some of the metrics are blocked by your
consent settings
Investigation of regularization theory for four-class classification in brain-computer interface
(2014-01-01)
Thang, Le Quoc
;
Temiyasathit, Chivalai
Common spatial patterns (CSP) is one of the most prevalent feature extraction approaches that has been used in Brain-computer interfaces (BCI) due to its simplicity and efficiency. Nevertheless, CSP suffers from the problems of sensitivity to noise and overfitting. To overcome these issues, the regularized CSP (RCSP) has been proposed recently. In addition, CSP was originally designed for two-class classification. However, a practical BCI usually needs four-class commands to be able to operate. Thus, there is a high demand for increasing the performance of multi-class BCI. In this paper, we provide a complete study of classification accuracy in multi-class BCI using regularization theory, and compare it with the standard CSP to determine the suitable method for feature extraction in BCI learning. Besides CSP, linear discriminant analysis (LDA) has shown its robust and widespread use for machine learning in BCI. LDA estimates covariance matrices from extracted features. But for high-dimensional features with only a small amount of training data given, the estimation may become imprecise. In the attempt of clarifying the regularizing effects in BCI, this paper also provides the classification results of the regularized LDA (RLDA). The performance evaluation of this work was taken on data from 9 subjects, from BCI competition datasets. Results show that the combination of standard CSP and LDA has a slightly better accuracy than the regularizing methods.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results