KMITL

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

Browse

Search Results

Now showing 1 - 6 of 6

Some of the metrics are blocked by your
consent settings
EEG-BBNet: A Hybrid Framework for Brain Biometric Using Graph Connectivity
(2025-01-01)
Lakhan, Payongkit
;
Banluesombatkul, Nannapas
;
Sricom, Natchaya
;
Sawangjai, Phattarapong
;
Sangnark, Soravitt
Most EEG-based biometrics rely on either convolutional neural networks (CNNs) or graph convolutional neural networks (GCNNs) for personal authentication, potentially overlooking the limitations of each approach. To address this, we propose EEG-BBNet, a hybrid network that combines CNNs and GCNNs. EEG-BBNet leverages CNN’s capability for automatic feature extraction and the GCNN’s ability to learn connectivity patterns between EEG electrodes through graph representation. We evaluate its performance against solely CNN-based and graph-based models across three brain–computer interface tasks, focusing on daily motor and sensory activities. The results show that while EEG-BBNet with Rho index functional connectivity metric outperforms graph-based models, it initially lags behind CNN-based models. However, with additional fine-tuning, EEG-BBNet surpasses CNN-based models, achieving a correct recognition rate of approximately 90%. This improvement enables EEG-BBNet to adapt its learning in new sessions and to acquire different domain knowledge across various BCI tasks (e.g., motor imagery to steady-state visually evoked potentials), demonstrating promise for practical authentication.
Some of the metrics are blocked by your
consent settings
A Nanopower EEG Low-Pass Filter Using Current-Sharing Vertical Differential Pairs
(2025-01-01)
Pawarangkoon, Prajuab
;
Ahmad, Rafidah
;
Abdullah Zawawi, Ruhaifi
;
Abd Manaf, Asrulnizam
;
Surakampontorn, Wanlop
A follower-based g<inf>m</inf> - C low-pass filter that employs CMOS vertical source-couple-pair (VSCP) transconductors is proposed for practical use in EEG acquisition systems. The VSCP transconductor operates as a g<inf>m</inf> cell with current sharing and linearity enhancement features. It is applied in the first- and second-order g<inf>m</inf> - C sections cascaded to form a third-order low-pass filter targeting a 150-Hz bandwidth. To mitigate the effects of biasing current source mismatch, dynamic element matching (DEM) is optionally applied to the relevant biasing current source pairs, resulting in second harmonic distortion (HD2) and noise suppression. Implemented in a 0.18-µm process, the proposed filter consumes 16.3-nW power from a 1.2-V supply. Thanks to the DEM and VSCPs, the filter achieves a 150-mV<inf>P</inf> linear input range [measured at 1% total harmonic distortion (THD)], whereas the input-referred noise of 43 µV<inf>rms</inf> is obtained leading to a filter dynamic range (DR) of 65.15 dB. Overall performance comparisons with other recent nanopower filters indicate that the figure of merit (FoM) of this proposed filter is comparable, while the linear input range is larger.
Some of the metrics are blocked by your
consent settings
Hand Movement Classification Base on EEG Signals using Deep Learning and Dimensional Reduction Technique
(2019-11-01)
Boonme, Phattraporn
;
Thongserm, Petchanon
;
Arunsuriyasak, Peerachai
;
Phasukkit, Pattarapong
This research is presented the bio-signal activities of arm movements by using deep learning for classification between right-arm and left-arm. It's well-known that Electroencephalography (EEG) shows neural oscillation behaviors in electrical voltage form. Also, Brain-Computer Interface (BCI) is direct communication between neural oscillation and computer to control machines without physical movements. So, this paper aims to present the classification method of EEG signals data to develop a BCI in the future. By using deep learning to classification data is classified into raise the right arm, raise the left arm. And decrease EEG signal data by using Principal Component Analysis (PCA). PCA can reduce the data size of EEG signal from 1000x28 to 28x28. Experimental result of classification has accuracy 90.86% and 94.71%
Some of the metrics are blocked by your
consent settings
Stress and office-syndrome detection using EEG, HRV and hand movement
(2017-02-21)
Reanaree, Parkbhum
;
Tananchana, Polachet
;
Narongwongwathana, Worapong
;
Pintavirooj, Chuchart
Stress and Office syndrome are a serious problem that affects a large number of people and tend to develop health problems that can interfere with work and quality of life. In fact, the Institute reports that up to 90 percent clinical studies have shown that stress and office syndrome are a major cause of cardiovascular disease, depression, suicide and substance abuse. Treatment's cost are more than ten million baht each year in healthcare expenses. According to these problems we designed to use wearable technology which can be tracked and managed to helping them reduce their problems. Low-cost single dry-sensor EEG Neurosky headset and intelligent watch made by Arduino was used in this project. The EEG signal, hear rate variation and hand movement are analyzed to indicate stress level and the Office syndrome can be detected by intelligent watch. The goals of this research is to detect stress and Office syndrome and reduce chance to be the diseases.
Some of the metrics are blocked by your
consent settings
Regularizing multi-bands Common Spatial Patterns (RMCSP): A data processing method for brain-computer interface
(2015-05-13)
Thang, Le Quoc
;
Temiyasathit, Chivalai
In this paper, we propose a novel approach which is called the Regularizing Multi-bands Common Spatial Patterns (RMCSP) that particularly used for processing motor-imagery based Electroencephalography (EEG) data in Brain-computer Interface (BCI). The usage of BCI is severely limited due to the inconvenience of large number of channels used in recording devices. Moreover, Common Spatial Patterns (CSP) is a very well-known algorithm for its efficiency, but it just can extract the spatial information of the brain signals. To address these issues, we introduce the RMCSP method that exploits data in spectral, temporal and spatial domains in order to increase the classification accuracy in BCI. In addition, RMCSP is designed to handle EEG with small number of channels. To verify the efficacy of our approach, we rigorously tested the performances of the method in 17 subjects, from BCI competition datasets, in both two-class and four-class problems. Results show that RMCSP approach can outperform normal CSP method by nearly 10% in terms of median classification accuracy. It also enables us to significantly reduce the number of channels used in the datasets without decreasing the performances of the subjects.
Some of the metrics are blocked by your
consent settings
Frequency component analysis of eeg recording on various visual tasks: Steady-state visual evoked potential experiment
(2015-02-27)
Inkaew, Narongrit
;
Charoenkitkamjorn, Nattaphon
;
Yangpaiboon, Chongkon
;
Phothisonothai, Montri
;
Nuthong, Chaiwat
Nowadays, steady-state visual evoked potential (SSVEP) is ongoing in many research topics. It also plays an important role in the response to various visual stimuli such as flickering rate (F), intensity (I), and duty cycle (D). The SSVEPs are practical and useful in research because of its excellent signal-to-noise ratio and relative immunity to artifacts. The application of using SSVEP-based system has been widely succeeded in many disciplines. In this paper, we investigate SSVEP corresponding to the different visual stimulation in terms of frequency component analysis in the four principal frequency bands, i.e., delta (0.1-3.5 Hz), theta (4.0-7.5 Hz), alpha (8.0-13.0 Hz), and beta (14.0-30.0 Hz). Subjects were instructed to fixate LED light source then record associated SSVEP waveform. The variation in displaying of the presentation stimuli during a task was examined. Experimental results showed that the major frequency distribution has been found in theta and alpha bands.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results