Dong-Ok Won

Prof. Dr. Dong-Ok Won

orcid

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 May 2018 in IEEE Transactions on Neural Systems and Rehabilitation Engineering
Verified
Journal Article
Open access
MLMinho Lee
Minho Lee
JWJohn Williamson
John Williamson
DWDong-Ok Won
Dong-Ok Won
SFSiamac Fazli
Siamac Fazli
SLSeong-Whan Lee
Seong-Whan Lee
In this paper, we propose a highly accurate and fast spelling system that employs multi-modal electroencephalography-electrooculography (EEG-EOG) signals and visual feedback technology. Over the last 20 years, various types of speller systems have been developed in brain-computer interface (BCI) and EOG/eye-tracking research; however, these conventional systems have a tradeoff between the spelling accuracy (or decoding) and typing speed. Healthy users and physically challenged participants, in particular, may become exhausted quickly; thus, there is a need for a speller system with fast typing speed while retaining a high level of spelling accuracy. In this study we propose the first hybrid speller system that combines EEG and EOG signals with visual feedback technology so that the user and the speller system can act cooperatively for optimal decision-making. The proposed spelling system consists of a classic row-column event-related potential (ERP) speller, an EOG command detector, as well as visual feedback modules. First, the online ERP speller calculates classification probabilities for all candidate characters from the EEG epochs. Second, characters are sorted by their probability, and the characters with the highest probabilities are highlighted as visual feedback within the row-column spelling layout. Finally, the user can actively select the character as the target by generating an EOG command. The proposed system shows 97.6% spelling accuracy and an information transfer rate of 39.6 (±13.2) [bits/min] across twenty participants. In our extended experiment, we redesigned the visual feedback and minimized the number of channels (4 channels) in order to enhance the speller performance and increase usability. Most importantly, a new weighted strategy resulted in 100% accuracy and a 57.8 (±23.6) [bits/min] information transfer rate (ITR) across six participants. This study demonstrates that the proposed system can provide a reliable communication channel for practical speller applications and may be used to supplement existing systems.

22 December 2015 in Journal of Neural Engineering
Verified
Journal Article
Closed access
PDF file
DWDong-Ok Won
Dong-Ok Won
HHHan-Jeong Hwang
Han-Jeong Hwang
SDSven Dähne
Sven Dähne
KMKlaus-Robert Müller
Klaus-Robert Müller
SLSeong-Whan Lee
Seong-Whan Lee
Objective. Most existing brain–computer interface (BCI) designs based on steady-state visual evoked potentials (SSVEPs) primarily use low frequency visual stimuli (e.g., <20 Hz) to elicit relatively high SSVEP amplitudes. While low frequency stimuli could evoke photosensitivity-based epileptic seizures, high frequency stimuli generally show less visual fatigue and no stimulus-related seizures. The fundamental objective of this study was to investigate the effect of stimulation frequency and duty-cycle on the usability of an SSVEP-based BCI system. Approach. We developed an SSVEP-based BCI speller using multiple LEDs flickering with low frequencies (6–14.9 Hz) with a duty-cycle of 50%, or higher frequencies (26–34.7 Hz) with duty-cycles of 50%, 60%, and 70%. The four different experimental conditions were tested with 26 subjects in order to investigate the impact of stimulation frequency and duty-cycle on performance and visual fatigue, and evaluated with a questionnaire survey. Resting state alpha powers were utilized to interpret our results from the neurophysiological point of view. Main results. The stimulation method employing higher frequencies not only showed less visual fatigue, but it also showed higher and more stable classification performance compared to that employing relatively lower frequencies. Different duty-cycles in the higher frequency stimulation conditions did not significantly affect visual fatigue, but a duty-cycle of 50% was a better choice with respect to performance. The performance of the higher frequency stimulation method was also less susceptible to resting state alpha powers, while that of the lower frequency stimulation method was negatively correlated with alpha powers. Significance. These results suggest that the use of higher frequency visual stimuli is more beneficial for performance improvement and stability as time passes when developing practical SSVEP-based BCI applications.

11 August 2017 in IEEE Transactions on Neural Systems and Rehabilitation Engineering
Verified
Journal Article
Open access
DWDong-Ok Won
Dong-Ok Won
Han-Jeong HwangHan-Jeong Hwang
Han-Jeong Hwang
DKDong-Min Kim
Dong-Min Kim
KMKlaus-Robert Muller
Klaus-Robert Muller
SLSeong-Whan Lee
Seong-Whan Lee
Most event-related potential (ERP)-based braincomputer interface (BCI) spellers primarily use matrix layouts, and generally require moderate eye movement for successful operation. The fundamental objective of this study is to enhance the perceptibility of target characters by introducing motion stimuli to classical rapid serial visual presentation (RSVP) spellers that do not require any eye movement, thereby applying them to paralyzed patients with oculomotor dysfunctions. To test the feasibility of the proposed motion-based RSVP paradigm, we implemented three RSVP spellers: i) fixed-direction motion (FM-RSVP), ii) random-direction motion (RM-RSVP), and iii) (the conventional) non-motion stimulation (NM-RSVP), and evaluated the effect of the three different stimulation methods on spelling performance. The two motion-based stimulation methods, FM- and RM-RSVP, showed shorter P300 latency and higher P300 amplitudes (i. e., 360.4-379.6 ms; 5.5867-5.7662 mV) than the NM-RSVP (i. e., 480.4 ms; 4.7426 mV). This led to higher and more stable performances for FM- and RMRSVP spellers than NM-RSVP speller (i. e., 79.06±6.45% for NM-RSVP, 90.60±2.98% for RM-RSVP, and 92.74±2.55% for FM-RSVP). In particular, the proposed motion-based RSVP paradigm was significantly beneficial for about half of the subjects who might not accurately perceive rapidly presented static stimuli. These results indicate that the use of proposed motion-based RSVP paradigm is more beneficial for target recognition when developing BCI applications for severely paralyzed patients with complex ocular dysfunctions.

30 September 2020 in Science Robotics
Verified
Journal Article
Closed access
DWDong-Ok Won
Dong-Ok Won
KMKlaus-Robert Müller
Klaus-Robert Müller
SLSeong-Whan Lee
Seong-Whan Lee
An AI curling robot can compete and win against top-ranked human teams in the game of curling.

1 January 2021 in Computational Intelligence and Neuroscience
Verified
Journal Article
Open access
PDF file
SPSUNIL KUMAR PRABHAKAR
SUNIL KUMAR PRABHAKAR
DWDong-Ok Won
Dong-Ok Won
To unlock information present in clinical description, automatic medical text classification is highly useful in the arena of natural language processing (NLP). For medical text classification tasks, machine learning techniques seem to be quite effective; however, it requires extensive effort from human side, so that the labeled training data can be created. For clinical and translational research, a huge quantity of detailed patient information, such as disease status, lab tests, medication history, side effects, and treatment outcomes, has been collected in an electronic format, and it serves as a valuable data source for further analysis. Therefore, a huge quantity of detailed patient information is present in the medical text, and it is quite a huge challenge to process it efficiently. In this work, a medical text classification paradigm, using two novel deep learning architectures, is proposed to mitigate the human efforts. The first approach is that a quad channel hybrid long short‐term memory (QC‐LSTM) deep learning model is implemented utilizing four channels, and the second approach is that a hybrid bidirectional gated recurrent unit (BiGRU) deep learning model with multihead attention is developed and implemented successfully. The proposed methodology is validated on two medical text datasets, and a comprehensive analysis is conducted. The best results in terms of classification accuracy of 96.72% is obtained with the proposed QC‐LSTM deep learning model, and a classification accuracy of 95.76% is obtained with the proposed hybrid BiGRU deep learning model.

3 May 2022 in IEEE Transactions on Emerging Topics in Computing
Verified
Journal Article
Open access
DWDong-Ok Won
Dong-Ok Won
YJYong-Nam Jang
Yong-Nam Jang
SLSeong-Whan Lee
Seong-Whan Lee
Zero-day malicious software (malware) refers to a previously unknown or newly discovered software vulnerability. The fundamental objective of this paper is to enhance detection for analogous zero-day malware by efficient learning to plausible generated data. To detect zero-day malware, we proposed a malware training framework based on the generated analogous malware data using generative adversarial networks (PlausMal-GAN). Thus, the PlausMal-GAN can suitably produce analogous zero-day malware images with high quality and high diversity from the existing malware data. The discriminator, as a detector, learns various malware features using both real and generated malware images. In terms of performance, the proposed framework showed higher and more stable performances for the analogous zero-day malware images, which can be assumed to be analogous zero-day malware data. We obtained reliable accuracy performances in the proposed PlausMal-GAN framework with representative GAN models (i.e., deep convolutional GAN, least-squares GAN, Wasserstein GAN with gradient penalty, and evolutionary GAN). These results indicate that the use of the proposed framework is beneficial for the detection and prediction of numerous and analogous zero-day malware data from noted malware when developing and updating malware detection systems.