Dong-Joo Kim

Cheol-Hui Lee, Hwa-Yeon Lee, Dong-Joo Kim

The quality of data augmentation serves as a critical determinant for the performance of contrastive learning in EEG tasks. Although this paradigm is promising for utilizing unlabeled data, static or random augmentation strategies often fail to preserve intrinsic information due to the non-stationarity of EEG signals where statistical properties change over time. To address this, we propose RL-BioAug, a framework that leverages a label-efficient reinforcement learning (RL) agent to autonomously determine optimal augmentation policies. While utilizing only a minimal fraction (10%) of labeled data to guide the agent's policy, our method enables the encoder to learn robust representations in a strictly self-supervised manner. Experimental results demonstrate that RL-BioAug significantly outperforms the random selection strategy, achieving substantial improvements of 9.69% and 8.80% in Macro-F1 score on the Sleep-EDFX and CHB-MIT datasets, respectively. Notably, this agent mainly chose optimal strategies for each task--for example, Time Masking with a 62% probability for sleep stage classification and Crop & Resize with a 77% probability for seizure detection. Our framework suggests its potential to replace conventional heuristic-based augmentations and establish a new autonomous paradigm for data augmentation. The source code is available at https://github.com/dlcjfgmlnasa/RL-BioAug.

Cheol-Hui Lee, Hakseung Kim, Hyun-jee Han et al.

The classification of sleep stages is a pivotal aspect of diagnosing sleep disorders and evaluating sleep quality. However, the conventional manual scoring process, conducted by clinicians, is time-consuming and prone to human bias. Recent advancements in deep learning have substantially propelled the automation of sleep stage classification. Nevertheless, challenges persist, including the need for large datasets with labels and the inherent biases in human-generated annotations. This paper introduces NeuroNet, a self-supervised learning (SSL) framework designed to effectively harness unlabeled single-channel sleep electroencephalogram (EEG) signals by integrating contrastive learning tasks and masked prediction tasks. NeuroNet demonstrates superior performance over existing SSL methodologies through extensive experimentation conducted across three polysomnography (PSG) datasets. Additionally, this study proposes a Mamba-based temporal context module to capture the relationships among diverse EEG epochs. Combining NeuroNet with the Mamba-based temporal context module has demonstrated the capability to achieve, or even surpass, the performance of the latest supervised learning methodologies, even with a limited amount of labeled data. This study is expected to establish a new benchmark in sleep stage classification, promising to guide future research and applications in the field of sleep analysis.

Cheol-Hui Lee, Hakseung Kim, Byung C. Yoon et al.

Sleep is essential for maintaining human health and quality of life. Analyzing physiological signals during sleep is critical in assessing sleep quality and diagnosing sleep disorders. However, manual diagnoses by clinicians are time-intensive and subjective. Despite advances in deep learning that have enhanced automation, these approaches remain heavily dependent on large-scale labeled datasets. This study introduces SynthSleepNet, a multimodal hybrid self-supervised learning framework designed for analyzing polysomnography (PSG) data. SynthSleepNet effectively integrates masked prediction and contrastive learning to leverage complementary features across multiple modalities, including electroencephalogram (EEG), electrooculography (EOG), electromyography (EMG), and electrocardiogram (ECG). This approach enables the model to learn highly expressive representations of PSG data. Furthermore, a temporal context module based on Mamba was developed to efficiently capture contextual information across signals. SynthSleepNet achieved superior performance compared to state-of-the-art methods across three downstream tasks: sleep-stage classification, apnea detection, and hypopnea detection, with accuracies of 89.89%, 99.75%, and 89.60%, respectively. The model demonstrated robust performance in a semi-supervised learning environment with limited labels, achieving accuracies of 87.98%, 99.37%, and 77.52% in the same tasks. These results underscore the potential of the model as a foundational tool for the comprehensive analysis of PSG data. SynthSleepNet demonstrates comprehensively superior performance across multiple downstream tasks compared to other methodologies, making it expected to set a new standard for sleep disorder monitoring and diagnostic systems.

Cheol-Hui Lee, Hwa-Yeon Lee, Min-Kyung Jung et al.

Missing or corrupted modalities are common in physiological signal-based medical applications owing to hardware constraints or motion artifacts. However, most existing methods assume the availability of all modalities, resulting in substantial performance degradation in the absence of any modality. To overcome this limitation, this study proposes PhysioME, a robust framework designed to ensure reliable performance under missing modality conditions. PhysioME adopts: (1) a multimodal self-supervised learning approach that combines contrastive learning with masked prediction; (2) a Dual-PathNeuroNet backbone tailored to capture the temporal dynamics of each physiological signal modality; and (3) a restoration decoder that reconstructs missing modality tokens, enabling flexible processing of incomplete inputs. The experimental results show that PhysioME achieves high consistency and generalization performance across various missing modality scenarios. These findings highlight the potential of PhysioME as a reliable tool for supporting clinical decision-making in real-world settings with imperfect data availability.

Tae-Seong Han, Jae-Wook Heo, Hakseung Kim et al.

Electrocardiography (ECG) signals are frequently degraded by noise, limiting their clinical reliability in both conventional and wearable settings. Existing methods for addressing ECG noise, relying on artifact classification or denoising, are constrained by annotation inconsistencies and poor generalizability. Here, we address these limitations by reframing ECG noise quantification as an anomaly detection task. We propose a diffusion-based framework trained to model the normative distribution of clean ECG signals, identifying deviations as noise without requiring explicit artifact labels. To robustly evaluate performance and mitigate label inconsistencies, we introduce a distribution-based metric using the Wasserstein-1 distance ($W_1$). Our model achieved a macro-average $W_1$ score of 1.308, outperforming the next-best method by over 48\%. External validation confirmed strong generalizability, facilitating the exclusion of noisy segments to improve diagnostic accuracy and support timely clinical intervention. This approach enhances real-time ECG monitoring and broadens ECG applicability in digital health technologies.

Byeong-Hoo Lee, Ji-Hoon Jeong, Kyung-Hwan Shim et al.

Brain-computer interface (BCI) decodes brain signals to understand user intention and status. Because of its simple and safe data acquisition process, electroencephalogram (EEG) is commonly used in non-invasive BCI. One of EEG paradigms, motor imagery (MI) is commonly used for recovery or rehabilitation of motor functions due to its signal origin. However, the EEG signals are an oscillatory and non-stationary signal that makes it difficult to collect and classify MI accurately. In this study, we proposed a band-power feature refining convolutional neural network (BFR-CNN) which is composed of two convolution blocks to achieve high classification accuracy. We collected EEG signals to create MI dataset contained the movement imagination of a single-arm. The proposed model outperforms conventional approaches in 4-class MI tasks classification. Hence, we demonstrate that the decoding of user intention is possible by using only EEG signals with robust performance using BFR-CNN.

Byoung-Hee Kwon, Ji-Hoon Jeong, Dong-Joo Kim

In this study, 3D brain-computer interface (BCI) training platforms were used to stimulate the subjects for visual motion imagery and visual perception. We measured the activation brain region and alpha-band power activity when the subjects perceived and imagined the stimuli. Based on this, 4-class were classified in visual stimuli session and visual motion imagery session respectively. The results showed that the occipital region is involved in visual perception and visual motion imagery, and alpha-band power is increased in visual motion imagery session and decreased in visual motion stimuli session. Compared with the performance of visual motion imagery and motor imagery, visual motion imagery has higher performance than motor imagery. The binary class was classified using one versus rest approach as well as analysis of brain activation to prove that visual-related brain wave signals are meaningful, and the results were significant.

Jeong-Hyun Cho, Ji-Hoon Jeong, Dong-Joo Kim et al.

Developing electroencephalogram (EEG) based brain-computer interface (BCI) systems is challenging. In this study, we analyzed natural grasp actions from EEG. Ten healthy subjects participated in this experiment. They executed and imagined three sustained grasp actions. We proposed a novel approach which estimates muscle activity patterns from EEG signals to improve the overall classification accuracy. For implementation, we have recorded EEG and electromyogram (EMG) simultaneously. Using the similarity of the estimated pattern from EEG signals compare to the activity pattern from EMG signals showed higher classification accuracy than competitive methods. As a result, we obtained the average classification accuracy of 63.89($\pm$7.54)% for actual movement and 46.96($\pm$15.30)% for motor imagery. These are 21.59% and 5.66% higher than the result of the competitive model, respectively. This result is encouraging, and the proposed method could potentially be used in future applications, such as a BCI-driven robot control for handling various daily use objects.