arXiv subjects

Ki H. Chon

Publications and source records attributed to Ki H. Chon.

9 recordsLinked to original sources

arXiv2026

A New Approach to Characterize Dynamics of ECG-Derived Skin Nerve Activity via Time-Varying Spectral Analysis

Assessment of the sympathetic nervous system (SNS) is one of the major approaches for studying affective states. Skin nerve activity (SKNA) derived from high-frequency components of electrocardiogram (ECG) signals has been a promising surrogate for assessing the SNS. However, current SKNA analysis tools have shown high variability across study protocols and experiments. Hence, we propose a time-varying spectral approach based on SKNA to assess the SNS with higher sensitivity and reliability. We collected ECG signals at a sampling frequency of 10 kHz from sixteen participants who underwent various SNS stimulations. Our spectral analysis revealed that frequency bands between 150 - 1,000 Hz showed significant increases in power during SNS stimulations. Using this information, we developed a time-varying index of sympathetic function measurement based on SKNA, termed Time-Varying Skin Nerve Activity (TVSKNA). TVSKNA is calculated in three steps: time-frequency decomposition, reconstruction using selected frequency bands, and smoothing. TVSKNA indices exhibited generally higher Youden's J, balanced accuracy, and area under the receiver operating characteristic curve, indicating higher sensitivity. The coefficient of variance was lower with TVSKNA indices for most SNS tasks. TVSKNA can serve as a highly sensitive and reliable marker of quantitative assessment of sympathetic function, especially during emotion and stress.

eess.SP↗

arXiv2026

AF-Mamba: Efficient Long-Term Signal Modeling for Early Prediction of Atrial Fibrillation Onset

Atrial fibrillation (AF) is the most common cardiac arrhythmia and is associated with increased risks of stroke and heart failure. The growing availability of wearable and portable ECG monitoring enables continuous assessment of cardiac rhythm outside clinical settings. Predicting AF before its onset could provide additional lead time for timely clinical assessment and potentially improve the management of patients at risk of AF-related complications. This study focuses on predicting AF onset one hour in advance using long-term RR intervals (RRIs). To address this challenge, we propose a deep learning architecture that integrates temporal convolutional networks (TCNs) for local features encoding with Mamba, a selective state-space model capable of long-range sequence modeling. This hybrid TCN-Mamba design enables efficient training and inference on one-hour input windows, overcoming limitations of Transformers' quadratic scaling and recurrent networks' vanishing gradients. In subject-wise 5-fold testing, the proposed model achieved a sensitivity of 0.889, specificity of 0.943, F1-score of 0.813, AUROC of 0.974, and AUPRC of 0.933. In paired cross-dataset holdout evaluation, AF-Mamba maintained discriminative performance across unseen AF and NSR datasets, achieving a mean AUROC of 0.897. Compared against state-of-the-art AF prediction models and general time-series models, AF-Mamba achieved competitive predictive performance while providing a favorable performance-efficiency trade-off for long RRI sequences. These findings demonstrate the potential of AF-Mamba for accurate AF prediction one hour in advance and real-time continuous ambulatory monitoring.

cs.LG↗

arXiv2026

Memory-Efficient EDA Denoising via Knowledge Distillation for Wearable IoT Under Severe Motion Artifacts and Underwater Conditions

Electrodermal activity (EDA) is widely used in wearable Internet of Medical Things (IoMT) systems for continuous health monitoring, including autonomic assessment. However, EDA signals are highly vulnerable to motion artifacts and environmental noise, limiting reliable deployment in harsh operating conditions such as underwater. This study proposes a robust, deployable EDA denoising framework that generalizes across multiple measurement locations and harsh environments. The framework integrates a hybrid CNN-Transformer teacher model with a lightweight depth-wise separable CNN student model via a knowledge distillation (KD) strategy. To further improve robustness, a realistic data augmentation scheme is introduced to simulate diverse motion artifacts and environmental distortions. The KD-based student model significantly reduces model size (7.87 MB to 0.51 MB) and computational cost (105.1M to 11.61M FLOPs) while maintaining denoising performance (MAE: 0.144, SNR improvement: 12.08 dB) using the public dataset validation. In real-world underwater conditions (UMAC dataset) testing, the proposed method substantially improves skin conductance response reconstruction, reducing mean absolute error from 2.809 to 0.215. Furthermore, on independent testing using the CNS-OT dataset, the denoised signals enhanced downstream CNS-OT prediction performance, achieving the highest AUROC (0.806) compared to prior denoising methods. The proposed method also improved the early prediction rate (sensitivity) from 0.550 to 0.767, enabling CNS-OT prediction up to a median of 6.9 minutes before symptom onset. These results demonstrate that the proposed framework not only improves EDA signal quality but also enhances clinically relevant prediction performance while remaining suitable for deployment in resource-constrained wearable Internet of Things systems operating in harsh environments.

eess.SP↗

arXiv2026

ospEDA: Orthogonal Subspace Projection for Electrodermal Activity Decomposition

Electrodermal activity (EDA) is a widely used physiological signal for assessing sympathetic nervous activity, such as arousal, stress, and pain. However, reliable decomposition into tonic and phasic components remains challenging, particularly in noisy environments and across individuals with varying signal morphologies and stimulus responses. We propose ospEDA, a novel Orthogonal Subspace Projection (OSP) based method for EDA decomposition. The method integrates (1) tonic estimation via physiologically motivated valley detection for noise robustness; (2) phasic extraction using OSP to accommodate inter subject variability; and (3) phasic driver estimation through non-negative least squares (NNLS) deconvolution with ridge regularization. We evaluated ospEDA on five real-world datasets and one simulated EDA dataset with ground-truth components, comparing its performance against six existing methods. In simulations with a 20 dB signal to noise ratio (SNR), ospEDA achieved the lowest root mean square error (RMSE) for estimated tonic (0.131) and phasic (0.132) components. Under noisier conditions (10 dB SNR), it maintained superior phasic RMSE (0.293), Pearson correlation (0.782), and R^2 (0.979) values. Furthermore, ospEDA consistently provided the highest F1 scores (0.573, 0.617, 0.638) for sympathetic nerve activity detection across 10, 20, and 30 dB SNR levels, respectively, compared to existing methods. On the real world datasets, ospEDA achieved a stimulus classification AUROC of 0.766 and consistently maintained strong effect sizes (ω^2>0.14) across all five datasets. Overall, ospEDA represents a promising framework for EDA decomposition, showing generally consistent performance and reliable phasic driver estimation under the varying noise conditions, with potential utility for real world physiological monitoring applications.

eess.SP↗

arXiv2025

Lightweight Deep Autoencoder for ECG Denoising with Morphology Preservation and Near Real-Time Hardware Deployment

Electrocardiogram (ECG) signals are often degraded by various noise sources such as baseline wander, motion artifacts, and electromyographic interference, posing a major challenge in clinical settings. This paper presents a lightweight deep learning-based denoising framework, forming a compact autoencoder architecture. The model was trained under severe noise conditions (-5 dB signal-to-noise ratio (SNR)) using a rigorously partitioned dataset to ensure no data leakage and robust generalization. Extensive evaluations were conducted across seven noise configurations and three SNR levels (-5 dB, 0 dB, and +5 dB), showing consistent denoising performance with minimal morphological distortion, critical for maintaining diagnostic integrity. In particular, tests on clinically vital rhythms such as ventricular tachycardia (VT) and ventricular fibrillation (VF) confirm that the proposed model effectively suppresses noise without altering arrhythmic features essential for diagnosis. Visual and quantitative assessments, including SNR improvement, RMSE, and correlation metrics, validate the model's efficacy in preserving waveform fidelity. To demonstrate real-world applicability, the model was deployed on a Raspberry Pi 4 using TensorFlow Lite with float16 precision. Inference latency was measured at just 1.41 seconds per 14-second ECG segment, indicating feasibility for near-real-time use in edge devices. Overall, this study introduces a lightweight, hardware-validated, and morphologically reliable ECG denoising solution suitable for integration into portable or wearable healthcare systems.

eess.SP↗

arXiv2025

Atrial Fibrillation Prediction Using a Lightweight Temporal Convolutional and Selective State Space Architecture

Atrial fibrillation (AF) is the most common arrhythmia, increasing the risk of stroke, heart failure, and other cardiovascular complications. While AF detection algorithms perform well in identifying persistent AF, early-stage progression, such as paroxysmal AF (PAF), often goes undetected due to its sudden onset and short duration. However, undetected PAF can progress into sustained AF, increasing the risk of mortality and severe complications. Early prediction of AF offers an opportunity to reduce disease progression through preventive therapies, such as catecholamine-sparing agents or beta-blockers. In this study, we propose a lightweight deep learning model using only RR Intervals (RRIs), combining a Temporal Convolutional Network (TCN) for positional encoding with Mamba, a selective state space model, to enable early prediction of AF through efficient parallel sequence modeling. In subject-wise testing results, our model achieved a sensitivity of 0.908, specificity of 0.933, F1-score of 0.930, AUROC of 0.972, and AUPRC of 0.932. Additionally, our method demonstrates high computational efficiency, with only 73.5 thousand parameters and 38.3 MFLOPs, outperforming traditional Convolutional Neural Network-Recurrent Neural Network (CNN-RNN) approaches in both accuracy and model compactness. Notably, the model can predict AF up to two hours in advance using just 30 minutes of input data, providing enough lead time for preventive interventions.

cs.LG↗

arXiv2024

Skin Sympathetic Nerve Activity Driver Extraction through Non-Negative Sparse Decomposition

In recent years, skin sympathetic nerve activity (SKNA) extracted from electrocardiogram has gained attention as a novel noninvasive measure of the sympathetic nervous system (SNS), while electrodermal activity (EDA) has long served this purpose. SparsEDA is a sparse deconvolution technique originally developed for EDA to extract phasic drivers indicating the start of sympathetic burst responses. Our focus is on applying this method to preprocessed SKNA signals, justified by both SKNA and EDA signals' connection to sympathetic nerve activity and prior observed similarities. In a thermal-grill pain experiment, 16 subjects underwent six stimulations each to elicit SNS responses, with simultaneous recording of EDA and SKNA. We confirmed the method's accuracy in identifying stimuli initiation. Results were assessed for burst detection and accuracy of driver placement compared to annotated labels. The SKNA drivers achieved an RMSE of 0.42 from annotated stimulations, a 97% hit rate in detecting applied stimuli, and minimal false alarms during the 2-minute control period and interstimulus intervals.

q-bio.NC↗

arXiv2024

Towards Continuous Skin Sympathetic Nerve Activity Monitoring: Removing Muscle Noise

Continuous monitoring of non-invasive skin sympathetic nerve activity (SKNA) holds promise for understanding the sympathetic nervous system (SNS) dynamics in various physiological and pathological conditions. However, muscle noise artifacts present a challenge in accurate SKNA analysis, particularly in real-life scenarios. This study proposes a deep convolutional neural network (CNN) approach to detect and remove muscle noise from SKNA recordings obtained via ECG electrodes. Twelve healthy participants underwent controlled experimental protocols involving cognitive stress induction and voluntary muscle movements, while collecting SKNA data. Power spectral analysis revealed significant muscle noise interference within the SKNA frequency band (500-1000 Hz). A 2D CNN model was trained on the spectrograms of the data segments to classify them into baseline, stress-induced SKNA, and muscle noise-contaminated periods, achieving an average accuracy of 89.85% across all subjects. Our findings underscore the importance of addressing muscle noise for accurate SKNA monitoring, advancing towards wearable SKNA sensors for real-world applications.

cs.LG↗

arXiv2024

Multiclass Arrhythmia Classification using Smartwatch Photoplethysmography Signals Collected in Real-life Settings

Most deep learning models of multiclass arrhythmia classification are tested on fingertip photoplethysmographic (PPG) data, which has higher signal-to-noise ratios compared to smartwatch-derived PPG, and the best reported sensitivity value for premature atrial/ventricular contraction (PAC/PVC) detection is only 75%. To improve upon PAC/PVC detection sensitivity while maintaining high AF detection, we use multi-modal data which incorporates 1D PPG, accelerometers, and heart rate data as the inputs to a computationally efficient 1D bi-directional Gated Recurrent Unit (1D-Bi-GRU) model to detect three arrhythmia classes. We used motion-artifact prone smartwatch PPG data from the NIH-funded Pulsewatch clinical trial. Our multimodal model tested on 72 subjects achieved an unprecedented 83% sensitivity for PAC/PVC detection while maintaining a high accuracy of 97.31% for AF detection. These results outperformed the best state-of-the-art model by 20.81% for PAC/PVC and 2.55% for AF detection even while our model was computationally more efficient (14 times lighter and 2.7 faster).

eess.SP↗