SBSohyeon Bang

Sohyeon Bang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Sohyeon Bang has a total of 4 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Classification of Surface Electromyography Recordings from Young and Older Adults Using CWT Scalograms: A Window-Level Proof-of-Concept Study

    by SoHyeon Bang, JinHyoung Jeong, YuYeon Jung

    Background/Objectives: Age-related changes in skeletal muscle involve alterations in both muscle structure and neuromuscular function. Surface electromyography (sEMG) provides a non-invasive method for assessing muscle electrical activity. This study aimed to investigate whether time–frequency representations of sEMG signals combined with deep learning could classify recordings obtained from healthy young and older adults, without assuming that the discriminative features necessarily reflect age-related neuromuscular changes. Methods: sEMG signals were experimentally collected from 60 healthy adults, including 30 young and 30 older adults. The resulting continuous wavelet transform (CWT) scalogram images were randomly divided into training and test sets at the image-window level using an 80:20 ratio. Consequently, windows from the same participant could appear in both sets. Signals were filtered, segmented into overlapping windows, and converted into CWT scalogram images for classification using ResNet-18. Results: At the window level, the CWT-ResNet model achieved an accuracy of 78.98%, an area under the receiver operating characteristic curve (AUC) of 0.8589, a sensitivity of 71.34%, a specificity of 85.06%, and a balanced accuracy of 78.20%. Muscle-specific analyses showed window-level classification accuracies ranging from 78.57% to 79.89% across all three muscle sites. However, the observed classification performance may have been influenced by differences in movement timing, active and resting periods, anthropometric characteristics, and participant overlap between the training and test sets. These potential influences were not isolated through additional control analyses. Conclusions: CWT-based time–frequency representations of sEMG combined with ResNet-18 demonstrated preliminary feasibility for classifying sEMG recordings obtained from young and older adults under the revised preprocessing and image-window-level evaluation conditions. The findings do not establish that the model specifically detects age-related neuromuscular changes. Participant-independent validation and analyses controlling for task execution and anthropometric characteristics are required.

  • Open Access

    Implementation of a Stress Biomarker and Development of a Deep Neural Network-Based Multi-Mental State Classification Model

    by Sangsik Lee, Jaehyun Jo, Sohyeon Bang, Jinhyoung Jeong

    The purpose of this study was to develop a model capable of predicting stress levels and interpreting the underlying physiological patterns using large-scale, real-life biosignal data. To achieve this, we utilized approximately 137,000 longitudinal measurements voluntarily collected from residents of Sejong Special Self-Governing City over a two-year period (February 2023–December 2024). Based on these data, we constructed a stress prediction framework that integrates both static machine-learning models—such as Random Forest and LightGBM—and time-series deep learning models, including LSTM and Transformer architectures. Model interpretability was further enhanced through SHapley Additive exPlanations (SHAP), which quantified the contribution of key biomarkers, and through visualization of Transformer attention weights to reveal temporal interactions within the biosignal sequences. The central objective of this study was to evaluate how accurately a deep learning model can learn and reproduce stress indices generated by existing heart rate variability (HRV)-based algorithms embedded in K-FDA-approved wearable devices. Accordingly, the ground truth used in this work reflects algorithmic outputs rather than clinically validated assessments such as salivary cortisol or psychological scales. Thus, rather than identifying independent clinical stress markers, the present work focuses on determining whether a Transformer-based model can effectively approximate device-derived physiological stress levels over time, thereby providing a methodological foundation for future applications using clinically validated stress labels. Experimental results demonstrated that the Transformer model achieved approximately 98% classification accuracy across this large dataset, indicating that it successfully captures short-term biosignal fluctuations as well as long-term temporal structure. These findings collectively demonstrate the engineering feasibility of developing a large-scale, wearable-based stress monitoring system.

  • Open Access

    A Study on the Performance Comparison of Brain MRI Image-Based Abnormality Classification Models

    by Jinhyoung Jeong, Sohyeon Bang, Yuyeon Jung, Jaehyun Jo

    We developed a model that classifies normal and abnormal brain MRI images. This study initially referenced a small-scale real patient dataset (98 normal and 155 abnormal MRI images) provided by the National Institute of Aging (NIA) to illustrate the class imbalance challenge. However, all experiments and performance evaluations were conducted on a larger synthetic dataset (10,000 images; 5000 normal and 5000 abnormal) generated from the National Imaging System (NIS/AI Hub). Therefore, while the NIA dataset highlights the limitations of real-world data availability, the reported results are based exclusively on the synthetic dataset. In the preprocessing step, all MRI images were normalized to the same size, and data augmentation techniques such as rotation, translation, and flipping were applied to increase data diversity and reduce overfitting during training. Based on deep learning, we fine-tuned our own CNN model and a ResNet-50 transfer learning model using ImageNet pretrained weights. We also compared the performance of our model with traditional machine learning using SVM (RBF kernel) and random forest classifiers. Experimental results showed that the ResNet-50 transfer learning model achieved the best performance, achieving approximately 95% accuracy and a high F1 score on the test set, while our own CNN also performed well. In contrast, SVM and random forests showed relatively poor performance due to their inability to sufficiently learn the complex characteristics of the images. This study confirmed that deep learning techniques, including transfer learning, achieve excellent brain abnormality detection performance even with limited real-world medical data. These results highlight methodological potential but should be interpreted with caution, as further validation with real-world clinical MRI data is required before clinical applicability can be established.