WLWon Hee Lee

Won Hee Lee

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Won Hee Lee has a total of 31 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • The Diagnosis Method of Major Depressive Disorder Using Wavelet Coherence and State-Pathology Separation Network

    by Guangming Wang, Yi Tao, Ning Wu, Rihui Li, Won Hee Lee, Zehong Cao, Xiangguo Yan, Badong Chen, Gang Wang

    Major depressive disorder (MDD) is a serious psychiatric disorder characterized by persistent feelings of sadness, hopelessness, and lack of interest or pleasure in daily activities. Yet, reliable diagnostic tools for this brain disorder remain lacking. Functional near-infrared spectroscopy (fNIRS), an optical brain imaging technique, offers a promising approach for monitoring cerebral hemodynamic activity associated with MDD. In this study, we propose a novel algorithm based on wavelet coherence and a state-pathology separation network (WCSN) to automatically detect MDD using a dual-channel fNIRS system. The fNIRS signals were first preprocessed and transformed into two-dimensional feature maps using a wavelet coherence method. Following this, a wrapped exhaustive search was applied to select the optimal subset of feature maps, which was then utilized to reconstruct the dataset. Finally, samples were classified using the state-pathology separation network that employed a dual-encoder convolutional autoencoder (DCoAE) module to separate the feature maps into state features and pathology features, while a Transformer module distinguished MDD patients from healthy controls based solely on pathology features. The WCSN algorithm achieved exceptional performance with an accuracy of 0.923 ± 0.068 and a subject accuracy of 0.918 ± 0.076. Our result highlights the WCSN algorithm's ability to isolate pure pathology features, enhancing classification robustness and generalizability under dual-channel data conditions. Taken together, the proposed WCSN algorithm is well-suited for home-based MDD screening applications.


  • A Feature Fusion Model Based on Temporal Convolutional Network for Automatic Sleep Staging Using Single-Channel EEG

    by Jiameng Bao, Guangming Wang, Tianyu Wang, Ning Wu, Shimin Hu, Won Hee Lee, Sio-Long Lo, Xiangguo Yan, Yang Zheng, Gang Wang

    Sleep staging is a crucial task in sleep monitoring and diagnosis, but clinical sleep staging is both time-consuming and subjective. In this study, we proposed a novel deep learning algorithm named feature fusion temporal convolutional network (FFTCN) for automatic sleep staging using single-channel EEG data. This algorithm employed a one-dimensional convolutional neural network (1D-CNN) to extract temporal features from raw EEG, and a two-dimensional CNN (2D-CNN) to extract time-frequency features from spectrograms generated through continuous wavelet transform (CWT) at the epoch level. These features were subsequently fused and further fed into a temporal convolutional network (TCN) to classify sleep stages at the sequence level. Moreover, a two-step training strategy was used to enhance the model's performance on an imbalanced dataset. Our proposed method exhibits superior performance in the 5-class classification task for healthy subjects, as evaluated on the SHHS-1, Sleep-EDF-153, and ISRUC-S1 datasets. This work provided a straightforward and promising method for improving the accuracy of automatic sleep staging using only single-channel EEG, and the proposed method exhibited great potential for future applications in professional sleep monitoring, which could effectively alleviate the workload of sleep technicians. The code is available at https://github.com/bjm-123/FFTCN.


  • Channel-Selection-Based Temporal Convolutional Network for Patient-Specific Epileptic Seizure Detection

    by Guangming Wang, Xiyuan Lei, Wen Li, Won Hee Lee, Lianchi Huang, Jialin Zhu, Shanshan Jia, Dong Wang, Yang Zheng, Hua Zhang, et al.

    Since sudden and recurrent epileptic seizures seriously affect people’s lives, computer-aided automatic seizure detection is crucial for precise diagnosis and prompt treatment. A novel seizure detection algorithm named channel selection-based temporal convolutional network (CS-TCN) was proposed in this paper. Firstly, EEG recordings were segmented into 2-second intervals and features were extracted from both the time and frequency domains. Then the expanded fisher score channel selection method was employed to select channels that contribute the most to seizure detection. Finally, the features from selected EEG channels were fed into the temporal convolutional network (TCN) to capture inherent temporal dependencies of EEG signals and detect seizure events. CHB-MIT and Siena datasets were used to verify the detection performance of the CS-TCN algorithm, achieving sensitivities of 98.56% and 98.88%, and specificities of 99.80% and 99.88% in sample-wise analysis, respectively. In event-wise analysis, the algorithm achieved sensitivities of 97.57% and 95.00%, with delays of 6.91 and 18.62 seconds, and FDR/h of 0.11 and 0.39, respectively. These results surpassed state-of-the-art few-channel algorithms for both datasets. CS-TCN algorithm offers excellent performance while simplifying model complexity and computational requirements, thus showcasing its potential for facilitating seizure detection in home environments.


  • Top Cited Papers

    Classification of Three Anesthesia Stages Based on Near-Infrared Spectroscopy Signals

    by Zhian Liu, Lichengxi Si, Shaoxian Shi, Jing Li, Jing Zhu, Won Hee Lee, Sio-Long Lo, Xiangguo Yan, Badong Chen, Feng Fu, et al.

    Proper monitoring of anesthesia stages can guarantee the safe performance of clinical surgeries. In this study, different anesthesia stages were classified using near-infrared spectroscopy (NIRS) signals with machine learning. The cerebral hemodynamic variables of right proximal oxyhemoglobin (HbO 2 ) in maintenance (MNT), emergence (EM) and the consciousness (CON) stage were collected and then the differences between the three stages were compared by phase-amplitude coupling (PAC). Then combined with time-domain including linear (mean, standard deviation, max, min and range), nonlinear (sample entropy) and power in frequency-domain signal features, feature selection was performed and finally classification was performed by support vector machine (SVM) classifier. The results show that the PAC of the NIRS signal was gradually enhanced with the deepening of anesthesia level. A good three-classification accuracy of 69.27% was obtained, which exceeded the result of classification of any single category feature. These results indicate the fesibility of NIRS signals in performing three or even more anesthesia stage classifications, providing insight into the development of new anesthesia monitoring modalities.


  • The Diagnosis of Major Depressive Disorder Through Wearable fNIRS by Using Wavelet Transform and Parallel-CNN Feature Fusion

    by Guangming Wang, Ning Wu, Yi Tao, Won Hee Lee, Zehong Cao, Xiangguo Yan, Gang Wang

    Depression is a common mental illness that can even lead to suicide in severe cases. Thus, it is essential to diagnose and duly treat the depressive disorder accurately. Functional near-infrared spectroscopy (fNIRS) signals can monitor cerebral hemodynamic activity and may serve as a biomarker of depression. In this study, using wavelet transform and parallel convolutional neural network (CNN) feature fusion (WPCF), a novel algorithm based on a few channels of fNIRS signals was proposed to diagnose depressive disorder. Firstly, the preprocessed fNIRS signals were transformed into two-dimensional wavelet feature maps. Secondly, the feature maps with best quality were selected to form a feature map subset. Finally, the feature map subset was used as input into the WPCF algorithm for discriminating between the patients with major depressive disorder (MDD) and the healthy subjects. When using the subject-wise split data, the WPCF achieved good performance with an accuracy of 89.1 % in the post-task resting state. For record-wise split data, the results attained by the proposed WPCF algorithm had an accuracy of 95.4 %. These results indicated that the WPCF algorithm based on fNIRS signals may be applied to the home environment due to the portability and noninvasive measurement of the wearable fNIRS instrument.