Yongseok Lee

Prof. Yongseok Lee

Department of Electronics, Chungwoon University, Incheon, Republic of Korea
orcid

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

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

Representative Publications

View All Publications
30 March 2023 in Applied Sciences
Verified
Journal Article
Open access
PDF file
YLYongseok Lee
Yongseok Lee
JKJongweon Kim
Jongweon Kim
In recent years, artificial intelligence technologies in vision tasks have gradually begun to be applied to the physical world, proving they are vulnerable to adversarial attacks. Thus, the importance of improving robustness against adversarial attacks has emerged as an urgent issue in vision tasks. This article aims to provide a historical summary of the evolution of adversarial attacks and defense methods on CNN-based models and also introduces studies focusing on brain-inspired models that mimic the visual cortex, which is resistant to adversarial attacks. As the origination of CNN models was in the application of physiological findings related to the visual cortex of the time, new physiological studies related to the visual cortex provide an opportunity to create more robust models against adversarial attacks. The authors hope this review will promote interest and progress in artificially intelligent security by improving the robustness of deep learning models for vision tasks.

18 November 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
YLYongseok Lee
Yongseok Lee
Electrocardiogram (ECG) monitoring on low-power edge devices requires models that balance accuracy, latency, and energy consumption. This study evaluates abrupt change detection in ECG using spiking neural networks (SNNs) trained on spike-encoded signals that preserve salient cardiac dynamics. This study used 4910 ECG segments from 290 subjects (PTB Diagnostic Database; 2.5-s windows at 1 kHz), providing context for the reported results. Under a unified architecture, preprocessing pipeline, and training schedule, we compare two representative neuron models—leaky integrate-and-fire (LIF) and adaptive exponential integrate-and-fire (AdEx). We report balanced accuracy, sensitivity, inference latency, and an energy proxy based on spike-event counts, and we examine robustness to input noise and temporal distortions. Across operating points, AdEx yields the highest overall accuracy and sensitivity, whereas LIF achieves the lowest energy cost and shortest latency, favoring deployment on resource-constrained hardware. Both SNN variants substantially reduce computational events—hence estimated energy—relative to conventional artificial neural network baselines, supporting their suitability for real-time, on-device diagnostics. These findings provide practical guidance for selecting neuron dynamics and decision thresholds to meet target accuracy–sensitivity trade-offs under energy and latency budgets. Overall, combining spike-encoded ECG with appropriately chosen SNN dynamics enables reliable abrupt change detection with notable efficiency gains, offering a path toward scalable edge-level cardiovascular monitoring. While lightweight CNNs and shallow transformers are important references, to keep the scope focused on SNN design choices and policy-aware thresholding for edge constraints, we refrain from reporting additional ANN numbers here. A seed-controlled head-to-head benchmark is reserved for future work.

28 August 2023 in Applied Sciences
Verified
Journal Article
Open access
PDF file
YLYongseok Lee
Yongseok Lee
JKJongweon Kim
Jongweon Kim
In the past few years, deep convolutional neural networks (DCNNs) have surpassed human performance in tasks related to recognizing objects. However, DCNNs are also threatened by performance degradation due to adversarial examples. DCNNs are essentially black-boxed, and it is not known how the output is determined internally; consequently, it is not known how adversarial attacks cause performance degradation inside the DCNNs. To observe the internal neuronal activities of DCNN models for adversarial examples, we analyzed the population sparseness index (PSI) values at each layer of two representative DCNN models, namely AlexNet and VGG11. From the experimental results, we observed that the internal responses of the two DCNN models to adversarial examples exhibited distinct layer-wise PSI values, differing from the internal responses to benign examples. The main contribution of this study is the discovery of significant differences in the internal responses of two specific DCNN models to adversarial and benign examples by PSI. Furthermore, our research has the potential not only to contribute to the design of more robust DCNN models against adversarial examples but also to bridge the gap between the fields of artificial intelligence and neurophysiology of the brain.


1 July 2026 in Biomimetics
Verified
Journal Article
Open access
PDF file
YLYongseok Lee
Yongseok Lee
Phosphene-based visual neuroprostheses require encoding schemes that preserve task-relevant information while remaining feasible under safety-constrained stimulation. This study proposes a stress-based evaluation framework that reframes phosphene encoder assessment as a tri-objective operating-envelope problem rather than a single-metric comparison. Four representative encoders—rate, sparse, temporal, and optim—were evaluated under structured perturbations using two simulated prosthetic-vision(SPV) benchmarks: EMNIST Letters for symbolic recognition and a COCO-derived balanced subset for a reduced four-class COCO-derived image-level classification task. The final experimental configuration used 20,000/3000/3000 train/validation/test samples for EMNIST and 4000/1000/1000 for the COCO-derived benchmark. The framework combined structured stress sweeps, residual proxy safety-burden analysis, topology-based representation metrics, and stress-integrated utility summaries within a simulation-based evaluation setting. The results showed that clean-conditioning accuracy alone was insufficient to predict encoder behavior under stress. EMNIST exhibited broad operator-dependent degradation, whereas the COCO-derived benchmark showed a lower but more compressed performance regime. Residual proxy safety burden was only loosely aligned with performance, with moderate dissociation between performance and residual proxy safety burden in EMNIST and weaker alignment between these two axes in the COCO-derived benchmark. In the point-estimate utility summaries, the sparse encoder tended to yield comparatively favorable tri-objective utility values within the present single-run simulation-based framework, simplified SPV percept-synthesis operator, and fixed benchmark-specific decoder setting, primarily because it maintained an almost negligible residual proxy safety burden while preserving competitive performance and topology-based representation metrics. Topology-based analysis further indicated that topology-based representation metrics largely tracked task degradation in EMNIST, whereas topology-based representation metrics showed larger relative variation than decoder accuracy within the evaluated simulation setting under degraded COCO-derived conditions. Taken together, these findings provide an exploratory, benchmark-specific assessment suggesting that phosphene encoder evaluation may benefit from a multi-axis operating-envelope-oriented analysis that jointly considers stressed functional performance, residual proxy safety burden, and topology-based representation metrics within the present simplified SPV and fixed-decoder evaluation setting. These results should therefore be interpreted as simulation-level, configuration-dependent observations under a simplified SPV percept-synthesis operator, with safety-related quantities treated as residual proxy safety-burden summaries rather than as direct physiological, electrochemical, clinical, or implant-specific safety measurements.

28 December 2016 in Indian Journal of Science and Technology
Verified
Journal Article
Open access
PDF file
YLYongseok Lee
Yongseok Lee
Objectives: The watermark embedding in Non-Activity Region (NAR) of the underlying audio signal results for the degradation of audio quality. This research focused on the development of audio activity detection method for the audio watermarking procedure to prevent from watermark embedding in the NAR. Methods/Statistical Analysis: We propose the audio activity detection method based on the wavelet denoising algorithm to classify the NAR in audio signal. We experiment and apply three- type wavelet denoising algorithms, subsequently the wavelet denoising algorithms showed the same performance. We analyze the audio quality by the Signal to Noise Ratio (SNR) for two cases that the embedding and non-embedding of watermark in the NAR. Findings: We surveyed the effects on the watermarking embedding in the NAR. Decreasing a payload on watermarking, the watermark embedding in the NAR increases the audio quality in SNR and audio test by MUSHRA (Multi Stimulus Test with Hidden Reference and Anchor). In extraction process the extraction rate of embedded watermark is slightly increasing when our method is applied. In comparisons of the other research results such as DFT (Discrete Fourier Transform) based method and MFCC (Mel Frequency Cepstral Coefficients) based method, our method has the better accuracy in AAD. And also our method is in low complexity for the analysis of computational complexity by the effective computational structure of filter bank for implementation of wavelet filter. In additional research results, we find out that the audio signal in the NAR has a random- like pattern by the analysis of power spectrum of it.In statistical experiment a signal in NAR analyzed by statistical parameters such as mean and variance. As a result, our method is effective for computational complexity and produces good audio quality for the watermark embedding procedure. Improvements/Applications: Our method for audio activity detection is very effective computational complexity and produces high audio quality for watermark embedding procedure. It is applicable for the audio watermarking system for high- quality watermarked audio signal.