http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
비접촉형 심박수 측정 정확도 향상을 위한 인공지능 기반 CW 레이더 신호처리
윤원열,권남규,Won Yeol Yoon,Nam Kyu Kwon 대한임베디드공학회 2023 대한임베디드공학회논문지 Vol.18 No.6
Vital signals provide essential information regarding the health status of individuals, thereby contributing to health management and medical research. Present monitoring methods, such as ECGs (Electrocardiograms) and smartwatches, demand proximity and fixed postures, which limit their applicability. To address this, Non-contact vital signal measurement methods, such as CW (Continuous-Wave) radar, have emerged as a solution. However, unwanted signal components and a stepwise processing approach lead to errors and limitations in heart rate detection. To overcome these issues, this study introduces an integrated neural network approach that combines noise removal, demodulation, and dominant-frequency detection into a unified process. The neural network employed for signal processing in this research adopts a MLP (Multi-Layer Perceptron) architecture, which analyzes the in-phase and quadrature signals collected within a specified time window, using two distinct input layers. The training of the neural network utilizes CW radar signals and reference heart rates obtained from the ECG. In the experimental evaluation, networks trained on different datasets were compared, and their performance was assessed based on loss and frequency accuracy. The proposed methodology exhibits substantial potential for achieving precise vital signals through non-contact measurements, effectively mitigating the limitations of existing methodologies.
In Seok Park(박인석),Nam Kyu Kwon(권남규),PooGyeon Park(박부견) 대한전기학회 2017 정보 및 제어 심포지엄 논문집 Vol.2017 No.4
This paper considers the problem of H∞ control for Markovian jump systems with partly unknown transition probabilities and input saturation. Using the convex property of normalized mode transition probabilities, less conservative H∞ stochastic stabilization conditions for discrete-time Markovian jump systems with partly unknown transition probabilities and input saturation are derived. Then, the derived conditions are represented as linear matrix inequalities (LMIs) conditions. The numerical examples will show that the proposed theorem exhibited better performance in view of the minimum cost √.
딥러닝 기반 Doppler Cardiogram Signal 압축 및 복원 방법에 사용된 네트워크 구조에 따른 성능 비교
장영인(Young In Jang),권남규(Nam Kyu Kwon) 대한전자공학회 2021 대한전자공학회 학술대회 Vol.2021 No.6
This paper proposes the signal compression and reconstruction performance of the deep learning networks using Doppler cardiogram(DCG) signals. Based on the variational autoencoder(VAE), multi-layer perceptron(MLP), convolutional neural network(CNN), and long short-term memory(LSTM) networks are used to compress and reconstruct the DCG signals. The results of the compression and reconstruction are compared with the evaluation criteria such as mean square error (MSE) and compression ratio (CR). The quantitative analysis results of signal processing performance from this paper will be useful in selection of the deep learning network for the analysis of the heartbeat signal.
Robust trajectory control of an excavator manipulator using an advanced time-delay controller
Dong Woo Kim(김동우),Kwon Nam kyu(권남규),Seok Young Lee(이석영),PooGyeon Park(박부견) 대한전기학회 2017 정보 및 제어 심포지엄 논문집 Vol.2017 No.4
We designed a time-delay controller (TDC) to control an excavator manipulator. Before designing the controller, the kinematics and dynamics analysis were derived. Using MATLAB simulink, we found that the TDC was stable and robust in the excavator manipulator system. For improving the TDC, we added a hold function and KI gain in input of the TDC. The hold function which is consisted of hyperbolic tangent improved an error convergence by substituting the error to a modified error. KI gain was also helpful to decrease steady-state error.