• 한국멀티미디어학회논문지
• /
• 제22권12호
• /
• pp.1396-1403
• /
• 2019

The radar wind profiler data contaminates with various non-atmospheric components that produce errors in moments and wind velocity estimations. This study implemented an adaptive Gaussian model to detect and remove the clutter from the radar return. This model includes DC filtering, ground clutter recognition, Gaussian fitting, and cost function to mitigate the clutter component. The adaptive model tested for the various types of clutter components and found that it is effective in clutter removal process. It is also applied for the both time series and spectrum datasets. The moments estimated using this method are compared with those derived using conventional DC-filtering clutter removal method. The comparisons show that the proposed method effectively removes the clutter and produce reliable moments.

• 한국수자원학회논문집
• /
• 제56권1호
• /
• pp.63-74
• /
• 2023

높은 신뢰도의 댐 유입량 예측은 효율적인 댐 운영을 위해 필요하다. 최근 다층퍼셉트론(Multi Layer Perceptron, MLP)을 활용하여 댐의 유입량을 예측하는 연구들이 진행되었다. 기존 연구들은 MLP의 연산자 중 자료 간의 최적 상관관계를 찾는 optimizer로 경사하강법(Gradient Descent, GD) 기반의 optimizer를 사용하였다. 하지만, GD 기반의 optimizer들은 지역 최적값으로의 수렴 가능성과 저장공간 부재로 인해 예측성능이 저하된다는 단점이 있다. 본 연구는 GD 기반 optimizer 중 Adaptive moments와 Improved Harmony Search (IHS)를 결합한 Adaptive moments combined with Improved Harmony Search (AdamIHS)를 개발하여 GD 기반 optimizer의 단점을 개선하였다. AdamIHS를 사용한 MLP의 학습 및 예측성능을 평가하기 위해 대청댐 유입량을 학습 및 예측하였으며, GD 기반 optimizer를 사용한 MLP의 학습 및 예측성능과 비교하였다. 학습결과를 비교하면, AdamIHS를 사용한 은닉층 5개인 MLP의 Mean Squared Error (MSE) 평균값이 11,577로 가장 낮았다. 예측결과를 비교하면, AdamIHS를 사용한 은닉층 1개인 MLP의 MSE 평균값이 413,262로 가장 낮았다. 본 연구에서 개발된 AdamIHS를 활용하면 다양한 분야에서 향상된 예측성능을 보여줄 수 있을 것이다.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2000년도 추계학술대회논문집
• /
• pp.667-673
• /
• 2000

A number of issues related with the vibrational behavior of pretwisted rotating beams featuring anisotropic properties and incorporating adaptive capabilities are considered in this paper. The adaptive capabilities are provided by a system of piezoactuators bonded or embedded into the structure. Based on the converse piezoelectric effect and on the out of phase activation, boundary control moments are pizoelectrically induced at the beam tip. A feedback control law relating the induced bending moments with the kinematical response quantities appropriately selected is used, and its beneficial effects, considered in conjunction with that of the beam anisotropy and structural pretwist upon the eigenvibration characteristics are highlighted

• 한국수자원학회논문집
• /
• 제57권2호
• /
• pp.73-85
• /
• 2024

하천과 저수지의 수질을 예측하는 것은 수자원관리를 위해 필요하다. 높은 정확도의 수질 예측을 위해 많은 연구들에서 인공신경망이 활용되었다. 기존 연구들은 매개변수를 탐색하는 인공신경망의 연산자인 옵티마이저로 경사하강법 기반 옵티마이저를 사용하였다. 그러나 경사하강법 기반 옵티마이저는 지역 최적값으로의 수렴 가능성과 해의 저장 및 비교구조가 없다는 단점이 있다. 본 연구에서는 인공신경망을 이용한 수질 예측성능을 향상시키기 위해 개량형 옵티마이저를 개발하여 경사하강법 기반 옵티마이저의 단점을 개선하였다. 본 연구에서 제안한 옵티마이저는 경사하강법 기반 옵티마이저 중 학습오차가 낮은 Adaptive moments (Adam)과 Nesterov-accelerated adaptive moments (Nadam)를 Harmony Search(HS) 또는 Novel Self-adaptive Harmony Search (NSHS)와 결합한 옵티마이저이다. 개량형 옵티마이저의 학습 및 예측성능 평가를 위해 개량형 옵티마이저를 Long Short-Term Memory (LSTM)에 적용하여 국내의 다산 수질관측소의 수질인자인 수온, 용존산소량, 수소이온농도 및 엽록소-a를 학습 및 예측하였다. 학습결과를 비교하면, Nadam combined with NSHS (NadamNSHS)를 사용한 LSTM의 Mean Squared Error (MSE)가 0.002921로 가장 낮았다. 또한, 각 옵티마이저별 4개 수질인자에 대한 MSE 및 R²에 따른 예측순위를 비교하였다. 각 옵티마이저의 평균 순위를 비교하면, NadamNSHS를 사용한 LSTM이 2.25로 가장 높은 것을 확인하였다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 하계종합학술대회 논문집 Ⅳ
• /
• pp.1731-1734
• /
• 2003

In this paper, we describe an approach for image denoising using the lifting construction, with the spatial adaptive wavelet transform. The adaptive lifting scheme is implemented in spatial domain to be adjusted thresholds to reduce noise. In this approach we represent adaptive characteristics of biorthogonal wavelets for choosing predictors effectively. Predict filter is changed from sample to sample according to local signal features with their vanishing moments. We in this approach have implemented and applied to image denoising by finding a relevant minimax threshold. Experimental results show that the adaptive method of denoising process is compared with existing ones, such as non-adaptive wavelet, CRF(13, 7) and SWE(13, 7) wavelets used by JPEG2000.

• Journal of the Korean Statistical Society
• /
• 제30권3호
• /
• pp.419-433
• /
• 2001

In this paper we introduce a method of improving efficiency of the moment estimator of Dekkers, Einmahl and de Haan(1989) for the extreme value index $\beta$. a new estimator of $\beta$ is proposed by adding the third moment ot the original moment estimator which is composed of the first two moments of the log-transformed sample data. We establish asymptotic normality of the new estimator and examine and adaptive procedure for the new estimator. The resulting adaptive estimator proves to be asymptotically better than the moment estimator particularly for $\beta$<0.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1999년도 하계종합학술대회 논문집
• /
• pp.579-582
• /
• 1999

In this paper, we propose a human face detection algorithm using adaptive skin color model and neural networks. To attain robustness in the changes of illumination and variability of human skin color, we perform a color segmentation of input image by thresholding adaptively in modified hue-saturation color space (TSV). In order to distinguish faces from other segmented objects, we calculate invariant moments for each face candidate and use the multilayer perceptron neural network of backpropagation algorithm. The simulation results show superior performance for a variety of poses and relatively complex backgrounds, when compared to other existing algorithm.

• 항공우주시스템공학회지
• /
• 제11권5호
• /
• pp.28-35
• /
• 2017

자기부상 비접촉식 밸런스(MSBS: Magnetic Suspension and Balance System)는 자기력 및 자기모멘트를 이용하여 기계적 접촉 없이 시험 대상체의 위치 및 자세각을 정밀하게 변경하며 외력을 측정하는 것이 가능하다. MSBS를 활용한 풍동실험의 신뢰도 및 안정성을 확보하기 위해서는 위치 및 자세각 제어시스템의 명령 추종 성능과 구성장비의 고장에 대한 강건성을 높일 필요가 있다. 본 연구에서는 실제 개발된 풍동실험용 MSBS의 시뮬레이션을 통해 Iterative Feedback Tuning (IFT)과 $L_1$ adaptive output feedback 알고리즘을 활용하여 제어 이득값을 자동적으로 최적화하고 전류공급장치의 고장에 강건한 제어시스템을 설계하는 방법의 유효성을 검증하였다.

• Communications for Statistical Applications and Methods
• /
• 제24권5호
• /
• pp.493-505
• /
• 2017

Maximum likelihood estimation (MLE) of the generalized extreme value distribution (GEVD) is known to sometimes over-estimate the positive value of the shape parameter for the small sample size. The maximum penalized likelihood estimation (MPLE) with Beta penalty function was proposed by some researchers to overcome this problem. But the determination of the hyperparameters (HP) in Beta penalty function is still an issue. This paper presents some data adaptive methods to select the HP of Beta penalty function in the MPLE framework. The idea is to let the data tell us what HP to use. For given data, the optimal HP is obtained from the minimum distance between the MLE and MPLE. A bootstrap-based method is also proposed. These methods are compared with existing approaches. The performance evaluation experiments for GEVD by Monte Carlo simulation show that the proposed methods work well for bias and mean squared error. The methods are applied to Blackstone river data and Korean heavy rainfall data to show better performance over MLE, the method of L-moments estimator, and existing MPLEs.

• Structural Engineering and Mechanics
• /
• 제56권5호
• /
• pp.787-796
• /
• 2015

When the temperature of a structure varies, there is a tendency to produce changes in the shape of the structure. The resulting actions may be of considerable importance in the analysis of the structures having non-prismatic members. The computation of design forces for the non-prismatic beams having symmetrical parabolic haunches (NBSPH) is fairly difficult because of the parabolic change of the cross section. Due to their non-prismatic geometrical configuration, their assessment, particularly the computation of fixed-end horizontal forces and fixed-end moments becomes a complex problem. In this study, the efficiency of the Artificial Neural Networks (ANN) and Adaptive Neuro Fuzzy Inference Systems (ANFIS) in predicting the design forces and the design moments of the NBSPH due to temperature changes was investigated. Previously obtained finite element analyses results in the literature were used to train and test the ANN and ANFIS models. The performances of the different models were evaluated by comparing the corresponding values of mean squared errors (MSE) and decisive coefficients ($R^2$). In addition to this, the comparison of ANN and ANFIS with traditional methods was made by setting up Linear-regression (LR) model.