• 대한기계학회논문집A
• /
• 제20권9호
• /
• pp.2833-2842
• /
• 1996

This paper is to practice optimal rigidity design by the strain energy density estimation method for static buckling and sizing design sensitivity analysis for dynamic buckling of a nonlinear vehicle frame structure from those results. Using these sizing design sensitivity resutls, an optimization of a nonlinear vehicle frame structure with dynamic buckling constraint is carrried out with the graient projection method.

• 응용통계연구
• /
• 제25권1호
• /
• pp.197-203
• /
• 2012

In fitting a regression model, we often encounter data sets which do not follow Gaussian distribution and/or do not have equal variance. In this case estimation of the conditional density of a response variable at a given design point is hardly solved by a standard least squares method. To solve this problem, we propose a simple method to estimate the distribution of the fitted vales under heteroscedasticity using the idea of quantile regression and the histogram techniques. Application of this method to a real data sets is given.

• 한국정보통신학회논문지
• /
• 제15권8호
• /
• pp.1659-1664
• /
• 2011

Fuzzy C-Means (FCM)는 군집화를 위해 널리 사용되는 알고리듬 중 하나로 다양한 응용 분야에서 성공적으로 사용되어 왔다. 하지만 FCM은 여러 가지 단점을 가지고 있으며 초기 원형 설정이 그 중 하나이다. FCM은 국부 최적해에 수렴하므로 초기 원형 설정에 따라 군집화의 결과가 달라진다. 따라서 초기 원형의 설정은 군집화 결과 향상을 위해 중요하다. 이 논문에서는 이러한 FCM의 초기 원형 설정 문제를 해결하는 방안으로 커널 밀도 추정을 활용하는 방법을 제안한다. 커널 밀도 추정은 비모수적 분포들에도 사용할 수 있어 국부적인 데이터 밀도 추정에 유용하다. 제안한 방법에서는 커널 밀도 추정을 수행한 후 밀도가 높은 지역에 클러스터의 초기 원형을 설정하고 원형이 설정된 영역의 밀도를 감소시키는 과정을 반복함으로써 효율적으로 초기 원형을 선택할 수 있다. 제안된 방법이 일반적으로 사용되는 무작위 초기화 방법에 비해 효율적이라는 사실은 실험 결과를 통해 확인할 수 있다.

• IEIE Transactions on Smart Processing and Computing
• /
• 제6권3호
• /
• pp.183-192
• /
• 2017

k-nearest neighbor (K-NN) is a well-known classification algorithm, being feature space-based on nearest-neighbor training examples in machine learning. However, K-NN, as we know, is a lazy learning method. Therefore, if a K-NN-based system very much depends on a huge amount of history data to achieve an accurate prediction result for a particular task, it gradually faces a processing-time performance-degradation problem. We have noticed that many researchers usually contemplate only classification accuracy. But estimation speed also plays an essential role in real-time prediction systems. To compensate for this weakness, this paper proposes correlation coefficient-based clustering (CCC) aimed at upgrading the performance of K-NN by leveraging processing-time speed and plurality rule-based density (PRD) to improve estimation accuracy. For experiments, we used real datasets (on breast cancer, breast tissue, heart, and the iris) from the University of California, Irvine (UCI) machine learning repository. Moreover, real traffic data collected from Ojana Junction, Route 58, Okinawa, Japan, was also utilized to lay bare the efficiency of this method. By using these datasets, we proved better processing-time performance with the new approach by comparing it with classical K-NN. Besides, via experiments on real-world datasets, we compared the prediction accuracy of our approach with density peaks clustering based on K-NN and principal component analysis (DPC-KNN-PCA).

• 한국정밀공학회지
• /
• 제30권2호
• /
• pp.231-235
• /
• 2013

The purpose of this paper is to compare with estimation of equivalent fatigue load in time domain and frequency domain and estimate the fatigue life of structure with multi-axial vibration loading. The fatigue analysis with two methods is implemented with various signals like random, sinusoidal signals. Also an equivalent fatigue life estimated by rainflow cycle counting in time domain is compared with results estimated with probability density function of each signal in frequency domain. In case of frequency domain, equivalent fatigue life can estimate through Dirlik's method with probability density function. And the work proposed in this paper compared the fatigue damage accumulated under uni-axial loading to that induced by multi-axial loading. The comparison is preformed for a simple cantilever beam, which is exposed to vibrations of several directions. For verification of estimation performance of fatigue life, results are compared to those of FEM analysis (ANSYS).

• Fisheries and Aquatic Sciences
• /
• 제26권12호
• /
• pp.689-697
• /
• 2023

This study used a multi-frequency acoustic method to assess the density and spatial distribution of dominant zooplankton, euphausiids and copepods, which are representative species of the zooplankton immigrating the sea around Republic of Korea. Acoustic surveys were carried out in the East Sea and South Sea from June 16 to 29, 2017, using the research vessel Tamgu 20th from the National Institute of Fisheries Science. From the results of the acoustic survey, the distribution of euphausiids was relatively higher in the East Sea than in the South Sea. Additionally, although the distribution of copepods was low in all areas, they were abundant in certain areas in the East Sea and the southern area of the Jeju Sea. Euphausiid and copepod density was estimated to be 1.2 g/m² (CV = 19.1%) and 2.8 g/m² (CV = 23.5%), respectively.

• Communications for Statistical Applications and Methods
• /
• 제9권2호
• /
• pp.305-313
• /
• 2002

Regarding to inference about a scalar measure of internal scatter of Ρ-variate normal population, this paper considers an interval estimation of the generalized variance, │$\Sigma$│. Due to complicate sampling distribution, fully parametric frequentist approach for the interval estimation is not available and thus Bayesian method is pursued to calculate the highest probability density (HPD) interval for the generalized variance. It is seen that the marginal posterior distribution of the generalized variance is intractable, and hence a weighted Monte Carlo method, a variant of Chen and Shao (1999) method, is developed to calculate the HPD interval of the generalized variance. Necessary theories involved in the method and computation are provided. Finally, a simulation study is given to illustrate and examine the proposed method.

• 한국음향학회지
• /
• 제35권2호
• /
• pp.102-109
• /
• 2016

본 논문은 밀접한 간격의 두 개의 마이크 배열 환경에서 SNR(Signal-to-Noise Ratio) 추정을 통한 잡음 억제 방법을 제안한다. 기존의 방법은 전 밴드에서 간섭 함수 기반의 SNR 추정을 통해 이득 함수를 얻는 잡음 억제 방법을 사용한다. 그러나 이 방법은 잡음으로 인한 손상이 모든 특징 벡터 성분에 영향을 미쳐 성능을 저하시키는 문제점을 가지고 있다. 따라서 주파수 영역의 신호를 N개의 다중 주파수 밴드로 구분하고 각 밴드별로 간섭 함수 기반의 SNR 추정을 통한 이득 함수를 얻는 잡음 억제 방법을 제안한다. 제안하는 방법의 성능평가는 ITU-T(International Telecommunications Union Telecommunication)에서 제공되는 객관적인 품질 평가 방법인 PESQ(Perceptual Evaluation of Speech Quality)로 비교하여 나타내었다.

• 한국전자파학회논문지
• /
• 제23권2호
• /
• pp.235-243
• /
• 2012

본 논문에서는 주파수 선택적 채널 환경의 OFDM 시스템에서 파일럿 심볼을 이용한 채널 추정 기법인 pilot Symbol Assisted Modulation(PSAM) 채널 추정 성능을 개선하는 방법을 제안한다. OFDM시스템에서는 채널 추정에 쓰이는 파일럿의 밀도가 적을수록 시스템의 유효 데이터량과 전력 효율이 증가되는 장점이 있다. 이를 위해 송신단에서는 채널 추정에 사용되는 파일럿의 수를 적게 사용하는 것이 좋다. 본 논문에서의 수신단에서는 인접한 파일럿 중간에 위치한 채널값이 먼저 추정된 후, 기존의 파일럿 값과 추정된 중간값을 사용하여 나머지 채널값을 추정한다. 그 후 채널의 최대 응답 길이를 고려하여 설계된 보호 구간의 길이를 이용하여 추정된 채널값의 오차를 줄여준다. 제안된 채널 추정 기법의 평균 제곱 오차(MSE) 성능은 기존의 PSAM 채널 추정 방법에 비해 신호대 잡음비 면에서 약 2 dB 정도의 개선 효과를 보여주었다.

• 드라이브 ㆍ 컨트롤
• /
• 제21권2호
• /
• pp.53-64
• /
• 2024

Global population growth has resulted in an increased demand for food production. Simultaneously, aging rural communities have led to a decrease in the workforce, thereby increasing the demand for automation in agriculture. Drones are particularly useful for unmanned pest control fields. However, the current method of uniform spraying leads to environmental damage due to overuse of pesticides and drift by wind. To address this issue, it is necessary to enhance spraying performance through precise performance evaluation. Therefore, as a foundational study aimed at optimizing drone-based pest control technologies, this research evaluated water-sensitive paper (WSP) via density map estimation using convolutional neural networks (CNN) with a encoder-decoder structure. To achieve more accurate estimation, this study implemented multi-task learning, incorporating an additional classifier for image segmentation alongside the density map estimation classifier. The proposed model in this study resulted in a R-squared (R²) of 0.976 for coverage area in the evaluation data set, demonstrating satisfactory performance in evaluating WSP at various density levels. Further research is needed to improve the accuracy of spray result estimations and develop a real-time assessment technology in the field.