• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2007.11a
• /
• pp.318-321
• /
• 2007

Since human listening is very sensitive to sound, a subjective index of a sound quality is required. Therefore, in the analysis for each situation, the sound evaluation is composed with sound quality factor. Many researchers spends their effort to make a more reliable and more accurate of sound in term of sound quality index for various system noise. The previous methods to evaluation of the SQ about vehicle interior noise are linear regression analysis of subjective SQ metrics by statistics and the estimation of the subjective SQ values by neural network. But these are so depended on jury test very much that they result in many difficulties. So, to reduce jury test weight, we suggested a new method using Mahalanobis distance for SQ evaluation. Threrefore, in this study Mahalanobis distance for the vehicle interior noise was derived using the objective SQ except jury test. Finnaly, the results of the SQ evaluation was analyzed discrimination between reference and abnormal group.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.25 no.5
• /
• pp.894-899
• /
• 2011

Traditional Korean Medicine (TKM) has been actively researched through various approaches, including computational methods. This paper aims at providing an overview of domestic studies using the computational techniques in TKM field. A literature search was conducted in Korean publications using OASIS system, and major studies of data mining in TKM were identified. A review was presented in six diagnosis fields, including sasang constitution diagnosis, eight constitution diagnosis, tongue diagnosis, pattern diagnosis for stroke, diagnosis based on ontology, diagnosis for cause of disease. They collect clinical data themselves for experiments and primarily applied a algorithm of decision tree, SVM, neural network, case-based reasoning, ontology reasoning, discriminant analysis. In the future, there needs to identify which algorithm is suitable to diagnosis or other fields of TKM.

• Journal of the Korean Society for Precision Engineering
• /
• v.31 no.4
• /
• pp.297-301
• /
• 2014

The biggest factors, which lower the machining accuracy of machine, are thermal deformation and chatter vibration. In this article, we introduce the development case of a device and technology that can automatically compensate thermal deformation errors of machine during long-time processing on the machine tool's CNC (Computerized Numerical Controller) in real time. In machine processing, the data acquisition of temperature signal in real time and auto-compensation of the machine origin of machine tools depending on thermal deformation have significant influence on improving the machining accuracy and the rate of operation. Thus, we attempts to introduce the related contents of the development we have made in this article : The development of a device that embedded the acquisition part of temperature data, linear regression to get compensation value, compensation model of neural network and a system that compensates the machine origin of machine tool automatically during manufacturing process on the CNC.

• Journal of the Korean Society for Precision Engineering
• /
• v.19 no.6
• /
• pp.96-103
• /
• 2002

The objective of this study is to adjust the roll gap fur the dimension accuracy of bar in hot bar rolling process considering roll wear. In this study hot bar rolling processes fur round and oval passes have been investigated. In order to predict the roll wear, the wear model is reformulated as an incremental from and then wear depth of roll is calculated at each deformation step on contact area using the results of finite element analysis, such as relative sliding velocity and normal pressure at contact area. Archard's wear model was applied to predict the roll wear. To know the effects of thermal softening of DCI (Ductile Cast Iron) roll material according to operating conditions, high temperature micro hardness test is executed and a new wear model has been proposed by considering the thermal softening of DCI roll expressed in terms of the main tempering curve. The new technique developed in this study for adjusting roll gap can give more systematically and economically feasible means to improve the dimension accuracy of bar with full usefulness and generality.

• Journal of Korean Society of Water and Wastewater
• /
• v.24 no.2
• /
• pp.183-193
• /
• 2010

Well planned rehabilitation order of pipes is essential for efficient maintenance and management of Water Distribution Systems. In this study, not only deterioration rate of pipes but also structural and nonstructural failure which causes abnormal condition of WDS is considered to determine rehabilitation order. Probabilistic Neural Network is used for calculating deterioration rate at present and the importance of pipes is computed under structural and nonstructural failure by using Pipe by Pipe Failure Analysis and Effect Index. Utopian Approach, one of the Multi-Criteria Decision Making methods, is used for assessment of final rehabilitation order based on distance measure between utopian point and alternative one. Developed model in this study shows that it gives more reliable results than existing methods considering hydraulic relative importance does in application to real networks. In this point, the newly developed model, which gives advantages over existing models, can make a credible decision and simple application.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2009.05a
• /
• pp.1412-1416
• /
• 2009

최근의 극심한 기상이변으로 인하여 발생되는 이상호우의 예측에 관한 사항은 치수 이수는 물론 방재의 측면에서도 역시 매우 중요한 관심사로 부각되고 있다. 강우를 예측하기 위해 많은 방법들이 사용되고 있으나 강우의 메커니즘은 매우 복잡하여 수문순환과정에서 가장 예측하기 힘든 요소이며, 추계학적 예측모형이나 확정론적 예측모형 모두에 있어 상당한 불확실성을 내포하고 있다. 기상예측모형 등을 이용하여 강우예측에 대한 정도를 높여가고는 있으나 많은 수문학적 모형에서 요구하는 시공간적으로 정도가 높은 강우를 예측하기에는 힘들다. 인공신경망은 과거자료의 입 출력 패턴에서 정보를 추출하여 지식으로 보유하고, 이를 근거로 새로운 상황에 대한 해답을 제시하도록 하는 인공지능분야의 학습기법으로 인간이 과거의 경험과 훈련으로 지식을 축적하듯이 시스템의 입 출력에 의하여 연결강도를 최적화함으로서 모형의 구조를 스스로 조직화하기 때문에 모형의 구조에 적합한 최적 매개변수를 추정할 수 있다. 따라서 정확한 예측이 어려운 강우사상을 과거의 자료로부터 신경망의 수학적 알고리즘을 통해 강우의 예측에 적용할 수 있을 것이다. 따라서 본 연구에서는 이러한 인공신경망의 기법 중 오류 역전파 알고리즘을 통하여 과거의 강우사상들을 입 출력 자료로 이용하여 인공신경망을 학습시켜 강우의 예측에 대한 정도를 높이도록 하였다.

• Proceedings of the KSRS Conference
• /
• 2005.10a
• /
• pp.325-328
• /
• 2005

To estimate presumptive local ground subsidence area near Abandoned Under ground Coal Mine(AUCM) at Samcheok city in Korea, the geological properties of existing ground subsidence area and the geophysical prospecting data were analyzed using GIS. The electrical resistivity survey and seismic reflection survey database were constructed from investigation reports and factors which are related with ground subsidence such as geological map, topological map, land use map, lineament map, groundwater level, RMR (Rock Mass Rating), mining tunnel map and slope database were constructed also to make a comparative study of each parameters. As a result of the spatial analysis of existing ground subsidence area, 9 major factors causing ground subsidence were extracted and a connection between the structure of underground and the ground subsidence was determined from the analysis of geophysical prospecting data. The estimation of presumptive ground subsidence area was performed using the correlation between the result from neural network analysis of 9 factors and the scrutiny of geophysical prospecting data.

• Proceedings of the KIEE Conference
• /
• 2011.07a
• /
• pp.1956-1957
• /
• 2011

본 연구는 White LED를 이용하여 주변 밝기 변화에 빠르게 적응하는 퍼지 뉴로 Dimming Control System을 설계한다. 본 논문에서는 방사형기저함수 신경회로망(Radial Basis Function Neural Network: RBFNN)을 설계하여 실제 White LED Dimming Control System에 적용시켜 모델의 근사화 및 일반화 성능을 평가한다. 제안한 모델에서의 은닉층은 방사형기저함수를 사용하여 적합도를 구현하였고, 후반부의 연결가중치는 경사하강법을 사용한다. 이때 멤버쉽 함수의 중심점은 HCM 클러스터링 (Hard C-Means Clustering)을 적용하여 결정한다. 연결가중치는 4가지 형태의 다항식을 대입하여 출력을 평가하였다. 최종 출력의 최적화를 위하여 PSO(Particle Swarm Optimization)을 이용하여 은닉층 노드수 및 다항식 형태를 결정한다. 본 논문에서 제안한 LED Dimming Control System은 Atmega8535를 사용하여 PWM 제어 방식을 사용하고, 조도계(Cds)를 이용하여 LED의 밝기에 따른 주변의 밝기를 감지하여 조명에 적응시키는 방법을 적용하였다.

• Proceedings of the KIEE Conference
• /
• 2011.07a
• /
• pp.1954-1955
• /
• 2011

본 연구에서는 교육용으로 제작된 NXT 장비에 설치된 Light 센서, Ultrasonic센서, Sound센서를 이용하여 각 거리(10~60cm)에서 5cm 간격으로 각 센서 데이터를 취득하였다. 데이터 취득은 NI(National Instrument)에서 제공하는 LabVIEW Software를 사용하여 각 거리마다 100개의 셈플 데이터를 취득하였다. 취득한 데이터는 제안한 모델의 입력 데이터로 사용하여 실제거리와 모델 출력과의 정확도를 평가 하였다. 본 연구에서 제안한 모델은 지능형 모델 중 퍼지추론 기반의 최적 다항식 RBF 뉴럴네트워크(Radial Basis Function Neural Network; RBFNN)를 설계한다. 제안된 RBFNN은 기존 RBF 뉴럴네트워크를 기반으로 한 구조로, 퍼지추론 메커니즘의 기능적 모듈 동작 특성을 갖도록 정규화 부분을 추가하고, 은닉층과 출력층 사이의 연결가중치를 기존 상수항에서 선형식(first order)으로 확장한 형태이다. 또한 최적의 알고리즘인 PSO(Paticle Swarm Optimization)와 DE(Differential Evolution)을 이용하여 제안된 모델의 파라미터들을 동정하여 성능을 비교, 분석 하였다.

• Journal of the Korean Society for Precision Engineering
• /
• v.23 no.6 s.183
• /
• pp.44-51
• /
• 2006

This paper deals with the aspects of die design for the multistage fine tooth hub gear in the cold forging process. In order to manufacture the cold forged product for the precision hub gear used as the ARD 370 system of bicycle, it examines the influences of different designs on the metal flow through experiments and FE-simulation. To find the combination of design parameters which minimize the damage value, the low gear length, upper gear length and inner diameter as design parameters are considered. An orthogonal fraction factorial experiment is employed to study the influence of each parameter on the objective function or characteristics. The optimal punch shape of fine tooth hub gear is designed using the results of FE-simulation and the artificial neural network. To verify the optimal punch shape, the experiments of the cold forging of the hub gear are executed.