• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2004년도 ICEIC The International Conference on Electronics Informations and Communications
• /
• pp.237-243
• /
• 2004

A multichannel smart sound sensor capable to detect and identify sound events in noisy conditions is presented in this paper. Sound information extraction is a complex task and the main difficulty consists is the extraction of high­level information from an one-dimensional signal. The input of smart sound sensor is composed of data collected by 5 microphones and its output data is sent through a network. For a real time working purpose, the sound analysis is divided in three steps: sound event detection for each sound channel, fusion between simultaneously events and sound identification. The event detection module find impulsive signals in the noise and extracts them from the signal flow. Our smart sensor must be capable to identify impulsive signals but also speech presence too, in a noisy environment. The classification module is launched in a parallel task on the channel chosen by data fusion process. It looks to identify the event sound between seven predefined sound classes and uses a Gaussian Mixture Model (GMM) method. Mel Frequency Cepstral Coefficients are used in combination with new ones like zero crossing rate, centroid and roll-off point. This smart sound sensor is a part of a medical telemonitoring project with the aim of detecting serious accidents.

• 한국통신학회논문지
• /
• 제29권4C호
• /
• pp.472-484
• /
• 2004

본 논문에서는 CEGI (Complex Extended Gaussian Image)를 이용한 3D 메쉬 모델 워터마킹 알고리즘을 제안하였다. 제안한 알고리즘에서는 VRML 데이터의 3D 메쉬 모델을 6개 패치로 분할한 후, 각 패치의 CEGI 분포에서 복소 가중치의 크기가 큰 셀에 투영되는 메쉬의 법선 백터 방향에 워터마크를 삽입한다. 그리고 각 패치의 중점 좌표 및 CEGI 크기 분포의 우선 순위 정보를 이용하여 워터마크를 추출한다. 또한 아편 (affine) 변형된 모델에서는 패치의 초기 중점 좌표의 재배열 과정을 이용하여 원 모델의 방향으로 전환한 후, 워터마크를 추출한다. 본 논문에서 제안한 알고리즘의 성능을 평가하기 위한 실험에서 기하학적 및 위상학적 변형에 강인한 특성을 가짐을 확인하였다.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2005년도 추계학술대회논문집
• /
• pp.287-292
• /
• 2005

This paper presents a rational polynomial approximation method to estimate modal parameters of wind excited structures using incomplete noisy measurements of structural responses and partial measurements of wind velocities only. A stochastic model of the excitation wind force acting on the structure is estimated from partial measurements of wind velocities. Then the transfer functions of the structure are approximated as rational polynomial functions. From the poles and zeros of the estimated rational polynomial functions, the modal parameters, such as natural frequencies, damping ratios, and mode shapes are extracted. Since the frequency characteristics of wind forces acting on structures can be assumed as a smooth Gaussian process especially around the natural frequencies of the structures according to the central limit theorem (Brillinger, 1969; Yaglom, 1987), the estimated modal parameters are robust and reliable with respect to the assumed stochastic input models. To verify the proposed method, the modal parameters of a TV transmission tower excited by gust wind are estimated. Comparison study with the results of other researchers shows the efficacy of the suggested method.

• Geomechanics and Engineering
• /
• 제31권3호
• /
• pp.265-279
• /
• 2022

Tunnel convergence prediction is essential for the safe construction and design of tunnels. This study proposes five machine learning models of deep neural network (DNN), K-nearest neighbors (KNN), Gaussian process regression (GPR), support vector regression (SVR), and decision trees (DT) to predict the convergence phenomenon during or shortly after the excavation of tunnels. In this respect, a database including 650 datasets (440 for training, 110 for validation, and 100 for test) was gathered from the previously constructed tunnels. In the database, 12 effective parameters on the tunnel convergence and a target of tunnel wall convergence were considered. Both 5-fold and hold-out cross validation methods were used to analyze the predicted outcomes in the ML models. Finally, the DNN method was proposed as the most robust model. Also, to assess each parameter's contribution to the prediction problem, the backward selection method was used. The results showed that the highest and lowest impact parameters for tunnel convergence are tunnel depth and tunnel width, respectively.

• 소성∙가공
• /
• 제32권6호
• /
• pp.321-328
• /
• 2023

To ensure driver safety, high-strength steel pipes are utilized in the chassis and internal structures design of automobiles. ERW(electric resistance welding) pipes, fabricated through welding at joints using electrical resistance, form a Heat-Affected Zone (HAZ) during the welding process. Due to characteristics such as increased hardness and reduced ductility compared to the base material, HAZ poses challenges in finite element analysis (FEA) for pipe shapes. In this study, for FEA considering HAZ properties, mechanical properties were measured through uniaxial tensile testing and digital image correlation (DIC) techniques after specimen fabrication. These measurements were validated using reverse engineering methods. Furthermore, hardness measurements and gaussian functions were employed to ascertain the hardness distribution within the HAZ, serving as a basis for subdividing the HAZ and modeling the pipe shape. To validate the effectiveness of the HAZ modeling approach, models were interpreted incorporating only base material properties and models incorporating average-calculated HAZ properties. Comparative analysis was performed, revealing that the model subdividing the HAZ based on hardness measurements closely approximated experimental values. This validation offered a methodology for HAZ modeling in FEA.

• Geomechanics and Engineering
• /
• 제25권1호
• /
• pp.1-16
• /
• 2021

Machine learning models have been widely used for landslide susceptibility assessment (LSA) in recent years. The large number of inputs or conditioning factors for these models, however, can reduce the computation efficiency and increase the difficulty in collecting data. Feature selection is a good tool to address this problem by selecting the most important features among all factors to reduce the size of the input variables. However, two important questions need to be solved: (1) how do feature selection methods affect the performance of machine learning models? and (2) which feature selection method is the most suitable for a given machine learning model? This paper aims to address these two questions by comparing the predictive performance of 13 feature selection-based machine learning (FS-ML) models and 5 ordinary machine learning models on LSA. First, five commonly used machine learning models (i.e., logistic regression, support vector machine, artificial neural network, Gaussian process and random forest) and six typical feature selection methods in the literature are adopted to constitute the proposed models. Then, fifteen conditioning factors are chosen as input variables and 1,017 landslides are used as recorded data. Next, feature selection methods are used to obtain the importance of the conditioning factors to create feature subsets, based on which 13 FS-ML models are constructed. For each of the machine learning models, a best optimized FS-ML model is selected according to the area under curve value. Finally, five optimal FS-ML models are obtained and applied to the LSA of the studied area. The predictive abilities of the FS-ML models on LSA are verified and compared through the receive operating characteristic curve and statistical indicators such as sensitivity, specificity and accuracy. The results showed that different feature selection methods have different effects on the performance of LSA machine learning models. FS-ML models generally outperform the ordinary machine learning models. The best FS-ML model is the recursive feature elimination (RFE) optimized RF, and RFE is an optimal method for feature selection.

• Geomechanics and Engineering
• /
• 제30권6호
• /
• pp.489-502
• /
• 2022

In this study, a Gaussian process regression (GPR) model as well as six GPR-based metaheuristic optimization models, including GPR-PSO, GPR-GWO, GPR-MVO, GPR-MFO, GPR-SCA, and GPR-SSO, were developed to predict fly-rock distance in the blasting operation of open pit mines. These models included GPR-SCA, GPR-SSO, GPR-MVO, and GPR. In the models that were obtained from the Soungun copper mine in Iran, a total of 300 datasets were used. These datasets included six input parameters and one output parameter (fly-rock). In order to conduct the assessment of the prediction outcomes, many statistical evaluation indices were used. In the end, it was determined that the performance prediction of the ML models to predict the fly-rock from high to low is GPR-PSO, GPR-GWO, GPR-MVO, GPR-MFO, GPR-SCA, GPR-SSO, and GPR with ranking scores of 66, 60, 54, 46, 43, 38, and 30 (for 5-fold method), respectively. These scores correspond in conclusion, the GPR-PSO model generated the most accurate findings, hence it was suggested that this model be used to forecast the fly-rock. In addition, the mutual information test, also known as MIT, was used in order to investigate the influence that each input parameter had on the fly-rock. In the end, it was determined that the stemming (T) parameter was the most effective of all the parameters on the fly-rock.

• 예술인문사회 융합 멀티미디어 논문지
• /
• 제8권3호
• /
• pp.57-67
• /
• 2018

앙상블 기법은 기계학습에서 다수의 알고리즘을 사용하여 더 좋은 성능을 내기 위해 사용하는 방법이다. 본 논문에서는 앙상블 기법에서 많이 사용되는 부스팅과 배깅에 대해 소개를 하고, 서포트벡터 회귀, 방사기저함수 네트워크, 가우시안 프로세스, 다층 퍼셉트론을 이용하여 설계한다. 추가적으로 순환신경망과 MOHID 수치모델을 추가하여 실험을 진행한다. 실험적 검증를 위해 사용하는 뜰개 데이터는 7 개의 지역에서 관측된 683 개의 관측 자료다. 뜰개 관측 자료를 이용하여 6 개의 알고리즘과의 비교를 통해 앙상블 기법의 성능을 검증한다. 검증 방법으로는 평균절대오차를 사용한다. 실험 방법은 배깅, 부스팅, 기계학습을 이용한 앙상블 모델을 이용하여 진행한다. 각 앙상블 모델마다 동일한 가중치를 부여한 방법, 차등한 가중치를 부여한 방법을 이용하여 오류율을 계산한다. 가장 좋은 오류율을 나타낸 방법은 기계학습을 이용한 앙상블 모델로서 6 개의 기계학습의 평균에 비해 61.7%가 개선된 결과를 보였다.

• 한국항공우주학회지
• /
• 제49권9호
• /
• pp.709-719
• /
• 2021

최근 들어 비행 시뮬레이션 기술의 정확도 향상과 기술의 발전으로 실제 비행시험 횟수를 줄이고 시뮬레이션으로 비행 안전과 인증을 확인하는 가상 인증이 확대되는 추세에 있다. 고신뢰도의 비행 시뮬레이션을 위해서는 고정밀도의 공력 데이터를 다양한 받음각과 마하수, 옆 미끄럼각 범위에서 구성해야 한다. 본 연구에서는 정밀한 공력 데이터베이스의 구축을 위해 최적 설계에 주로 사용되는 다양한 데이터 융합 기법의 하나인 Gaussian Process(GP) 기반의 변형 정밀도 모델링(VFM, Variable Fidelity Modeling) 기법과 Adaptive Sampling 기법을 결합하여 개선 변형 정밀도(Improved VFM) 기법을 제안하였다. Case study로 F-16 전투기를 선정하고 고정밀도 데이터의 종류에 따라 4개의 Case를 분류하여 각각의 오차와 정확도를 확인하였다. 여기에 본 연구에서 제안하는 개선 VFM 데이터 융합 기법을 적용하여 고정밀 공력 데이터 사용 횟수를 최소화함으로써 그 유용함을 확인할 수 있었다. 또한, Gliding, Short Term Pitch Response, Roll Mode 기동에 대한 실제 실험 데이터 대비 항공안전 인증 요구 만족 여부를 확인하였다. 이를 통해 개선 변형 정밀도 모델링을 사용한 고정밀도 시뮬레이션의 가상 인증 적용 가능성을 확인하였다.

• 응용통계연구
• /
• 제33권1호
• /
• pp.25-46
• /
• 2020

본 논문에서는 Bayesian spectral analysis regression (BSAR) 방법론을 이용한 베이지안 순서형 프로빗 준모수 회귀모형에 대해서 고찰한다. 순서형 프로빗 회귀모형은 순서가 있는 범주형 자료를 모형화하는 방법으로, 정규 분포의 분포함수의 역함수인 프로빗 연결함수를 이용해 각 범주의 확률과 설명변수을 연결함으로써 반응변수의 확률을 모형화한다. 베이지안 프로빗 회귀 모형은 정규 분포를 따르는 잠재변수를 도입함으로써 사후 분포 도출을 용이하게 하고, 절단점에 따라 나뉘어지는 잠재변수들의 값에 따라서 반응 변수들이 범주화된다. 본 논문에서는 이러한 잠재 변수 방법을 확장해 BSAR 방법론에 기반하여 단조증가/감소와 같은 형태제약을 반영할 수 있는 베이지안 이항형 및 순서형 프로빗 준모수 회귀모형에 대해 연구한다. 모의실험을 통하여 이항형 프로빗 준모수 회귀모형과 기존의 다른 모형들 간의 적합결과를 비교하고, 형태 제약에 따른 순서형 프로빗 준모수 회귀모형의 적합결과를 비교 분석하도록 한다. 아울러, 국민건강영양조사 제 7기 1차년도 (2016) 자료(Korean National Health and Nutrition Examination Survey (KNHANES), 2016)를 바탕으로, 본 논문에서 고찰한 이항형 및 순서형 프로빗 준모수 회귀모형을 적용하여, 흡연양태와 커피섭취 간의 관계에 대한 실증적 분석을 수행한다.