• Title/Summary/Keyword: 다항회귀모델

Search Result 35, Processing Time 0.027 seconds

An Artificial Neural Network for Efficiently Learning and Representation the Advection and Remove of Fire-Flake Particles (불똥 입자의 이류과 삭제를 효율적으로 학습 표현하는 인공신경망)

  • Kim, Donghui;Kim, Jong-Hyun
    • Proceedings of the Korean Society of Computer Information Conference
    • /
    • 2022.01a
    • /
    • pp.345-348
    • /
    • 2022
  • 본 논문에서는 유체 시뮬레이션(Fluid simulation)중 화염에서 표현되는 불똥 입자(Fire-flake particle)의 생성, 움직임과 삭제를 효율적으로 학습하고 표현할 수 있는 인공지능 기법에 대해 소개한다. 유체 시뮬레이션을 계산하기 위해서는 일반적으로 수치해석학과 같은 학문의 이해가 필요하며 불똥이나 거품과 같은 유체의 2차 효과(Secondary effect)는 기반유체(Underlying fluids)를 통해 추출되기 때문에 복잡하고 계산양이 많아진다. 이러한 문제를 완화하고자 본 논문에서는 인공신경망을 이용한 분류 모델 학습을 통해 격자 내에서 표현되어야 하는 불똥 입자의 생성을 학습하고, 다항 회귀 모델 학습을 통해 불똥 입자의 움직임을 예측한다. 또한, 불똥 입자가 삭제되어야하는 상태를 네트워크 학습을 통해 얻어내며, 수명(Lifespan) 임계값 조절하여 다양한 장면에서 불똥을 제어할 수 있다. 결과적으로 화염의 움직임을 기반으로 불똥의 움직임을 복잡한 수학식이나 디자이너에게 의존하지 않고 인공지능 학습을 통해 쉽게 제어하고 예측하는 결과를 보여준다.

  • PDF

A Study on the Application of Suitable Urban Regeneration Project Types Reflecting the Spatial Characteristics of Urban Declining Areas (도시 쇠퇴지역 공간 특성을 반영한 적합 도시재생 사업유형 적용방안 연구)

  • CHO, Don-Cherl;SHIN, Dong-Bin
    • Journal of the Korean Association of Geographic Information Studies
    • /
    • v.24 no.4
    • /
    • pp.148-163
    • /
    • 2021
  • The diversification of the New Deal urban regeneration projects, that started in 2017 in accordance with the "Special Act on Urban Regeneration Activation and Support", generated the increased demand for the accuracy of data-driven diagnosis and project type forecast. Thus, this research was conducted to develop an application model able to identify the most appropriate New Deal project type for "eup", "myeon" and "dong" across the country. Data for application model development were collected through Statistical geographic information service(SGIS) and the 'Urban Regeneration Comprehensive Information Open System' of the Urban Regeneration Information System, and data for the analysis model was constructed through data pre-processing. Four models were derived and simulations were performed through polynomial regression analysis and multinomial logistic regression analysis for the application of the appropriate New Deal project type. I verified the applicability and validity of the four models by the comparative analysis of spatial distribution of the previously selected New Deal projects by targeting the sites located in Seoul by each model and the result showed that the DI-54 model had the highest concordance rate.

Evaluation of a Thermal Conductivity Prediction Model for Compacted Clay Based on a Machine Learning Method (기계학습법을 통한 압축 벤토나이트의 열전도도 추정 모델 평가)

  • Yoon, Seok;Bang, Hyun-Tae;Kim, Geon-Young;Jeon, Haemin
    • KSCE Journal of Civil and Environmental Engineering Research
    • /
    • v.41 no.2
    • /
    • pp.123-131
    • /
    • 2021
  • The buffer is a key component of an engineered barrier system that safeguards the disposal of high-level radioactive waste. Buffers are located between disposal canisters and host rock, and they can restrain the release of radionuclides and protect canisters from the inflow of ground water. Since considerable heat is released from a disposal canister to the surrounding buffer, the thermal conductivity of the buffer is a very important parameter in the entire disposal safety. For this reason, a lot of research has been conducted on thermal conductivity prediction models that consider various factors. In this study, the thermal conductivity of a buffer is estimated using the machine learning methods of: linear regression, decision tree, support vector machine (SVM), ensemble, Gaussian process regression (GPR), neural network, deep belief network, and genetic programming. In the results, the machine learning methods such as ensemble, genetic programming, SVM with cubic parameter, and GPR showed better performance compared with the regression model, with the ensemble with XGBoost and Gaussian process regression models showing best performance.

Flood Risk Forecasting using Logistic Regression for the Han River Basin (로지스틱 회귀분석을 활용한 한강권역 홍수위험 예보기법 개발)

  • Lee, Seon Mi;Choi, Youngje;Yi, Jaeeung
    • Proceedings of the Korea Water Resources Association Conference
    • /
    • 2021.06a
    • /
    • pp.354-354
    • /
    • 2021
  • 2020년은 장마기간이 49일간 지속됨에 따라 침수, 산사태 등 많은 홍수피해가 발생하였다. 특히 서울에서는 한강 본류의 수위가 급격하게 증가함에 따라 둔치 및 도로 침수 피해가 발생하였다. 이처럼 하천의 수위증가로 인한 홍수피해에 대응하기 위해 홍수통제소 및 기초지자체에서는 홍수특보를 발령한다. 이 홍수특보는 수위관측소 지점별 계획홍수량의 50 %, 70 % 이상의 홍수량이 발생할 경우 홍수주의보와 홍수경보가 발령되며, 이 기준은 각 권역별로 동일하다. 하지만 2017년 의정부시에서는 중랑천 수위증가로 인해 주변 지역에 침수피해가 발생하였지만, 이때 홍수량은 계획홍수량 대비 약 30 %에 불과하였다. 이처럼 한강권역 내 하천수위 증가로 인한 홍수피해는 계획홍수량의 50 % 이내에서 발생하기도 한다. 이에 본 연구에서는 한강권역을 대상으로 현재 2단계로 발령되는 홍수특보를 3단계로 세분화하고자 하였다. 단계별 홍수량 위험기준을 산정하기 위해 과거 홍수피해 발생 이력이 있는 한강권역 내 43개의 수위관측소 지점을 선정하였으며, 지점별 홍수기 동안의 홍수량 및 피해액 자료를 수집하였다. 각 단계별 홍수량 기준을 산정하기 위해서는 로지스틱 회귀분석 방법을 활용하여 피해발생 확률을 산정하였다. 1단계 기준은 계획홍수량 대비 홍수량 비율과 홍수피해 발생여부를 고려한 이항 로지스틱 회귀분석 모델을 구축한 후 3계 도함수에 적용하여 홍수피해 발생확률이 급격하게 증가하는 특이점을 산정하였다. 2단계와 3단계 기준은 다항 로지스틱 회귀분석 중 계층형 로지스틱 회귀분석을 활용하여 지점별 피해액 비율이 60 ~ 80 %, 80 ~ 100 % 구간에 속할 확률을 산정하고, 1단계와 동일한 방법으로 특이점을 산정하였다. 그 결과 지점별로 기존 제공되고 있는 홍수특보 기준을 과거 발생한 홍수피해를 고려하여 세분화할 수 있었으며, 이 결과는 지역별 홍수피해 저감대책에 활용될 수 있을 것으로 판단된다.

  • PDF

Recognition for Noisy Speech by a Nonstationary AR HMM with Gain Adaptation Under Unknown Noise (잡음하에서 이득 적응을 가지는 비정상상태 자기회귀 은닉 마코프 모델에 의한 오염된 음성을 위한 인식)

  • 이기용;서창우;이주헌
    • The Journal of the Acoustical Society of Korea
    • /
    • v.21 no.1
    • /
    • pp.11-18
    • /
    • 2002
  • In this paper, a gain-adapted speech recognition method in noise is developed in the time domain. Noise is assumed to be colored. To cope with the notable nonstationary nature of speech signals such as fricative, glides, liquids, and transition region between phones, the nonstationary autoregressive (NAR) hidden Markov model (HMM) is used. The nonstationary AR process is represented by using polynomial functions with a linear combination of M known basis functions. When only noisy signals are available, the estimation problem of noise inevitably arises. By using multiple Kalman filters, the estimation of noise model and gain contour of speech is performed. Noise estimation of the proposed method can eliminate noise from noisy speech to get an enhanced speech signal. Compared to the conventional ARHMM with noise estimation, our proposed NAR-HMM with noise estimation improves the recognition performance about 2-3%.

Velocity Considered Sectional Porosity Equivalent Model (VSPE) of Filters for CFD Analysis of Breakaway Devices (수소 브레이크어웨이 디바이스 유동해석을 위한 필터의 구간별 다공성 등가 모델 제시)

  • Son, Seong-Jae;An, Su-Jin;Song, Tae-Hoon;Joe, Choong-Hee;Park, Sang-Hu
    • Journal of the Korean Society of Manufacturing Process Engineers
    • /
    • v.18 no.8
    • /
    • pp.82-90
    • /
    • 2019
  • We propose an equivalent model of a sintered metal mesh filter calculated by Ergun's equation and polynomial regression for the CFD analysis of breakaway devices at a hydrogen fueling station. CFD analysis of filters that cause high pressure loss is essential because breakaway devices in high-pressure hydrogen conditions require low pressure loss. A differential pressure experiment with a filter was performed in a low-pressure air condition considering similarities. An equivalent model was developed by deriving the resistance value by the polynomial regression using the experimental results. The results of CFD analysis using the equivalent model show that there was almost no error in the operating condition of the breakaway device compared to the experimental results. Through this work, we believe that the proposed equivalent model of a filter can be applied to the analysis of breakaway devices in hydrogen fueling stations. We will study how to optimize the shape and position of the filter in breakaway devices using the developed equivalent model.

Implementation of the Color Matching Between Mobile Camera and Mobile LCD Based on RGB LUT (모바일 폰의 카메라와 LCD 모듈간의 RGB 참조표에 기반한 색 정합의 구현)

  • Son Chang-Hwan;Park Kee-Hyon;Lee Cheol-Hee;Ha Yeong-Ho
    • Journal of the Institute of Electronics Engineers of Korea SP
    • /
    • v.43 no.3 s.309
    • /
    • pp.25-33
    • /
    • 2006
  • This paper proposed device-independent color matching algorithm based on the 3D RGB lookup table (LUT) between mobile camera and mobile LCD (Liquid Crystal Display) to improve the color-fidelity. Proposed algorithm is composed of thee steps, which is device characterization, gamut mapping, 3D RGB-LUT design. First, the characterization of mobile LCD is executed using the sigmoidal function, different from conventional method such as GOG (Gain Offset Gamma) and S-curve modeling, based on the observation of electro-optical transfer function of mobile LCD. Next, mobile camera characterization is conducted by fitting the digital value of GretagColor chart captured under the daylight environment (D65) and tristimulus values (CIELAB) using the polynomial regression. However, the CIELAB values estimated by polynomial regression exceed the maximum boundary of the CIELAB color space. Therefore, these values are corrected by linear compression of the lightness and chroma. Finally, gamut mapping is used to overcome the gamut difference between mobile camera and moible LCD. To implement the real-time processing, 3D RGB-LUT is designed based on the 3D RGB-LUT and its performance is evaluated and compared with conventional method.

Optimization of Synthesis Condition of Monolithic Sorbent Using Response Surface Methodology (반응 표면 분석법을 이용한 일체형 흡착제의 합성 조건 최적화)

  • Park, Ha Eun;Row, Kyung Ho
    • Applied Chemistry for Engineering
    • /
    • v.24 no.3
    • /
    • pp.299-304
    • /
    • 2013
  • A 17-run Box-Behnken design was used to optimize the synthesis conditions of a monolithic sorbent. The effects of the amount of monomer (mL), crosslink (mL) and porogen (mL) were investigated. The experimental data were fitted to a second-order polynomial equation by the multiple regression analysis and examined using statistical methods. The adjusted coefficient of determination ($R^2$) of the model was 0.9915. The probability value (p < 0.0001) demonstrated a high significance for the regression model. A mean amount of polymer as 2120.15 mg was produced under the following optimum synthesis conditions: the optimized volumes of monomer, crosslink and porogen are 0.30, 1.40, and 1.47 mL, respectively. This was in good agreement with the predicted model value.

An analysis methodology for the power generation of a solar power plant considering weather, location, and installation conditions (입지 및 설치방식에 따른 태양광 발전량 분석 방법에 관한 연구)

  • Byoung Noh Heo;Jae Hyun Lee
    • Journal of Korea Society of Industrial Information Systems
    • /
    • v.28 no.6
    • /
    • pp.91-98
    • /
    • 2023
  • The amount of power generation of a solar plant has a high correlation with weather conditions, geographical conditions, and the installation conditions of solar panels. Previous studies have found the elements which impacts the amount of power generation. Some of them found the optimal conditions for solar panels to generate the maximum amount of power. Considering the realistic constraints when installing a solar power plant, it is very difficult to satisfy the conditions for the maximum power generation. Therefore, it is necessary to know how sensitive the solar power generation amount is to factors affecting the power generation amount, so that plant owners can predict the amount of solar power generation when examining the installation of a solar power plant. In this study, we propose a polynomial regression analysis method to analyze the relationship between solar power plant's power generation and related factors such as weather, location, and installation conditions. Analysis data were collected from 10 solar power plants installed and operated in Daegu and Gyeongbuk. As a result of the analysis, it was found that the amount of power generation was affected by panel type, amount of insolation and shade. In addition, the power generation was affected by interaction of the installation angle and direction of the panel.

Longitudinal Patterns of Stages of Changes in Smoking Behaviors among Korean Adult Smokers: Applying the Transtheoretical Model of Change (범이론적 모델에 기반을 둔 흡연자의 금연행동 변화단계에 대한 탐색적 연구)

  • Park, Hyunyong;Jun, Jina;Sohn, Sunju
    • Korean Journal of Social Welfare Studies
    • /
    • v.49 no.1
    • /
    • pp.5-28
    • /
    • 2018
  • Smoking is one of the important public health concerns because it is preventable causes regarding individuals' negative health consequences and increased social and economic cost. However, few studies have examined longitudinal patterns of stages of changes(SOC) in smoking behaviors among the general population. The purpose of the study is to explore the latent patterns of SOC over time among Korean adult smokers using the 2008-2016 Korea Welfare Panel Study. A repeated measure latent class analysis is employed in the present study. The finding of the present study are as follows: First, four latent groups were identified: (1) action/maintenance stage(33.6%), (2) contemplation/preparation to action/maintenance stage(14.8%), (3) continuously contemplation/preparation stage(29.6%), and (4) continuously pre-contemplation stage(22.1%). Second, the results of a multinomial logistic regression found that socio-demographic and clinical characteristics were associated with the identified longitudinal patterns of smoking behaviors. Compared to a continuously pre-contemplation stage, higher levels of depressive symptoms and drinking behavior were associated with increased odds of being in action/maintenance stage. The findings of the present study highlight that a tailored intervention is needed for individuals with continuously pre-contemplation stage and contemplation stage.