• 응용통계연구
• /
• 제23권4호
• /
• pp.759-765
• /
• 2010

In this paper, two new inverse regression methods are introduced. One is a distance based method, and the other is a likelihood based method. While a model is fitted by minimizing the sum of squared prediction errors of y's and x's in the classical and inverse methods, respectively. In the new distance based method, we simultaneously minimize the sum of both squared prediction errors. In the likelihood based method, we propose an inverse regression with Arnold-Beaver Skew Normal(ABSN) error distribution. Using the cross validation method with an asymmetric real data set, two new and two existing methods are studied based on the relative prediction bias(RBP) criteria.

• 대한기계학회논문집A
• /
• 제27권12호
• /
• pp.2061-2071
• /
• 2003

The macro-parametric approach, which is a method of CAD model exchange, has recently been proposed. CAD models can be exchanged in the form of a macro file, which is a sequence of modeling commands. As an event-driven commands set, the standard macro file can transfer design intents such as parameters, features and constraints. Moreover it is suitable for the network environment because the standard macro commands are open, explicit, and the data size is small. This paper introduces the concept of the macro-parametric method and proposes its representation using XML technology. Representing the macro-parametric data using XML allows managing vast amount of dynamic contents, Web-enabled distributed applications, and inherent characteristic of structure and validation.

• Wind and Structures
• /
• 제1권1호
• /
• pp.77-109
• /
• 1998

An evaluation and comparison of seven of the world's major building codes and standards is conducted in this study, with specific discussion of their estimations of the alongwind, acrosswind, and torsional response, where applicable, for a given building. The codes and standards highlighted by this study are those of the United States, Japan, Australia, the United Kingdom, Canada, China and Europe. In addition, the responses predicted by using the measured power spectra of the alongwind, acrosswind and torsional responses for several building shapes tested in a wind tunnel are presented and a comparison between the response predicted by wind tunnel data and that estimated by some of the standards is conducted. This study serves not only as a comparison of the response estimates by international codes and standards, but also introduces a new set of wind tunnel data for validation of wind tunnel-based empirical expressions.

• Tuberculosis and Respiratory Diseases
• /
• 제86권3호
• /
• pp.203-215
• /
• 2023

Background: Surgical resection is the standard treatment for early-stage lung cancer. Since postoperative lung function is related to mortality, predicted postoperative lung function is used to determine the treatment modality. The aim of this study was to evaluate the predictive performance of linear regression and machine learning models. Methods: We extracted data from the Clinical Data Warehouse and developed three sets: set I, the linear regression model; set II, machine learning models omitting the missing data: and set III, machine learning models imputing the missing data. Six machine learning models, the least absolute shrinkage and selection operator (LASSO), Ridge regression, ElasticNet, Random Forest, eXtreme gradient boosting (XGBoost), and the light gradient boosting machine (LightGBM) were implemented. The forced expiratory volume in 1 second measured 6 months after surgery was defined as the outcome. Five-fold cross-validation was performed for hyperparameter tuning of the machine learning models. The dataset was split into training and test datasets at a 70:30 ratio. Implementation was done after dataset splitting in set III. Predictive performance was evaluated by R² and mean squared error (MSE) in the three sets. Results: A total of 1,487 patients were included in sets I and III and 896 patients were included in set II. In set I, the R² value was 0.27 and in set II, LightGBM was the best model with the highest R² value of 0.5 and the lowest MSE of 154.95. In set III, LightGBM was the best model with the highest R² value of 0.56 and the lowest MSE of 174.07. Conclusion: The LightGBM model showed the best performance in predicting postoperative lung function.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2020년도 학술발표회
• /
• pp.170-170
• /
• 2020

Due to the development of technologies, complex computation of huge data set is possible with a prevalent personal computer. Therefore, machine learning methods have been widely applied in the hydrologic field such as regression-based regional frequency analysis (RFA). The main purpose of this study is to compare two frameworks of RFA based on the artificial neural network (ANN) models: quantile regression technique (QRT-ANN) and parameter regression technique (PRT-ANN). As an output layer of the ANN model, the QRT-ANN predicts quantiles for various return periods whereas the PRT-ANN provides prediction of three parameters for the generalized extreme value distribution. Rainfall gauging sites where record length is more than 20 years were selected and their annual maximum rainfalls and various hydro-meteorological variables were used as an input layer of the ANN model. While employing the ANN model, 70% and 30% of gauging sites were used as training set and testing set, respectively. For each technique, ANN model structure such as number of hidden layers and nodes was determined by a leave-one-out validation with calculating root mean square error (RMSE). To assess the performances of two frameworks, RMSEs of quantile predicted by the QRT-ANN are compared to those of the PRT-ANN.

• 한국식품저장유통학회지
• /
• 제6권1호
• /
• pp.29-36
• /
• 1999

Using Fuji apple fruits cultivated in Kyungpook prefecture, the calibration model for firmness evaluation of fruits by near infrared(NIR) reflectance spectroscopy was developed, and the various influence factors such as instrument variety, measuring method, sample group, apple peel and selection of firmness point were investigated. Spectra of sample were recorded in wavelength range of 1100∼2500nm using NIR spectrometer (InfraAlyzer 500), and data were analyzed by stepwise multiple linear regression of IDAS program. The accuracy of calibration model was the highest when using sample group with wide range, and the firmness mean values obtained in graph by texture analyser(TA) were used as standard data. Chemometrics models were developed using a calibration set of 324 samples and an independent validation set of 216 samples to evaluate the predictive ability of the models. The correlation coefficients and standard error of prediction were 0.84 and 0.094kg, respectively. Using developed calibration model, it was possible to monitor the firmness change of fruits during storage frequently. Time, which was reached to firmness high value in graph by TA, is possible to use as new parameter for freshness of fruit surface during storage.

• Structural Engineering and Mechanics
• /
• 제32권6호
• /
• pp.787-809
• /
• 2009

Recent interest in the use of wireless sensor networks for structural health monitoring (SHM) is mainly due to their low implementation costs and potential to measure the responses of a structure at unprecedented spatial resolution. Approaches capable of detecting damage using distributed processing must be developed in parallel with this technology to significantly reduce the power consumption and communication bandwidth requirements of the sensor platforms. In this investigation, a damage detection system based on a distributed processing approach is proposed and experimentally validated using a wireless sensor network deployed on two laboratory structures. In this distributed approach, on-board processing capabilities of the wireless sensor are exploited to significantly reduce the communication load and power consumption. The Damage Location Assurance Criterion (DLAC) is used for localizing damage. Processing of the raw data is conducted at the sensor level, and a reduced data set is transmitted to the base station for decision-making. The results indicate that this distributed implementation can be used to successfully detect and localize regions of damage in a structure. To further support the experimental results obtained, the capabilities of the proposed system were tested through a series of numerical simulations with an expanded set of damage scenarios.

• Korean Journal of Radiology
• /
• 제23권12호
• /
• pp.1260-1268
• /
• 2022

Objective: To propose standardized MRI-proton density fat fraction (PDFF) cutoff values for diagnosing hepatic steatosis, evaluated using contemporary PDFF measuring methods in a large population of healthy adults, using histologic fat fraction (HFF) as the reference standard. Materials and Methods: A retrospective search of electronic medical records between 2015 and 2018 identified 1063 adult donor candidates for liver transplantation who had undergone liver MRI and liver biopsy within a 7-day interval. Patients with a history of liver disease or significant alcohol consumption were excluded. Chemical shift imaging-based MRI (CS-MRI) PDFF and high-speed T2-corrected multi-echo MR spectroscopy (HISTO-MRS) PDFF data were obtained. By temporal splitting, the total population was divided into development and validation sets. Receiver operating characteristic (ROC) analysis was performed to evaluate the diagnostic performance of the MRI-PDFF method. Two cutoff values with sensitivity > 90% and specificity > 90% were selected to rule-out and rule-in, respectively, hepatic steatosis with reference to HFF ≥ 5% in the development set. The diagnostic performance was assessed using the validation set. Results: Of 921 final participants (624 male; mean age ± standard deviation, 31.5 ± 9.0 years), the development and validation sets comprised 497 and 424 patients, respectively. In the development set, the areas under the ROC curve for diagnosing hepatic steatosis were 0.920 for CS-MRI-PDFF and 0.915 for HISTO-MRS-PDFF. For ruling-out hepatic steatosis, the CS-MRI-PDFF cutoff was 2.3% (sensitivity, 92.4%; specificity, 63.0%) and the HISTO-MRI-PDFF cutoff was 2.6% (sensitivity, 88.8%; specificity, 70.1%). For ruling-in hepatic steatosis, the CS-MRI-PDFF cutoff was 3.5% (sensitivity, 73.5%; specificity, 88.6%) and the HISTO-MRI-PDFF cutoff was 4.0% (sensitivity, 74.7%; specificity, 90.6%). Conclusion: In a large population of healthy adults, our study suggests diagnostic thresholds for ruling-out and ruling-in hepatic steatosis defined as HFF ≥ 5% by contemporary PDFF measurement methods.

• 지능정보연구
• /
• 제16권3호
• /
• pp.77-97
• /
• 2010

매매시점결정은 금융시장에서 초과수익을 얻기 위해 사용되는 투자전략이다. 일반적으로, 매매시점 결정은 거래를 통한 초과수익을 얻기 위해 언제 매매할 것인지를 결정하는 것을 의미한다. 몇몇 연구자들은 러프집합분석이 매매시점결정에 적합한 도구라고 주장하였는데, 그 이유는 이 분석방법이 통제함수를 이용하여 시장의 패턴이 불확실할 때에는 거래를 위한 신호를 생성하지 않는다는 점 때문이었다. 러프집합은 분석을 위해 범주형 데이터만을 이용하므로, 분석에 사용되는 데이터는 연속형의 수치값을 이산화하여야 한다. 이산화란 연속형 수치값의 범주화 구간을 결정하기 위한 적절한 "경계값"을 찾는 것이다. 각각의 구간 내에서의 모든 값은 같은 값으로 변환된다. 일반적으로, 러프집합 분석에서의 데이터 이산화 방법은 등분위 이산화, 전문가 지식에 의한 이산화, 최소 엔트로피 기준 이산화, Na$\ddot{i}$ve and Boolean reasoning 이산화 등의 네 가지로 구분된다. 등분위 이산화는 구간의 수를 고정하고 각 변수의 히스토그램을 확인한 후, 각각의 구간에 같은 숫자의 표본이 배정되도록 경계값을 결정한다. 전문가 지식에 의한 이산화는 전문가와의 인터뷰 또는 선행연구 조사를 통해 얻어진 해당 분야 전문가의 지식에 따라 경계값을 정한다. 최소 엔트로피 기준 이산화는 각 범주의 엔트로피 측정값이 최적화 되도록 각 변수의 값을 재귀분할 하는 방식으로 알고리즘을 진행한다. Na$\ddot{i}$ve and Boolean reasoning 이산화는 Na$\ddot{i}$ve scaling 후에 그로 인해 분할된 범주값을 Boolean reasoning 방법으로 종속변수 값에 대해 최적화된 이산화 경계값을 구하는 방법이다. 비록 러프집합분석이 매매시점결정에 유망할 것으로 판단되지만, 러프집합분석을 이용한 거래를 통한 성과에 미치는 여러 이산화 방법의 효과에 대한 연구는 거의 이루어지지 않았다. 본 연구에서는 러프집합분석을 이용한 주식시장 매매시점결정 모형을 구성함에 있어서 다양한 이산화 방법론을 비교할 것이다. 연구에 사용된 데이터는 1996년 5월부터 1998년 10월까지의 KOSPI 200데이터이다. KOSPI 200은 한국 주식시장에서 최초의 파생상품인 KOSPI 200 선물의 기저 지수이다. KOSPI 200은 제조업, 건설업, 통신업, 전기와 가스업, 유통과 서비스업, 금융업 등에서 유동성과 해당 산업 내의 위상 등을 기준으로 선택된 200개 주식으로 구성된 시장가치 가중지수이다. 표본의 총 개수는 660거래일이다. 또한, 본 연구에서는 유명한 기술적 지표를 독립변수로 사용한다. 실험 결과, 학습용 표본에서는 Na$\ddot{i}$ve and Boolean reasoning 이산화 방법이 가장 수익성이 높았으나, 검증용 표본에서는 전문가 지식에 의한 이산화가 가장 수익성이 높은 방법이었다. 또한, 전문가 지식에 의한 이산화가 학습용과 검증용 데이터 모두에서 안정적인 성과를 나타내었다. 본 연구에서는 러프집합분석과 의사결정 나무분석의 비교도 수행하였으며, 의사결정나무분석은 C4.5를 이용하였다. 실험결과, 전문가 지식에 의한 이산화를 이용한 러프집합분석이 C4.5보다 수익성이 높은 매매규칙을 생성하는 것으로 나타났다.

• Advances in nano research
• /
• 제12권2호
• /
• pp.197-212
• /
• 2022

The purpose of this study is to develop an automatic software system for bone age evaluation and to evaluate its accuracy in testing and feasibility in clinical practice. 20394 left-hand radiographs of healthy children (2-18 years old) were collected from China Skeletal Development Survey data of 1998 and China Skeletal Development Survey data of 2005. Three experienced radiologists and China-05 standard maker jointly evaluate the stages of bone development and the reference bone age was determined by consensus. 1020 from 20394 radiographs were picked randomly as test set and the remaining 19374 radiographs as training set and validation set. Accuracy of the automatic software system for bone age assessment is evaluated in test set and two clinical test sets. Compared with the reference standard, the automatic software system based on RUS-CHN for bone age assessment has a 0.04 years old mean difference, ±0.40 years old in 95% confidence interval by single reading, a 85.6% percentage agreement of ratings, a 93.7% bone age accuracy rate, 0.17 years old of MAD, 0.29 years old of RMS; Compared with the reference standard, the automatic software system based on TW3-C RUS has a 0.04 years old mean difference, a ±0.38 years old in 95% confidence interval by single reading, a 90.9% percentage agreement of ratings, a 93.2% bone age accuracy rate, a 0.16 years of MAD, and a 0.28 years of RMS. Automatic software system, AI-China-05 showed reliably accuracy in bone age estimation and steady determination in different clinical test sets.