• Communications for Statistical Applications and Methods
• /
• 제27권4호
• /
• pp.445-458
• /
• 2020

The least absolute shrinkage and selection operator (LASSO) is a popular method for a high-dimensional regression model. LASSO has high prediction accuracy; however, it also selects many irrelevant variables. In this paper, we consider the moderately clipped LASSO (MCL) for the high-dimensional generalized linear model which is a hybrid method of the LASSO and minimax concave penalty (MCP). The MCL preserves advantages of the LASSO and MCP since it shows high prediction accuracy and successfully selects relevant variables. We prove that the MCL achieves the oracle property under some regularity conditions, even when the number of parameters is larger than the sample size. An efficient algorithm is also provided. Various numerical studies confirm that the MCL can be a better alternative to other competitors.

• 국제학술발표논문집
• /
• The 4th International Conference on Construction Engineering and Project Management Organized by the University of New South Wales
• /
• pp.432-438
• /
• 2011

The purpose of the present thesis is to develop bankruptcy prediction models capable of being applied to the Korean construction industry and to deduce an optimal model through comparative evaluation of final developed models. A study population was selected as general contractors in the Korean construction industry. In order to ease the sample securing and reliability of data, it was limited to general contractors receiving external audit from the government. The study samples are divided into a bankrupt company group and a non-bankrupt company group. The bankruptcy, insolvency, declaration of insolvency, workout and corporate reorganization were used as selection criteria of a bankrupt company. A company that is not included in the selection criteria of the bankrupt company group was selected as a non-bankrupt company. Accordingly, the study sample is composed of a total of 112 samples and is composed of 48 bankrupt companies and 64 non-bankrupt companies. A financial ratio was used as early predictors for development of an estimation model. A total of 90 financial ratios were used and were divided into growth, profitability, productivity and added value. The MDA (Multivariate Discriminant Analysis) model and BLRA (Binary Logistic Regression Analysis) model were used for development of bankruptcy prediction models. The MDA model is an analysis method often used in the past bankruptcy prediction literature, and the BLRA is an analysis method capable of avoiding equal variance assumption. The stepwise (MDA) and forward stepwise method (BLRA) were used for selection of predictor variables in case of model construction. Twenty two variables were finally used in MDA and BLRA models according to timing of bankruptcy. The ROC-Curve Analysis and Classification Analysis were used for analysis of prediction performance of estimation models. The correct classification rate of an individual bankruptcy prediction model is as follows: 1) one year ago before the event of bankruptcy (MDA: 83.04%, BLRA: 93.75%); 2) two years ago before the event of bankruptcy (MDA: 77.68%, BLRA: 78.57%); 3) 3 years ago before the event of bankruptcy (MDA: 84.82%, BLRA: 91.96%). The AUC (Area Under Curve) of an individual bankruptcy prediction model is as follows. : 1) one year ago before the event of bankruptcy (MDA: 0.933, BLRA: 0.978); 2) two years ago before the event of bankruptcy (MDA: 0.852, BLRA: 0.875); 3) 3 years ago before the event of bankruptcy (MDA: 0.938, BLRA: 0.975). As a result of the present research, accuracy of the BLRA model is higher than the MDA model and its prediction performance is improved.

• Journal of Information Processing Systems
• /
• 제14권4호
• /
• pp.904-915
• /
• 2018

We demonstrate how social media content can be used to predict the unemployment rate, a real-world indicator. We present a novel method for predicting the unemployment rate using social media analysis based on natural language processing and statistical modeling. The system collects social media contents including news articles, blogs, and tweets written in Korean, and then extracts data for modeling using part-of-speech tagging and sentiment analysis techniques. The autoregressive integrated moving average with exogenous variables (ARIMAX) and autoregressive with exogenous variables (ARX) models for unemployment rate prediction are fit using the analyzed data. The proposed method quantifies the social moods expressed in social media contents, whereas the existing methods simply present social tendencies. Our model derived a 27.9% improvement in error reduction compared to a Google Index-based model in the mean absolute percentage error metric.

• 대한산업공학회지
• /
• 제40권3호
• /
• pp.257-266
• /
• 2014

The semiconductor manufacturing industry is managed by a number of parameters from the FAB which is the initial step of production to package test which is the final step of production. Various methods for prediction for the quality and yield are required to reduce the production costs caused by a complicated manufacturing process. In order to increase the accuracy of quality prediction, we have to extract the significant features from the large amount of data. In this study, we propose the method for extracting feature from the cell level data of probe test process using OPTICS which is one of the density-based clustering to improve the prediction accuracy of the quality of the assembled chips that will be placed in a package test. Two features extracted by using OPTICS are used as input variables of quality prediction model because of having position information of the cell defect. The package test progress for chips classified to the correct quality grade by performing the improved prediction method is expected to bring the effect of reducing production costs.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.1343-1346
• /
• 2005

In the cold rolling mill, coil breakage that generated in rolling process makes the various types of troubles such as the degradation of productivity and the damage of equipment. Recent researches were done by the mechanical analysis such as the analysis of roll chattering or strip inclining and the prevention of breakage that detects the crack of coil. But they could cover some kind of breakages. The prediction of Coil breakage was very complicated and occurred rarely. We propose to build effective prediction modes for coil breakage in rolling process, based on data mining model. We proposed three prediction models for coil breakage: (1) decision tree based model, (2) regression based model and (3) neural network based model. To reduce model parameters, we selected important variables related to the occurrence of coil breakage from the attributes of coil setup by using the methods such as decision tree, variable selection and the choice of domain experts. We developed these prediction models and chose the best model among them using SEMMA process that proposed in SAS E-miner environment. We estimated model accuracy by scoring the prediction model with the posterior probability. We also have developed a software tool to analyze the data and generate the proposed prediction models either automatically and in a user-driven manner. It also has an effective visualization feature that is based on PCA (Principle Component Analysis).

• Communications for Statistical Applications and Methods
• /
• 제29권2호
• /
• pp.251-261
• /
• 2022

As AI has a wide range of influence on human social life, issues of transparency and ethics of AI are emerging. In particular, it is widely known that due to the existence of historical bias in data against ethics or regulatory frameworks for fairness, trained AI models based on such biased data could also impose bias or unfairness against a certain sensitive group (e.g., non-white, women). Demographic disparities due to AI, which refer to socially unacceptable bias that an AI model favors certain groups (e.g., white, men) over other groups (e.g., black, women), have been observed frequently in many applications of AI and many studies have been done recently to develop AI algorithms which remove or alleviate such demographic disparities in trained AI models. In this paper, we consider a problem of using the information in the sensitive variable for fair prediction when using the sensitive variable as a part of input variables is prohibitive by laws or regulations to avoid unfairness. As a way of reflecting the information in the sensitive variable to prediction, we consider a two-stage procedure. First, the sensitive variable is fully included in the learning phase to have a prediction model depending on the sensitive variable, and then an imputed sensitive variable is used in the prediction phase. The aim of this paper is to evaluate this procedure by analyzing several benchmark datasets. We illustrate that using an imputed sensitive variable is helpful to improve prediction accuracies without hampering the degree of fairness much.

• International Journal of Aeronautical and Space Sciences
• /
• 제7권2호
• /
• pp.26-32
• /
• 2006

This paper targets a direct and quantitative prediction of characteristics of unstable waves in a combustion chamber, which employs the governing equations derived in terms of amplification factors of flow variables. A freshly formulated nonlinear acoustic equation is obtained and the analysis of unsteady waves in a rocket engine is attempted. In the present formalism, perturbation method decomposes the variables into time-averaged part that can be obtained easily and accurately and time-varying part which is assumed to be harmonic. Excluding the use of conventional spatially sinusoidal eigenfunctions, a direct numerical solution of wave equation replaces the initial spatial distribution of standing waves and forms the nonlinear space-averaged terms. Amplification factor is also calculated independently by the time rate of changes of fluctuating variables, and is no longer an explicit function for compulsory representation. Employing only the numerical computation, major assumptions inevitably inherent, and in erroneous manner, in up to date analytical methods could be avoided. With two definitions of amplification factor, 1-D stable wave and 3-D unstable wave are examined, and clearly demonstrated the potentiality of a suggested theoretical-numerical method of combustion instability.

• 지능정보연구
• /
• 제29권2호
• /
• pp.241-265
• /
• 2023

기업의 부실 예측 모델은 기업의 재무 상태를 객관적으로 모니터링하는 데 필수적인 도구 역할을 한다. 적시에 경고하고 대응 조치를 용이하게 하며 파산 위험을 완화하고 성과를 개선하기 위한 효과적인 관리 전략을 수립할 수 있도록 지원한다. 투자자와 금융 기관은 금융 손실을 최소화하기 위해 부실 예측 모델을 이용한다. 기업 부실 예측을 위한 인공지능(AI) 기술 활용에 대한 관심이 높아지면서 이 분야에 대한 광범위한 연구가 진행되고 있다. 해석 가능성과 신뢰성이 강조되며 기업 부실 예측에서 설명 가능한 AI 모델에 대한 수요가 증가하고 있다. 널리 채택된 SHAP(SHapley Additive exPlanations) 기법은 유망한 성능을 보여주었으나 변수 수에 따른 계산 비용, 처리 시간, 확장성 문제 등의 한계가 있다. 이 연구는 전체 데이터 세트를 사용하는 대신 부트스트랩 된 데이터 하위 집합에서 SHAP 값을 평균화하여 변수 수를 줄이는 새로운 변수 선택 접근법을 소개한다. 이 기술은 뛰어난 예측 성능을 유지하면서 계산 효율을 향상시키는 것을 목표로 한다. 해석 가능성이 높은 선택된 변수를 사용하여 랜덤 포레스트, XGBoost 및 C5.0 모델을 훈련하여 분류 결과를 얻고자 한다. 분류 결과는 고성능 모델 설계를 목표로 soft voting을 통해 생성된 앙상블 모델의 분류 정확성과 비교한다. 이 연구는 1,698개 한국 경공업 기업의 데이터를 활용하고 부트스트래핑을 사용하여 고유한 데이터 그룹을 생성한다. 로지스틱 회귀 분석은 각 데이터 그룹의 SHAP 값을 계산하는 데 사용되며, SHAP 값 평균은 최종 SHAP 값을 도출하기 위해 계산된다. 제안된 모델은 해석 가능성을 향상시키고 우수한 예측 성능을 달성하는 것을 목표로 한다.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2021년도 학술발표회
• /
• pp.205-205
• /
• 2021

Surface soil moisture, which governs the partitioning of precipitation into infiltration and runoff, plays an important role in the hydrological cycle. The assimilation of satellite soil moisture retrievals into a land surface model or hydrological model has been shown to improve the predictive skill of hydrological variables. This study aims to improve streamflow prediction with Weather Research and Forecasting model-Hydrological modeling system (WRF-Hydro) by assimilating Soil Moisture Active and Passive (SMAP) data at 3 km and analyze its impacts on hydrological components. We applied Cumulative Distribution Function (CDF) technique to remove the bias of SMAP data and assimilate SMAP data (April to July 2015-2019) into WRF-Hydro by using an Ensemble Kalman Filter (EnKF) with a total 12 ensembles. Daily inflow and soil moisture estimates of major dams (Soyanggang, Chungju, Sumjin dam) of South Korea were evaluated. We investigated how hydrologic variables such as runoff, evaporation and soil moisture were better simulated with the data assimilation than without the data assimilation. The result shows that the correlation coefficient of topsoil moisture can be improved, however a change of dam inflow was not outstanding. It may attribute to the fact that soil moisture memory and the respective memory of runoff play on different time scales. These findings demonstrate that the assimilation of satellite soil moisture retrievals can improve the predictive skill of hydrological variables for a better understanding of the water cycle.

• Industrial Engineering and Management Systems
• /
• 제10권4호
• /
• pp.272-278
• /
• 2011

Decision tree as a classification tool is being used successfully in many areas such as medical diagnosis, customer churn prediction, signal detection and so on. The main advantage of decision tree classifiers is their capability to break down a complex structure into a collection of simpler structures, thus providing a solution that is easy to interpret. Since decision tree is a top-down algorithm using a divide and conquer induction process, there is a risk of reaching a local optimal solution. This paper proposes a procedure of optimally determining thresholds of the chosen variables for a decision tree using an adaptive particle swarm optimization (APSO). The proposed algorithm consists of two phases. First, we construct a decision tree and choose the relevant variables. Second, we find the optimum thresholds simultaneously using an APSO for those selected variables. To validate the proposed algorithm, several artificial and real datasets are used. We compare our results with the original CART results and show that the proposed algorithm is promising for improving prediction accuracy.