• 한국전자거래학회지
• /
• 제22권4호
• /
• pp.159-173
• /
• 2017

기술력 기반의 중소벤처기업에 대한 기술금융 지원을 위해 정부는 2014년 7월부터 기술보증기금 및 일정 자격을 갖춘 민간 기술신용평가사에게 일종의 기술력 등급평가인 기술신용평가를 실시하여 은행의 여신에 활용토록 하였다. 본 논문에서는 최근까지의 기술신용평가 현황 및 한국신용정보원에서 축적하고 있는 기술평가 관련 가용 지표들에 대한 선행 연구를 개략적으로 살펴본 후 기술평가등급점수에 유의적인 영향을 미치는 지표(indicator)를 통상적인 다중회귀기법으로 탐색할 것이다. 본 논문의 관심 대상인 지표 별 등급 영향도와 모형의 적합도는 대표적인 기계학습 분류기(classifier)인 일반화가속모형(Generalized Boosting Model; GBM)을 적용하여 분석하였는 바, 주요 지표를 독립변수(feature)로 투입하여 지표의 상대적 중요성 및 분류 정확도를 산출하였다. 분석결과 회귀모형과 기계학습 모형 간 지표별 상대적인 중요도는 크게 차이나지 않는 것으로 분석되었으나, GBM 모형의 경우 회귀모형에 비해서 이노비즈인증, 연구소 및 연구개발전담부서 보유, 특허등록건수, 벤처확인 지표 등 기술개발역량이 상대적으로 기술등급에 더 큰 영향을 미치는 것으로 분석되었다.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2023년도 학술발표회
• /
• pp.358-358
• /
• 2023

본 연구에서는 그동안 수자원분야 강우유출 해석분야에 활용되었던 대표적인 머신러닝&딥러닝(ML&DL) 모델을 활용하여 모델의 하이퍼파라미터 튜닝뿐만 아니라 모델의 특성을 고려한 기상 및 수문데이터의 조합과 전처리(lag-time, 이동평균 등)를 통하여 데이터 특성과 ML&DL모델의 조합시나리오에 따른 일 유입량 예측성능을 비교 검토하는 연구를 수행하였다. 이를 위해 소양강댐 유역을 대상으로 1974년에서 2021년까지 축적된 기상 및 수문데이터를 활용하여 1) 강우, 2) 유입량, 3) 기상자료를 주요 영향변수(독립변수)로 고려하고, 이에 a) 지체시간(lag-time), b) 이동평균, c) 유입량의 성분분리조건을 적용하여 총 36가지 시나리오 조합을 ML&DL의 입력자료로 활용하였다. ML&DL 모델은 1) Linear Regression(LR), 2) Lasso, 3) Ridge, 4) SVR(Support Vector Regression), 5) Random Forest(RF), 6) LGBM(Light Gradient Boosting Model), 7) XGBoost의 7가지 ML방법과 8) LSTM(Long Short-Term Memory models), 9) TCN(Temporal Convolutional Network), 10) LSTM-TCN의 3가지 DL 방법, 총 10가지 ML&DL모델을 비교 검토하여 일유입량 예측을 위한 가장 적합한 데이터 조합 특성과 ML&DL모델을 성능평가와 함께 제시하였다. 학습된 모형의 유입량 예측 결과를 비교·분석한 결과, 소양강댐 유역에서는 딥러닝 중에서는 TCN모형이 가장 우수한 성능을 보였고(TCN>TCN-LSTM>LSTM), 트리기반 머신러닝중에서는 Random Forest와 LGBM이 우수한 성능을 보였으며(RF, LGBM>XGB), SVR도 LGBM수준의 우수한 성능을 나타내었다. LR, Lasso, Ridge 세가지 Regression모형은 상대적으로 낮은 성능을 보였다. 또한 소양강댐 댐유입량 예측에 대하여 강우, 유입량, 기상계열을 36가지로 조합한 결과, 입력자료에 lag-time이 적용된 강우계열의 조합 분석에서 세가지 Regression모델을 제외한 모든 모형에서 NSE(Nash-Sutcliffe Efficiency) 0.8이상(최대 0.867)의 성능을 보였으며, lag-time이 적용된 강우와 유입량계열을 조합했을 경우 NSE 0.85이상(최대 0.901)의 더 우수한 성능을 보였다.

• 산업경영시스템학회지
• /
• 제46권1호
• /
• pp.23-31
• /
• 2023

Research and interest in sustainable printing are increasing in the packaging printing industry. Currently, predicting the amount of ink required for each work is based on the experience and intuition of field workers. Suppose the amount of ink produced is more than necessary. In this case, the rest of the ink cannot be reused and is discarded, adversely affecting the company's productivity and environment. Nowadays, machine learning models can be used to figure out this problem. This study compares the ink usage prediction machine learning models. A simple linear regression model, Multiple Regression Analysis, cannot reflect the nonlinear relationship between the variables required for packaging printing, so there is a limit to accurately predicting the amount of ink needed. This study has established various prediction models which are based on CART (Classification and Regression Tree), such as Decision Tree, Random Forest, Gradient Boosting Machine, and XGBoost. The accuracy of the models is determined by the K-fold cross-validation. Error metrics such as root mean squared error, mean absolute error, and R-squared are employed to evaluate estimation models' correctness. Among these models, XGBoost model has the highest prediction accuracy and can reduce 2134 (g) of wasted ink for each work. Thus, this study motivates machine learning's potential to help advance productivity and protect the environment.

• International Journal of Internet, Broadcasting and Communication
• /
• 제13권4호
• /
• pp.121-128
• /
• 2021

In order to design a real time big data collection and analysis system of manufacturing data in a smart factory, it is important to establish an appropriate wired/wireless communication system and protocol. This paper introduces the latest communication protocol, OPC-UA (Open Platform Communication Unified Architecture) based client/server function, applied user interface technology to configure a network for real-time data collection through IoT Integration. Then, Database is designed in MES (Manufacturing Execution System) based on the analysis table that reflects the user's requirements among the data extracted from the new cutting process automation process, bush inner diameter indentation measurement system and tool monitoring/inspection system. In summary, big data analysis system introduced in this paper performs SPC (statistical Process Control) analysis and visualization analysis with interface of OPC-UA-based wired/wireless communication. Through AI learning modeling with XGBoost (eXtream Gradient Boosting) and LR (Linear Regression) algorithm, quality and visualization analysis is carried out the storage and connection to the cloud.

• International Journal of Advanced Culture Technology
• /
• 제10권4호
• /
• pp.499-510
• /
• 2022

This study examines the reporting factors of crime against business in Korea and proposes a corresponding predictive model using machine learning. While many previous studies focused on the individual factors of theft victims, there is a lack of evidence on the reporting factors of crime against a business that serves the public good as opposed to those that protect private property. Therefore, we proposed a crime prevention model for the willingness factor of theft reporting in businesses. This study used data collected through the 2015 Commercial Crime Damage Survey conducted by the Korea Institute for Criminal Policy. It analyzed data from 834 businesses that had experienced theft during a 2016 crime investigation. The data showed a problem with unbalanced classes. To solve this problem, we jointly applied the Synthetic Minority Over Sampling Technique and the Tomek link techniques to the training data. Two prediction models were implemented. One was a statistical model using logistic regression and elastic net. The other involved a support vector machine model, tree-based machine learning models (e.g., random forest, extreme gradient boosting), and a stacking model. As a result, the features of theft price, invasion, and remedy, which are known to have significant effects on reporting theft offences, can be predicted as determinants of such offences in companies. Finally, we verified and compared the proposed predictive models using several popular metrics. Based on our evaluation of the importance of the features used in each model, we suggest a more accurate criterion for predicting var.

• Computers and Concrete
• /
• 제32권4호
• /
• pp.373-381
• /
• 2023

Fly ash, granulated blast furnace slag, marble waste powder, etc. are just some of the by-products of other sectors that the construction industry is looking to include into the many types of concrete they produce. This research seeks to use surrogate machine learning methods to forecast the compressive strength of self-compacting concrete. The surrogate models were developed using Gradient Boosting Machine (GBM), Support Vector Machine (SVM), Random Forest (RF), and Gaussian Process Regression (GPR) techniques. Compressive strength is used as the output variable, with nano silica content, cement content, coarse aggregate content, fine aggregate content, superplasticizer, curing duration, and water-binder ratio as input variables. Of the four models, GBM had the highest accuracy in determining the compressive strength of SCC. The concrete's compressive strength is worst predicted by GPR. Compressive strength of SCC with nano silica is found to be most affected by curing time and least by fine aggregate.

• 한국정보시스템학회지:정보시스템연구
• /
• 제32권4호
• /
• pp.229-245
• /
• 2023

Purpose This study aims to understand the inclinations of young job seekers towards "hidden champions" - small but competitive companies that are emerging as potential solutions to the growing disparity between youth-targeted job vacancies and job seekers. We utilize machine learning techniques to discern the appeal of these hidden champions. Design/methodology/approach We examined the characteristics of small and medium-sized enterprises using data sourced from the Ministry of Employment and Labor and Youth Worknet. By comparing the efficacy of five machine learning classification models (i.e., Logistic Regression, Random Forest Classifier, Gradient Boosting Classifier, LGBM Classifier, and XGB Classifier), we discovered that the predictive model utilizing the LGBM Classifier yielded the most consistent performance. Findings Our analysis of the relative significance of preference determinants revealed that industry type, geographical location, and employee count are pivotal factors influencing preference. Drawing from these insights, we propose targeted strategic interventions for policymakers, hidden champions, and young job seekers.

• 한국재난정보학회 논문집
• /
• 제19권4호
• /
• pp.924-935
• /
• 2023

Purpose: The central aim of this study is to leverage machine learning techniques for the classification of Intrusion Detection System (IDS) data, with a specific focus on identifying the variables responsible for enhancing overall performance. Method: First, we classified 'R2L(Remote to Local)' and 'U2R (User to Root)' attacks in the NSL-KDD dataset, which are difficult to detect due to class imbalance, using seven machine learning models, including Logistic Regression (LR) and K-Nearest Neighbor (KNN). Next, we use the SHapley Additive exPlanation (SHAP) for two classification models that showed high performance, Random Forest (RF) and Light Gradient-Boosting Machine (LGBM), to check the importance of variables that affect classification for each model. Result: In the case of RF, the 'service' variable and in the case of LGBM, the 'dst_host_srv_count' variable were confirmed to be the most important variables. These pivotal variables serve as key factors capable of enhancing performance in the context of classification for each respective model. Conclusion: In conclusion, this paper successfully identifies the optimal models, RF and LGBM, for classifying 'R2L' and 'U2R' attacks, while elucidating the crucial variables associated with each selected model.

• Steel and Composite Structures
• /
• 제49권6호
• /
• pp.645-666
• /
• 2023

Due to the steadily declining supply of natural coarse aggregates, the concrete industry has shifted to substituting coarse aggregates generated from byproducts and industrial waste. Oil palm shell is a substantial waste product created during the production of palm oil (OPS). When considering the usage of OPSC, building engineers must consider its uniaxial compressive strength (UCS). Obtaining UCS is expensive and time-consuming, machine learning may help. This research established five innovative hybrid AI algorithms to predict UCS. Aquila optimizer (AO) is used with methods to discover optimum model parameters. Considered models are artificial neural network (AO - ANN), adaptive neuro-fuzzy inference system (AO - ANFIS), support vector regression (AO - SVR), random forest (AO - RF), and extreme gradient boosting (AO - XGB). To achieve this goal, a dataset of OPS-produced concrete specimens was compiled. The outputs depict that all five developed models have justifiable accuracy in UCS estimation process, showing the remarkable correlation between measured and estimated UCS and models' usefulness. All in all, findings depict that the proposed AO - XGB model performed more suitable than others in predicting UCS of OPSC (with R², RMSE, MAE, VAF and A_15-index at 0.9678, 1.4595, 1.1527, 97.6469, and 0.9077). The proposed model could be utilized in construction engineering to ensure enough mechanical workability of lightweight concrete and permit its safe usage for construction aims.

• Nuclear Engineering and Technology
• /
• 제55권12호
• /
• pp.4607-4616
• /
• 2023

We implement machine learning regression models to predict peak pressures of primary and secondary systems, a major safety concern in Loss Of Condenser Vacuum (LOCV) accident. We selected the Multi-dimensional Analysis of Reactor Safety-KINS standard (MARS-KS) code to analyze the LOCV accident, and the reference plant is the Korean Optimized Power Reactor 1000MWe (OPR1000). eXtreme Gradient Boosting (XGBoost) is selected as a machine learning tool. The MARS-KS code is used to generate LOCV accident data and the data is applied to train the machine learning model. Hyperparameter optimization is performed using a simulated annealing. The randomly generated combination of initial conditions within the operating range is put into the input of the XGBoost model to predict the peak pressure. These initial conditions that cause peak pressure with MARS-KS generate the results. After such a process, the error between the predicted value and the code output is calculated. Uncertainty about the machine learning model is also calculated to verify the model accuracy. The machine learning model presented in this paper successfully identifies a combination of initial conditions that produce a more conservative peak pressure than the values calculated with existing methodologies.