• 한국융합학회논문지
• /
• 제8권10호
• /
• pp.215-223
• /
• 2017

본 논문은 법인의 전기 사내유보가 당기 배당률에 미치는 영향을 분석함으로써 미환류 소득세제가 어느 정도 효과를 거두고 있는지 실증분석 하고자 하였으며 추가로 부채비율을 조절변수로 사용하여 정부정책의 유효성도 알아보고자 하였다. 또한 DRF와 GBM 모델을 이용하여 그 효과를 한 번 더 살펴보았다. 실증분석 결과 모형1, 모형2, 모형3에서 모두 현금흐름비율, 자기자본순이익률, 외국인보유비중 변수가 99% 수준에서 유의미함을 확인할 수 있었던 반면 광고선전비 비율, 대주주지분율 변수는 모든 모형에서 유의미하지 않은 결과를 보여주었다. 융합 차원에서 실시한 DRF와 GBM 모형의 분석 결과를 보면 DRF가 depth와 leaves에서 GBM 보다 더 높게 나타났으나 모형의 설명력에 있어서는 GBM이 DRF보다 더 높았다. 앞으로의 과제는 미환류 소득세제의 시행기간인 3년간(2015~2017)의 시계열 분석을 통하여 정부정책의 효과를 살펴볼 필요가 있다.

• 한국융합학회논문지
• /
• 제13권2호
• /
• pp.249-255
• /
• 2022

본 연구는 최근 가공 불량 예측 방법으로 주목받고 있는 머신러닝 기반의 모델을 이용하여 CNC 가공 불량 발생의 실시간 예측을 위한 분석 프레임워크를 제안하고, 해당 프레임워크에 기반하여 XGBoost, CatBoost, LightGBM, 랜덤 포레스트, Extra Trees, SVM, k-최근접 이웃, 로지스틱 회귀 모델을 CNC 설비에 기본 내장된 센서들로부터 추출된 데이터에 적용 및 분석하였다. 분석 결과 XGBoost, CatBoost, LightGBM 모델이 동일하게 가장 우수한 정확도, 정밀도, 재현율, F1 점수, AUC 값을 보였으며, 이 중 LightGBM 모델이 소요 실행 시간이 가장 짧은 것으로 나타났다. 이러한 짧은 소요 실행 시간은 실 시스템 구축 비용 절감, 빠른 불량 예측에 따른 CNC 장비 파손 확률 감소, 전체적인 CNC 활용률 증가 등의 실무적 장점을 가지므로 LightGBM 모델이 기본 센서들만 설치된 CNC 설비에 적용 시 가공 불량 예측에 가장 효과적으로 판단된다. 또한 소요 실행 시간 및 컴퓨팅 파워의 제약이 없는 상황에서는 LightGBM, Extra Trees, k-최근접 이웃, 로지스틱 회귀 모형으로 구성된 앙상블 모델을 적용할 경우 분류 성능이 최대화됨을 확인하였다.

• Asian Pacific Journal of Cancer Prevention
• /
• 제15권8호
• /
• pp.3629-3633
• /
• 2014

Background: Glioblastoma (GBM) is an immunosuppressive tumor whose median survival time is only 12-15 months, and patients with GBM have a uniformly poor prognosis. It is known that heredity contributes to formation of glioma, but there are few genetic studies concerning GBM. Materials and Methods: We genotyped six tagging SNPs (tSNP) in Han Chinese GBM and control patients. We used Microsoft Excel and SPSS 16.0 statistical package for statistical analysis and SNP Stats to test for associations between certain tSNPs and risk of GBM in five different models. ORs and 95%CIs were calculated for unconditional logistic-regression analysis with adjustment for age and gender. The SHEsis software platform was applied for analysis of linkage disequilibrium, haplotype construction, and genetic associations at polymorphism loci. Results: We found rs891835 in CCDC26 to be associated with GBM susceptibility at a level of p=0.009. The following genotypes of rs891835 were found to be associated with GBM risk in four different models of gene action: i) genotype GT (OR=2.26; 95%CI, 1.29-3.97; p=0.019) or GG (OR=1.33; 95%CI, 0.23-7.81; p=0.019) in the codominant model; ii) genotypes GT and GG (OR=2.18; 95%CI, 1.26-3.78; p=0.0061) in the dominant model; iii) GT (OR=2.24; 95%CI, 1.28-3.92; p=0.0053) in the overdominant model; iv) the allele G of rs891835 (OR=1.85; 95%CI, 1.14-3.00; p=0.015) in the additive model. In addition, "CG" and "CGGAG" were found by haplotype analysis to be associated with increased GBM risk. In contrast, genotype GG of CCDC26 rs6470745 was associated with decreased GBM risk (OR=0.34; 95%CI, 0.12-1.01; p=0.029) in the recessive model. Conclusions: Our results, combined with those from previous studies, suggest a potential genetic contribution of CCDC26 to GBM progression among Han Chinese.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2022년도 학술발표회
• /
• pp.150-150
• /
• 2022

This study investigates the roles of decomposition methods on high accuracy in daily rainfall prediction from light gradient boosting machine (LightGBM) algorithm. Here, empirical mode decomposition (EMD) and singular spectrum analysis (SSA) methods were considered to decompose and reconstruct input time series into trend terms, fluctuating terms, and noise components. The decomposed time series from EMD and SSA methods were used as input data for LightGBM algorithm in two hybrid models, including empirical mode-based light gradient boosting machine (EMDGBM) and singular spectrum analysis-based light gradient boosting machine (SSAGBM), respectively. A total of four parameters (i.e., temperature, humidity, wind speed, and rainfall) at a daily scale from 2003 to 2017 is used as input data for daily rainfall prediction. As results from statistical performance indicators, it indicates that the SSAGBM model shows a better performance than the EMDGBM model and the original LightGBM algorithm with no decomposition methods. It represents that the accuracy of LightGBM algorithm in rainfall prediction was improved with the SSA method when using multivariate dataset.

• 한국전자통신학회논문지
• /
• 제15권6호
• /
• pp.1123-1130
• /
• 2020

본 연구는 고속도로 교통사고 심각도 예측모델을 구축하기 위해 다섯가지 머신러닝 기반의 분류모형 적용하였다. 2015년~2017년 동안 전국 고속도로에서 발생한 사고 데이터 21,013건을 5가지의 분류 모형을 적용한 결과 LightGBM(Light Gradient Boosting Model)이 가장 좋은 성능을 나타내는 것으로 나타났다. LightGBM에서는 교통사고심각도 추정에 있어 우선순위 요인으로 사고차량 수, 사고유형, 사고지점, 사고차로유형, 사고차량 유형 순으로 나타났다. 이러한 모형의 결과를 기반으로 일관적인 사고심각도 예측 과정을 통하여 교통사고대응관리 전략 수립에 활용할 수 있다. 본 연구는 국내 기계학습을 활용한 사례가 적은 여건에서 향후 빅데이터 기반의 다양한 기계학습 기법을 활용이 가능함을 제시하고 있다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권8호
• /
• pp.2016-2029
• /
• 2023

Accurate prediction of critical illness is significant for ensuring the lives and health of patients. The selection of indicators affects the real-time capability and accuracy of the prediction for critical illness. However, the diversity and complexity of these indicators make it difficult to find potential connections between them and critical illnesses. For the first time, this study proposes an indicator analysis model to extract key indicators from the preoperative and intraoperative clinical indicators and laboratory results of critical illnesses. In this study, preoperative and intraoperative data of heart failure and respiratory failure are used to verify the model. The proposed model processes the datum and extracts key indicators through four parts. To test the effectiveness of the proposed model, the key indicators are used to predict the two critical illnesses. The classifiers used in the prediction are light gradient boosting machine (LightGBM) and eXtreme Gradient Boosting (XGBoost). The predictive performance using key indicators is better than that using all indicators. In the prediction of heart failure, LightGBM and XGBoost have sensitivities of 0.889 and 0.892, and specificities of 0.939 and 0.937, respectively. For respiratory failure, LightGBM and XGBoost have sensitivities of 0.709 and 0.689, and specificity of 0.936 and 0.940, respectively. The proposed model can effectively analyze the correlation between indicators and postoperative critical illness. The analytical results make it possible to find the key indicators for postoperative critical illnesses. This model is meaningful to assist doctors in extracting key indicators in time and improving the reliability and efficiency of prediction.

• Computers and Concrete
• /
• 제33권2호
• /
• pp.137-145
• /
• 2024

The technique of experimentally determining concrete's compressive strength for a given mix design is time-consuming and difficult. The goal of the current work is to propose a best working predictive model based on different machine learning algorithms such as Gradient Boosting Machine (GBM), Stacked Ensemble (SE), Distributed Random Forest (DRF), Extremely Randomized Trees (XRT), Generalized Linear Model (GLM), and Deep Learning (DL) that can forecast the compressive strength of ternary geopolymer concrete mix without carrying out any experimental procedure. A geopolymer mix uses supplementary cementitious materials obtained as industrial by-products instead of cement. The input variables used for assessing the best machine learning algorithm not only include individual ingredient quantities, but molarity of the alkali activator and age of testing as well. Myriad statistical parameters used to measure the effectiveness of the models in forecasting the compressive strength of ternary geopolymer concrete mix, it has been found that GBM performs better than all other algorithms. A sensitivity analysis carried out towards the end of the study suggests that GBM model predicts results close to the experimental conditions with an accuracy between 95.6 % to 98.2 % for testing and training datasets.

• 한국융합학회논문지
• /
• 제9권1호
• /
• pp.9-20
• /
• 2018

본 논문은 법인의 전기 사내유보가 당기 연구개발 투자에 미치는 영향을 분석함으로써 미환류 소득세제가 어느 정도 효과를 거두고 있는지 실증분석 하고자 하였으며 추가로 교육훈련비를 조절변수로 사용하여 정부정책의 유효성도 알아보고자 하였다. 또한 GBM 모델을 이용하여 그 효과를 한 번 더 살펴보았다. 연구 결과 교육훈련비의 조절효과와 매개효과 모두 유의미한 효과가 있는 것으로 판단할 수 있었고 모형1, 모형2, 모형3에서 모두 이자비용과 복리후생비 변수가 99% 수준에서 유의미함을 확인할 수 있었던 반면 전기유보율은 모든 모형에서 유의미하지 않은 결과를 보여주었다. 이를 통해 정부의 미환류 소득세제 도입 취지인 사내 유보금 과세를 추진하면 기업은 그 재원으로 물적 및 인적 투자를 늘릴 것이라는 가정은 아직 그 효과가 미미한 것으로 사료된다. 추가분석으로 실시한 융합 차원에서의 GBM 모형에서도 비슷한 결과가 도출되었다. 앞으로의 과제는 미환류 소득세제의 시행기간인 3년간(2015~2017)의 시계열 분석을 통하여 정부정책의 효과를 살펴볼 필요가 있다.

• Molecules and Cells
• /
• 제43권6호
• /
• pp.539-550
• /
• 2020

Glioblastoma multiforme (GBM) is a fatal malignant tumor that is characterized by diffusive growth of tumor cells into the surrounding brain parenchyma. However, the diffusive nature of GBM and its relationship with the tumor microenvironment (TME) is still unknown. Here, we investigated the interactions of GBM with the surrounding microenvironment in orthotopic xenograft animal models using two human glioma cell lines, U87 and LN229. The GBM cells in our model showed different features on the aspects of cell growth rate during their development, dispersive nature of glioma tumor cells along blood vessels, and invasion into the brain parenchyma. Our results indicated that these differences in the two models are in part due to differences in the expression of CXCR4 and STAT3, both of which play an important role in tumor progression. In addition, the GBM shows considerable accumulation of resident microglia and peripheral macrophages, but polarizes differently into tumor-supporting cells. These results suggest that the intrinsic factors of GBM and their interaction with the TME determine the diffusive nature and probably the responsiveness to non-cancer cells in the TME.

• 한국운동역학회지
• /
• 제32권1호
• /
• pp.1-8
• /
• 2022

Objective: This study proposes a methodology to analyze important variables that have a significant impact on the putting direction prediction using a machine learning-based putting direction prediction model trained with IMU sensor data. Method: Putting data were collected using an IMU sensor measuring 12 variables from 6 adult males in their 20s at K University who had no golf experience. The data was preprocessed so that it could be applied to machine learning, and a model was built using five machine learning algorithms. Finally, by comparing the performance of the built models, the model with the highest performance was selected as the proposed model, and then 12 variables of the IMU sensor were applied one by one to analyze important variables affecting the learning performance. Results: As a result of comparing the performance of five machine learning algorithms (K-NN, Naive Bayes, Decision Tree, Random Forest, and Light GBM), the prediction accuracy of the Light GBM-based prediction model was higher than that of other algorithms. Using the Light GBM algorithm, which had excellent performance, an experiment was performed to rank the importance of variables that affect the direction prediction of the model. Conclusion: Among the five machine learning algorithms, the algorithm that best predicts the putting direction was the Light GBM algorithm. When the model predicted the putting direction, the variable that had the greatest influence was the left-right inclination (Roll).