• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.11
• /
• pp.126-136
• /
• 2018

The purpose of this study was to develop a severity-adjustment model for predicting mortality in acute stroke patients using machine learning. Using the Korean National Hospital Discharge In-depth Injury Survey from 2006 to 2015, the study population with disease code I60-I63 (KCD 7) were extracted for further analysis. Three tools were used for the severity-adjustment of comorbidity: the Charlson Comorbidity Index (CCI), the Elixhauser comorbidity index (ECI), and the Clinical Classification Software (CCS). The severity-adjustment models for mortality prediction in patients with acute stroke were developed using logistic regression, decision tree, neural network, and support vector machine methods. The most common comorbid disease in stroke patients were hypertension, uncomplicated (43.8%) in the ECI, and essential hypertension (43.9%) in the CCS. Among the CCI, ECI, and CCS, CCS had the highest AUC value. CCS was confirmed as the best severity correction tool. In addition, the AUC values for variables of CCS including main diagnosis, gender, age, hospitalization route, and existence of surgery were 0.808 for the logistic regression analysis, 0.785 for the decision tree, 0.809 for the neural network and 0.830 for the support vector machine. Therefore, the best predictive power was achieved by the support vector machine technique. The results of this study can be used in the establishment of health policy in the future.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.485-485
• /
• 2021

최근 세계적인 기상이변으로 자연재해의 발생빈도 증가는 물론 이로 인한 피해가 점차 다양화 및 대형화되어 가고 있는 추세이다. 재난으로 인한 피해는 발생지역 피해뿐만 아니라 국가 경제 전반에 큰 영향을 미치는 특징이 있다. 우리나라의 자연재해 중 대설은 다른 자연재해에 비해 발생빈도는 낮지만 광역적인 피해를 유발하며, 피해 면적에 비해 피해액 규모가 크다. 또한 현재에는 강원권이 가장 취약한 것으로 취약성 분석 결과에서 보여주지만, 미래에는 강원권, 충청권, 호남권을 연결하는 축으로 취약지역이 확대될 것으로 전망된다. 본 연구에서는 현재 사회 전반에서 다양하게 활용되고 있는 머신러닝 기법을 이용하여 우리나라 대설피해액을 예측하는 대설피해 예측모형을 개발하고자 하였다. 머신러닝 기법으로는 랜덤포레스트, 서포트 벡터 머신, 인공신경망 기법을 이용하였고, 모형에 사용한 변수는 기상관측자료, 사회·경제적 요소 등을 활용하여 모형을 개발하였다. 결과적으로 기존연구에서 다중회귀모형을 이용하여 개발된 예측모형과 본 연구에서 3개의 머신러닝 기법으로 개발된 예측모형의 예측력을 비교 분석하였고, 예측력이 가장 높은 모형을 제시하였다. 본 연구결과를 활용하여 모형의 개선 및 데이터 품질 개선이 이루어진다면 향후 대설피해에 대한 개략적인 대비가 가능할 것으로 기대된다.

• Communications for Statistical Applications and Methods
• /
• v.17 no.4
• /
• pp.561-574
• /
• 2010

We studied the performance of 8 data mining algorithms including decision trees, logistic regression, LDA, QDA, Neral network, and SVM and their combinations of 2 ensemble techniques, bagging and boosting. In this study, we utilized 13 data sets with binary responses. Sensitivity, Specificity and missclassificate error were used as criteria for comparison.

• 한국벤처창업학회:학술대회논문집
• /
• 2021.11a
• /
• pp.185-187
• /
• 2021

관리종목 지정 제도는 상장 기업 내 기업의 부실화를 경고하여 기업에게는 회생 기회를 주고, 투자자들에게는 투자 위험을 경고하기 위한 시장규제 제도이다. 본 연구는 관리종목과 비관리종목의 기업의 재무 데이터를 표본으로 하여 관리종목 지정 예측에 대한 연구를 진행하였다. 분석에 쓰인 분석 방법은 로지스틱 회귀분석, 의사결정나무, 서포트 벡터 머신, 소프트 보팅, 랜덤 포레스트, LightGBM이며 분류 정확도가 82.73%인 LightGBM이 가장 우수한 예측 모형이었으며 분류 정확도가 가장 낮은 예측 모형은 정확도가 71.94%인 의사결정나무였다. 대체적으로 앙상블을 이용한 학습 모형이 단일 학습 모형보다 예측 성능이 높았다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.5
• /
• pp.576-583
• /
• 2020

This paper proposes a technique to determine the spam comments on YouTube, which have recently seen tremendous growth. On YouTube, the spammers appeared to promote their channels or videos in popular videos or leave comments unrelated to the video, as it is possible to monetize through advertising. YouTube is running and operating its own spam blocking system, but still has failed to block them properly and efficiently. Therefore, we examined related studies on YouTube spam comment screening and conducted classification experiments with six different machine learning techniques (Decision tree, Logistic regression, Bernoulli Naive Bayes, Random Forest, Support vector machine with linear kernel, Support vector machine with Gaussian kernel) and ensemble model combining these techniques in the comment data from popular music videos - Psy, Katy Perry, LMFAO, Eminem and Shakira.

• Geophysics and Geophysical Exploration
• /
• v.23 no.3
• /
• pp.192-207
• /
• 2020

We acquire seismic data with regularly or irregularly missing traces, due to economic, environmental, and mechanical problems. Since these missing data adversely affect the results of seismic data processing and analysis, we need to reconstruct the missing data before subsequent processing. However, there are economic and temporal burdens to conducting further exploration and reconstructing missing parts. Many researchers have been studying interpolation methods to accurately reconstruct missing data. Recently, various machine learning technologies such as support vector regression, autoencoder, U-Net, ResNet, and generative adversarial network (GAN) have been applied in seismic data interpolation. In this study, by reviewing these studies, we found that not only neural network models, but also support vector regression models that have relatively simple structures can interpolate missing parts of seismic data effectively. We expect that future research can improve the interpolation performance of these machine learning models by using open-source field data, data augmentation, transfer learning, and regularization based on conventional interpolation technologies.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.43 no.7
• /
• pp.601-608
• /
• 2015

The static aeroelastic analysis and optimization of flexible wings are conducted for steady state conditions while both aerodynamic and structural parameters can be used as optimization variables. The system of multidisciplinary design optimization as a robust methodology to couple commercial codes for a static aeroelastic optimization purpose to yield a convenient adaptation to engineering applications is developed. Aspect ratio, taper ratio, sweepback angle are chosen as optimization variables and the skin thickness of the wing. The real-coded adaptive range multi-objective genetic algorithm code, which represents the global multi-objective optimization algorithm, was used to control the optimization process. The support vector regression(SVR) is applied for optimization, in order to reduce the time of computation. For this multi-objective design optimization problem, numerical results show that several useful Pareto optimal designs exist for the flexible wing.

• The Korean Journal of Applied Statistics
• /
• v.30 no.6
• /
• pp.809-825
• /
• 2017

The number of TV entertainment shows is increasing. Competition among programs in the entertainment market is intensifying since cable channels air many entertainment TV shows. There is now a need for research on program ratings and the number of episodes. This study presents predictive models for entertainment TV show ratings and number of episodes. We use various data mining techniques such as linear regression, logistic regression, LASSO, random forests, gradient boosting, and support vector machine. The analysis results show that the average program ratings before the first broadcast is affected by broadcasting company, average ratings of the previous season, starting year and number of articles. The average program ratings after the first broadcast is influenced by the rating of the first broadcast, broadcasting company and program type. We also found that the predicted average ratings, starting year, type and broadcasting company are important variables in predicting of the number of episodes.

• The Korean Journal of Applied Statistics
• /
• v.28 no.5
• /
• pp.977-990
• /
• 2015

Food delivery services are well developed in the Republic of Korea, The increase of one person households and the success of app applications influence delivery services these days. We consider a prediction model for the food delivery service based on weather and dates to predict the number of food delivery services in 2014 using various data mining techniques. We use linear regression, random forest, gradient boosting, support vector machines, neural networks, and logistic regression to find the best prediction model. There are four categories of food delivery services and we consider two methods. For the first method, we estimate the total number of delivery services and the posterior probabilities of each delivery service. For the second method, we use different models for each category and combine them to estimate the total number of delivery services. The neural network and linear regression model perform best in the first method, this is followed by the neural network which is the best for the second method. The result shows that we can estimate the number of deliveries accurately based on dates and weather information.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.10a
• /
• pp.770-773
• /
• 2019

본 논문에서는 매년 성장하는 웹툰 시장 속에서 신인 작가들이 성공할 수 있는 성공 요인을 밝히고자 하였다. 국내 1위 웹툰 플랫폼인 네이버 웹툰 중 데뷔작을 기준으로 완결 웹툰 212개, 연재 중인 웹툰 112개, 총 324개의 웹툰을 수집하여 연구를 진행하였다. 기존 선행연구와의 차별화를 두기 위해 독자의 직접적인 반응 중 하나인 댓글을 성공 요인에 포함하였다. 댓글에 담긴 긍정, 부정을 나타내는 주관을 탐지하기 위해 딥러닝을 이용하여 감성 분석을 실시하였다. 각 웹툰에 대한 댓글 반응을 포함하여 평균, '좋아요' 수, 장르 그리고 첫 화 댓글 수와 5화까지 평균 댓글 수를 흥행에 영향을 미치는 독립변수로 사용했다. 댓글 반응이 중요 요인인지를 확인하기 위해 각 모델 생성 시 댓글 반응을 포함한 모델과 포함하지 않은 모델을 생성하여 성능 평가를 실시하였다. 로지스틱 회귀분석, 아다 부스트, 그리고 서포트 벡터 머신 모델을 정확도와 ROC 그래프를 이용해 효율성을 비교하고, 이를 통해 댓글 반응을 활용한 로지스틱 회귀 모델이 가장 적합하다고 판단하였다. 모델 생성 결과 '좋아요' 수, 1화 댓글 수, 댓글 반응 순으로 성공 요인에 많은 영향을 미치는 것을 알 수 있었다.