• Proceedings of the Korean Society of Computer Information Conference
• /
• 2013.07a
• /
• pp.275-278
• /
• 2013

영화의 흥행 요소를 파악하여 영화의 흥행 여부를 예측하는 것은 영화의 수익성 부분에서 아주 중요하다. 영화 시장이 과거와는 다르게 증가함에 따라, 다양한 영화 흥행에 관한 예측 연구들이 개발되었다. 본 논문에서는 영화 흥행 요소들을 수집하고 다중회귀 분석을 통해서 유의수준을 만족하는 흥행 요소들을 선택한다. 그 후, 이러한 요소들을 예측 방법들의 입력값으로 사용하여 영화 흥행을 예측한다. 성능을 비교하기 위해 본 논문에서 제안한 방법과 현재 개발된 영화 흥행 예측 방법(다중회귀, 의사결정트리, 인공신경망)들을 정확도와 평균제곱근오차를 통해 예측 모형의 성능을 비교한다. 그 결과, 다중 회귀 분석을 통해 유의한 흥행요소들만을 고려한 예측 방법의 정확도가 모든 흥행 요소들을 고려한 예측 방법보다 평균 8.2% 향상되었고, 현재까지 개발된 영화 흥행 예측 방법보다 더 높은 예측 성능을 보여준다.

• Annual Conference of KIPS
• /
• 2021.05a
• /
• pp.316-318
• /
• 2021

영화 수익에 있어 영화의 흥행 여부는 중요한 영향을 끼친다. 영화 흥행 요인은 영화 산업의 규모가 커지면서 많은 제작사들 및 투자자들이 고려해야 하는 사항이 되었다. 따라서 영화의 흥행을 예측하기 위한 많은 모델이 연구되었다. 본 연구의 목적은 선행연구에서 흥행에 유의미한 영향을 끼친다고 밝혀진 스크린 수, 감독명, 제작사명 등의 내재적인 속성과 더불어 온라인 구전 변수를 사용하여 영화 흥행 예측 모델을 만드는 것이다. 이때 기사 수, 블로그 수와 같이 온라인 구전의 크기를 나타내는 변수들을 사용하는 대신 개봉 후 첫 주간의 관람객 리뷰를 텍스트마이닝을 이용하여 전체 리뷰 중 긍정 리뷰의 비율에 따라 점수를 매긴 후 독립변수로 사용한다. 그 후, 데이터 마이닝 기법을 활용하여 만든 모델에 앞서 언급한 독립변수를 입력 값으로 사용하여 영화의 흥행을 예측한다. 최종적으로 의사결정트리와 로지스틱회귀를 수행한 결과 영화 흥행에 영향을 주는 독립변수를 찾고 모델의 성능을 평가하였다. 로지스틱회귀의 결과 관객 수, 평점이 영화의 흥행에 특히 유의한 영향을 끼치는 변수로 선정되었고 리뷰 역시 유의한 변수로 선정되었다. 이때 만들어진 모델은 약 90%의 높은 수준의 정확도를 보여주었다. 의사결정트리의 결과 관객 수가 가장 중요한 변수로 선정되었다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.192-192
• /
• 2020

취약성 분석의 결과로 폭설에 의한 기후노출은 현재에는 강원권이 가장 취약한 것으로 나타났다. 그러나 미래에는 강원권, 충청권, 호남권을 연결하는 축으로 취약지역이 확대될 것으로 전망된다. 본 연구에서는 다양한 머신러닝 기법을 이용하여 대설피해 예측을 실시하였다. 머신러닝 기법으로는 로지스틱회귀모형, 서포트벡터 머신, 의사결정트리 모형을 적용하였다. 종속변수로 대설피해액 자료를 이용하였고, 독립변수로 기상관측자료, 사회·경제적 요소를 사용하였다. 결과적으로 기존에 사용했던 다중회귀모형과 머신러닝 기법으로 예측한 예측력을 비교 및 분석하였고, 예측력이 가장 높은 머신러닝 기법을 제시하였다. 본 연구에서 대설피해 예측을 위해 사용된 예측력이 가장 높은 기법을 활용하여 대설피해를 예측한다면, 미래에 전국적으로 확대될 대설피해에 대해 효과적으로 대비할 수 있을 것으로 기대된다.

• Journal of Engineering Education Research
• /
• v.13 no.4
• /
• pp.51-59
• /
• 2010

In order to manage the lectures efficiently in the university and improve the educational outcome, the process is needed that make diagnosis of the present educational outcome of each classes on a lecture and find factors of educational outcome. In most studies for finding the factors of the efficient lecture, statistical methods such as association analysis, regression analysis are used usually, and recently decision tree analysis is employed, too. The decision tree analysis have the merits that is easy to understand a result model, and to be easy to apply for the decision making, but have the weaknesses that is not strong for characteristic of input data such as multicollinearity. This paper indicates the weaknesses of decision tree analysis, and suggests the experimental solution using multiple decision tree algorithm to supplement these problems. The experimental result shows that the suggested method is more effective in finding the reliable factors of the educational outcome.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.7
• /
• pp.827-833
• /
• 2020

In this paper, to reduce the unpaid rate of local governments, the internal data elements affecting the arrears in Water-INFOS are searched through interviews with meter readers in certain local governments. Candidate data affecting arrears from national statistical data were derived. The influence of the independent variable on the dependent variable was sampled by examining the disorder of the dependent variable in the data set called information gain. We also evaluated the higher prediction rates of decision tree and logistic regression using n-fold cross-validation. The results confirmed that the decision tree can find more accurate customer payment patterns than logistic regression. In the process of developing an analysis algorithm model using machine learning, the optimal values of two environmental variables, the minimum number of data and the maximum purity, which directly affect the complexity and accuracy of the decision tree, are derived to improve the accuracy of the algorithm.

• Journal of Aerospace System Engineering
• /
• v.18 no.5
• /
• pp.1-14
• /
• 2024

This paper aimed to develop mesh stiffness prediction models using spur gear design parameters as input variables through a machine learning ensemble method. A dataset was generated by calculating individual stiffness using a calculation method presented in previous studies and deriving the minimum and maximum values of total mesh stiffness. Using multivariate linear regression, support vector regression, and decision tree regression, models were created to predict the minimum and maximum values of mesh stiffness. The stacking ensemble method was used to create meta models. Prediction models of three algorithms were used as base models. These Ensemble meta models were verified with specifications of gears used in actual aircraft engine starters, showing very high prediction performances. Thus, feasibility of applying Ensemble meta models to an actual gear system and their effectiveness were confirmed.

• Journal of The Korean Association of Information Education
• /
• v.17 no.4
• /
• pp.433-447
• /
• 2013

The purpose of this study is to find out the factors of the students' achievement on the computer training courses which are based on computer practice. In order to improve the academic achievement of the students, it is necessary to analyze the factors affecting academic achievement and apply the results of the analysis to education. In particular, it is necessary to study for finding out factors of the academic achievement in practical computer training courses, because these courses are different from other courses focusing on the theory. In this study, in order to find out the factors, the logistic regression analysis and the decision tree analysis which is the field of data mining were peformed. For the experimental data, the test results of the MOS certification of the S university in seoul were used. Through logistic regression analysis it is found that the factors of the professors, class size, lecture time, group(lecture period) are important in order. Through decision tree analysis of data mining, it is found that there are some additional factors ; entrance year, whether the course is retaken, and the classroom environment. and these various factors effect the academic achievement compositively as identified through the model tree. The tree model was presented as a result of the analysis, and the importance of the factors is expressed numerically from multiple tree models by using the proposed mathematical formula.

• Journal of the Institute of Convergence Signal Processing
• /
• v.24 no.4
• /
• pp.186-191
• /
• 2023

Data processing techniques play a critical role in decision-making, including handling missing and outlier data, prediction, and recommendation models. This requires a clear explanation of the validity, reliability, and accuracy of all processes and results. In addition, it is necessary to solve data problems through explainable models using decision trees, inference, etc., and proceed with model lightweight by considering various types of learning. The multi-layer mining classification method that applies the sixth principle is a method that discovers multidimensional relationships between variables and attributes that occur frequently in transactions after data preprocessing. This explains how to discover significant relationships using mining on transactions and model the data through regression analysis. It develops scalable models and logistic regression models and proposes mining techniques to generate class labels through data cleansing, relevance analysis, data transformation, and data augmentation to make explanatory decisions.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.15 no.6
• /
• pp.311-319
• /
• 2015

In this paper, in order to increase the production efficiency of the industrial plant, and predicts the resources of the manufacturing process, we have proposed a decision-making system for resource implementing the risk management effectively forecasting and risk management. A variety of information that occurs at each step efficiently difficult the creation of detailed process steps in the scenario you want to manage, is a frequent condition change of manufacturing facilities for the production of various products even within the same process. The data that is not contiguous products production cycle also not constant occurs, there is a problem that needs to check the variation in the small amount of data. In order to solve these problems, data centralized manufacturing processes, process resource prediction, risk prediction, through a process current status monitoring, must allow action immediately when a problem occurs. In this paper, the range of change in the design drawing, resource prediction, a process completion date using a regression algorithm to derive the formula, classification tree technique was proposed decision system in three stages through the boundary value analysis.

• Smart Media Journal
• /
• v.5 no.4
• /
• pp.75-82
• /
• 2016

Although Korea's economic and domestic automobile market through the change of road environment are growth, the traffic accident rate has also increased, and the casualties is at a serious level. For this reason, the government is establishing and promoting policies to open traffic accident data and solve problems. In this paper, describe the method of predicting traffic accidents by eliminating the class imbalance using the traffic accident data and constructing the Hybrid Model. Using the original traffic accident data and the sampled data as learning data which use FP-Growth algorithm it learn patterns associated with traffic accident injury severity. Accordingly, In this paper purpose a method for predicting the severity of a victim of a traffic accident by analyzing the association patterns of two learning data, we can extract the same related patterns, when a decision tree and multinomial logistic regression analysis are performed, a hybrid model is constructed by assigning weights to related attributes.