• 한국콘텐츠학회논문지
• /
• 제22권2호
• /
• pp.545-558
• /
• 2022

본 연구의 목적은 전통적인 통계과 기계학습(Machine Learning)을 통해 중국 문화산업 기업의 재무적 곤경을 정확하게 예측하는 분석 모형을 탐색하는 데 있다. 예측모형을 구축하기 위하여 중국 128개 문화산업상장 기업의 데이터를 수집하였다. 25개 설명변수로 이뤄진 데이터베이스를 토대로 판별분석과 로지스틱 회귀(Logistic) 등 전통적인 통계 방법과 서포트 벡터 기계(SVM), 결정 트리(Decision Tree)와 랜덤 포레스트(Random Forest) 등 기계학습을 이용한 예측모형을 구축하고 각 모형의 성능 평가를 위해 Python 소프트웨어를 사용한다. 분석 결과, 예측 성능이 가장 좋은 모형은 랜덤 포레스트(Random Forest) 모형으로 95%의 정확도를 보였다. 그 다음은 서포트 벡터 기계(SVM) 모형으로 93%의 정확도를 보였다. 그 다음은 결정 트리(Decision Tree) 모형으로 92%의 정확도를 보였다. 그 다음은 판정분석 모형으로 89%의 정확도를 보였다. 예측 효과가 가장 낮은 모형은 로지스틱 회귀(Logistic) 모형으로 88%의 정확도를 보였다. 이는 중국 문화산업 기업의 재무적 곤경을 예측하면서 기계학습 모형이 전통적인 통계 모형보다 더 좋은 예측 효과를 얻을 수 있음을 설명한다.

• IEIE Transactions on Smart Processing and Computing
• /
• 제6권4호
• /
• pp.281-291
• /
• 2017

Nowadays, as traffic jams are a daily elementary problem in both developed and developing countries, systems to monitor, predict, and detect traffic conditions are playing an important role in research fields. Comparing them, researchers have been trying to solve problems by applying many kinds of technologies, especially roadside sensors, which still have some issues, and for that reason, any one particular method by itself could not generate sufficient traffic prediction results. However, these sensors have some issues that are not useful for research. Therefore, it may not be best to use them as stand-alone methods for a traffic prediction system. On that note, this paper mainly focuses on predicting traffic conditions based on a hybrid prediction approach, which stands on accuracy comparison of three prediction models: multinomial logistic regression, decision trees, and support vector machine (SVM) classifiers. This is aimed at selecting the most suitable approach by means of integrating proficiencies from these approaches. It was also experimentally confirmed, with test cases and simulations that showed the performance of this hybrid method is more effective than individual methods.

• Child Health Nursing Research
• /
• 제11권4호
• /
• pp.436-443
• /
• 2005

Purpose: This study was done to explore the levels of depression experienced by adolescents, and to compare health behavior between depressed and non-depressed adolescents. Method: Participants were chosen by a stratified random sampling of adolescents in the second grade of a high school in P city. Levels of depression and health behavior of the students were measured using questionnaires. Data collection was done in May, 2002. Data were analyzed with descriptive statistics and logistic regression using the SPSS WIN 10.0 Program. Results: The prevalence of depression (CES-D) among the students was $53.5\%$. In multiple logistic regression analysis, sex (OR 1.80, $95\%$ Cl 1.35-2.41), school performance, mid (OR 1.68, $95\%$ Cl 1.48-1.97) and low (OR 1.42, $95\%$ Cl 1.29-1.61), drinking (OR 1.47, $95\%$ Cl 1.09-1.98), and not eating breakfast (OR 1.74, $95\%$ Cl 1.56-1.97) were significantly higher in students in the depressed group than those in the non-depressed group. Conclusions: Based on the findings, we concluded that many adolescent experience depression and depression in adolescents is significantly related to behaviors of smoking, alcohol, no exercise, and not eating breakfast. However this study did not address causality among these variables. There, further research, such as a longitudinal study, is needed to identify causality among the variables.

• 응용통계연구
• /
• 제34권2호
• /
• pp.141-152
• /
• 2021

미결정자 추론을 재평가하기 위해 기존 변수에 새로운 변수들을 추가하는 통계 모형이 필요하다. 미결정자와 결정자의 양성률은 다르게 계산되기 때문에 MNAR 가정이 필요하다. 본 연구에서는 두 통계적 모형이 계층 관계를 가지고 있으므로, 두 AUC 차이의 신뢰구간을 이용하여 MNAR 가정하에서 미결정자를 추론한다. AUC 차이 신뢰구간의 추정방법 중에서 모의실험을 통하여 네 종류의 방법의 성능이 우수함을 발견하였다. 그리고 네 종류의 방법을 바탕으로 로지스틱 회귀를 이용한 미결정자 추론에 도움이 되는 변수를 선택하는 방법을 제안한다.

• 한국인공지능학회지
• /
• 제11권1호
• /
• pp.1-7
• /
• 2023

In this paper, a study was conducted to compare the prediction model of cardiovascular disease occurrence. It is the No.1 disease that accounts for 1/3 of the world's causes of death, and it is also the No. 2 cause of death in Korea. Primary prevention is the most important factor in preventing cardiovascular diseases before they occur. Early diagnosis and treatment are also more important, as they play a role in reducing mortality and morbidity. The Results of an experiment using Azure ML, Logistic Regression showed 88.6% accuracy, Decision Tree showed 86.4% accuracy, and Support Vector Machine (SVM) showed 83.7% accuracy. In addition to the accuracy of the ROC curve, AUC is 94.5%, 93%, and 92.4%, indicating that the performance of the machine learning algorithm model is suitable, and among them, the results of applying the logistic regression algorithm model are the most accurate. Through this paper, visualization by comparing the algorithms can serve as an objective assistant for diagnosis and guide the direction of diagnosis made by doctors in the actual medical field.

• 경영과학
• /
• 제34권1호
• /
• pp.27-45
• /
• 2017

The purpose of this study is to empirically analyze whether open innovation activities are significant and which methods are more effective in developing new businesses. Based on the latest technological innovation survey data of the Science and Technology Policy Institute, the results were analyzed by binary logistic regression analysis. As a result of the analysis, we confirmed that open innovation activities have a positive effect on the performance of developing new businesses. In the open innovation activities, Recruitment (invitation) of specialist in related fields, Business alliance technical agreement, Dispatch of personnel, M&A, Acquisitions identify related field trends showed more influence in order. It would be beneficial to improve the performance of developing new businesses with a low probability of success if utilize more effective innovation activities in developing new business in enterprises or organizations throughout this study.

• 한국콘텐츠학회:학술대회논문집
• /
• 한국콘텐츠학회 2018년도 춘계 종합학술대회 논문집
• /
• pp.7-8
• /
• 2018

본 연구에서는 Word2vec을 머신러닝 분류기를 이용해 효율적인 오피니언 마이닝 방법을 제안한다. 본 연구의 목적을 위해 BOW(Bag-of-Words) 방법과 Word2vec방법을 이용해 속성 셋을 구성했다. 구성된 속성 셋은 Decision tree, Logistic regression, Support vector machine, Random forest를 이용해 오피니언 마이닝을 수행했다. 연구 결과, Word2vec 방법과 RF분류기가 가장 높은 정확도를 나타냈다. 그리고 Word2vec 방법이 BOW방법 보다 각 분류기에서 높은 성능을 나타냈다.

• ETRI Journal
• /
• 제43권3호
• /
• pp.538-548
• /
• 2021

This paper proposes an approach to improve the performance of no-reference video quality assessment for sports videos with dynamic motion scenes using an efficient spatiotemporal model. In the proposed method, we divide the video sequences into video blocks and apply a 3D shearlet transform that can efficiently extract primary spatiotemporal features to capture dynamic natural motion scene statistics from the incoming video blocks. The concatenation of a deep residual bidirectional gated recurrent neural network and logistic regression is used to learn the spatiotemporal correlation more robustly and predict the perceptual quality score. In addition, conditional video block-wise constraints are incorporated into the objective function to improve quality estimation performance for the entire video. The experimental results show that the proposed method extracts spatiotemporal motion information more effectively and predicts the video quality with higher accuracy than the conventional no-reference video quality assessment methods.

• Earthquakes and Structures
• /
• 제15권3호
• /
• pp.253-261
• /
• 2018

This article details a bridge-specific fragility method developed to enhance the seismic design and resilience of bridges. Current seismic design processes provide guidance for the design of a bridge that will not collapse during a design hazard event. However, they do not provide performance information of the bridge at different hazard levels or due to design changes. Therefore, there is a need for a supplement to this design process that will provide statistical information on the performance of a bridge, beyond traditional emphases on collapse prevention. This article proposes a bridge-specific parameterized fragility method to enable efficient estimation of various levels of damage probability for alternative bridge design parameters. A multi-parameter demand model is developed to incorporate bridge design details directly in the fragility estimation. Monte Carlo simulation and Logistic regression are used to determine the fragility of the bridge or bridge component. The resulting parameterized fragility model offers a basis for a bridge-specific design tool to explore the influence of design parameter variation on the expected performance of a bridge. When used as part of the design process, these tools can help to transform a prescriptive approach into a more performance-based approach, efficiently providing probabilistic performance information about a new bridge design. An example of the method and resulting fragility estimation is presented.

• 중환자간호학회지
• /
• 제9권1호
• /
• pp.27-39
• /
• 2016

Purpose: The purpose of this study lies in investigating nursing and medical staff perceptions on the importance of surgical patient safety protocol, teamwork, and patient safety culture, and how their grasp of the factors affects the degree of their performance of the protocol. Methods: A survey was conducted on 249 nurses and medical staff participating in the operating rooms of one higher general hospital in Seoul, using a 5-point scale self-reported questionnaire. Logistic regression analyses were used. Results: Operating room nurses yielded the highest scores on both the importance of the patient safety protocol and its performance. In patient safety culture, the operating medical staff yielded significantly higher scores than those of operating room nurses. Perception of the importance of the patient safety protocol and teamwork had a significant effect on the nurses' complete performance of the protocol. Conclusion: It is important to create a safety culture, where all the staff can actively and freely communicate with one another through team-based training programs. By enhancing teamwork and patient safety culture, it will be possible to establish the surgical patient safety protocol and to improve the performance of the protocol by health professionals.