http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
- 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
- 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
RISS 인기검색어
- 검색키워드
- 저자 : 진창호(Jihn, Chang-Ho) (검색결과 4 건)
- 무료
- 기관 내 무료
- 유료
-
-
윤도원(Dowon Yoon),진창호(Chang-Ho Jihn) 한국산업경영시스템학회 2021 한국산업경영시스템학회지 Vol.44 No.4
Treatment and management of chronic low back pain (CLBP) should be tailored to the patient’s individual context. However, there are limited resources available in which to find and manage the causes and mechanisms for each patient. In this study, we designed and developed a personalized context awareness system that uses machine learning techniques to understand the relationship between a patient’s lower back pain and the surrounding environment. A pilot study was conducted to verify the context awareness model. The performance of the lower back pain prediction model was successful enough to be practically usable. It was possible to use the information from the model to understand how the variables influence the occurrence of lower back pain.
-
전현진(Hyeon Jin Jeon),진창호(Chang-Ho Jihn) 한국산업경영시스템학회 2021 한국산업경영시스템학회지 Vol.44 No.4
Depression is one of the most important psychiatric disorders worldwide. Most depression-related data mining and machine learning studies have been conducted to predict the presence of depression or to derive individual risk factors. However, since depression is caused by a combination of various factors, it is necessary to identify the complex relationship between the factors in order to establish effective anti-depression and management measures. In this study, we propose a methodology for identifying and interpreting patterns of depression expressions using the method of deriving random forest rules, where the random forest rule consists of the condition for the manifestation of the depressive pattern and the prediction result of depression when the condition is met. The analysis was carried out by subdividing into 4 groups in consideration of the different depressive patterns according to gender and age. Depression rules derived by the proposed methodology were validated by comparing them with the results of previous studies. Also, through the AUC comparison test, the depression diagnosis performance of the derived rules was evaluated, and it was not different from the performance of the existing PHQ-9 summing method. The significance of this study can be found in that it enabled the interpretation of the complex relationship between depressive factors beyond the existing studies that focused on prediction and deduction of major factors.
-
Random Forest를 활용한 영화 시나리오 최적 구상안 도출에 관한 융합 연구
김성수(Kim, Sungsu),진창호(Jihn, Chang-Ho) 한국전시산업융합연구원 2021 한국과학예술융합학회 Vol.39 No.5
본 연구는 온라인 사용자의 연령대와 영화의 장르를 기반으로 성공적인 영화 시나리오 구성을 파악하고자 하는 것에서 시작되었다. 본 연구의 목적은 사용자의 평점 데이터를 기반으로 Random Forest를 활용하여 관객이 선호하는 영화의 유형을 규칙으로 정의함으로써 영화 시나리오의 이상적인 조합을 식별하는 것이다. 따라서 본 논문은 관객의 평점에 따라 장르 18개와 연령대 측면에서 영화의 성공과 실패를 좌우하는 영화 시나리오 조건들을 규칙으로 해석을 시도하였다. 또한 시나리오 조건과 결과(성공, 실패)로 구성된 규칙의 유용성(frequency)과 신뢰도(error)를 장르와 목표연령대의 바람직한 조합을 선별하는 기준으로 정의했다. 연구 결과 및 내용은 다음과 같다. 첫째, 여러 개의 의사결정나무로 이루어진 Random Forest 알고리즘을 활용하여 많은 수의 규칙을 생성함으로써 신뢰성이 높은 규칙들을 산출하였다. 둘째, 규칙 내 불필요한 조건들을 제거하여 규칙을 일반화함으로써 실용적인 규칙을 생성하였다. 셋째, 공통된 요소를 포함하는 규칙들을 묶어서 단일 규칙의 의미보다 확장된 해석을 할 수 있었다. 이러한 연구 결과를 바탕으로 정의된 규칙들이 성공적인 영화 시나리오 구성에 있어 초석이 될 수 있기를 기대한다. 더불어 본 연구는 각 영화 요소들의 유기적 관계를 데이터마이닝 기법인 Random Forest을 통해 도출하였기에 영화 예술과 데이터 과학의 융합 연구로서 의미를 지닌다. This study started with an attempt to identify the composition of a successful movie scenario based on the age groups of online users and the genres of movies. The purpose of this study is to identify the ideal combination of movie scenarios by defining the types of movies preferred by the audience as a rule based on the user’s rating data using a random forest. Therefore, this paper tried to interpret the movie scenario conditions that determine the success or failure of a movie in terms of 18 genres and age groups as rules according to audience ratings. In addition, the usefulness(frequency) and reliability(error) of the rule composed of scenario conditions and outcomes (success and failure) were used as the criteria for selecting the desired combination of genre and target age group. The research results and contents are as follows. First, rules with high reliability were calculated by generating a large number of rules using the Random Forest algorithm consisting of several decision trees. Second, the practicality of the selected rules was improved by generalizing the rules by removing unnecessary conditions in the rules. Second, practical rules were created by generalizing the rules by removing unnecessary conditions in the rules. Third, by grouping rules containing common elements, it was possible to interpret more extensively than the meaning of a single rule. Based on these research results, it is expected that the defined rules can become a cornerstone for successful film scenario construction. In addition, this study is meaningful as a convergence study of film art and data science because the organic relationship of each film element was derived through a data mining technique, Random Forest.
ScienceON연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
