• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제10권4호
• /
• pp.253-258
• /
• 2010

The causal network represents the knowledge related to the dependency relationship between all attributes. If the causal network is available, the dependency relationship can be employed to estimate the missing values for improving the estimation performance. However, the previous method had a limitation in that it did not consider the bidirectional characteristic of the causal network. The proposed method considers the bidirectional characteristic by applying prior and posterior conditions, so that it outperforms the previous method.

• 논리연구
• /
• 제8권1호
• /
• pp.47-67
• /
• 2005

베이즈망은 탐구 공간을 구성하는 변수들 사이에 성립하는 확률적 관계를 이용하여 그 변수들 사이에 성립된다고 가정되는 인과 관계를 추론하는데 이용된다. 베이즈망에 관한 철학적 논쟁의 대상은 특정한 변수들의 확률적 독립성을 가정하는 인과적 마코프 조건이다. 베이즈망 이론에 대한 강력한 비판자인 카트라이트는 인과적 마코프 조건이 비결정적 세계에서는 성립될 수 없기 때문에 인과적 추리에 대한 타당한 원리가 될 수 없다고 주장한다. 이글의 목적은 인과적 마코프 조건이 인과적 추리에 대한 타당한 원리가 될 수 없다는 카트라이트의 비판이 타당한가를 검토하는 것이다. 나는 인과적 사건들의 연쇄를 허용하는 연속모델은 카트라이트의 비판을 벗어날 수 있다고 주장한다.

• 한국체육학회지인문사회과학편
• /
• 제54권5호
• /
• pp.233-250
• /
• 2015

본 연구의 목적은 대학 교양 요가수업 참여자가 요가수련을 통해 체험하는 변화와 정서를 추출하고, 이러한 변화와 정서 체험이 일상생활에 미치는 영향력을 인과 네트워크(causal network)로 구체화 하는데 있다. H대학교 교양 요가수업 참여자 77명을 대상으로 참여일지를 통해 전반적인 변화요인을 추출한 뒤, 이중 7명을 선정하여 구체적인 자료수집을 위한 심층면담을 진행하였다. 심층면담에서는 요가를 통해 체험한 변화는 어떤 것인지, 이로 인해 유발되었던 정서는 무엇인지, 그리고 이러한 변화와 정서체험이 일상생활에 어떤 영향을 미쳤는지의 질문으로 구성된 반구조화설문지를 활용하였다. 그리고 수집된 결과는 질문의 흐름에 따라 인과 네트워크(causal network)로 도식화하였다. 연구결과, 요가를 통한 변화는 신체기능적 변화, 정서적 변화, 인지적 변화, 생리적 변화의 4개 영역으로 범주화되었으며, 각 변화요인과 변화에 따라 유발된 정서는 이후의 일상생활에 영향을 미치는 것으로 나타났다. 연구결과를 토대로 요가의 효과 및 참여행동의 다각적 접근 필요성, 그리고 이를 위한 방법으로서 인과 네트워크의 활용 가능성을 논의하였다.

• 한국시스템다이내믹스연구
• /
• 제13권4호
• /
• pp.33-55
• /
• 2012

The research is to identify important diffusion factors and their effects on green car diffusion process using system dynamics perspectives and a causal-loop analysis. Through a deep review on previous research, we have found the important factors of green car diffusion process. Price, driving range, network effect, recharge system, fuel cost had important facilitation on consumer attraction and green car diffusion. Based on the review, we have constructed a causal loop diagram explaining hybrid car diffusion process. We have found 3 important reinforcing loops in the causal loop diagram. Loop for learning & economies of scale(supply side), loop for network effect(consumer side), and loop for battery development(technology side) had most significant roles in the whole diffusion process. Through a deliberate analysis on the 3 causal loops, we have found meaningful results. First, there seems to exist a critical mass in the diffusion. Second, of the 3 loops, the battery technology had most significant role. Third, not consumer installed base but sales must be a standard to decide whether the critical mass is achieved or not. Based on these findings, several meaningful implications are suggested for the government and corporations related to the green car industries.

• 정보처리학회논문지B
• /
• 제15B권2호
• /
• pp.147-158
• /
• 2008

본 논문에서는 인과관계 지식의 표현과 추론에 가장 대표적으로 사용되는 퍼지인식도(FCM, Fuzzy Cognitive Map)와 베이지안 신뢰 네트워크(BBN, Bayesian Belief Network)를 구조적으로 분석한다. 퍼지인식도와 베이지안 신뢰 네트워크는 의사 결정을 지원하는데 중요한 인과관계 지식을 표현하고 추론하는데 사용되는 가장 대표적인 프레임워크이지만 인과관계 지식응용 영역에서 두 프레임워크의 역할에 대한 구조적 비교 연구는 이루어지지 않고 있다. 본 논문에서는 두 프레임워크의 구조적 비교를 통해 퍼지인식도와 베이지안 신뢰 네트워크의 중요한 특징들을 추출하고, 이를 통해 인과 지식 공학에서 어떻게 퍼지 인식도와 베이지안 신뢰 네트워크가 이용되어야 하는지를 보인다. 인과관계 지식의 표현과 추론의 과정을 평가하는데 비교 평가를 위한 항목으로서 본 논문에서는 사용성, 표현력, 추론능력, 정형화와 완결성이 사용되었다.

• 대한골대사학회지
• /
• 제25권4호
• /
• pp.251-266
• /
• 2018

Background: The causal networks among genes that are commonly expressed in osteoblasts and during bone metastasis (BM) of breast cancer (BC) are not well understood. Here, we developed a machine learning method to obtain a plausible causal network of genes that are commonly expressed during BM and in osteoblasts in BC. Methods: We selected BC genes that are commonly expressed during BM and in osteoblasts from the Gene Expression Omnibus database. Bayesian Network Inference with Java Objects (Banjo) was used to obtain the Bayesian network. Genes registered as BC related genes were included as candidate genes in the implementation of Banjo. Next, we obtained the Bayesian structure and assessed the prediction rate for BM, conditional independence among nodes, and causality among nodes. Furthermore, we reported the maximum relative risks (RRs) of combined gene expression of the genes in the model. Results: We mechanistically identified 33 significantly related and plausibly involved genes in the development of BC BM. Further model evaluations showed that 16 genes were enough for a model to be statistically significant in terms of maximum likelihood of the causal Bayesian networks (CBNs) and for correct prediction of BM of BC. Maximum RRs of combined gene expression patterns showed that the expression levels of UBIAD1, HEBP1, BTNL8, TSPO, PSAT1, and ZFP36L2 significantly affected development of BM from BC. Conclusions: The CBN structure can be used as a reasonable inference network for accurately predicting BM in BC.

• 한국간호교육학회지
• /
• 제10권1호
• /
• pp.54-63
• /
• 2004

The purpose of this study is to identify the factors that influence stress experienced by nursing students and to provide a perceived causal structure model among these variables. The ultimate goal of this study is to develop efficient guidance to clinical nursing education in this population. This study intends to apply perceived causal structure: network analysis method which was developed by Kelly(1983), and has been applied in nursing research. This method is selected to show dynamic relationship of stressor using network method. Data was collected from convenient sample of 186 junior college nursing students who had the clinical practice experience during 10 weeks. Data collection and analysis was conducted in 2 steps from December, 9, 2002 to February, 8, 2003. Step 1.: Data was collected using literature review(10 articles) to identify the causes of stress. Nine causes of stress were extracted. Step 2.: As perceived casual structure network study, data was collected using questionnaires which included 9 extracted cause and stress. The questionnaire contained a 10 X 10 grid table with 10 causes and effects printed. In network analysis, 'Yes' was scored as 1, 'No' was scored as 0, and the mean(maximum 1, minimum 0) was calculated. Construction of the network under inductive eliminative analysis which stopped the construction of the network when the consensual agreement level dropped near 50% was proceeded by adding causes in order of the mean rating level. In this study, construction of the final network was stopped by consensual agreement level of 52% of the total subjects. The results are summarized as follows : Step 1: Investigation of the causes of stress ; The extracted causes of stress from quality data was identified 9 categories ; negative nurse, lack of clinical practice opportunity, ambiguous role, negative patient, lack of nursing knowledge and skill, difficult of personal relations, inefficient clinical practice guidance, gap of theory and practice, lack of support. Step 2 : Construction of the perceived causal structure model ; 1) The most central cause of stress is ambiguous role in the systems of causation. 2) The distal cause of stress is inefficient clinical practice guidance 3) The causes that have a number of outgoing link are negative nurse, ambiguous role. 4) The causes that have a number of incoming link are ambiguous role, gap of theory- practice, lack of clinical practice opportunity, lack of nursing knowledge- skill. 5) There is a mutual relationship between stress and difficult of personal relations, stress and ambiguous role, ambiguous role and negative nurse, ambiguous role and lack of clinical practice opportunity, ambiguous role and lack of nursing knowledge-skill, lack of nursing knowledge-skill and gap of theory- practice. In conclusion, the network suggests that the first centre cause is related on ambiguous role and the second on negative nurse, inefficient clinical practice guidance in the systems of causation

• 응용통계연구
• /
• 제36권2호
• /
• pp.129-139
• /
• 2023

변동성의 예측은 자산의 리스크에 대비하는 데에 중요한 역할을 하기때문에 필수적이다. 인공지능을 통하여 이러한 복잡한 특성을 지닌 변동성 예측을 시도하였는데 기존 시계열 예측에 적합하다 알려진 LSTM (1997)과 GRU (2014)은 기울기 소실로 인한 문제, 방대한 연산량의 문제, 그로 인한 메모리양의 문제 등이 존재하였다. 변동성 데이터는 비정상성(non-stationarity)과 정상성(stationarity)을 모두 가지고 있는 특성이 있으며, 자산 가격 하방 쇼크에 더 큰 폭으로 상승하는 비대칭성과 상당한 장기 기억성, 시장에 큰 사건이 발생할 때 기존의 값들에 비해 이상치라 할 수 있을 정도의 예측할 수 없는 큰 값이 발생하는 특성들이 존재한다. 이렇게 여러 가지 복잡한 특성들은 하나의 모형으로 구조화되기 어려워서 전통적인 방식의 모형으로는 변동성에 대한 예측력을 높이기 어려운 면이 있다. 이러한 문제를 해결하기 위해 1D CNN의 발전된 형태인 causal TCN (causal temporal convolutional network) 모형을 변동성 예측에 적용하고, 예측력을 최대화 할 수 있는 TCN 구조를 설계하고자 하였다. S&P 500, DJIA, Nasdaq 지수에 해당하는 변동성 지수 VIX, VXD, and VXN, 에 대하여 예측력 비교를 하였으며, TCN 모형이 RNN 계열의 모형보다도 전반적으로 예측력이 높음을 확인하였다.

• 한국간호교육학회지
• /
• 제11권2호
• /
• pp.161-168
• /
• 2005

Purpose: The purposes are to identify the factors that influence work-based stressor experienced by clinical nurses and to provide a perceived causal structural model among these factors. Method: Data was collected and analyzed in 2 steps to apply a perceived causal structure : network analysis which was developed by Kelley(1983). Results: 1. The extracted causes from qualitative data were identified 10 categories ; over loaded work, relative feelings of deprived, inefficient duty schedule, negative attitudes of patient, burden of extra affair, inadequate administrative support, negative attitudes of physician, conflict with other personnels in hospital, lack of professional knowledge and skill, nursing service marketing burden. 2. Construction of the perceived causal structural model ; 1) The most central cause is over loaded work and the distal causes were inadequate administrative support, lack of professional knowledge and skill in the systems of causation. 2) The causes that have a number of outgoing link were over loaded work, inadequate administrative support, negative attitudes of physician. 3) The cause that have a number of incoming link was relative feelings of deprived. Conclusion: The network suggests that the first centre cause was related on over loaded work.

• Journal of Electrical Engineering and Technology
• /
• 제11권6호
• /
• pp.1812-1824
• /
• 2016

The neural dynamics underlying the causal network during motor planning or imagery in the human brain are not well understood. The lack of signal processing tools suitable for the analysis of nonlinear and nonstationary electroencephalographic (EEG) hinders such analyses. In this study, noise-assisted multivariate empirical mode decomposition (NA-MEMD) is used to estimate the causal inference in the frequency domain, i.e., partial directed coherence (PDC). Natural and intrinsic oscillations corresponding to the motor imagery tasks can be extracted due to the data-driven approach of NA-MEMD, which does not employ predefined basis functions. Simulations based on synthetic data with a time delay between two signals demonstrated that NA-MEMD was the optimal method for estimating the delay between two signals. Furthermore, classification analysis of the motor imagery responses of 29 subjects revealed that NA-MEMD is a prerequisite process for estimating the causal network across multichannel EEG data during mental tasks.