• International Journal of Internet, Broadcasting and Communication
• /
• 제15권3호
• /
• pp.191-202
• /
• 2023

This study aims to propose a framework for evaluating the impact of artificial intelligence (AI) services, based on the concept of AI service impact. It also suggests a model for evaluating this impact and identifies relevant factors and measurement approaches for each item of the model. The study classifies the impact of AI services into five categories: ethics, safety and reliability, compliance, user rights, and environmental friendliness. It discusses these five categories from a broad perspective and provides 21 detailed factors for evaluating each category. In terms of ethics, the study introduces three additional factors-accessibility, openness, and fairness-to the ten items initially developed by KISDI. In the safety and reliability category, the study excludes factors such as dependability, policy, compliance, and awareness improvement as they can be better addressed from a technical perspective. The compliance category includes factors such as human rights protection, privacy protection, non-infringement, publicness, accountability, safety, transparency, policy compliance, and explainability.For the user rights category, the study excludes factors such as publicness, data management, policy compliance, awareness improvement, recoverability, openness, and accuracy. The environmental friendliness category encompasses diversity, publicness, dependability, transparency, awareness improvement, recoverability, and openness.This study lays the foundation for further related research and contributes to the establishment of relevant policies by establishing a model for evaluating the impact of AI services. Future research is required to assess the validity of the developed indicators and provide specific evaluation items for practical use, based on expert evaluations.

• International journal of advanced smart convergence
• /
• 제12권1호
• /
• pp.53-58
• /
• 2023

With the fast development of artificial intelligence day by day, users are demanding explanations about the results of algorithms and want to know what parameters influence the results. In this paper, we propose a model for bankruptcy prediction with interpretability using the SHAP framework. SHAP (SHAPley Additive exPlanations) is framework that gives a visualized result that can be used for explanation and interpretation of machine learning models. As a result, we can describe which features are important for the result of our deep learning model. SHAP framework Force plot result gives us top features which are mainly reflecting overall model score. Even though Fully Connected Neural Networks are a "black box" model, Shapley values help us to alleviate the "black box" problem. FCNNs perform well with complex dataset with more than 60 financial ratios. Combined with SHAP framework, we create an effective model with understandable interpretation. Bankruptcy is a rare event, then we avoid imbalanced dataset problem with the help of SMOTE. SMOTE is one of the oversampling technique that resulting synthetic samples are generated for the minority class. It uses K-nearest neighbors algorithm for line connecting method in order to producing examples. We expect our model results assist financial analysts who are interested in forecasting bankruptcy prediction of companies in detail.

• 시스템엔지니어링학술지
• /
• 제19권2호
• /
• pp.135-144
• /
• 2023

Artificial Intelligence (AI) is a prominent topic in almost every field. In Korea, Systems Engineering (SE) procedures are applied in Defense Acquisition, and it is anticipated that SE procedures will also be applied to systems incorporating AI capabilities. This study explores the applicability of the concepts "AI4SE (AI for SE)" and "SE4AI (SE for AI)," which have been proposed in the United States, to the Korean context. The research examines the feasibility of applying these concepts, identifies necessary tasks, and proposes implementation strategies. For the AI4SE, many attempts and studies applying AI to SE Processes both Requirements & Architectures Define, System implementation & V&V, and Sustainment. It needs Explainability and Security. For the SE4AI, the Functional AI implementation level, Quality & Security of the Data-set, AI Ethics, and Review policies are needed. Furthermore, it provides perspectives on how these two concepts should ultimately converge and suggests future directions for development.

• International Journal of Internet, Broadcasting and Communication
• /
• 제16권1호
• /
• pp.203-214
• /
• 2024

This study seeks to provide implications for domestic-related policies through exploratory analysis research to support AI-based policy decision-making. The following should be considered when establishing an AI-based decision-making model in Korea. First, we need to understand the impact that the use of AI will have on policy and the service sector. The positive and negative impacts of AI use need to be better understood, guided by a public value perspective, and take into account the existence of different levels of governance and interests across public policy and service sectors. Second, reliability is essential for implementing innovative AI systems. In most organizations today, comprehensive AI model frameworks to enable and operationalize trust, accountability, and transparency are often insufficient or absent, with limited access to effective guidance, key practices, or government regulations. Third, the AI system is accountable. The OECD AI Principles set out five value-based principles for responsible management of trustworthy AI: inclusive growth, sustainable development and wellbeing, human-centered values and fairness values and fairness, transparency and explainability, robustness, security and safety, and accountability. Based on this, we need to build an AI-based decision-making system in Korea, and efforts should be made to build a system that can support policies by reflecting this. The limiting factor of this study is that it is an exploratory study of existing research data, and we would like to suggest future research plans by collecting opinions from experts in related fields. The expected effect of this study is analytical research on artificial intelligence-based decision-making systems, which will contribute to policy establishment and research in related fields.

• 문화기술의 융합
• /
• 제4권2호
• /
• pp.81-87
• /
• 2018

본 연구는 도시지역 독거노인들의 주관적 건강상태, 자기효능감, 사회적 지지와 건강행위 정도를 알아보고, 건강행위에 영향을 주는 요인을 확인하기 위해 시행하였다. C 시의 도시지역에 거주하는 독거노인 203명을 대상으로 하였다. 연구결과 대상자의 주관적 건강상태는 평균 2.89점(5점)으로 중간수준 3점보다 낮았고, 자기효능감은 평균 2.64점(4점), 사회적 지지는 평균 3.87점(5점), 건강행위 정도는 평균 3.14점(4점)으로 중간수준보다 높게 나타났다. 대상자의 건강행위에 영향을 주는 요인으로 자기효능감, 사회적지지, 주관적 건강상태, 경제상태, 종교, 성별로 나타났다. 이들은 도시지역 독거노인의 건강행위를 설명하는데 43%의 설명력을 나타내었다. 이 결과는 도시지역 독거노인들의 건강증진프로그램을 개발하는데 유용하게 활용될 수 있을 것이다.

• 한국산학기술학회논문지
• /
• 제16권2호
• /
• pp.1109-1117
• /
• 2015

본 연구는 간호대학생의 비판적 사고 성향과 자아존중감에 따른 취업스트레스의 정도를 파악하고 이들 변수간의 관계를 파악하는 서술적 상관관계 연구로써, 강원도에 소재하는 3개 대학에서 편의 추출하여 332명의 대상으로 하여 수행하였다. 비판적 사고 성향은 $89.57{\pm}9.77$점, 자아 존중감은 $25.11{\pm}2.58$점, 취업 스트레스는 $46.38{\pm}17.67$이었으며, 비판적 사고 성향과 자아존중감(r=.294, p<.001)은 양의 상관관계가 있었고, 비판적 사고 성향과 취업스트레스(r=-.240, p<.001) 및 자아존중감(r=-.209, p<.001)과는 유의한 음의 상관관계가 있었다. 비판적 사고 성향과 자아존중감은 취업 스트레스에 영향을 미치는 변수였고, 35.2%로 설명되었다. 따라서 간호대학생의 비판적 사고 성향과 자아존중감 향상을 통해 취업스트레스를 감소시킬 수 있는 통합적 교육프로그램을 개발하여 적용할 필요가 있겠다.

• 정보화정책
• /
• 제28권2호
• /
• pp.98-113
• /
• 2021

본 연구는 우리나라와 미국, 영국, EU의 국가 데이터전략, 데이터 정책과 제도 및 거버넌스를 비교함으로써 우리 환경에 맞는 시사점을 제안했다. 비교분석 결과 범정부 차원의 데이터 정책을 총괄할 수 있는 거버넌스, 데이터 윤리를 포함하는 데이터 정책을 고려할 수 있어야 할 것으로 보인다. 이에 본 연구는 데이터 정책의 총괄 거버넌스 확립을 위해 국가 차원의 최고데이터책임자(CDO)를 요구하면서 대통령 소속 데이터특별위원회를 두거나 대통령 비서실 내에 가칭 '국가디지털혁신실'을 설치하는 방안을 제시했다. 또한 민간 부문의 데이터도 규율할 수 있는 데이터산업기본법의 제정, 데이터 중심 보안과 정보보호 체계, 설명가능성과 책임 등 신뢰 확보를 위해 요구되는 공공부문의 데이터 전문역량과 전문가 윤리 관념 기반의 공직윤리 및 인사, 교육훈련 제도와의 연계 등을 제안했다.

• 한국정보시스템학회지:정보시스템연구
• /
• 제30권4호
• /
• pp.21-42
• /
• 2021

Purpose In order for companies to continue to grow, they should properly manage human resources, which are the core of corporate competitiveness. Employee turnover means the loss of talent in the workforce. When an employee voluntarily leaves his or her company, it will lose hiring and training cost and lead to the withdrawal of key personnel and new costs to train a new employee. From an employee's viewpoint, moving to another company is also risky because it can be time consuming and costly. Therefore, in order to reduce the social and economic costs caused by employee turnover, it is necessary to accurately predict employee turnover intention, identify the factors affecting employee turnover, and manage them appropriately in the company. Design/methodology/approach Prior studies have mainly used logistic regression and decision trees, which have explanatory power but poor predictive accuracy. In order to develop a more accurate prediction model, XGBoost is proposed as the classification technique. Then, to compensate for the lack of explainability, SHAP, one of the XAI techniques, is applied. As a result, the prediction accuracy of the proposed model is improved compared to the conventional methods such as LOGIT and Decision Trees. By applying SHAP to the proposed model, the factors affecting the overall employee turnover intention as well as a specific sample's turnover intention are identified. Findings Experimental results show that the prediction accuracy of XGBoost is superior to that of logistic regression and decision trees. Using SHAP, we find that jobseeking, annuity, eng_test, comm_temp, seti_dev, seti_money, equl_ablt, and sati_safe significantly affect overall employee turnover intention. In addition, it is confirmed that the factors affecting an individual's turnover intention are more diverse. Our research findings imply that companies should adopt a personalized approach for each employee in order to effectively prevent his or her turnover.

• 산업경영시스템학회지
• /
• 제44권4호
• /
• pp.1-11
• /
• 2021

Recently, the importance of preventive maintenance has been emerging since failures in a complex system are automatically detected due to the development of artificial intelligence techniques and sensor technology. Therefore, prognostic and health management (PHM) is being actively studied, and prediction of the remaining useful life (RUL) of the system is being one of the most important tasks. A lot of researches has been conducted to predict the RUL. Deep learning models have been developed to improve prediction performance, but studies on identifying the importance of features are not carried out. It is very meaningful to extract and interpret features that affect failures while improving the predictive accuracy of RUL is important. In this paper, a total of six popular deep learning models were employed to predict the RUL, and identified important variables for each model through SHAP (Shapley Additive explanations) that one of the explainable artificial intelligence (XAI). Moreover, the fluctuations and trends of prediction performance according to the number of variables were identified. This paper can suggest the possibility of explainability of various deep learning models, and the application of XAI can be demonstrated. Also, through this proposed method, it is expected that the possibility of utilizing SHAP as a feature selection method.

• 대한토목학회논문집
• /
• 제26권4D호
• /
• pp.573-580
• /
• 2006

포화차두시간은 신호시간 설계와 교차로 용량추정에 있어서 중요한 변수 중에 하나이다. 그러나 현재의 기법은 신호교차로에서 포화차두시간에 영향을 미치는 요인들 중 정성적인 요인들을 다루기에는 부적절하다. 본 연구에서는 퍼지적 성격을 가진 정성적 인자인 강우조건과 주변 밝기정도를 선택하여 ANFIS를 이용해서 현장에서 관측된 관측치와 입 출력 데이터 집합의 학습을 통해 퍼지근사추론 모형을 구축하였다. 강우조건은 강우량에 따라 3개의 퍼지변수로, 주변 밝기정도는 2개의 퍼지변수로 구분하였다. 이렇게 구축된 모형의 예측력은 검증자료를 이용한 관측치와 추론치를 비교함으로써 평가되었다. 결정계수와 오차 및 분산정도를 나타내는 척도인 평균절대 오차(MAE)와 평균제곱근 오차(MSE)가 각각 0.993, 0.0289, 0.00173으로 나타나 본 모형의 설명력이 높은 것으로 평가 된다.