• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.563-568
• /
• 2020

본 연구에서는 블랙박스로 알려진 딥러닝 모델에 설명 근거를 제공할 수 있는 설명자 모델을 적용해 보았다. 영화평 감성 분석을 위해 MLP, CNN으로 구성된 딥러닝 모델과 결정트리의 앙상블인 Gradient Boosting 모델을 이용하여 감성 분류기를 구축하였다. 설명자 모델로는 기울기(gradient)을 기반으로 하는 IG와 레이어 사이의 가중치(weight)을 기반으로 하는 CAM, 그리고 설명가능한 대리 모델을 이용하는 LIME과 입력 속성에 대한 선형모델을 추정하는 SHAP을 사용하였다. 설명자 모델의 특성을 보기 위하여 히트맵과 관련성 높은 N개의 속성을 추출해 보았다. 설명자가 제공하는 기여도에 따라 입력 속성을 제거해 가며 분류기 성능 변화를 측정하는 정량적 평가도 수행하였다. 또한, 사람의 판단 근거와의 일치도를 살펴볼 수 있는 '설명 근거 정확도'라는 새로운 평가 방법을 제안하여 적용해 보았다.

• Information Systems Review
• /
• v.24 no.1
• /
• pp.105-123
• /
• 2022

Thanks to the remarkable success of Artificial Intelligence (A.I.) techniques, a new possibility for its application on the real-world problem has begun. One of the prominent applications is the bankruptcy prediction model as it is often used as a basic knowledge base for credit scoring models in the financial industry. As a result, there has been extensive research on how to improve the prediction accuracy of the model. However, despite its impressive performance, it is difficult to implement machine learning (ML)-based models due to its intrinsic trait of obscurity, especially when the field requires or values an explanation about the result obtained by the model. The financial domain is one of the areas where explanation matters to stakeholders such as domain experts and customers. In this paper, we propose a novel approach to incorporate financial domain knowledge into local rule generation to provide explanations for the bankruptcy prediction model at instance level. The result shows the proposed method successfully selects and classifies the extracted rules based on the feasibility and information they convey to the users.

• Journal of the KSME
• /
• v.24 no.3
• /
• pp.193-202
• /
• 1984

본고에서는 피로파괴에 관하여 크게 두가지로 나누어서 설명한다. 첫째 피로현상에 의하여 생기는 피로파면형태 및 전위조직에 관하여 설명하고 그 다음에는 피로균열의 생성기구에 관하여 피로균열의 각 단계별로 설명하고 파면의 특성에 관하여 파괴역학적인 수법도 사용하여 설명한다.

• Journal of Gifted/Talented Education
• /
• v.22 no.1
• /
• pp.141-155
• /
• 2012

The purpose of this study was to analyse characteristics of explanatory writing of scientifically gifted students who participated in gifted educational programs. Considering aspect of content of their explanations about cell, many of them explained the common characteristics of animal and plant cells, but a few of them did cellular characteristics of one kind of animal and plant. Some gifted students regarded cell membrane function as that of cell wall, and had a misconception that the cell was the smallest unit to consist human body. In terms of the structure of explanation, most of them didn't know the structural characteristics of explanatory writing. Finally, more than 50% of them had written using various ways to explain cell such as classifying, comparing, contrasting and exemplifying. Especially, all biologically gifted students had creatively explained drawing a picture. It was findings that the explanatory writing could be used as the instrument to evaluate knowledges of gifted students and suggested the elements of writing to teach scientific explanatory writing.

• Journal of the Korean Society for information Management
• /
• v.26 no.3
• /
• pp.145-168
• /
• 2009

The basic rights of the public for sustaining public accountability relations between public sector organizations and the citizens is the accessibility to information of public sector organizations. Public organizations in Korea get checked under multiple public accountability relations, which increases steadily the information provision requests from stakeholders. To respond these requirements effectively and efficiently, public sector organizations are required to transform their information management regime to comply with accountability-oriented settings. This study (1) suggests procedures and methods to select 'information for accountability' from the organization's whole information as an important object to be managed, (2) suggests procedures and methods to establish control criteria for the organization to manage its information for accountability in appropriate ways, and (3) gives an example of applying the procedures and methods to the specific context of universities' information disclosure. The procedures and methods suggested are described from a viewpoint of the consulting for the accountability information management regime.

• The Journal of the Korea Contents Association
• /
• v.20 no.8
• /
• pp.653-665
• /
• 2020

As the use of recommended agents has become more active, the "Explain Facilities" is drawing attention as a way to solve the black-box problem that could not explain internal logic to users. This study wants to look at how the description Method and Detail affects to user experience. The Explanation method was divided into 'why the agent did a particular action' and 'why not do a particular action' and the detail condition were divided into 'high or low'. Studies have found that 'why method' have a positive effect on users' transparency, trust, satisfaction, and behavioral intention to use, and 'high detail condition' higher the user' Psychological reactance. In addition, it was found that the explanation methods and detail influenced the 'Explanation' perception through interaction and tended to affect satisfaction and intention to adopt recommendation. This study suggested that careful attention is needed to determine the method and detail of the Explanation facilities in the context of the recommended agent, based on the research findings that it affects the user experience through the interaction of the method and detail.

• Journal of The Korean Association For Science Education
• /
• v.22 no.4
• /
• pp.683-695
• /
• 2002

In this study, we analyzed types of explanation on osmosis concept that were represented in chemistry and biology textbooks of high school and college. There were 5 types of explanation on osmosis concept. The types of explanation were diffusion of solvent, collision, hydration, equilibrium of concentration and screen of holes. Last two types of explanation were classified into misconceptions. The various types of explanation on osmosis concept might cause to have be a reason that students had many misconceptions and to feel difficult to learn about osmosis concept. Many of textbooks is accord to types of concept explanation and figure explanation on osmosis but some is not.

• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.307-332
• /
• 2022

One of the most intensively conducted research areas in business application study is a bankruptcy prediction model, a representative classification problem related to loan lending, investment decision making, and profitability to financial institutions. Many research demonstrated outstanding performance for bankruptcy prediction models using artificial intelligence techniques. However, since most machine learning algorithms are "black-box," AI has been identified as a prominent research topic for providing users with an explanation. Although there are many different approaches for explanations, this study focuses on explaining a bankruptcy prediction model using a counterfactual example. Users can obtain desired output from the model by using a counterfactual-based explanation, which provides an alternative case. This study introduces a counterfactual generation technique based on a genetic algorithm (GA) that leverages both domain knowledge (i.e., causal feasibility) and feature importance from a black-box model along with other critical counterfactual variables, including proximity, distribution, and sparsity. The proposed method was evaluated quantitatively and qualitatively to measure the quality and the validity.

• Journal of Korean Society of Transportation
• /
• v.30 no.1
• /
• pp.113-123
• /
• 2012

This study introduces a new type of a modal split model that use zonal data instead of cost data as independent variables. It has been indicated that the ones using cost data have deficiencies in the multicollinearity of travel time and cost variables and unpredictability of independent variables. The zonal data employed in this study include (1) socioeconomic data, (2) land use data and (3) transportation system data. The test results showed that the proposed modal split model using zonal data performs better than the other does.

• Journal of the Korean earth science society
• /
• v.27 no.6
• /
• pp.606-619
• /
• 2006

In this paper we investigated the types of the explanatory consistency of preservice secondary teachers in explaining the lunar phase. The explanatory consistencies were proposed into four discrete mental models depending on their attributes. The four types based on the explanatory consistency by the preservice secondary teachers' explanations are as follows: ad hoc expansion, competitive theory addition, transition of unexplainable each, and transition using in context of several situations.