• Journal of Information Processing Systems
• /
• 제19권6호
• /
• pp.803-816
• /
• 2023

Explainable artificial intelligence is a method that explains how a complex model (e.g., a deep neural network) yields its output from a given input. Recently, graph-type data have been widely used in various fields, and diverse graph neural networks (GNNs) have been developed for graph-type data. However, methods to explain the behavior of GNNs have not been studied much, and only a limited understanding of GNNs is currently available. Therefore, in this paper, we propose an explanation method for node classification using graph convolutional networks (GCNs), which is a representative type of GNN. The proposed method finds out which features of each node have the greatest influence on the classification of that node using GCN. The proposed method identifies influential features by backtracking the layers of the GCN from the output layer to the input layer using the gradients. The experimental results on both synthetic and real datasets demonstrate that the proposed explanation method accurately identifies the features of each node that have the greatest influence on its classification.

• 한국품질경영학회:학술대회논문집
• /
• 한국품질경영학회 2006년도 추계 학술대회
• /
• pp.221-226
• /
• 2006

We usually use two techniques(influence function and local influence) for detecting outliers. But, we cannot use these difficult techniques in elementary industrial statistics course for college students. We can use some simple graphical methods(box plot, dandelion seed plot, influence graph and cumulative deletion plot) for univariate and bivariate outlier detection and outlier effect in elementary industrial statistics course for college students.

• 한국수학교육학회지시리즈A:수학교육
• /
• 제51권3호
• /
• pp.197-210
• /
• 2012

In this study, we will develop and implement the teaching program of 'Function', on the subject of "Poster-Making utilizing the Graph Art" in the Math Camp for middle-school students. And we will examine the didactical significance through student's activities and products. The teaching program of 'Function' utilizing the Graph Art can be promoted self-directly the understanding of 'Function' concept and the ability for handling 'Function'. In the process of drawing up the graph art, in particular, this program help students to promote the ability for problem-solving and mathematical thinking, and to communicate mathematically and attain the his own level. Ultimately, this program have a positive influence upon cognitive and affective and areas with regard to mathematics.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권7호
• /
• pp.2568-2584
• /
• 2015

Spectral clustering has become one of the most popular clustering approaches in recent years. Similarity graph constructed on the data is one of the key factors that influence the performance of spectral clustering. However, the similarity graphs constructed by existing methods usually contain some unreliable edges. To construct reliable similarity graph for spectral clustering, an efficient method based on Markov random walk (MRW) is proposed in this paper. In the proposed method, theMRW model is defined on the raw k-NN graph and the neighbors of each sample are determined by the probability of the MRW. Since the high order transition probabilities carry complex relationships among data, the neighbors in the graph determined by our proposed method are more reliable than those of the existing methods. Experiments are performed on the synthetic and real-world datasets for performance evaluation and comparison. The results show that the graph obtained by our proposed method reflects the structure of the data better than those of the state-of-the-art methods and can effectively improve the performance of spectral clustering.

• 터널과지하공간
• /
• 제15권5호
• /
• pp.369-377
• /
• 2005

지하공동의 안정성은 생산성과 안전을 확보해야 하는 광산의 운영에 있어서 가장 중요한 관심사이다. 암반분류는 많은 경험적인 설계방법의 근간을 이룰 뿐만 아니라 수치해석을 위한 기초자료로 이용되고 있다. 공동의 안정성에 영향을 주는 많은 요소들 중 주어진 암반의 조건 중에서 공동폭은 하나의 중요한 설계요소가 된다. 이 논문에서는 Lug에 의해 제안된 한계 공동폭 기준, Mathews stability graph method 그리고 저자들에 의해 제안된 한계 공동폭 기준을 비교하였다. Methews stability graph method를 이용하여 저자들에 의해 수정된 한계 공동폭 기준을 제안하였고 이것을 여러 석회석 광산 지하공동의 안정성을 평가하는 데 사용하였다.

• 산업경영시스템학회지
• /
• 제23권55호
• /
• pp.85-96
• /
• 2000

This paper describes IDMS, a graph-based modeling system that supports problem structuring. We employs influence diagram as a problem representation tool, that is, a modeling tool. In particular, IDMS is designed as domain-independent shell. Therefore, a modeler can change the contents of the knowledge base to suit his/her own interested domain. Since the knowledge base of IDMS contains both modeling knowledge and domain knowledge, IDMS provides not only the syntactic support for modeling tool, but also the semantic support for problem domain. To apply the method in the real world context, we tested IDMS on the process selection problem in business reengineering, which is typical semi-structured problem.

• Journal of Electrical Engineering and information Science
• /
• 제1권1호
• /
• pp.164-172
• /
• 1996

The partitioning of related objects should be performed before clustering for an efficient access in object-oriented databases. In this paper, a horizontal partition of related objects in object-oriented databases is presented. All subclass nodes in a class inheritance hierarchy of a schema graph are shrunk to a class node in the graph that is called condensed schema graph because the aggregation hierarchy has more influence on the partition than the class inheritance hierarchy. A set function and an accessibility function are defined to find a maximal subset of related objects among the set of objects in a class. A set function maps a subset of the domain class objects to a subset of the range class objects. An accessibility function maps a subset of the objects of a class into a subset of the objects of the same class through a composition of set functions. The algorithm derived in this paper is to find the related objects of a condensed schema graph using accessibility functions and set functions. The existence of a maximal subset of the related objects in a class is proved to show the validity of the partition algorithm using the accessibility function.

• 의료ㆍ복지 건축 : 한국의료복지건축학회 논문집
• /
• 제21권3호
• /
• pp.25-35
• /
• 2015

Purpose: Signs that are installed at unnoticeable places or that disconnect before the destination can bring errors of location information delivery. Therefore, this study aims to find out the spatial relation between structure of space and signs in the perspective of visual exposure possibility, operating arrangement and assesment by applying spatial structure theory. Methods: Effectiveness of organization of guidance signs was evaluated after the four way-finding factors(Plan Configuration, Sign System, Perceptual Access, Architectural Difference) that G.D.Weisman suggested were interpreted by spatial structure theory(J-Graph analysis, Space Syntax, Visual Graph Analysis) under the premise that it is closely related to the structure of space. Results: 1) Because the south corridor that connects each department of outpatient division is located in the hierarchy center of the space, and walking density is expected to be high, guidance signs need to be organized at the place with high integration value. 2) The depth to the destination space can be estimated through J-Graph analysis. The depth means a switch of direction, and the guidance signs are needed according to the number. 3) According to visibility graph analysis, visual exposure can be different in the same hierarchy unit space according to the shape of the flat surface. Based on these data, location adjustment of signs is possible, and the improvement effect can be estimated quantitatively. Implications: Spatial structure theory can be utilized to design and evaluate sign systems, and it helps to clearly understand the improvement effect. It is desirable to specify design and estimation of sign systems in the order of J-Graph analysis${\rightarrow}$Space Syntax Theory${\rightarrow}$visibility graph analysis.

• 한국정보통신학회논문지
• /
• 제20권10호
• /
• pp.1967-1972
• /
• 2016

본 논문은 깊이 영상의 손 영역을 위해 거리 그래프를 정의하고 그것을 이용해 손가락을 검출하는 알고리즘을 제안한다. 거리 그래프는 손바닥 중심과 손 윤곽선 사이의 각과 유클리디안 거리로 손 윤곽선을 표현한 그래프이다. 거리 그래프는 손끝들의 위치에서 국부 최댓값을 갖고 있어 손가락 위치를 검출할 수 있고 손가락 개수를 인식할 수 있다. 윤곽선은 항상 360 개의 각으로 나누어지고 그들은 손목 중심을 기준으로 정렬된다. 그래서 제안된 알고리즘은 손의 크기와 방향에 대해 영향을 받지 않으며 손가락을 잘 검출한다. 다소 제한된 인식 실험 조건에서 손가락 개수 인식 실험은 1~3 개의 손가락은 100% 인식율과 4~5 개 손가락은 98% 인식율을 보여주었고, 또한 실패한 경우도 추가 가능한 단순한 조건에 의해 인식이 가능할 수 있음을 보여주었다.

• 한국지구과학회지
• /
• 제29권6호
• /
• pp.487-494
• /
• 2008

본 연구의 목적은 7학년 "해수의 성분과 운동" 단원에서 MBL 실험 수업이 학생들의 과학탐구능력과 그래프 작성 및 해석능력에 미치는 효과를 알아본 연구로 그 결과는 다음과 같다. 첫째, 6차시에 걸쳐 MBL 수업을 실시하고 사후 t-검정을 통해 학생들의 과학탐구능력에 미치는 영향에 대해 분석하였다. 그 결과 실험집단과 통제집단 간 과학탐구 능력 결과에서 유의미한 차이가 나타나 MBL 수업이 학생들의 과학탐구능력 향상에 더 효과적임을 알 수 있었다. 둘째, 사후 t-검정을 통해 학생들의 그래프 작성 및 해석능력에 미치는 영향에 대해 분석하였다. 그 결과 실험집단과 통제집단 간에 그래프 작성능력에서는 유의미한 차이를 보이지 않았으나, 그래프 해석능력에서는 두 집단 간 유의미한 차이를 나타내고 있어 MBL을 활용한 수업이 학생들의 그래프 해석능력의 향상에 더 효과적임을 알 수 있었다.