• Journal of the Korean Physical Society
• /
• 제73권10호
• /
• pp.1589-1595
• /
• 2018

Similarity index measures the topological proximity of node pairs in a complex network. Numerous similarity indices have been defined and investigated, but the dependency of structure on the performance of similarity indices has not been sufficiently investigated. In this study, we investigated the relationship between the performance of similarity indices and structural properties of a network by employing a two-state random network. A node in a two-state network has binary types that are initially given, and a connection probability is determined from the state of the node pair. The performances of similarity indices are affected by the number of links and the ratio of intra-connections to inter-connections. Similarity indices have different characteristics depending on their type. Local indices perform well in small-size networks and do not depend on whether the structure is intra-dominant or inter-dominant. In contrast, global indices perform better in large-size networks, and some such indices do not perform well in an inter-dominant structure. We also found that link prediction performance and the performance of similarity are correlated in both model networks and empirical networks. This relationship implies that link prediction performance can be used as an approximation for the performance of the similarity index when information about node type is unavailable. This relationship may help to find the appropriate index for given networks.

• 인지과학
• /
• 제17권1호
• /
• pp.53-74
• /
• 2006

유사성은 인지구조와 그 처리과정을 설명하는 중요한 개념으로 알려져 있으며 유사성 비교과정을 설명하기 위해 제안된 대표적인 초기모형으로는 다차원 척도모형(Shepard, 1964; Nosofsky, 1991)과 대비모형(Tversky, 1977)이 있다. 그러나 초기 모형에 의해 설명되기 어려운 경험적 연구결과들이 발표되면서 유사성의 개념적 타당성에 대한 의문이 제기되었다. Goldstone(1994)은 유사성이 속성차원간의 정렬과정에서 정의된다고 가정하고, 구조적 정렬 개념을 유사성을 둘러싼 개념적 논쟁들을 해결할 수 있는 유망한 대안으로 제안하였다. 본 연구에서는 우선 초기 유사성모형들의 기본 가정과 알고리즘을 개관한 후 속성차원에 대한 선택적 주의의 임의성이나 속성차원들 사이에 존재하는 상관적 구조와 같이 초기 유사성 모형들에 의해 설명되기 어려운 개념적 문제들을 살펴보았다. 그리고 SIAM(Goldston,, 1994)의 개념적 특징과 알고리즘을 알아본 후 구조적 정렬 개념이 범주화, 명사결합, 유추 추리 등의 인지심리학 분야들에 어떻게 적용되었는지를 개관하였다. 끝으로 자료 주도적 처리와 대안적 처리과정의 가능성과 관련된 SIAM의 한계점을 검토하고 가능한 발전방향에 대해 논의하였다.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제37권4호
• /
• pp.297-304
• /
• 2010

통계기계번역에서 번역성능의 향상을 위해서 문장의 유형이나 장르에 따라 클러스터링을 수행하여 도메인에 특화된 번역을 시도하는 방법이 있다. 그러나 기존의 연구 중 문장의 유형 정보와 장르에 따른 정보를 동시에 사용한 경우는 없었다. 본 논문에서는 각 문장의 문법적 구조 유사도에 따른 유형별분류 기법과, 단어 유사도 정보를 사용한 장르 구분법을 적용하여 기존의 두 기법을 통합하였다. 이렇게 분류된 말뭉치에서 추출한 도메인 특화 모델과 전체 말뭉치에서 추출된 모델에서 보간법(interpolation)을 사용하여 통계기계번역의 성능을 향상하였다. 문장구조 유사도와 단어 유사도의 계산 방법으로는 각각 커널과 코사인 유사도를 적용하였으며, 두 유사도를 적용하여 말뭉치를 분류하는 과정에서는 K-Means 알고리즘과 유사한 기계학습 기법을 사용하였다. 이를 일본어-영어의 특허문서에서 실험한 결과 최선의 경우 약 2.5%의 상대적인 성능 향상을 얻었다.

• 방송공학회논문지
• /
• 제14권1호
• /
• pp.36-43
• /
• 2009

최근 에러의 가시도를 측정하던 기존 패러다임의 한계를 극복하고자 structural similarity (SSIM) metric이 제안되어 우수한 성능을 보이고 있다. 하지만 SSIM은 기존에 활발히 연구되어오던 인간시각체계의 민감도에 대한 특성을 완전히 배제함으로써 새로운 한계점을 노출한다. 본 논문에서는 포비에이션 포인트로부터의 거리, 평균 휘도 값, DCT 계수, 모션 정보를 이용하여 통합된 시각적 가중치를 정의하였고 이를 SSIM과 자연스럽게 결합함으로써 성능을 개선하였다. VQEG 멀티미디어 그룹의 테스트 플랜을 이용한 테스트를 통해 본 논문의 품질측정 기준이 기존의 SSIM 보다 주관적 화질평가의 결과와 연관도가 더 높음을 보임으로써 성능 향상을 증명하였다.

• Journal of Information Processing Systems
• /
• 제17권2호
• /
• pp.213-226
• /
• 2021

Given that most of the link prediction algorithms for signed social networks can only complete sign prediction, a novel algorithm is proposed aiming to achieve both link prediction and sign prediction in signed networks. Based on the structural balance theory, the local link tightness and global link tightness are defined respectively by using the structural information of paths with the step size of 2 and 3 between the two nodes. Then the total similarity of the node pair can be obtained by combining them. Its absolute value measures the possibility of the two nodes to establish a link, and its sign is the sign prediction result of the predicted link. The effectiveness and correctness of the proposed algorithm are verified on six typical datasets. Comparison and analysis are also carried out with the classical prediction algorithms in signed networks such as CN-Predict, ICN-Predict, and PSNBS (prediction in signed networks based on balance and similarity) using the evaluation indexes like area under the curve (AUC), Precision, improved AUC', improved Accuracy', and so on. Results show that the proposed algorithm achieves good performance in both link prediction and sign prediction, and its accuracy is higher than other algorithms. Moreover, it can achieve a good balance between prediction accuracy and computational complexity.

• Nuclear Engineering and Technology
• /
• 제55권12호
• /
• pp.4591-4596
• /
• 2023

Single-photon emission computed tomography SPECT image reconstruction methods have a significant influence on image quality, with filtered back projection (FBP) and ordered subset expectation maximization (OSEM) being the most commonly used methods. In this study, we proposed newly-designed adaptive non-blind deconvolution with a structural similarity (SSIM) index that can take advantage of the FBP and OSEM image reconstruction methods. After acquiring brain SPECT images, the proposed image was obtained using an algorithm that applied the SSIM metric, defined by predicting the distribution and amount of blurring. As a result of the contrast to noise ratio (CNR) and coefficient of variation evaluation (COV), the resulting image of the proposed algorithm showed a similar trend in spatial resolution to that of FBP, while obtaining values similar to those of OSEM. In addition, we confirmed that the CNR and COV values of the proposed algorithm improved by approximately 1.69 and 1.59 times, respectively, compared with those of the algorithm involving an inappropriate deblurring process. To summarize, we proposed a new type of algorithm that combines the advantages of SPECT image reconstruction techniques and is expected to be applicable in various fields.

• 대한수학교육학회지:수학교육학연구
• /
• 제17권1호
• /
• pp.67-90
• /
• 2007

본 연구의 목적은 문제해결의 결과로 나타나는 성공과 실패에 대한 학생들의 사고 과정을 유사성의 관점에서 이해하고자 하는 것이다. 따라서 사례연구 방법을 사용하여 정답을 제시한 학생들의 사고과정이 반드시 바람직하지 않을 수 있다는 의사(擬似) 분석적 사고와 분석적 사고에 대한 Vinner(1997a, 1997b)의 연구내용을 근거로 학생들의 사고과정을 분석하고자 하였다. 본 사례 연구 분석 결과, 학교 성적이 중상위권인 2명의 연구대상자들은 각각 의사(擬似) 분석적 사고와 분석적 사고를 함으로써 대수 문장제 해결에서 성공하거나 실패하였다. 학생들의 의사(擬似) 분석적 사고와 분석적 사고의 특징은 구조적 유사성의 구성에서 각 연구 대상자들이 인식한 해법 공식이 변형이 가능한 것인가의 여부와 해법을 적용하는 과정에서 학생 자신의 사고를 통제하거나 조절할 수 있는가의 여부에 따라 구분된다는 것이었다. 따라서 본 연구에서는 학생들이 해법으로 인식하는 공식의 형태가 어떠한 것이며, 그러한 해법을 어떻게 적용하는가를 유사성의 관점에서 문제 해결의 성공 여부와 관련하여 분석할 수 있었다.

• Asia pacific journal of information systems
• /
• 제9권2호
• /
• pp.19-37
• /
• 1999

Computer aided process planning(CAPP) is a key for implementing CIM. It is bridge between CAD and CAM and translates the design information into manufacturing instructions. Generally, manufacturing is an area where intelligent systems will not be able to rely on methods requiring formalized knowledge. Manufacturing lacks a body of knowledge that is specific, formalized, and rigorous, and which can be coded as rules or procedures. Thus expertise in manufacturing is developed over a period of many years. Case-based reasoning(CBR) offers a new approach for developing intelligent system. In the case-based approach the problem solving experience of the experts is encoded in the form of cases. CBR's retrieval process can be divided to two step. The first step is matching step, and the second step is selection step. For selecting base case, new preference heuristics were introduced using similarity concept. Similarity concept has three has three dimensions, i.e. entity similarity, structural similarity, and goal similarity. In this paper, bolt's process planning was selected an application domain. Following the test result, the new preference heuristics were approved as a useful procedure in CAPP.

• Computers and Concrete
• /
• 제22권1호
• /
• pp.101-116
• /
• 2018

As one of the most important engineering structures, arch dams are huge constructions built with human hands and have strategical importance. Because of the fact that long construction duration, water supply, financial reasons, major loss of life and material since failure etc., the design of arch dams is very important problem and should be done by expert engineers to determine the structural behavior more accurately. Finite element analyses and non-destructive experimental measurements can be used to investigate the structural response, but there are some difficulties such as spending a long time while modelling, analysis and in-situ testing. Therefore, it is more useful to conduct the research on the laboratory conditions and to transform the obtained results into real constructions. Within the scope of this study, it is aimed to determine the structural behavior of arch dams considering experimentally validated prototype laboratory model using similitude and scaling laws. Type-1 arch dam, which is one of five arch dam types suggested at the "Arch Dams" Symposium in England in 1968 is selected as reference prototype model. The dam is built considering dam-reservoir-foundation interaction and ambient vibration tests are performed to validate the finite element results such as dynamic characteristics, displacements, principal stresses and strains. These results are considered as reference parameters and used to determine the real arch dam response with different scales factors such as 335, 400, 416.67 and 450. These values are selected by considering previously examined dam projects. Arch heights are calculated as 201 m, 240 m, 250 m and 270 m, respectively. The structural response is investigated between the model and prototype by using similarity requirements, field equations, scaling laws etc. To validate these results, finite element models are enlarged in the same scales and analyses are repeated to obtain the dynamic characteristics, displacements, principal stresses and strains. At the end of the study, it is seen that there is a good agreement between all results obtained by similarity requirements with scaling laws and enlarged finite element models.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권11호
• /
• pp.2824-2838
• /
• 2013

There has been a lot of attention paid recently to analyze dynamic human gestures that vary over time. Most attention to dynamic gestures concerns with spatio-temporal features, as compared to analyzing each frame of gestures separately. For accurate dynamic gesture recognition, motion feature extraction algorithms need to find representative features that uniquely identify time-varying gestures. This paper proposes a new feature-extraction algorithm using temporal self-similarity based on a hierarchical human model. Because a conventional temporal self-similarity method computes a whole movement among the continuous frames, the conventional temporal self-similarity method cannot recognize different gestures with the same amount of movement. The proposed model-based temporal self-similarity method groups body parts of a hierarchical model into several sets and calculates movements for each set. While recognition results can depend on how the sets are made, the best way to find optimal sets is to separate frequently used body parts from less-used body parts. Then, we apply a multiclass support vector machine whose optimization algorithm is based on structural support vector machines. In this paper, the effectiveness of the proposed feature extraction algorithm is demonstrated in an application for taebo gesture recognition. We show that the model-based temporal self-similarity method can overcome the shortcomings of the conventional temporal self-similarity method and the recognition results of the model-based method are superior to that of the conventional method.