• 한국컴퓨터정보학회논문지
• /
• 제26권11호
• /
• pp.149-156
• /
• 2021

추천 시스템의 여러 구현 기법들 중 협력 필터링은 과거 평가 이력을 토대로 유사성이 높은 인접 이웃들을 선정하여, 그들이 선호했던 상품들을 추천하는데, 많은 상업 사이트에서 성공적으로 활용되고 있다. 유사도의 정확한 측정은 시스템의 성능을 좌우하는 매우 중요한 요소이다. 기존에 다양한 방식의 유사도 척도들이 개발되었는데, 대개 전통적인 유사도 척도와 기개발된 여러 계수들과의 통합 방식이었다. 본 연구에서는 새로운 방식의 유사도 척도를 제안한다. 두 사용자 간의 공통 평가 영역을 평가치 크기에 따라 분할하여 각 부분 영역별로 유사도를 측정하고 이들을 가중 통합함으로써, 유사한 영역이 구체적으로 파악되어 최종 유사도값에 반영된다. 두 종류의 개방형 데이터셋을 활용한 성능을 측정하였고, 그 결과 특히 밀집 데이터셋에서 제안 방법의 예측 정확도, 순위 정확도, 평균 정밀도 성능이 기존보다 우수하였다. 제안 척도는 다양한 상업 시스템에서 사용자들의 선호에 보다 적합한 상품을 추천하는데 유용하게 활용될 것으로 기대한다.

• 한국멀티미디어학회논문지
• /
• 제14권10호
• /
• pp.1252-1261
• /
• 2011

본 논문은 내용기반 동영상 분할을 위한 장면의 유사도 패턴 비교 방법을 제안한다. 동영상 장면 전환의 종류는 크게 급진적 전환과 디졸브(dissolve), 페이드인(fade-in), 페이드아웃(fade-out), 와이프 전환(wipe transition)을 포함하는 점진적 전환 형태로 나눌 수 있다. 제안하는 방법은 모든 종류의 장면 전환 검출 문제를 단지 발생 유무의 문제로 간단 정의하고, 장면 전환 종류는 별도로 구분하지 않는다. 장면 전환을 검출하기 위해서는 프레임간의 유사도를 정의해야 한다. 본 논문에서는 장면 내 유사도(within similarity)와 장면 간 유사도(between similarity)를 정의하며 두 유사도의 통계적 패턴 비교를 통하여 최종적으로 장면 전환을 검출하게 된다. 장면 내 유사도와 장면 간 유사도의 비율을 구하는 방법을 통해 플래시라이트나영상 내 물체 움직임에 대한 거짓 양성 검출을 별도의 후처리 과정 없이도 방지할 수 있음을 확인하였다. 프레임의 특징 값으로는 컬러 히스토그램과 프레임 내 평균 화소값을 이용하였다. TREC-2001, TREC-2002 동영상 셋을 포함한 실험 셋에서 성능을 평가한 결과 제안하는 알고리즘의 경우 총 91.84%의 재현율(recall)과 86.43%의 정확도(precision)의 성능을 보임을 확인할 수 있었다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권10호
• /
• pp.4987-5005
• /
• 2017

This paper introduces a new method to solve Similarity Recognition for Cloth Products, which is based on Fuzzy logic and Particle swarm optimization algorithm. For convenience, it is called the SRCPFP method hereafter. In this paper, the SRCPFP method combines Fuzzy Logic (FL) and Particle Swarm Optimization (PSO) algorithm to solve similarity recognition for cloth products. First, it establishes three features, length, thickness, and temperature resistance, respectively, for each cloth product. Subsequently, these three features are engaged to construct a Fuzzy Inference System (FIS) which can find out the similarity between a query cloth and each sampling cloth in the cloth database D. At the same time, the FIS integrated with the PSO algorithm can effectively search for near optimal parameters of membership functions in eight fuzzy rules of the FIS for the above similarities. Finally, experimental results represent that the SRCPFP method can realize a satisfying recognition performance and outperform other well-known methods for similarity recognition under considerations here.

• 한국융합학회논문지
• /
• 제4권2호
• /
• pp.35-41
• /
• 2013

Data management with fuzzy entropy and similarity measure were discussed and verified by applying reliable data selection problem. Calculation of certainty or uncertainty for data, fuzzy entropy and similarity measure are designed and proved. Proposed fuzzy entropy and similarity are considered as dissimilarity measure and similarity measure, and the relation between two measures are explained through graphical illustration.Obtained measures are useful to the application of decision theory and mutual information analysis problem. Extension of data quantification results based on the proposed measures are applicable to the decision making and fuzzy game theory.

• 영어어문교육
• /
• 제9권spc호
• /
• pp.61-78
• /
• 2003

The purpose of this article is to examine the role of similarity in the metaphor and simile preference and offer empirical evidence against the equivalence view of simile and metaphor. This evidence was obtained from two experiments to examine the correlation between the similarity ratings and the preference ratings. The results suggest that Korean people choose the metaphor form when the similarity of a target and a source increases, whereas they choose the simile form when the similarity of a target and a source decreases. The results from these experiments are consistent with Chiappe and Kennedy's (1999, 2001) findings. Moreover, the experiments found that Korean people were more likely to express particular comparisons as similes over metaphors than American people.

• 한국소음진동공학회논문집
• /
• 제24권4호
• /
• pp.310-316
• /
• 2014

The location template matching(LTM) method is a technique of identifying an impact location on a structure, and requires a certain measure of similarity between two time signals. In general, the correlation coefficient is widely used as the measure of similarity, while the group delay based method is recently proposed to improve the accuracy of the impact localization. Another possible measure is the frequency response assurance criterion(FRAC), though this has not been applied yet. In this paper, these three different measures of similarity are examined comparatively by using experimental data in order to understand the properties of these measures of similarity. The comparative study shows that the correlation coefficient and the FRAC give almost the same information while the group delay based method gives the shape oriented information that is best suitable for the location template matching method.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2014년도 춘계학술대회 논문집
• /
• pp.506-511
• /
• 2014

The location template matching (LTM) method is a technique of identifying an impact location on a structure, and requires a certain measure of similarity between two time signals. In general, the correlation coefficient is widely used as the measure of similarity, while the group delay based method is recently proposed to improve the accuracy of the impact localization. Another possible measure is the frequency response assurance criterion (FRAC), though this has not been applied yet. In this paper, these three different measures of similarity are examined comparatively by using experimental data in order to understand the properties of these measures of similarity. The comparative study shows that the correlation coefficient and the FRAC give almost the same information while the group delay based method gives the shape oriented information that is best suitable for the location template matching method.

• 대한산업공학회지
• /
• 제41권1호
• /
• pp.10-16
• /
• 2015

In this study, we suggest a method to predict probability distribution of a new customer's degree of loyalty using C-CRF that reflects the RFM score and similarity to the neighbors of the customer. An RFM score prediction model is introduced to construct the first feature function of C-CRF. Integrating demographical similarity, purchasing characteristic similarity and purchase history similarity, we make a unified similarity variable to configure the second feature function of C-CRF. Then parameters of each feature function are estimated and we train our C-CRF model by training data set and suggest a probabilistic distribution to estimate a new customer's degree of loyalty. An example is provided to illustrate our model.

• 한국통신학회논문지
• /
• 제30권9C호
• /
• pp.854-859
• /
• 2005

모호함의 측도를 위하여 퍼지 엔트로피와 거리측도 그리고 유사측도와의 관계를 이용하여 새로운 퍼지 측도를 제안하였다. 제안된 퍼지 엔트로피는 거리측도를 이용하여 구성된다. 거리측도는 일반적으로 사용되는 해밍 거리를 이용하였다. 또한 집합사이의 유사성을 측정하기 위한 유사측도를 거리 측도를 이용하여 구성하였고, 제안한 퍼지 엔트로피와 유사측도를 증명을 통하여 타당성을 확인하였다.

• 치과방사선
• /
• 제5권1호
• /
• pp.11-21
• /
• 1975

The study was performed to investigate cephalomeric similarity between parents and offspring of the Korean family by lateral cephalometric analysis. The lateral cephalograms consist of the 8 families comprising 16 parents, 5 sons and 7 daughters. In order to make an investigation of the similarity, set up, and 22 linear measurements on each depth measurements were made. The author drew up the profilograms to compare parents with offspring in each family group. The obtained results were as follows: 12 measuring points were and height and 5 angular 1. There was no common similarity on specific region between parents and offspring on each family group. 2. There was partial similarity between single parent and offspring. 3. The partial similarity between single parent and offspring was noted on the upper face in general.