A Novel Similarity Measure for Generalized Trapezoidal Fuzzy Numbers and its Application to Decision-Making

Yixiang Zhou 보안공학연구지원센터 2016 International Journal of u- and e- Service, Scienc Vol.9 No.3

Similarity measures of fuzzy numbers have been widely applied in various areas. In the last decade, many similarity measures of generalized fuzzy numbers were proposed. However, there are two main limitations in existing similarity measures: 1) they cannot correctly calculate the degree of similarity between two generalized trapezoidal fuzzy numbers in some cases; and 2) the definitions of recently developed similarity measures are complicated and difficult to interpret. In this paper, a novel approach to similarity measurement between generalized trapezoidal fuzzy numbers is proposed. The proposed similarity measure has a simple definition and is easier to understand intuitively. Furthermore, we analyze its properties and compare it with existing similarity measures. The results show that the proposed measure outperforms existing similarity measures. Finally, we apply the proposed similarity measure to develop a fuzzy-logic-based approach for new product go/nogo decision-making at the front end. The proposed fuzzy software quality evaluation method is more flexible and more intelligent than existing methods due to the fact that it considers the degrees of confidence of evaluators’ opinions.

Fuzzy Entropy Construction based on Similarity Measure

Wook-Je Park,Park Hyun Jeong,Sang H. Lee 한국지능시스템학회 2007 한국지능시스템학회 학술발표 논문집 Vol.17 No.2

In this paper we derived fuzzy entropy that is based on similarity measure. Similarity measure represents the degree of similarity between two informations, those informations characteristics are not important. First we construct similarity measure between two informations, and derived entropy functions with obtained similarity measure. Obtained entropy is verified with proof. With the help of one-to-one similarity is also obtained through distance measure, this similarity measure is also proved in our paper.

Analysis between Similarity and Dissimilarity Measure for Fuzzy Sets

이상혁(Sang-Hyuk Lee),김상진(Sangjin Kim),김채형(Jaehyung Kim) 한국지능시스템학회 2008 한국지능시스템학회 학술발표 논문집 Vol.18 No.2

In this paper, we have surveyed the relation between similarity measure and dissimilarity measure for fuzzy sets. First, we study the entropy for fuzzy set and similarity for corresponding crisp set. By the obtaining result, we pointed out that the similarity between fuzzy set and corresponding complementary fuzzy set satisfy fuzzy entropy. We also found out that the summation of similarity and dissimilarity measure between fuzzy set and complementary fuzzy set constitute total information of fuzzy set itself. With the obtained result we have extended the results to two data group fuzz sets. In the process of designing similarity measure and dissimilarity, we also proved the usefulness of proposed measures. We can also verified and discussed the one-to-one correspondence characteristics between similarity measure and dissimilarity measure(entropy).

Fuzzy Entropy Construction based on Similarity Measure

Park Hyun Jeong(박현정),Insuk Yang(양인석),Soorok Ryu(류수록),Sang H. Lee(이상혁) 한국지능시스템학회 2008 한국지능시스템학회논문지 Vol.18 No.2

In this paper we derived fuzzy entropy that is based on similarity measure. Similarity measure represents the degree of similarity between two informations, those informations characteristics are not important. First we construct similarity measure between two informations, and derived entropy functions with obtained similarity measure. Obtained entropy is verified with proof. With the help of one-to-one similarity is also obtained through distance measure, this similarity measure is also proved in our paper.

Similarity Measure Construction with Fuzzy Entropy and Distance Measure

Sang-Hyuk Lee 한국지능시스템학회 2005 INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGE Vol.5 No.4

The similarity measure is derived using fuzzy entropy and distance measure. By the relations of fuzzy entropy, distance measure, and similarity measure, we first obtain the fuzzy entropy. And with both fuzzy entropy and distance measure, similarity measure is obtained. We verify that the proposed measure become the similarity measure.

C-Rank: A link-based similarity measure for scientific literature databases

Yoon, S.H.,Kim, S.W.,Park, S. Elsevier science 2016 Information sciences Vol.326 No.-

<P>As the number of people who use scientific literature databases has grown, the demand for literature retrieval services has steadily increased. One of the most popular retrieval service methods is to find a set of papers similar to the paper under consideration, which requires a measure that computes the similarities between the papers. Scientific literature databases exhibit two interesting characteristics that are not found in general databases. First, the papers cited by older papers are often not included in the database due to technical and economic reasons. Second, since a paper references previously published papers, few papers cite recently published papers. These two characteristics cause all existing similarity measures to fail in at least one of the following cases: (1) measuring the similarity between old, but similar papers, (2) measuring the similarity between recent, but similar papers, and (3) measuring the similarity between two similar papers: one old, the other recent. In this paper, we propose a new link-based similarity measure called C-Rank, which uses both in-link and out-link references, disregarding the direction of the references. In addition, we discuss the most suitable normalization method for scientific literature databases and we propose an evaluation method for measuring the accuracy of similarity measures. For the experiments, we used real-world papers from DBLP's database with reference information crawled from Libra. We then compared the performance of C-Rank with that of existing similarity measures. Experimental results showed that C-Rank achieved a higher accuracy than existing similarity measures. (C) 2015 Elsevier Inc. All rights reserved.</P>

신뢰성 있는 정보의 추출을 위한 퍼지집합의 유사측도 구성

이상혁,Lee Sang-Hyuk 한국통신학회 2005 韓國通信學會論文誌 Vol.30 No.9C

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. We construct the fuzzy entropy for measuring of uncertainty with the help of relation between distance measure and similarity measure. Proposed fuzzy entropy is constructed through distance measure. In this study, the distance measure is used Hamming distance measure. Also for the measure of similarity between fuzzy sets or crisp sets, we construct similarity measure through distance measure, and the proposed 려zzy entropies and similarity measures are proved.

Similarity Measure Construction with Fuzzy Entropy and Distance Measure

Lee Sang-Hyuk Korean Institute of Intelligent Systems 2005 INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGE Vol.5 No.4

The similarity measure is derived using fuzzy entropy and distance measure. By the elations of fuzzy entropy, distance measure, and similarity measure, we first obtain the fuzzy entropy. And with both fuzzy entropy and distance measure, similarity measure is obtained., We verify that the proposed measure become the similarity measure.

A similarity measure of fuzzy sets

Kwon, Soon H. 한국지능시스템학회 2001 한국지능시스템학회논문지 Vol.11 No.3

지금까지 제안된 유사도 척도는 첫째, 기하학적 유사도 척도, 둘째, 집합론적 유사도 척도, 그리고 마지막으로 일치 함수를 이용한 유사도 척도와 같이 세 종류로 분류될 수 있다. 본 논문에서는 이러한 기존의 유사도 척도가 갖는 여러 가지 성질에 근거하여 퍼지 집합에 관한 새로운 유사도 척도를 제안하고 이의 성질을 알아본다. 마지막으로, 예제를 통하여 제안된 유사도 척도와 기존의 유사도 척도의 특성을 비교한다. Conventional similarity measures suggested so far can be classified into three categories: (i) geometric similarity measures, (ij) set-theoretic similarity measures, and (iii) matching function-based similarity measures. On the basis of the characteristics of the conventional similarity measures, in this paper, we propose a new similarity measure of fuzzy sets and investigate its properLies. Finally, numelical examples are provided for the comparison of characteristics of the proposed similarity measure and other previous similarity measures.

상품들의 계층적 분류체계를 고려한 구매 이력 간 효율적인 유사도 측정

양유정,이기용 한국정보과학회 2020 정보과학회논문지 Vol.47 No.10

온라인 쇼핑몰 또는 오프라인 매장에서 각 고객이 구매한 상품들은 시간의 흐름에 따라 해당 고객의 구매 이력을 형성한다. 또한 대부분의 경우 상품들에는 그들의 세부 분류를 나타내는 계층적 분류체계가 존재한다. 본 논문에서는 상품들의 구매 순서뿐만 아니라 상품들에 존재하는 계층적 분류체계까지 고려하는 새로운 구매 이력 간 유사도 측정 방법을 제안한다. 제안 방법은 기존의 대표적인 시퀀스 간 유사도 측정 방법인 동적 타임 워핑(dynamic time warping) 유사도를 상품들의 계층적 분류체계를 반영하도록 확장하였다. 제안 방법은 두 시퀀스 내 원소들을 비교할 때 원소들의 일치 여부에 따라 원소들 간의 유사도를 0 또는 1로만 부여하던 기존 방법과 달리 계층적 분류체계를 반영하여 0에서 1 사이의 실수 값을 부여한다. 이와 함께 본 논문은 제안하는 유사도 측정 방법에 대한 효율적인 계산 기법을 제안한다. 제안하는 계산 기법은 세그먼트 트리(segment tree)를 사용하여 계층적 분류체계 내에서 두 상품 간의 유사도를 매우 빠르게 계산한다. 본 논문에서는 실데이터에 기반한 다양한 실험을 통해 제안 방법이 계층적 분류체계가 존재하는 상품들의 구매 이력 간 유사도를 매우 효과적이고 빠르게 측정할 수 있음을 보인다. In an online shopping mall or offline store, the products purchased by each customer over time form a purchase history of the customer. Also, in most cases, products have a hierarchical classification that represents their subcategories. In this paper, we propose a new similarity measure for purchase histories considering not only the purchase order of products but also the hierarchical classification of products. The proposed method extends the dynamic time warping similarity that is an existing representative similarity measure for sequences, to reflect the hierarchical classification of products. Unlike the existing method, where the similarity between the elements in two sequences is only 0 or 1 depending on whether the two elements are the same or not, the proposed method can assign any real number between 0 and 1 as the similarity between the two elements considering the hierarchical classification of elements. We also propose an efficient method for computing the proposed similarity measure. The proposed computation method uses the segment tree to evaluate the similarity between the two products in a hierarchical classification tree in an efficient manner. Through various experiments based on the real data, we show that the proposed method can measure the similarity between purchase histories of products with hierarchical classification in an exceedingly effective and efficient manner.