• Journal of Korean Institute of Industrial Engineers
• /
• v.31 no.1
• /
• pp.20-26
• /
• 2005

This paper proposes the heuristic algorithm for the generalized GT problems to consider the restrictions which are given the number of machine cell and maximum number of machines in machine cell as well as minimum number of machines in machine cell. This approach is split into two phase. In the first phase, we use the similarity coefficient which proposes and calculates the similarity values about each pair of all machines and sort these values descending order. If we have a machine pair which has the largest similarity coefficient and adheres strictly to the constraint about birds of a different feather (BODF) in a machine cell, then we assign the machine to the machine cell. In the second phase, we assign parts into machine cell with the smallest number of exceptional elements. The results give a machine-part grouping. The proposed algorithm is compared to the Modified p-median model for machine-part grouping.

• Journal of the Korea Society of Computer and Information
• /
• v.20 no.11
• /
• pp.25-30
• /
• 2015

The enormous increase of data with the development of the information technology make internet users to be hard to find suitable information tailored to their needs. In the face of changing environment, the information filtering method, which provide sorted-out information to users, is becoming important. The data on the internet exists as various type. However, similarity calculation algorithm frequently used in existing collaborative filtering method is tend to be suitable to the numeric data. In addition, in the case of the categorical data, it shows the extreme similarity like Boolean Algebra. In this paper, We get the similarity in SNS user's information which consist of the mixed data using the Gower's similarity coefficient. And we suggest a method that is softer than radical expression such as 0 or 1 in categorical data. The clustering method using this algorithm can be utilized in SNS or various recommendation system.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.1565-1568
• /
• 1997

In this paper, a fuzzy based machine-cell formation algorithm for cellular manufacturing is presented. The fuzzy lovic is employed to express the degree of appropriateness when alternative machnies are specified to process a part shape. For machine grouping, the similarity coefficient based approach is used. The algorithm produces efficient machine cells and part families which maximize the similarity values.

• The Korean Journal of Zoology
• /
• v.24 no.2
• /
• pp.91-98
• /
• 1981

It has been confirmed that two dendrograms resulted from two similarity matrices, average taxonomic distance and correlation coefficient matrices, are different with each other when cluster analyses were performed with 571 adults of deer mice, Peromyscus maniculatus using 30 morphometric characters. To choose one of two similarity matrices mentioned above in order to construct a dendrogram representing phenetic relationships among taxa, an objective method using the result from principal component analysis as a standard result to compare with two matrices has been suggested.

• Industrial Engineering and Management Systems
• /
• v.1 no.1
• /
• pp.19-28
• /
• 2002

An operation sequence of parts is one of the most important production factors in the design of cellular manufacturing systems. Many similarity coefficient method (SCM) based approaches have been proposed to solve cell formation problems in the literature. However, most of them do not consider the operation sequence factor. This study presents an operation sequence ratio (OSR) and modifies some existing similarity coefficients using the OSR to solver cell formation problems considering operation sequences. The computational results show that the OSR ratio is useful and robust in solving cell formation problems with operation sequences.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.26 no.5
• /
• pp.609-615
• /
• 2016

Measuring similarity between two signals is a key element of the location template matching (LTM) method which is one of impact source localization technique. As a measure of similarity, the correlation coefficient is most widely used, and the group delay based method is recently proposed to improve the accuracy of finding the impact source. In practice, the LTM method assumes that the similarity between two signals decreases as the distance between two corresponding impact points increases, where the distance between two neighboring impact points defines the grid spacing. In this paper, it is shown that this assumption is not always true but the correlation coefficients fluctuate forming a main robe and many side robes as the distance between two neighboring impact points increases. On the other hand, the standard deviation of group delay sharply increases with a small increase of the grid spacing. These are demonstrated by using a simple cantilever beam. Based on these findings, an optimal way of implementing the LTM method may be suggested by combining the correlation coefficient and the group delay based approaches.

• Korean journal of applied entomology
• /
• v.37 no.1
• /
• pp.31-37
• /
• 1998

Random amplified polymorphic DNA (RAPD) markers were used to analyze genetic similarity among 8 clones of apierous green peach aphid, two types (M. persicae Sulzer and M. nicotianae lack man) classified by their mo~hologi~cahla raters and host preference (Blackman, 1987), collected from tobacco plants. The genetic variation among these clones was evaluated by polymerase chain reaction amplification with 20 random primers. The higher GC contents of primers, the better in amplification efficiency of PCR reaction in general. The genetic similarities among eight aphid clones were analyzed from UPGMA (unweighted pair group average method) cluster analysis based on simple matching coefficient. The range of genetic similarity coefficients was 0.414 to 0.808. The most close relationship among the clones was similarity coefficient of 0.808 between the PG2 and the PG3 clone. The eight aphid clones analyzed were clustered into three groups by the genetic similarity coefficient. The first group, PG1, PG2, PG3 clone including in M. persicae type by their morphological characters and RED clone in M. nicotianae type was clustered at the genetic similarity coefficient of 0.643. The second group, GR1, GR2, BRN in M. nicotianae type was at the 0.636;and the third group was DBR clone in M. persicae type. The results did not indicate any correlation between m&-phological types (M. persicae and M. nicotianae) and RAPD polymorphism. We could not detect any obvious genetic relationships of the two morphological types of the green peach aphid collected from tobacco plants.

• Journal of Forest and Environmental Science
• /
• v.18 no.1
• /
• pp.73-86
• /
• 2001

Taking account of the structural variation on species composition according to the different topographic positions and aspects, the forest community attributes such as species composition, species diversity index, and similarity coefficient were comparatively analyzed for the three topographic positions and the four aspects in the natural deciduous forest of Mt. Gari area. The results are as follows 1. The most dominant species in the overstory were Quercus mongolica in the mid-slope, the ridge, and all aspects areas, however, the stands of the topographic positions were less similar than the stands of the aspects in species composition, because of the appearance of the specific domonant species such as Juglans mandshurica in the valley area and Pinus densiflora in the ridge area. 2. Among the three topographic positions, the mid-slope area had greatest species diversity index in overstory, but the index of the valley had greater value than those of mid-slope and ridge in mid-story and understory. The north-east area among the aspects had greatest the index in all canopy layers. However, The stands of the aspects showed more smaller variation than the stands of the topographic positions. 3. The ridge area showed greatest similarity coefficient value with the mid-slope area, but showed least similarity coefficient value with the valley. However, similarity coefficient among the topographic positions had much smaller value than similarity coefficient among the aspects.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.3
• /
• pp.143-149
• /
• 2022

This excerpt delineates a quantitative measure of relationship between a research title and its respective abstract extracted from different journal articles documented through a Korean Citation Index (KCI) database published through various journals. In this paper, we propose a machine learning-based similarity metric that does not assume normality on dataset, realizes the imbalanced dataset problem, and zero-variance problem that affects most of the rule-based algorithms. The advantage of using this algorithm is that, it eliminates the limitations experienced by Pearson correlation coefficient (r) and additionally, it solves imbalanced dataset problem. A total of 107 journal articles collected from the database were used to develop a corpus with authors, year of publication, title, and an abstract per each. Based on the experimental results, the proposed algorithm achieved high correlation coefficient values compared to others which are cosine similarity, euclidean, and pearson correlation coefficients by scoring a maximum correlation of 1, whereas others had obtained non-a-number value to some experiments. With these results, we found that an effective title must have high correlation coefficient with the respective abstract.

• Journal of electromagnetic engineering and science
• /
• v.6 no.3
• /
• pp.155-159
• /
• 2006

An efficient method is presented to design filters without the similarity transform of their coupling coefficient matrix as circuit parameters, which is very tedious due to pivoting and deciding rotation angles needed during the iterations. The transfer function of a filter is directly used for the design and its desired form is derived by the optimized rational-function fitting technique. A 3rd order coaxial lowpass filter is taken as an example to validate the proposed method.