Local cover image
Local cover image
Local cover image
Local cover image

Dissimilarity coefficients in hierarchical clustering for mixed and fuzzy feature variable / Gay A. Farofaldino

By: Material type: TextTextLanguage: English Description: 90 leavesSubject(s): Abstract: Yang's coefficient for mixed and fuzzy feature variable was modified in terms of the aggregation technique and the entropy-based distance function. There are four proposed dissimilarity coefficients which used Yang's coefficient for numerical attributes and fuzzy attributes while entropy such as Havrda-Charvat's structural a-entropy and Jensen-Shannon divergence for categorical attributes. The hierarchical clustering method was used for clustering mixed and fuzzy data. Single linkage clustering algorithm and UPGMA were employed to generate fuzzy dendrograms. The type of data has a significant effect on the clustering produced accompanied by the aggregation function used and the entropy measure employed. The dataset used in the study were small and large dataset. For small data, the proposed dissimilarity coefficients that used De Carvalho's extension of Ichino and Yaguchi's dissimilarity measure as aggregation produced better clustering solution in small data. On the other hand, for large data, the proposed dissimilarity coefficients that used the two aggregation function such as De Carvalho's dissimilarity measure and De Carvalho's extension of Ichino and Yamguchi's dissimilarity measure worked well in clustering. The proposed dissimilarity coefficients were compared to the original Yang's coefficient measures for mixed feature variable and fuzzy data to evaluate the effectiveness and efficiency of the propose dissimilarity coefficients. The proposed dissimilarity coefficients performed better with mixed and fuzzy feature variable compared to the original Yang's dissimilarity measures mixed and fuzzy data.
Tags from this library: No tags from this library for this title. Log in to add tags.
Star ratings
    Average rating: 0.0 (0 votes)
Holdings
Cover image Item type Current library Collection Call number Status Date due Barcode
Thesis Thesis University Library Theses Room-Use Only LG 993.5 2011 A64 F37 (Browse shelf(Opens below)) Not For Loan 3UPML00012779
Thesis Thesis University Library Archives and Records Preservation Copy LG 993.5 2011 A64 F37 (Browse shelf(Opens below)) Not For Loan 3UPML00033555

Thesis, Undergraduate (B.S. Applied Mathematics)-U.P. Mindanao.

Yang's coefficient for mixed and fuzzy feature variable was modified in terms of the aggregation technique and the entropy-based distance function. There are four proposed dissimilarity coefficients which used Yang's coefficient for numerical attributes and fuzzy attributes while entropy such as Havrda-Charvat's structural a-entropy and Jensen-Shannon divergence for categorical attributes. The hierarchical clustering method was used for clustering mixed and fuzzy data. Single linkage clustering algorithm and UPGMA were employed to generate fuzzy dendrograms. The type of data has a significant effect on the clustering produced accompanied by the aggregation function used and the entropy measure employed. The dataset used in the study were small and large dataset. For small data, the proposed dissimilarity coefficients that used De Carvalho's extension of Ichino and Yaguchi's dissimilarity measure as aggregation produced better clustering solution in small data. On the other hand, for large data, the proposed dissimilarity coefficients that used the two aggregation function such as De Carvalho's dissimilarity measure and De Carvalho's extension of Ichino and Yamguchi's dissimilarity measure worked well in clustering. The proposed dissimilarity coefficients were compared to the original Yang's coefficient measures for mixed feature variable and fuzzy data to evaluate the effectiveness and efficiency of the propose dissimilarity coefficients. The proposed dissimilarity coefficients performed better with mixed and fuzzy feature variable compared to the original Yang's dissimilarity measures mixed and fuzzy data.

There are no comments on this title.

to post a comment.

Click on an image to view it in the image viewer

Local cover image Local cover image
 
University of the Philippines Mindanao
The University Library, UP Mindanao, Mintal, Tugbok District, Davao City, Philippines
Email: library.upmindanao@up.edu.ph
Contact: (082)295-7025
Copyright @ 2022 | All Rights Reserved