SimUSF: an efficient and effective similarity measure that is invariant to violations of the interval scale assumption

详细信息    查看全文

• 作者：Thilak L. Fernando ; Geoffrey I. Webb
• 关键词：Similarity measure ; Interval scale ; Clustering ; CBMIR
• 刊名：Data Mining and Knowledge Discovery
• 出版年：2017
• 出版时间：January 2017
• 年：2017
• 卷：31
• 期：1
• 页码：264-286
• 全文大小：
• 刊物类别：Computer Science
• 刊物主题：Data Mining and Knowledge Discovery; Artificial Intelligence (incl. Robotics); Information Storage and Retrieval; Statistics for Engineering, Physics, Computer Science, Chemistry and Earth Sciences;
• 出版者：Springer US
• ISSN：1573-756X
• 卷排序：31

文摘

Similarity measures are central to many machine learning algorithms. There are many different similarity measures, each catering for different applications and data requirements. Most similarity measures used with numerical data assume that the attributes are interval scale. In the interval scale, it is assumed that a unit difference has the same meaning irrespective of the magnitudes of the values separated. When this assumption is violated, accuracy may be reduced. Our experiments show that removing the interval scale assumption by transforming data to ranks can improve the accuracy of distance-based similarity measures on some tasks. However the rank transform has high time and storage overheads. In this paper, we introduce an efficient similarity measure which does not consider the magnitudes of inter-instance distances. We compare the new similarity measure with popular similarity measures in two applications: DBScan clustering and content based multimedia information retrieval with real world datasets and different transform functions. The results show that the proposed similarity measure provides good performance on a range of tasks and is invariant to violations of the interval scale assumption.