Ultrametricity of Dissimilarity Spaces and Its Significance for Data Mining
نویسندگان
چکیده
We introduce a measure of ultrametricity for dissimilarity spaces and examine transformations of dissimilarities that impact this measure. Then, we study the influence of ultrametricity on the behavior of two classes of data mining algorithms (kNN classification and PAM clustering) applied on dissimilarity spaces. We show that there is an inverse variation between ultrametricity and performance of classifiers. For clustering, increased ultrametricity generate clusterings with better separation. Lowering ultrametricity produce more compact clusters.
منابع مشابه
Composite Kernel Optimization in Semi-Supervised Metric
Machine-learning solutions to classification, clustering and matching problems critically depend on the adopted metric, which in the past was selected heuristically. In the last decade, it has been demonstrated that an appropriate metric can be learnt from data, resulting in superior performance as compared with traditional metrics. This has recently stimulated a considerable interest in the to...
متن کاملOn Mining Fuzzy Classification Rules for Imbalanced Data
Fuzzy rule-based classification system (FRBCS) is a popular machine learning technique for classification purposes. One of the major issues when applying it on imbalanced data sets is its biased to the majority class, such that, it performs poorly in respect to the minority class. However many cases the minority classes are more important than the majority ones. In this paper, we have extended ...
متن کاملOn Mining Fuzzy Classification Rules for Imbalanced Data
Fuzzy rule-based classification system (FRBCS) is a popular machine learning technique for classification purposes. One of the major issues when applying it on imbalanced data sets is its biased to the majority class, such that, it performs poorly in respect to the minority class. However many cases the minority classes are more important than the majority ones. In this paper, we have extended ...
متن کاملA Geometric View of Similarity Measures in Data Mining
The main objective of data mining is to acquire information from a set of data for prospect applications using a measure. The concerning issue is that one often has to deal with large scale data. Several dimensionality reduction techniques like various feature extraction methods have been developed to resolve the issue. However, the geometric view of the applied measure, as an additional consid...
متن کاملClustering Symbolic Time-Series using L-tuples
Among the many dimensionality reduction methods for timeseries data, Symbolic Aggregate approXimation (SAX) is perhaps the most popular due to its simplicity and uniqueness. With SAX, time-series data can be represented as string sequences which enables the utilization of methods found in text mining and bioinformatics to enhance data mining tasks. We propose an application of L-tuples to impro...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2015