Clustering Large Datasets and Visualizations of Large Hierarchies and Pyramids Symbolic Data Analysis Approach
نویسندگان
چکیده
In the paper we present an approach to clustering large datasets of mixed units described by symbolic objects in form of histograms of values of variables. For visualization of (large) hierarchies and pyramids we present two solutions: hyperbolic display and flags. The hyperbolic display is an example of fish-eye displays that allow a closer look at the data in the selected neighborhood put into the context of the global view. It allows simultaneous view of complete pyramidal or hierarchical clustering and detailed inspection of selected region inside pyramid or hierarchy. It also represents a ’map’ structure over clusters. Selected nodes (clusters) can be represented and compared using other representations. Flags are a visual display in form of a graphical table (rows represent units/clusters, columns represent variables). Each cell is colored with a color assigned to the cell value. The third dimension can be used to display the frequencies of values. The power of the flags is in the interactive system for their manipulation. The hierarchical flags can be used also to perform ’visual’ – semi-manual clustering.
منابع مشابه
A Hybrid Time Series Clustering Method Based on Fuzzy C-Means Algorithm: An Agreement Based Clustering Approach
In recent years, the advancement of information gathering technologies such as GPS and GSM networks have led to huge complex datasets such as time series and trajectories. As a result it is essential to use appropriate methods to analyze the produced large raw datasets. Extracting useful information from large data sets has always been one of the most important challenges in different sciences,...
متن کاملApplication of modified balanced iterative reducing and clustering using hierarchies algorithm in parceling of brain performance using fMRI data
Introduction: Clustering of human brain is a very useful tool for diagnosis, treatment, and tracking of brain tumors. There are several methods in this category in order to do this. In this study, modified balanced iterative reducing and clustering using hierarchies (m-BIRCH) was introduced for brain activation clustering. This algorithm has an appropriate speed and good scalability in dealing ...
متن کاملEvaluation of Updating Methods in Building Blocks Dataset
With the increasing use of spatial data in daily life, the production of this data from diverse information sources with different precision and scales has grown widely. Generating new data requires a great deal of time and money. Therefore, one solution is to reduce costs is to update the old data at different scales using new data (produced on a similar scale). One approach to updating data i...
متن کاملA Clustering Approach by SSPCO Optimization Algorithm Based on Chaotic Initial Population
Assigning a set of objects to groups such that objects in one group or cluster are more similar to each other than the other clusters’ objects is the main task of clustering analysis. SSPCO optimization algorithm is anew optimization algorithm that is inspired by the behavior of a type of bird called see-see partridge. One of the things that smart algorithms are applied to solve is the problem ...
متن کاملClustering Large Datasets of Mixed Units
In the paper we propose an approach for clustering large datasets of mixed units based on representation of clusters by distributions of values of variables over a cluster – histograms, that are compatible with merging of clusters. The proposed representation can be used also for clustering symbolic data. On the basis of this representation the adapted versions of leaders method and adding meth...
متن کامل