Results 1  10
of
10
An Introduction to Symbolic Data Analysis and the Sodas Software
 Journal of Symbolic Data Analysis
, 2003
"... ..."
Knowledge Discovery From Symbolic Data And The Sodas Software
 Conf. on Principles and Practice of Knowledge Discovery in Databases, PPKDD2000
, 2000
"... The data descriptions of the units are called "symbolic" when they are more complex than the standard ones due to the fact that they contain internal variation and are structured. Symbolic data happen from many sources, for instance in order to summarise huge Relational Data Bases by their under ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
The data descriptions of the units are called "symbolic" when they are more complex than the standard ones due to the fact that they contain internal variation and are structured. Symbolic data happen from many sources, for instance in order to summarise huge Relational Data Bases by their underlying concepts. "Extracting knowledge" means getting explanatory results, that why, "symbolic objects" are introduced and studied in this paper. They model concepts and constitute an explanatory output for data analysis. Moreover they can be used in order to define queries of a Relational Data Base and propagate concepts between Data Bases. We define "Symbolic Data Analysis" (SDA) as the extension of standard Data Analysis to symbolic data tables as input in order to find symbolic objects as output. In this paper we give an overview on recent development on SDA. We present some tools and methods of SDA and introduce the SODAS software prototype (issued from the work of 17 teams of nine countries involved in an European project of EUROSTAT). 1
About Ordering Features of Single Linkage Clustering Algorithm
"... A new version of single linkage ierarchical clustering algorithm is presented. It may be used to obtain the shortest trajectory connecting all objects. A notion of perfect chain is introduced which is usefull for describing properties of the algorithm. Keywords: Data analysis, Clustering, Multid ..."
Abstract
 Add to MetaCart
A new version of single linkage ierarchical clustering algorithm is presented. It may be used to obtain the shortest trajectory connecting all objects. A notion of perfect chain is introduced which is usefull for describing properties of the algorithm. Keywords: Data analysis, Clustering, Multidimensional scaling, Travelling salesman problem. 1 Introduction One of the oldest methods of cluster analysis is the singlelink method (also known as "the nearest neighbour " method). Many papers have been published which are concerned with various computational algorithms corresponding to this clustering method. [Rolf, 1982] and [Jambu 1978] summarize some of the more important algorithms for the singlelink cluster analysis. In the most of existing algorithms the order of the merging elements is arbitrary. The ordering methods have to result in such object permutation that satisfy the following criterion  the near objects in the sequence are more similar than the distant ones. The au...
Random Dendrograms
"... An attempt is made to create some statistical tests for comparing results of ierarchical cluster analysis based on the uniform distribution over the set of all possible dendrograms. Three different uniform distributions are considered according to the degree of similarity of the dendrograms. Some ..."
Abstract
 Add to MetaCart
An attempt is made to create some statistical tests for comparing results of ierarchical cluster analysis based on the uniform distribution over the set of all possible dendrograms. Three different uniform distributions are considered according to the degree of similarity of the dendrograms. Some distances between dendrograms are defined and The solutions proposed are computational and are based on the embeding the sets of equivalent dendrograms into the set of lexicographically ordered words. Keywords: cluster analysis, dendrogram, distance 1 Introduction Cluster analysis attempts to group the objects of an observed set, on the basis of similaritiy or distance between them, into mutually exclusive subsets (clusters) which consist of close objects. These clusters may be grouped into larger sets and so on, until all points are eventually united in one cluster. The higher the level of aggregation is, the less similar are the objects in the respective cluster. These methods for cl...
C.2 LANDSAT Imaging Project
"... class for SeedMakerBase. Generell functionality to store a solution and the instance. // Derived classes must provide MakeSeed which is providing a new SeedSolution. // ==================================================================================================== class SeedMakerBase  public: ..."
Abstract
 Add to MetaCart
class for SeedMakerBase. Generell functionality to store a solution and the instance. // Derived classes must provide MakeSeed which is providing a new SeedSolution. // ==================================================================================================== class SeedMakerBase  public: SeedMakerBase (MinWOutlierProblem &Inst) : Inst(Inst)  SolData = NULL; ~SeedMakerBase ()  MinWOutlierProblem &Instance ()  return Inst; virtual void MakeSeed (MixedSolution &SeedSol) = 0; // Start the creation of the seeds void CollectData (MixedSolution &Sol)  if (SolData != NULL) delete SolData; SolData = new MixedSolution (Sol); void CleanSolution (MixedSolution &Solution); // Empty a solution protected: int FindAvailableCluster(MixedSolution &Solution); private: MixedSolution *SolData; MinWOutlierProblem &Inst; // Local storage of the reference for the problem ; // ==================================================================================================== // Fill a given solution with random seeds. // ==================================================================================================== class RandomSeedsMaker : public SeedMakerBase  public: RandomSeedsMaker (MinWOutlierProblem& Inst, int a); ~RandomSeedsMaker ()  void MakeSeed (MixedSolution &SeedSol); // Start the seed making void SetRandomSeed (int a)  RandomSeed = a; // Set the seed for the random number stream void SetSeedsize (int a)  // Set the seed size #ifdef DEBUG assert (a ? Instance().X().p()); #endif SeedSize = a; private: int SeedSize; long RandomSeed; ; // ==================================================================================================== // Generates just one Seed in the solution vector // ===========================================================...
Algebraic Approach and Optimal Physical . . .
 Artificial Intelligence, Pattern Recognit. Image Anal
, 2000
"... Perceptrontype interpolation systems of artificial intelligence are considered. A concept of optimal physical clusterization allows us to divide a second layer of hidden units into the compact sets of units (clusters). ..."
Abstract
 Add to MetaCart
Perceptrontype interpolation systems of artificial intelligence are considered. A concept of optimal physical clusterization allows us to divide a second layer of hidden units into the compact sets of units (clusters).
Effect of Landscape Structure and Dynamics on Species Diversity in Hedgerow Networks
, 1992
"... this paper I analyse how landscape structure and dynamics over the last thirty years have affect ed carabid beetles in hedgerows ..."
Abstract
 Add to MetaCart
this paper I analyse how landscape structure and dynamics over the last thirty years have affect ed carabid beetles in hedgerows
Invariant Hierarchical Clustering Schemes
"... Summary. A general parametric scheme of hierarchical clustering procedures with invariance under monotone transformations of similarity values and invariance under numeration of objects is described. This scheme consists of two steps: correction of given similarity values between objects and transit ..."
Abstract
 Add to MetaCart
Summary. A general parametric scheme of hierarchical clustering procedures with invariance under monotone transformations of similarity values and invariance under numeration of objects is described. This scheme consists of two steps: correction of given similarity values between objects and transitive closure of obtained valued relation. Some theoretical properties of considered scheme are studied. Different parametric classes of clustering procedures from this scheme based on perceptions like “keep similarity classes, ” “break bridges between clusters,” etc. are considered. Several examples are used to illustrate the application of proposed clustering procedures to analysis of similarity structures of data. 1