Basilis Boutsinas

The New k-Windows Algorithm for Improving thek -Means Clustering Algorithm

The process of partitioning a large set of patterns into disjoint and homogeneous clusters is fundamental in knowledge acquisition. It is called Clustering in the literature and it is applied in various fields including data mining, statistical data analysis, compression and vector quantization. The k-means is a very popular algorithm and one of the best for implementing the clustering process. The k-means has a time complexity that is dominated by the product of the number of patterns, the number of clusters, and the number of iterations. Also, it often converges to a local minimum. In this paper, we present an improvement of the k-means clustering algorithm, aiming at a better time complexity and partitioning accuracy. Our approach reduces the number of patterns that need to be examined for similarity, in each iteration, using a windowing technique. The latter is based on well known spatial data structures, namely the range tree, that allows fast range searches.

A method for improving the accuracy of data mining classification algorithms

In this paper we introduce a method called CL.E.D.M. (CLassification through ELECTRE and Data Mining), that employs aspects of the methodological framework of the ELECTRE I outranking method, and aims at increasing the accuracy of existing data mining classification algorithms. In particular, the method chooses the best decision rules extracted from the training process of the data mining classification algorithms, and then it assigns the classes that correspond to these rules, to the objects that must be classified. Three well known data mining classification algorithms are tested in five different widely used databases to verify the robustness of the proposed method.

On distributing the clustering process

Clustering algorithms require a large amount of computations of distances among patterns and centers of clusters. Hence, their complexity is dominated by the number of patterns. On the other hand, there is an explosive growth of business or scientific databases storing huge volumes of data. One of the main challenges of todays knowledge discovery systems is their ability to scale up to very large data sets. In this paper, we present a clustering methodology for scaling up any clustering algorithm. It is an iterative process that it is based on partitioning a sample of data into subsets. We, also, present extensive empirical tests that demonstrate the proposed methodology reduces the time complexity and at the same time may maintain the accuracy that would be achieved by a single clustering algorithm supplied with all the data.

Artificial nonmonotonic neural networks

In this paper, we introduce Artificial Nonmonotonic Neural Networks (ANNNs), a kind of hybrid learning systems that are capable of nonmonotonic reasoning. Nonmonotonic reasoning plays an important role in the development of artificial intelligent systems that try to mimic common sense reasoning, as exhibited by humans. On the other hand, a hybrid learning system provides an explanation capability to trained Neural Networks through acquiring symbolic knowledge of a domain, refining it using a set of classified examples along with Connectionist learning techniques and, finally, extracting comprehensible symbolic information. Artificial Nonmonotonic Neural Networks acquire knowledge represented by a multiple inheritance scheme with exceptions, such as nonmonotonic inheritance networks, and then can extract the refined knowledge in the same scheme. The key idea is to use a special cell operation during training in order to preserve the symbolic meaning of the initial inheritance scheme. Methods for knowledge initialization, knowledge refinement and knowledge extraction are introduced. We, also, prove that these methods address perfectly the constraints imposed by nonmonotonicity. Finally, performance of ANNNs is compared to other well-known hybrid systems, through extensive empirical tests. . 2001 Elsevier Science B.V. All rights reserved.

On clustering tree structured data with categorical nature

Clustering consists in partitioning a set of objects into disjoint and homogeneous clusters. For many years, clustering methods have been applied in a wide variety of disciplines and they also have been utilized in many scientific areas. Traditionally, clustering methods deal with numerical data, i.e. objects represented by a conjunction of numerical attribute values. However, nowadays commercial or scientific databases usually contain categorical data, i.e. objects represented by categorical attributes. In this paper we present a dissimilarity measure which is capable to deal with tree structured categorical data. Thus, it can be used for extending the various versions of the very popular k-means clustering algorithm to deal with such data. We discuss how such an extension can be achieved. Moreover, we empirically prove that the proposed dissimilarity measure is accurate, compared to other well-known (dis)similarity measures for categorical data.

Machine-part cell formation using biclustering

Cellular manufacturing is the cornerstone of many modern flexible manufacturing techniques, taking advantage of the similarities between parts in order to decrease the complexity of the design and manufacturing life cycle. Part-Machine Grouping (PMG) problem is the key step in cellular manufacturing aiming at grouping parts with similar processing requirements or similar design features into part families and by grouping machines into cells associated to these families. The PMG problem is NP-complete and the different proposed techniques for solving it are based on heuristics. In this paper, a new approach for solving the PMG problem is proposed which is based on biclustering. Biclustering is a methodology where rows and columns of an input data matrix are clustered simultaneously. A bicluster is defined as a submatrix spanned by both a subset of rows and a subset of columns. Although biclustering has been almost exclusively applied to DNA microarray analysis, we present that biclustering can be successfully applied to the PMG problem. We also present empirical results to demonstrate the efficiency and accuracy of the proposed technique with respect to related ones for various formations of the problem.

Improving the orthogonal range search k-windows algorithm

Clustering, that is the partitioning of a set of patterns into disjoint and homogeneous meaningful groups (clusters), is a fundamental process in the practice of science. k-windows is an efficient clustering algorithm that reduces the number of patterns that need to be examined for similarity. using a windowing technique. It exploits well known spatial data structures, namely the range free, that allows fast range searches. From a theoretical standpoint, the k-windows algorithm is characterized by lower time complexity compared to other well-known clustering algorithms. Moreover it achieves high quality clustering results. However, it appears that it cannot be directly applicable in high-dimensional settings due to the superlinear space requirements for the range tree. In this paper an improvement of the k-windows algorithm, aiming at resolving this deficiency, is presented. The improvement is based on an alternative solution to the orthogonal range search problem.

Estimating the number of clusters using a windowing technique

Clustering is the process of partitioning a set of patterns into disjoint and homogeneous meaningful groups (clusters). A fundamental and unresolved issue in cluster analysis is to determine how many clusters are present in a given set of patterns. In this paper, we present the z-windows clustering algorithm, which aims to address this problem using a windowing technique. Extensive empirical tests that illustrate the efficiency and the accuracy of the propsoed method are presented.

ONTOLOGY MAPPING BASED ON ASSOCIATION RULE MINING

Ontology mapping is one of the most important processes in ontology engineering. It is imposed by the decentralized nature of both the WWW and the Semantic Web, where heterogeneous and incompatible ontologies can be developed by different communities. Ontology mapping can be used to establish efficient information sharing by determining correspondences among such ontologies. The ontology mapping techniques presented in the literature are based on syntactic and/or semantic heuristics. In almost all of them, user intervention is required. In this paper, we present a new ontology mapping technique which, given two input ontologies, is able to map concepts in one ontology onto those in the other, without any user intervention. It is based on association rule mining applied to the concept hierarchies of the input ontologies. We also present experimental results that demonstrate the accuracy of the proposed technique.

ACCESSING DATA MINING RULES THROUGH EXPERT SYSTEMS

Data mining is an emerging research area that develops techniques for knowledge discovery in huge volumes of data. Usually, data mining rules can be used either to classify data into predefined classes, or to partition a set of patterns into disjoint and homogeneous clusters, or to reveal frequent dependencies among data. The discovery of data mining rules would not be very useful unless there are mechanisms to help analysts access them in a meaningful way. Actually, documenting and reporting the extracted knowledge is of considerable importance for the successful application of data mining in practice. In this paper, we propose a methodology for accessing data mining rules, which is based on using an expert system. We present how the different types of data mining rules can be transformed into the domain knowledge of any general-purpose expert system. Then, we present how certain attribute values given by the user as facts and/or goals can determine, through a forward and/or backward chaining, the related data mining rules. In this paper, we also present a case study that demonstrates the applicability of the proposed methodology.