Christian Borgelt

Mining molecular fragments: finding relevant substructures of molecules

We present an algorithm to find fragments in a set of molecules that help to discriminate between different classes of for instance, activity in a drug discovery context. Instead of carrying out a brute-force search, our method generates fragments by embedding them in all appropriate molecules in parallel and prunes the search tree based on a local order of the atoms and bonds, which results in substantially faster search by eliminating the need for frequent, computationally expensive reembeddings and by suppressing redundant search. We prove the usefulness of our algorithm by demonstrating the discovery of activity-related groups of chemical compounds in the well-known National Cancer Institutes HIV-screening dataset.

Introduction to Neural Networks

(Artificial) neural networks are information processing systems, whose structure and operation principles are inspired by the nervous system and the brain of animals and humans. They consist of a large number of fairly simple units, the so-called neurons, which are working in parallel. These neurons communicate by sending information in the form of activation signals, along directed connections, to each other.

Induction of Association Rules: Apriori Implementation

We describe an implementation of the well-known apriori algorithm for the induction of association rules [Agrawal et al. (1993), Agrawal et al. (1996)] that is based on the concept of a prefix tree. While the idea to use this type of data structure is not new, there are several ways to organize the nodes of such a tree, to encode the items, and to organize the transactions, which may be used in order to minimize the time needed to find the frequent itemsets as well as to reduce the amount of memory needed to store the counters. Consequently, our emphasis is less on concepts, but on implementation issues, which, however, can make a considerable difference in applications.

An implementation of the FP-growth algorithm

The FP-growth algorithm is currently one of the fastest approaches to frequent item set mining. In this paper I describe a C implementation of this algorithm, which contains two variants of the core operation of computing a projection of an FP-tree (the fundamental data structure of the FP-growth algorithm). In addition, projected FP-trees are (optionally) pruned by removing items that have become infrequent due to the projection (an approach that has been called FP-Bonsai). I report experimental results comparing this implementation of the FP-growth algorithm with three other frequent item set mining algorithms I implemented (Apriori, Eclat, and Relim).

An extension to possibilistic fuzzy cluster analysis

We explore an approach to possibilistic fuzzy clustering that avoids a severe drawback of the conventional approach, namely that the objective function is truly minimized only if all cluster centers are identical. Our approach is based on the idea that this undesired property can be avoided if we introduce a mutual repulsion of the clusters, so that they are forced away from each other. We develop this approach for the possibilistic fuzzy c-means algorithm and the possibilistic Gustafson‐Kessel algorithm. In our experiments we found that in this way we can combine the partitioning property of the probabilistic fuzzy c-means algorithm with the advantages of a possibilistic approach w.r.t. the interpretation of the membership degrees.

Guide to Intelligent Data Analysis

Each passing year bears witness to the development of ever more powerful computers, increasingly fast and cheap storage media, and even higher bandwidth data connections. This makes it easy to believe that we can now at least in principle solve any problem we are faced with so long as we only have enough data. Yet this is not the case. Although large databases allow us to retrieve many different single pieces of information and to compute simple aggregations, general patterns and regularities often go undetected. Furthermore, it is exactly these patterns, regularities and trends that are often most valuable. To avoid the danger of drowning in information, but starving for knowledge the branch of research known as data analysis has emerged, and a considerable number of methods and software tools have been developed. However, it is not these tools alone but the intelligent application of human intuition in combination with computational power, of sound background knowledge with computer-aided modeling, and of critical reflection with convenient automatic model construction, that results in successful intelligent data analysis projects. Guide to Intelligent Data Analysis provides a hands-on instructional approach to many basic data analysis techniques, and explains how these are used to solve data analysis problems. Topics and features: guides the reader through the process of data analysis, following the interdependent steps of project understanding, data understanding, data preparation, modeling, and deployment and monitoring; equips the reader with the necessary information in order to obtain hands-on experience of the topics under discussion; provides a review of the basics of classical statistics that support and justify many data analysis methods, and a glossary of statistical terms; includes numerous examples using R and KNIME, together with appendices introducing the open source software; integrates illustrations and case-study-style examples to support pedagogical exposition. This practical and systematic textbook/reference for graduate and advanced undergraduate students is also essential reading for all professionals who face data analysis problems. Moreover, it is a book to be used following ones exploration of it. Dr. Michael R. Berthold is Nycomed-Professor of Bioinformatics and Information Mining at the University of Konstanz, Germany. Dr. Christian Borgelt is Principal Researcher at the Intelligent Data Analysis and Graphical Models Research Unit of the European Centre for Soft Computing, Spain. Dr. Frank Hppner is Professor of Information Systems at Ostfalia University of Applied Sciences, Germany. Dr. Frank Klawonn is a Professor in the Department of Computer Science and Head of the Data Analysis and Pattern Recognition Laboratory at Ostfalia University of Applied Sciences, Germany. He is also Head of the Bioinformatics and Statistics group at the Helmholtz Centre for Infection Research, Braunschweig, Germany.

Possibilistic Graphical Models

Graphical modeling is an important method to efficiently represent and analyze uncertain information in knowledge-based systems. Its most prominent representatives are Bayesian networks and Markov networks for probabilistic reasoning. which have been well-known for over ten years now. However, they suffer from certain deficiencies, if imprecise information has to be taken into account. Therefore possibilistic graphical modeling has recently emerged as a promising new area of research. Possibilistic networks are a noteworthy alternative to probabilistic networks whenever it is necessary to model both uncertainty and imprecision. Imprecision, understood as set-valued data, has often to be considered in situations in which information is obtained from human observers or imprecise measuring instruments. In this paper we provide an overview on the state of the art of possibilistic networks w.r.t. to propagation and learning algorithms.

Combining Soft Computing and Statistical Methods in Data Analysis

Thank you for downloading combining soft computing and statistical methods in data analysis. As you may know, people have look hundreds times for their chosen books like this combining soft computing and statistical methods in data analysis, but end up in infectious downloads. Rather than enjoying a good book with a cup of tea in the afternoon, instead they juggled with some malicious bugs inside their desktop computer.

Keeping things simple: finding frequent item sets by recursive elimination

Recursive elimination is an algorithm for finding frequent item sets, which is strongly inspired by the FP-growth algorithm and very similar to the H-mine algorithm. It does its work without prefix trees or any other complicated data structures, processing the transactions directly. Its main strength is not its speed (although it is not slow, even outperforms Apriori and Eclat on some data sets), but the simplicity of its structure. Basically all the work is done in one simple recursive function, which can be written with relatively few lines of code.

Canonical Forms for Frequent Graph Mining

A core problem of approaches to frequent graph mining, which are based on growing subgraphs into a set of graphs, is how to avoid redundant search. A powerful technique for this is a canonical description of a graph, which uniquely identifies it, and a corresponding test. I introduce a family of canonical forms based on systematic ways to construct spanning trees. I show that the canonical form used in gSpan ([Yan and Han (2002)]) is a member of this family, and that MoSS/MoFa ([Borgelt and Berthold (2002), Borgelt et al. (2005)]) is implicitly based on a different member, which I make explicit and exploit in the same way.