José Ruiz-Shulcloper

A SURVEY OF CLUSTERING ENSEMBLE ALGORITHMS

Cluster ensemble has proved to be a good alternative when facing cluster analysis problems. It consists of generating a set of clusterings from the same dataset and combining them into a final clustering. The goal of this combination process is to improve the quality of individual data clusterings. Due to the increasing appearance of new methods, their promising results and the great number of applications, we consider that it is necessary to make a critical analysis of the existing techniques and future projections. This paper presents an overview of clustering ensemble methods that can be very useful for the community of clustering practitioners. The characteristics of several methods are discussed, which may help in the selection of the most appropriate one to solve a problem at hand. We also present a taxonomy of these techniques and illustrate some important applications.

Progress in Pattern Recognition, Speech and Image Analysis

Neurons, Dendrites, and Pattern Classification.- Robot Vision for Autonomous Object Learning and Tracking.- Graduated Scale Inspection Using Computer Vision.- Vision System for Subpixel Laser Stripe Profile Extraction with Real Time Operation.- Multi-channel Reconstruction of Video Sequences from Low-Resolution and Compressed Observations.- 3D Rigid Facial Motion Estimation from Disparity Maps.- Robust Techniques in Least Squares-Based Motion Estimation Problems.- Inexact Graph Matching for Facial Feature Segmentation and Recognition in Video Sequences: Results on Face Tracking.- Crater Marking and Classification Using Computer Vision.- Using Optical Flow for Tracking.- Another Paradigm for the Solution of the Correspondence Problem in Motion Analysis.- Improvement of the Fail-Safe Characteristics in Motion Analysis Using Adaptive Technique.- Spatially Adaptive Algorithm for Impulse Noise Removal from Color Images.- Improving Phase-Congruency Based Feature Detection through Automatic Scale-Selection.- Robust Estimation of Roughness Parameter in SAR Amplitude Images.- Two New Scale-Adapted Texture Descriptors for Image Segmentation.- Topological Query in Image Databases.- Reconstructing 3D Objects from Silhouettes with Unknown Viewpoints: The Case of Planar Orthographic Views.- Enforcing a Shape Correspondence between Two Views of a 3D Non-rigid Object.- A Colour Constancy Algorithm Based on the Histogram of Feasible Colour Mappings.- Reconstruction of Surfaces from Cross Sections Using Skeleton Information.- Extension of a New Method for Surface Reconstruction from Cross Sections.- Imposing Integrability in Geometric Shape-from-Shading.- Correcting Radial Lens Distortion Using Image and Point Correspondences.- Characterization of Surfaces with Sonars Using Time of Flight and Triangulation.- Non-speech Sound Feature Extraction Based on Model Identification for Robot Navigation.- Enhancement of Noisy Speech Using Sliding Discrete Cosine Transform.- Integrating High and Low Smoothed LMs in a CSR System.- Selection of Lexical Units for Continuous Speech Recognition of Basque.- Creating a Mexican Spanish Version of the CMU Sphinx-III Speech Recognition System.- Decision Tree-Based Context Dependent Sublexical Units for Continuous Speech Recognition of Basque.- Uniclass and Multiclass Connectionist Classification of Dialogue Acts.- A Technique for Extraction of Diagnostic Data from Cytological Specimens.- Segmentation and Morphometry of Histological Sections Using Deformable Models: A New Tool for Evaluating Testicular Histopathology.- Robust Markers for Blood Vessels Segmentation: A New Algorithm.- Discriminative Power of Lymphoid Cell Features: Factor Analysis Approach.- Retinal Angiography Based Authentication.- Suboptimal Classifier for Dysarthria Assessment.- Approximate Nearest Neighbour Search with the Fukunaga and Narendra Algorithm and Its Application to Chromosome Classification.- Characterization of Viability of Seeds by Using Dynamic Speckles and Difference Histograms.- An Adaptive Enhancer with Modified Signal Averaging Scheme to Detect Ventricular Late Potentials.- A Study on the Recognition of Patterns of Infant Cry for the Identification of Deafness in Just Born Babies with Neural Networks.- Patients Classification by Risk Using Cluster Analysis and Genetic Algorithms.- Mathematical Morphology on MRI for the Determination of Iberian Ham Fat Content.- Automatic Dark Fibres Detection in Wool Tops.- Musical Style Identification Using Grammatical Inference: The Encoding Problem.- New Distance Measures Applied to Marble Classification.- Online Handwritten Signature Verification Using Hidden Markov Models.- Fast Handwritten Recognition Using Continuous Distance Transformation.- Stroke Boundary Analysis for Identification of Drawing Tools.- Solving the Global Localization Problem for Indoor Mobile Robots.- Restricted Decontamination for the Imbalanced Training Sample Problem.- An Entropy Maximization Approach to Optimal Model Selection in Gaussian Mixtures.- Gaussian Mixture Models for Supervised Classification of Remote Sensing Multispectral Images.- Fast Multistage Algorithm for K-NN Classifiers.- Some Improvements in Tree Based Nearest Neighbour Search Algorithms.- Impact of Mixed Metrics on Clustering.- A Comparison between Two Fuzzy Clustering Algorithms for Mixed Features.- Extended Star Clustering Algorithm.- Two New Metrics for Feature Selection in Pattern Recognition.- Conditions of Generating Descriptive Image Algebras by a Set of Image Processing Operations.- Completeness Conditions of a Class of Pattern Recognition Algorithms Based on Image Equivalence.- Typical Segment Descriptors: A New Method for Shape Description and Identification.- A New Approach That Selects a Single Hyperplane from the Optimal Pairwise Linear Classifier.- A Characterization of Discretized Polygonal Convex Regions by Discrete Moments.- Learning probabilistic context-free grammars from treebanks.- Simulated Annealing for Automated Definition of Fuzzy Sets in Human Central Nervous System Modeling.- Automatic Tuning of Fuzzy Partitions in Inductive Reasoning.- Kernel Computation in Morphological Bidirectional Associative Memories.- Improving Still Image Coding by an SOM-Controlled Associative Memory.- A Morphological Methodology for Features Identification in Satellite Images for Semi-automatic Cartographic Updating.- Morphological Neural Networks with Dendrite Computation: A Geometrical Approach.- A Method for the Automatic Summarization of Topic-Based Clusters of Documents.- Improving Prepositional Phrase Attachment Disambiguation Using the Web as Corpus.- Determination of Similarity Threshold in Clustering Problems for Large Data Sets.- Content-Based Retrieval Using Color, Texture, and Shape Information.- Off the Shelf Methods for Robust Portuguese Cadastral Map Analysis.- Simultaneous Segmentation-Recognition-Vectorization of Meaningful Geographical Objects in Geo-Images.- Geomorphometric Analysis of Raster Image Data to detect Terrain Ruggedness and Drainage Density.- Morphological Applications for Maps Construction in Path Planning Tasks.- Compact Mapping in Plane-Parallel Environments Using Stereo Vision.- An Oscillatory Neural Network for Image Segmentation.- Generating Three-Dimensional Neural Cells Based on Bayes Rules and Interpolation with Thin Plate Splines.- A Maximum Entropy Approach to Sampling in EDA - The Single Connected Case.

Topic discovery based on text mining techniques

In this paper, we present a topic discovery system aimed to reveal the implicit knowledge present in news streams. This knowledge is expressed as a hierarchy of topic/subtopics, where each topic contains the set of documents that are related to it and a summary extracted from these documents. Summaries so built are useful to browse and select topics of interest from the generated hierarchies. Our proposal consists of a new incremental hierarchical clustering algorithm, which combines both partitional and agglomerative approaches, taking the main benefits from them. Finally, a new summarization method based on Testor Theory has been proposed to build the topic summaries. Experimental results in the TDT2 collection demonstrate its usefulness and effectiveness not only as a topic detection system, but also as a classification and summarization tool.

Weighted partition consensus via kernels

The combination of multiple clustering results (clustering ensemble) has emerged as an important procedure to improve the quality of clustering solutions. In this paper we propose a new cluster ensemble method based on kernel functions, which introduces the Partition Relevance Analysis step. This step has the goal of analyzing the set of partition in the cluster ensemble and extract valuable information that can improve the quality of the combination process. Besides, we propose a new similarity measure between partitions proving that it is a kernel function. A new consensus function is introduced using this similarity measure and based on the idea of finding the median partition. Related to this consensus function, some theoretical results that endorse the suitability of our methods are proven. Finally, we conduct a numerical experimentation to show the behavior of our method on several databases by making a comparison with simple clustering algorithms as well as to other cluster ensemble methods.

An overview of the evolution of the concept of testor

In this paper, the historical evolution of the concept of testor is presented. Testors in a bivalued logic, in a k-valued logic, and also in a fuzzy logic are considered, particular considerations about each case are expressed. This concept evolution is presented to English readers for the rst time. The authors reviewed this history because testor, in each particular formulation, is an interesting tool for feature selection problems, especially when the descriptions of objects are non-classical. ( 2001 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved.

Determining the feature relevance for non-classically described objects and a new algorithm to compute typical fuzzy testors

In this paper we introduce an algorithm for computing all the typical fuzzy testors of a training matrix with non-classically described objects in Goldmans approach. We also introduce a new expression for determining the feature relevance in crisp and fuzzy environments.

Mining frequent patterns and association rules using similarities

Most of the current algorithms for mining association rules assume that two object subdescriptions are similar when they are exactly equal, but in many real world problems some other similarity functions are used. Commonly these algorithms are divided in two steps: Frequent pattern mining and generation of interesting association rules from frequent patterns. In this work, two algorithms for mining frequent similar patterns using similarity functions different from the equality are proposed. Additionally, the GenRules Algorithm is adapted to generate interesting association rules from frequent similar patterns. Experimental results show that our algorithms are more effective and obtain better quality patterns than the existing ones.

Weighted Cluster Ensemble Using a Kernel Consensus Function

Cluster ensemble is a good alternative to face the problem of data clustering. Some studies based on mathematical models have shown that cluster ensemble methods lead to an effective improvement of the results of the standard clustering algorithms. In this paper, we focus on this problem, proposing a new approach to solve it, by adding a new step into the usual cluster ensemble methodology. Representing partitions by graphs and a new kernel function to measure the similarity between partitions are other proposals for this work. Experiments with synthetic and real databases show the suitability and effectiveness of our method.

LCMine: An efficient algorithm for mining discriminative regularities and its application in supervised classification

In this paper, we introduce an efficient algorithm for mining discriminative regularities on databases with mixed and incomplete data. Unlike previous methods, our algorithm does not apply an a priori discretization on numerical features; it extracts regularities from a set of diverse decision trees, induced with a special procedure. Experimental results show that a classifier based on the regularities obtained by our algorithm attains higher classification accuracy, using fewer discriminative regularities than those obtained by previous pattern-based classifiers. Additionally, we show that our classifier is competitive with traditional and state-of-the-art classifiers.

Weighted association based methods for the combination of heterogeneous partitions

Highlights? We show how the use of the original objects could improve the consensus results. ? Weighted association matrix extracts more information from clustering ensembles. ? Data representations and similarity measures can be summarized into a unified matrix. ? The two clustering ensemble algorithms have good performance on several datasets. ? These algorithms are able to work with numerical, categorical and mixed data. Co-association matrix has been a useful tool in many clustering ensemble techniques as a similarity measure between objects. In this paper, we introduce the weighted-association matrix, which is more expressive than the traditional co-association as a similarity measure, in the sense that it integrates information from the set of partitions in the clustering ensemble as well as from the original data of object representations. The weighted-association matrix is the core of the two main contributions of this paper: a natural extension of the well-known evidence accumulation cluster ensemble method by using the weighted-association matrix and a kernel based clustering ensemble method that uses a new data representation. These methods are compared with simple clustering algorithms as well as with other clustering ensemble algorithms on several datasets. The obtained results ratify the accuracy of the proposed algorithms.