Non-bossy social classification

We consider the problem of how societies should be partitioned into classes if individuals express their views about who should be put with whom in the same class. A non-bossy social aggregator depends only on those cells of the individual partitions the society members classify themselves in. This fact allows us to concentrate on a corresponding “opinion graph” for each profile of views. By means of natural sovereignty, liberalism, and equal treatment requirements, we characterize the non-bossy aggregators generating partitions in which the social classes are refinements of the weakly connected components of the opinion graph.     

Spatial classification

The aim of a spatial classification is to position the units on a spatial network and to give simultaneously a set of structured classes of these units “compatible” with the network. We introduce the basic needed definitions: compatibility between a classification structure and a tessellation, (m,k)-networks as a case of tessellation, convex, maximal and connected subsets in such networks, spatial pyramids and spatial hierarchies. As like Robinsonian dissimilarities induced by indexed pyramids generalize ultrametrics induced by indexed hierarchies we show that a new kind of dissimilarity called “Yadidean” induced by spatial pyramids generalize Robinsonian dissimilarities. We focus on spatial pyramids where each class is a convex for a grid, and we show that there are several one-to-one correspondences with different kinds of Yadidean dissimilarities. These new results produce also, as a special case, several one-to-one correspondences between spatial hierarchies (resp. standard indexed pyramids) and Yadidean ultrametrics (resp. Robinsonian) dissimilarities. Qualities of spatial pyramids and their supremum under a given dissimilarity are considered. We give a constructive algorithm for convex spatial pyramids illustrated by an example. We show finally by a simple example that spatial pyramids on symbolic data can produce a geometrical representation of conceptual lattices of “symbolic objects”.     

Gadget classification

The purpose of the paper is to classify a method used to solve some instances of the general factor problem. Hence, a problem of Pulleyblank is solved. Surprisingly, only one new type of gadget exists.     

On p-adic classification

A p-adic modification of the split-LBG classification method is presented in which first clusterings and then cluster centers are computed which locally minimize an energy function. The outcome for a fixed dataset is independent of the prime number p with finitely many exceptions. The methods are applied to the construction of p-adic classifiers in the context of learning.     

Isotonic boosting classification rules

Advances in Data Analysis and Classification - In many real classification problems a monotone relation between some predictors and the classes may be assumed when higher (or lower) values of those...     

Spectral classification of projections

Given two idempotents e and ? in a Banach algebra A, we study spectral characterizations to the effect that e and ? are not equivalent in A.     

Wavelet-RKHS-based functional statistical classification

A functional classification methodology, based on the Reproducing Kernel Hilbert Space (RKHS) theory, is proposed for discrimination of gene expression profiles. The parameter function involved in the definition of the functional logistic regression is univocally and consistently estimated, from the minimization of the penalized negative log-likelihood over a RKHS generated by a suitable wavelet basis. An iterative descendent method, the gradient method, is applied for solving the corresponding minimization problem, i.e., for computing the functional estimate. Temporal gene expression data involved in the yeast cell cycle are classified with the wavelet-RKHS-based discrimination methodology considered. A simulation study is developed for testing the performance of this statistical classification methodology in comparison with other statistical discrimination procedures.     

Benchmarking local classification methods

In recent years in the fields of statistics and machine learning an increasing amount of so called local classification methods has been developed. Local approaches to classification are not new, but have lately become popular. Well-known examples are the $k$ nearest neighbors method and classification trees. However, in most publications on this topic the term “local” is used without further explanation of its particular meaning. Only little is known about the properties of local methods and the types of classification problems for which they may be beneficial. We explain the basic principles and introduce the most important variants of local methods. To our knowledge there are very few extensive studies in the literature that compare several types of local methods and global methods across many data sets. In order to assess their performance we conduct a benchmark study on real-world and synthetic tasks. We cluster data sets and considered learning algorithms with regard to the obtained performance structures and try to relate our theoretical considerations and intuitions to these results. We also address some general issues of benchmark studies and cover some pitfalls, extensions and improvements.     

Constraint classification in mathematical programming

Consider a set of algebraic inequality constraints defining either an empty or a nonempty feasible region. It is known that each constraint can be classified as either absolutely strongly redundant, relatively strongly redundant, absolutely weakly redundant, relatively weakly redundant, or necessary. We show that is is worth making a distinction between weakly necessary constraints and strongly necessary constraints. We also present afeasible set cover method which can detect both weakly and strongly necessary constraints.The main interest in constraint classification is due to the advantages gained by the removal of redundant constraints. Since classification errors are likely to occur, we examine how the removal of a single constraint can affect the classification of the remaining constraints.     

Ellipsoidal classification via semidefinite programming

We propose a classification approach exploiting relationships between ellipsoidal separation and Support-vector Machine (SVM) with quadratic kernel. By adding a (Semidefinite Programming) SDP constraint to SVM model we ensure that the chosen hyperplane in feature space represents a non-degenerate ellipsoid in input space. This allows us to exploit SDP techniques within Support-vector Regression (SVR) approaches, yielding better results in case ellipsoid-shaped separators are appropriate for classification tasks. We compare our approach with spherical separation and SVM on some classification problems.     

Management of multicriteria inventory classification

The most common method that materials managers use for classifying inventory items for planning and control purposes is the annual-dollar-usage ranking method (ABC classification). Recently, it has been suggested that multiple criteria ABC classification can provide a more comprehensive managerial approach, allowing consideration of other criteria such as lead time and criticality. This paper proposes the use of the Analytical Hierarchy Process (AHP) to reduce these multiple criteria to a univariate and consistent measure to consider multiple inventory management objectives.     

Multi-group classification using fuzzy correlation

A non-supervised learning model based on fuzzy correlation is presented which enables an artificial hand to distinguish between classes of objects. This technique is applicable to large numbers of classes, and is computationally more efficient than several previous methods of a similar nature.     

Quasiharmonic classification of infinite networks

As a discrete analog to the quasiharmonic classification of Riemannian manifolds due to Nakai and Sario, we give a characterization of an infinite network by the class of discrete quasiharmonic functions on it. Some potential-theoretic properties of the network will be discussed in this paper.