Open-source machine learning: R meets Weka

Two of the prime open-source environments available for machine/statistical learning in data mining and knowledge discovery are the software packages Weka and R which have emerged from the machine learning and statistics communities, respectively. To make the different sets of tools from both environments available in a single unified system, an R package RWeka is suggested which interfaces Weka’s functionality to R. With only a thin layer of (mostly R) code, a set of general interface generators is provided which can set up interface functions with the usual “R look and feel”, re-using Weka’s standardized interface of learner classes (including classifiers, clusterers, associators, filters, loaders, savers, and stemmers) with associated methods.     

The “DUEL” expert system: Implementation of a dual approach for IBM-compatible computers

We describe the “DUEL” expert system, a software package intended for analyzing problem situations and decision making in medical, economic, engineering, and other systems, based on modern information technology, the introduction of knowledge and data bases, and deductive and inductive approaches to the synthesis and justification of decisions. “DUEL” is two inference machines: a deductive machine that uses the products contained in the knowledge base, and an inductive machine that provides generalization on the basis of precedents accumulated in the data base. Translated fromDinamicheskie Sistemy, No. 13, 1994, pp. 93–98.     

Strongest postcondition semantics as the formal basis for reverse engineering

Reverse engineering of program code is the process of constructing a higher level abstraction of an implementation in order to facilitate the understanding of a system that may be in a “legacy” or “geriatric” state. Changing architectures and improvements in programming methods, including formal methods in software development and object-oriented programming, have prompted a need to reverse engineer and re-engineer program code. This paper describes the application of the strongest postcondition predicate transformer (sp) as the formal basis for the reverse engineering of imperative program code. This work is supported in part by the National Science Foundation grants CCR-9407318, CCR-9209873, and CDA-9312389. This author is supported in part by a NASA Graduate Student Researchers Program Fellowship.     

Parallel computing in the statistical system Jasp

Modern statistical data analysis often requires powerful computers. Parallel computing is a technique to realize such a computer system. Although many “low-level” software technologies for parallel computing have been developed, they are not easy to use for statisticians who are accustomed to “high-level” statistical languages. In this paper, we describe high-level parallel computing functions in a statistical analysis system called Jasp. We implemented them mainly considering ease of use.     

Model development and optimization in interactive computing environments

Integrated computing systems—such as Maple, Mathematica, and MATLAB—enable the development of “live” electronic documents that include explanatory text, calculations, custom programming (code development), visualization, and other features. As a result, teachers and students, researchers and practitioners can develop applications in a completely interactive format. Such e-documents can be put to good use in developing textbooks, lecture notes, assignments and presentations, as well as in the context of research and development (R&D) projects. The interactive approach accelerates and enhances the process of learning and research. To illustrate this approach, we discuss a nonlinear (global and local) optimization software product and a topical electronic book that support interactive model development and optimization in Maple. We highlight the key features of the e-book and the software, present illustrative examples, and point towards a range of scientific and engineering applications.      

Polyhedral surfaces in wedge products

We introduce the wedge product of two polytopes. The wedge product is described in terms of inequality systems, in terms of vertex coordinates as well as purely combinatorially, from the corresponding data of its constituents. The wedge product construction can be described as an iterated “subdirect product” as introduced by McMullen (Discrete Math 14:347–358, 1976); it is dual to the “wreath product” construction of Joswig and Lutz (J Combinatorial Theor A 110:193–216, 2005). One particular instance of the wedge product construction turns out to be especially interesting: The wedge products of polygons with simplices contain certain combinatorially regular polyhedral surfaces as subcomplexes. These generalize known classes of surfaces “of unusually large genus” that first appeared in works by Coxeter (Proc London Math Soc 43:33–62, 1937), Ringel (Abh Math Seminar Univ Hamburg 20:10–19, 1956), and McMullen et al. (Israel J Math 46:127–144, 1983). Via “projections of deformed wedge products” we obtain realizations of some of the surfaces in the boundary complexes of 4-polytopes, and thus in \mathbb R³{{\mathbb R}^3} . As additional benefits our construction also yields polyhedral subdivisions for the interior and the exterior, as well as a great number of local deformations (“moduli”) for the surfaces in \mathbb R³{{\mathbb R}^3} . In order to prove that there are many moduli, we introduce the concept of “affine support sets” in simple polytopes. Finally, we explain how duality theory for 4-dimensional polytopes can be exploited in order to also realize combinatorially dual surfaces in \mathbb R³{{\mathbb R}^3} via dual 4-polytopes.     

Influence of viscosity on the structure of shock waves in the MKdV model

A “non-self-adjoint” integrable MKdV model with boundary conditions of “step-like” type is considered. The time-asymptotic behavior of the solution for the Cauchy problem is obtained. A similar problem for the dissipative perturbation of this problem is discussed. Bibliography: 10 titles. Translated fromZapiski Nauchnykh Seminarov POMI, Vol. 199, 1992, pp. 37–42. Translated by R. F. Bikbaev.     

A number theoretical observation about the degeneracy of the genetic code

We discuss the similarity of the degeneration structure of the genetic code with a purely number theoretic “divisors code.” The most interesting thing about our observation is not that there is a connection between number theory and the genetic code, but the simplicity of the rule. We hope that the observation and the naive model presented in this paper will spur ideas for other models of the degeneracy of the genetic code. Maybe, the ideas of this article can also be used in the area of artificial life to synthesize artificial genetic codes.     

$${\tt surveillance}$$: An R package for the monitoring of infectious diseases

Public health surveillance of emerging infectious diseases is an essential instrument in the attempt to control and prevent their spread. This paper presents the R package “surveillance”, which contains functionality to visualise routinely collected surveillance data and provides algorithms for the statistical detection of aberrations in such univariate or multivariate time series. For evaluation purposes, the package includes real-world example data and the possibility to generate surveillance data by simulation. To compare algorithms, benchmark numbers like sensitivity, specificity, and detection delay can be computed for a set of time series. Package motivation, use and potential are illustrated through a mixture of surveillance theory, case study and R code snippets.     

Code analysis and parallelizing vector operations in R

This paper presents some current work and preliminary thoughts on two seemingly unrelated areas. The first is the development of code analysis tools to help identify possible errors in R code. Current versions of these tools have been useful in finding bugs in R’s code as well as code in packages submitted to CRAN. The second area, where work is just beginning, is the development of mechanisms to allow R’s internal vectorized operations, as well as vectorized operations defined in packages, to take advantage of multiple processors. These two areas are related through their connections to ongoing efforts to develop a byte code compiler for R.     

Homotopy classification of equivariant regular sections

In his paper [2], Bierstone proves the equivariant Gromov theorem which is an integrability theorem for “open regularity condition” of equivariant sections of a smooth G-fibre bundle under the assumption that all orbit bundles of base manifold are non-closed. Here, we prove the result without his assumption under a nice “open regularity condition” which we call “G-extensible”. One of the examples of “G-extensible condition” is given by notions of Thom-Boardman singularities.     

Fix-mahonian calculus III; a quadruple distribution

A four-variable distribution on permutations is derived, with two dual combinatorial interpretations. The first one includes the number of fixed points “fix”, the second the so-called “pix” statistic. This shows that the duality between derangements and desarrangements can be extended to the case of multivariable statistics. Several specializations are obtained, including the joint distribution of (des, exc), where “des” and “exc” stand for the number of descents and excedances, respectively. Authors’ addresses: Dominique Foata, Institut Lothaire, 1 rue Murner, F-67000 Strasbourg, France; Guo-Niu Han, Center for Combinatorics, LPMC, Nankai University, Tianjin 300071, P.R. China; I.R.M.A. UMR 7501, Université Louis Pasteur et CNRS, 7, rue René-Descartes, F-67084 Strasbourg, France     

Statistical hydrodynamics of magnetic fluids. I. the nonequilibrium statistical operator method

The Zubarev nonequilibrium statistical operator is used to describe the generalized hydrodynamic state of a magnetic fluid in an external magnetic field. The magnetic fluid is modeled with “liquid-state” and “magnetic” subsystems described using the classical and quantum statistics methods respectively. Equations of the generalized statistical hydrodynamics for a magnetic fluid in a nonhomogeneous external magnetic field with the Heisenberg spin interaction are derived for “liquid-state” and “magnetic” subsystems characterized by different nonequilibrium temperatures. These equations can be used to describe both the weakly and strongly nonequilibrium states. Some limiting cases are analyzed in which the variables of one of the subsystems can be formally neglected. Translated from Teoreticheskaya i Matematicheskaya Fizika. Vol. 115, No. 1, pp. 132–153, April, 1998.     

Explorative and dynamic visualization of data in virtual reality

Summary  A software system has been developed for the study of dynamic glyph visualizations in the context of Visual Data Mining in Virtual Reality. The system uses parallel processing to calculate data visualizations in real-time, with real-time interaction and dynamic changes to the view. The system allows morphing between different visualizations, the use of dynamic features like “vibrations” and “rotations” of thousands of objects individually, and dynamic visualization, where the influence of any variable of a dataset with a “reasonable” distribution, can be shown as a dynamic development. It appears that these facilities for dynamic data visualization have a very promising potential, but their optimal use will depend on further developments in the context of their individual practical application.     

Linear systems on singular curves

We start this work by studying free linear systems on singular curves and related base point free linear systems on the non-singular model. We apply these results to the study of pencils of small degree on non-singular curves. We also prove a “base point free pencil trick” which holds for any (possibly) singular curve. Received: 15 June 1998     

Model Selection for Simplicial Approximation

In the computational geometry field, simplicial complexes have been used to describe an underlying geometric shape knowing a point cloud sampled on it. In this article, an adequate statistical framework is first proposed for the choice of a simplicial complex among a parametrized family. A least-squares penalized criterion is introduced to choose a complex, and a model selection theorem states how to select the “best” model, from a statistical point of view. This result gives the shape of the penalty, and then the “slope heuristics method” is used to calibrate the penalty from the data. Some experimental studies on simulated and real datasets illustrate the method for the selection of graphs and simplicial complexes of dimension two.     

Ads Manifolds With Particles and Earthquakes on Singular Surfaces

We prove two related results. The first is an “earthquake theorem” for closed hyperbolic surfaces with cone singularities where the total angle is less than π: any two such metrics in are connected by a unique left earthquake. The second result is that the space of “globally hyperbolic” AdS manifolds with “particles” – cone singularities (of given angle) along time-like lines – is parametrized by the product of two copies of the Teichmüller space with some marked points (corresponding to the cone singularities). The two statements are proved together. F.B. was partially supported by the A.N.R. project GEODYCOS. J.-M.S. was partially supported by the A.N.R. programs RepSurf, 2006-09, ANR-06-BLAN-0311, GeomEinstein, 2006-09, 06-BLAN-0154, and FOG, 2007-10, ANR-07-BLAN-0251-01.     

The Geometry of Standard Deontic Logic

Whereas geometrical oppositions (logical squares and hexagons) have been so far investigated in many fields of modal logic (both abstract and applied), the oppositional geometrical side of “deontic logic” (the logic of “obligatory”, “forbidden”, “permitted”, . . .) has rather been neglected. Besides the classical “deontic square” (the deontic counterpart of Aristotle’s “logical square”), some interesting attempts have nevertheless been made to deepen the geometrical investigation of the deontic oppositions: Kalinowski (La logique des normes, PUF, Paris, 1972) has proposed a “deontic hexagon” as being the geometrical representation of standard deontic logic, whereas Joerden (jointly with Hruschka, in Archiv für Rechtsund Sozialphilosophie 73:1, 1987), McNamara (Mind 105:419, 1996) and Wessels (Die gute Samariterin. Zur Struktur der Supererogation, Walter de Gruyter, Berlin, 2002) have proposed some new “deontic polygons” for dealing with conservative extensions of standard deontic logic internalising the concept of “supererogation”. Since 2004 a new formal science of the geometrical oppositions inside logic has appeared, that is “n-opposition theory”, or “NOT”, which relies on the notion of “logical bi-simplex of dimension m” (m = n − 1). This theory has received a complete mathematical foundation in 2008, and since then several extensions. In this paper, by using it, we show that in standard deontic logic there are in fact many more oppositional deontic figures than Kalinowski’s unique “hexagon of norms” (more ones, and more complex ones, geometrically speaking: “deontic squares”, “deontic hexagons”, “deontic cubes”, . . ., “deontic tetraicosahedra”, . . .): the real geometry of the oppositions between deontic modalities is composed by the aforementioned structures (squares, hexagons, cubes, . . ., tetraicosahedra and hyper-tetraicosahedra), whose complete mathematical closure happens in fact to be a “deontic 5-dimensional hyper-tetraicosahedron” (an oppositional very regular solid).      

Interaction dynamics of two reinforcement learners

The paper investigates a stochastic model where two agents (persons, companies, institutions, states, software agents or other) learn interactive behavior in a series of alternating moves. Each agent is assumed to perform “stimulus-response-consequence” learning, as studied in psychology. In the presented model, the response of one agent to the other agent's move is both the stimulus for the other agent's next move and part of the consequence for the other agent's previous move. After deriving general properties of the model, especially concerning convergence to limit cycles, we concentrate on an asymptotic case where the learning rate tends to zero (“slow learning”). In this case, the dynamics can be described by a system of deterministic differential equations. For reward structures derived from [2×2] bimatrix games, fixed points are determined, and for the special case of the prisoner's dilemma, the dynamics is analyzed in more detail on the assumptions that both agents start with the same or with different reaction probabilities.     

Gap orders of rational functions on plane curves with few singular points

We prove that certain integers n cannot occur as degrees of linear series without base points on the normalization of a plane curve whose only singularities are a “small” number of nodes and ordinary cusps. As a consequence we compute the gonality of such a curve. Work done with financial support of M.U.R.S.T. while the authors were members of C.N.R.