How weak categorizers based upon different principles strengthen performance

Combining the results of classifiers has shown much promise in machine learning generally. However, published work on combining text categorizers suggests that, for this particular application, improvements in performance are hard to attain. Explorative research using a simple voting system is presented and discussed in the light of a probabilistic model that was originally developed for safety critical software. It was found that typical categorization approaches produce predictions which are too similar for combining them to be effective since they tend to fail on the same records. Further experiments using two less orthodox categorizers are also presented which suggest that combining text categorizers can be successful, provided the essential element of ‘difference’ is considered.

Impact of suspected food allergy on emotional distress and family life of parents prior to allergy diagnosis

Background: Food allergy is associated with psychological distress in both child and parent. It is unknown whether parental distress is present prior to clinical diagnosis or whether experiences at clinic can reduce any distress present. This study aimed to assess anxiety and depression in parents and the impact of suspected food allergy on the lives of families before and after a visit to an allergy clinic. Methods: One hundred and twenty-four parents visiting an allergy clinic for the first time to have their child assessed for food allergy completed a study-specific questionnaire and the Hospital Anxiety and Depression Scale; 50 parents completed these 4-6 wk later in their own home. Results: Most parents (86.4%) reported suspected food allergy had an impact on their family life prior to clinic attendance; 76% had made changes to their child's diet. 32.5% of parents had mild-to-severe anxiety before their clinic visit; 17.5% had mild-to-moderate depression. Post-clinic, 40% had mild-to-severe anxiety; 13.1% had mild-to-moderate depression. There were no significant differences in anxiety (p = 0.34) or depression scores (p = 0.09) before and after the clinic visit. Conclusions: Anxiety and depression is present in a small proportion of parents prior to diagnosis of food allergy in their child and this does not reduce in the short term after the clinic visit. Identification of parents at risk of suffering from distress is needed and ways in which we communicate allergy information before and at clinic should be investigated to see if we can reduce distress. © 2013 John Wiley & Sons A/S. Published by John Wiley & Sons Ltd.

A weakly-supervised Bayesian model for violence detection from social media

Social streams have proven to be the mostup-to-date and inclusive information on cur-rent events. In this paper we propose a novelprobabilistic modelling framework, called violence detection model (VDM), which enables the identification of text containing violent content and extraction of violence-related topics over social media data. The proposed VDM model does not require any labeled corpora for training, instead, it only needs the in-corporation of word prior knowledge which captures whether a word indicates violence or not. We propose a novel approach of deriving word prior knowledge using the relative entropy measurement of words based on the in-tuition that low entropy words are indicative of semantically coherent topics and therefore more informative, while high entropy words indicates words whose usage is more topical diverse and therefore less informative. Our proposed VDM model has been evaluated on the TREC Microblog 2011 dataset to identify topics related to violence. Experimental results show that deriving word priors using our proposed relative entropy method is more effective than the widely-used information gain method. Moreover, VDM gives higher violence classification results and produces more coherent violence-related topics compared toa few competitive baselines.

Examples Illustrating some Aspects of the Weak Deligne-Simpson Problem

Research partially supported by INTAS grant 97-1644

Weak Polynomial Identities for M1,1(E)

* Partially supported by Universita` di Bari: progetto “Strutture algebriche, geometriche e descrizione degli invarianti ad esse associate”.

Strong-weak Stackelberg Problems in Finite Dimensional Spaces

We are concerned with two-level optimization problems called strongweak Stackelberg problems, generalizing the class of Stackelberg problems in the strong and weak sense. In order to handle the fact that the considered two-level optimization problems may fail to have a solution under mild assumptions, we consider a regularization involving ε-approximate optimal solutions in the lower level problems. We prove the existence of optimal solutions for such regularized problems and present some approximation results when the parameter ǫ goes to zero. Finally, as an example, we consider an optimization problem associated to a best bound given in [2] for a system of nondifferentiable convex inequalities.

Radon Measures on Banach Spaces with their Weak Topologies

The main concern of this paper is to present some improvements to results on the existence or non-existence of countably additive Borel measures that are not Radon measures on Banach spaces taken with their weak topologies, on the standard axioms (ZFC) of set-theory. However, to put the results in perspective we shall need to say something about consistency results concerning measurable cardinals.

Emotions and a Prior Knowledge Representation in Artificial General Intelligence

In this paper a prior knowledge representation for Artificial General Intelligence is proposed based on fuzzy rules using linguistic variables. These linguistic variables may be produced by neural network. Rules may be used for generation of basic emotions – positive and negative, which influence on planning and execution of behavior. The representation of Three Laws of Robotics as such prior knowledge is suggested as highest level of motivation in AGI.

Weak form equation–based finite-element modeling of viscoelastic asphalt mixtures

The objective of this study is to demonstrate using weak form partial differential equation (PDE) method for a finite-element (FE) modeling of a new constitutive relation without the need of user subroutine programming. The viscoelastic asphalt mixtures were modeled by the weak form PDE-based FE method as the examples in the paper. A solid-like generalized Maxwell model was used to represent the deforming mechanism of a viscoelastic material, the constitutive relations of which were derived and implemented in the weak form PDE module of Comsol Multiphysics, a commercial FE program. The weak form PDE modeling of viscoelasticity was verified by comparing Comsol and Abaqus simulations, which employed the same loading configurations and material property inputs in virtual laboratory test simulations. Both produced identical results in terms of axial and radial strain responses. The weak form PDE modeling of viscoelasticity was further validated by comparing the weak form PDE predictions with real laboratory test results of six types of asphalt mixtures with two air void contents and three aging periods. The viscoelastic material properties such as the coefficients of a Prony series model for the relaxation modulus were obtained by converting from the master curves of dynamic modulus and phase angle. Strain responses of compressive creep tests at three temperatures and cyclic load tests were predicted using the weak form PDE modeling and found to be comparable with the measurements of the real laboratory tests. It was demonstrated that the weak form PDE-based FE modeling can serve as an efficient method to implement new constitutive models and can free engineers from user subroutine programming.

Soliton's eigenvalue based analysis on the generation mechanism of rogue wave phenomenon in optical fibers exhibiting weak third order dispersion

One of the extraordinary aspects of nonlinear wave evolution which has been observed as the spontaneous occurrence of astonishing and statistically extraordinary amplitude wave is called rogue wave. We show that the eigenvalues of the associated equation of nonlinear Schrödinger equation are almost constant in the vicinity of rogue wave and we validate that optical rogue waves are formed by the collision between quasi-solitons in anomalous dispersion fiber exhibiting weak third order dispersion.

Weak Compatibility and Common Fixed Point Theorems for A-Contractive and E-expansive Maps in Uniform Spaces

2000 Mathematics Subject Classification: 47H10, 54E15.

Weak Ergodicity of Mt /Mt /N /N + R Queue

2000 Mathematics Subject Classification: 60J27, 60K25.

Weak Convergence to the Tangent Process of the Linear Multifractional Stable Motion

2000 Mathematics Subject Classification: 60G18, 60E07

SG Pseudo-Differential Operators and Weak Hyperbolicity

2002 Mathematics Subject Classification: 35S05, 47G30, 58J42.