Experimental and numerical investigation of fracture in double-edge notched steel plates

Double-edge notched (DENT) steel plates were pulled until complete fracture and several experimental observations were made (using profilometry and scanning electron microscopy). The essential work of fracture (EWF) model was found to be well verified. Numerical simulations—up to the maximum load only—of some experiments were performed using the finite element method (FEM), and incorporating geometric and material non-linearities (large deformation elasto-plasticity). Some experimental measurements were compared with the corresponding numerical computations and excellent agreement was found.     

Controlled oxidation of methane doped catalysts irradiated by microwaves

The oxidative coupling of methane has been studied on a (SmLiO₂)_0.8(CaOMgO)_0.2 catalyst by using two different modes of heating: a conventional oven and a microwave irradiation set-up. The C₂ selectivity obtained with microwave heating was much higher than with conventional heating especially at low conversions. This difference could arise from the reduction of oxidation products (ethane, ethylene) in the gas phase under microwave irradiation.     

FuzzyBagging: A novel ensemble of classifiers

In this work, a new method for the creation of classifier ensembles is introduced. The patterns are partitioned into clusters to group together similar patterns, a training set is built using the patterns that belong to a cluster. Each of the new sets is used to train a classifier. We show that the approach here presented, called FuzzyBagging, obtains performance better than Bagging.     

Comparison among feature extraction methods for HIV-1 protease cleavage site prediction

Recently, several works have approached the HIV-1 protease specificity problem by applying a number of methods from the field of machine learning. However, it is still difficult for researchers to choose the best method due to the lack of an effective comparison. For the first time we have made an extensive study on methods for feature extraction for the problem of HIV-1 protease. We show that a fusion of classifiers trained in different feature spaces permits to obtain a drastically error reduction with respect to the performance of the state-of-the-art.     

Learning Temperature Dynamics on Agar-Based Phantom Tissue Surface During Single Point CO $$_2$$ 2 Laser Exposure

Neural Processing Letters - This paper presents an approach to determine a model of superficial tissue temperature dynamics during continuous wave CO $$_2$$ laser irradiation. The main contribution...     

Clinical, morphologic and immunophenotypic data based on 10 cases of canine muco-cutaneous epidermotropic T-lymphoma (analogous to Mycosis Funcgo?de). Important of an animal model of spontaneous pathology

Our serie of ten canine cutaneous epitheliotropic T-cell lymphomas (CTCL), is found in old dogs, belonging mainly to the Boxer breed. Site on the mucous membranes (especially buccal), the muco-cutaneous junctions, their clinical expression is polymorphous. Lesions, follow on one after another (erythema, plaques, nodules) and are diversely associated in a given animal, the borders between the different stages often being difficult to establish. Adenopathies noted at the time of the diagnosis or during the course of the condition are accompanied by an involvement of the blood and organs (analogous to Sézary's disease). The progression of the disease can be very rapid in the buccal forms, which are generally aggressive, and in cases of violent, uncontrollable pruritus, which may be disturbing for the owner (with requests for euthanasia). The neoplastic infiltrate is constituted of small lymphocytes with hyperchromatic, convoluted nuclei (incipient stages), then large cells with a "histiocytic" appearance for the nodules. Epitheliotropism, which is maximal for the infiltrated plaque stage, shows up either in the form of a flux of totally epitheliotropic isolated cells (Ketron-Goodman type) or in that of Pautrier abscess-like collections. THe veterinary literature is in agreement that the CTCL cell expresses CD3, but two recent studies are in contradiction as regards its membership of helper or cytotoxic/suppressor populations. For our 10 cases, all the cells of lymphocytic morphology were, without exception, CD3+ and CD45+, irrespective of their situation within the epithelium or the chorion. The CD3+ cells in the epithelium were systematically CD8+, CD4- (confirming P.F. Moore's observations), expressing CD5 in a variable way, and, mostly, the Ki-67 nuclear proliferation Ag. The CD3+ cells of the chorion were exclusively, or mainly, CD8+, and occasionally CD4+. They expressed CD5 in a variable way, and, for a minority, the Ki-67 nuclear proliferation Ag. On the pathogenic level, it may be suggested that a T clone, CD8+, undergoes the "homing" phenomenon within the epithelium, enters the cell cycle, then manifests a tropism towards the chorion, which it infiltrates. Despite some particularities, which may be clinical (serious mucous attacks), cytological (the "histiocytic" appearance of the nodule cells) or immunophenotypic (expression of CD8, similar to what is observed in man in a considerable number of Pagetoid reticulosis), CTCL constitutes an interesting model of spontaneous pathology, and could prove useful in: - identifying various etiological factors (given that the dog, as a close commensal of man, is subject to the same environmental factors).     

The role of spectral resolution and classifier complexity in the analysis of hyperspectral images of forest areas

Remote sensing hyperspectral sensors are important and powerful instruments for addressing classification problems in complex forest scenarios, as they allow one a detailed characterization of the spectral behavior of the considered information classes. However, the processing of hyperspectral data is particularly complex both from a theoretical viewpoint [e.g. problems related to the Hughes phenomenon (Hughes, 1968) and from a computational perspective. Despite many previous investigations that have been presented in the literature on feature reduction and feature extraction in hyperspectral data, only a few studies have analyzed the role of spectral resolution on the classification accuracy in different application domains. In this paper, we present an empirical study aimed at understanding the relationship among spectral resolution, classifier complexity, and classification accuracy obtained with hyperspectral sensors for the classification of forest areas. We considered two different test sets characterized by images acquired by an AISA Eagle sensor over 126 bands with a spectral resolution of 4.6 nm, and we subsequently degraded its spectral resolution to 9.2, 13.8, 18.4, 23, 27.6, 32.2 and 36.8 nm. A series of classification experiments were carried out with bands at each of the degraded spectral resolutions, and bands selected with a feature selection algorithm at the highest spectral resolution (4.6 nm). The classification experiments were carried out with three different classifiers: Support Vector Machine, Gaussian Maximum Likelihood with Leave-One-Out-Covariance estimator, and Linear Discriminant Analysis. From the experimental results, important conclusions can be made about the choice of the spectral resolution of hyperspectral sensors as applied to forest areas, also in relation to the complexity of the adopted classification methodology. The outcome of these experiments are also applicable in terms of directing the user towards a more efficient use of the current instruments (e.g. programming of the spectral channels to be acquired) and classification techniques in forest applications, as well as in the design of future hyperspectral sensors.     

A multi-matcher system based on knuckle-based features

We describe a new multi-matcher biometric approach, using knuckle-based features extracted from the middle finger and from the ring finger, with fusion applied at the matching-score level. The features extraction is performed by Radon transform and by Haar wavelet, then these features are transformed by non-linear Fisher transform. Finally, the matching process is based on Parzen window classifiers. Moreover, we study a method based on tokenised pseudo-random numbers and user specific knuckle features. The experimental results show the effectiveness of the system in terms of equal error rate (EER) (near zero equal error rate).

Machine learning multi-classifiers for peptide classification

In this paper, we study the performance improvement that it is possible to obtain combining classifiers based on different notions (each trained using a different physicochemical property of amino-acids). This multi-classifier has been tested in three problems: HIV-protease; recognition of T-cell epitopes; predictive vaccinology. We propose a multi-classifier that combines a classifier that approaches the problem as a two-class pattern recognition problem and a method based on a one-class classifier. Several classifiers combined with the “sum rule” enables us to obtain an improvement performance over the best results previously published in the literature.

A simple method for improving local binary patterns by considering non-uniform patterns

The basic idea behind LBP is that an image is composed of micropatterns. A histogram of these micropatterns contains information about the local features in an image. These micropatterns can be divided into two types: uniform and non-uniform. In standard applications using LBP, only the uniform patterns are used. The non-uniform patterns are considered in only a single bin of the histogram that is used to extract features in the classification stage. Non-uniform patterns have undesirable characteristics: they are of a high dimension, partially correlated, and introduce unwanted noise. To offset these disadvantages, we explore using random subspace, well-known to work well with noise and correlated features, to train features based also on non-uniform patterns. We find that a stand-alone support vector machine performs best with the uniform patterns and random subspace with histograms of 50 bins performs best with the non-uniform patterns. Superior results are obtained when the two are combined. Based on extensive experiments conducted in several domains using several benchmark databases, it is our conclusion that non-uniform patterns improve classifier performance.