Feature Selection, Ranking of Each Feature and Classification for the Diagnosis of Community Acquired Legionella Pneumonia

Diagnosis of community acquired legionella pneumonia (CALP) is currently performed by means of laboratory techniques which may delay diagnosis several hours. To determine whether ANN can categorize CALP and non-legionella community-acquired pneumonia (NLCAP) and be standard for use by clinicians, we prospectively studied 203 patients with community-acquired pneumonia (CAP) diagnosed by laboratory tests. Twenty one clinical and analytical variables were recorded to train a neural net with two classes (LCAP or NLCAP class). In this paper we deal with the problem of diagnosis, feature selection, and ranking of the features as a function of their classification importance, and the design of a classifier the criteria of maximizing the ROC (Receiving operating characteristics) area, which gives a good trade-off between true positives and false negatives. In order to guarantee the validity of the statistics; the train-validation-test databases were rotated by the jackknife technique, and a multistarting procedure was done in order to make the system insensitive to local maxima.

Analysis of bulk and surface contributions in the neutron skin of nuclei

The neutron skin thickness of nuclei is a sensitive probe of the nuclear symmetry energy and has multiple implications for nuclear and astrophysical studies. However, precision measurements of this observable are difficult to obtain. The analysis of the experimental data may imply some assumptions about the bulk or surface nature of the formation of the neutron skin. Here we study the bulk or surface character of neutron skins of nuclei following from calculations with Gogny, Skyrme, and covariant nuclear mean-field interactions. These interactions are successful in describing nuclear charge radii and binding energies but predict different values for neutron skins. We perform the study by fitting two-parameter Fermi distributions to the calculated self-consistent neutron and proton densities. We note that the equivalent sharp radius is a more suitable reference quantity than the half-density radius parameter of the Fermi distributions to discern between the bulk and surface contributions in neutron skins. We present calculations for nuclei in the stability valley and for the isotopic chains of Sn and Pb.

Neutron skin of 208Pb, nuclear symmetry energy, and the parity radius experiment

A precise determination of the neutron skin thickness of a heavy nucleus sets a basic constraint on the nuclear symmetry energy (the neutron skin thickness is the difference of the neutron and proton rms radii of the nucleus). The parity radius experiment (PREX) may achieve it by electroweak parity-violating electron scattering (PVES) on 208Pb. We investigate PVES in nuclear mean field approach to allow the accurate extraction of the neutron skin thickness of 208Pb from the parity-violating asymmetry probed in the experiment. We demonstrate a high linear correlation between the parity-violating asymmetry and the neutron skin thickness in successful mean field forces as the best means to constrain the neutron skin of 208Pb from PREX, without assumptions on the neutron density shape. Continuation of the experiment with higher precision in the parity-violating asymmetry is motivated since the present method can support it to constrain the density slope of the nuclear symmetry energy to new accuracy.

The fossil crown wasp Electrostephanus petiolatus Brues in Baltic Amber (Hymenoptera, Stephanidae): designation of a neotype, revised classification,and a key to amber Stephanidae.

The fossil crown wasp Electrostephanus petiolatus Brues comb. rev.(Stephanidae, Electrostephaninae) is re-described from a single male preserved in middle Eocene Baltic Amber. The holotype was lost or destroyed around the time of World War II and subsequent interpretations of its identity have been based solely on the brief descriptive comments provided by Brues in his original account. The new specimen matches the original description and illustration provided by Brues in every detail and we hereby consider them to be conspecific, selecting the specimen as a neotype for the purpose of stabilizing the nomenclature for this fossil species. This neotype exhibits a free first metasomal tergum and sternum, contrary to the assertion of previous workers who indicated these to be fused. Accordingly, this species does indeed belong to the genus Electrostephanus Brues rather than to Denaeostephanus Engel & Grimaldi (Stephaninae). Electrostephanus petiolatus is transferred to a new subgenus, Electrostephanodes n. subgen. , based on its elongate pseudo- petiole and slender gaster, but may eventually warrant generic status as the phylogenetic placement of these fossil lineages continues to be clarifi ed. A revised key to the Baltic amber crown wasps is provided.

New cationic nanovesicular systems containing lysine-based surfactants for topical administration: Toxicity assessment using representative skin cell lines

Many strategies for treating diseases require the delivery of drugs into the cell cytoplasm following internalization within endosomal vesicles. Thus, compounds triggered by low pH to disrupt membranes and release endosomal contents into the cytosol are of particular interest. Cationic nanovesicles have attracted considerable interest as effective carriers to improve the delivery of biologically active molecules into and through the skin. In this study, lipid-based nanovesicles containing three different cationic lysine-based surfactants were designed for topical administration. We used representative skin cell lines and in vitro assays to assess whether the cationic compounds modulate the toxic responses of these nanocarriers. The nanovesicles were characterized in both water and cell culture medium. In general, significant agglomeration occurred after 24 h incubation under cell culture conditions. We found different cytotoxic responses among the formulations, which depended on the surfactant,cell line (3T3, HaCaT, and THP-1) and endpoint assayed (MTT, NRU, and LDH). Moreover, no potential phototoxicity was detected in fibroblast or keratinocyte cells, whereas only a slight inflammatory response was induced, as detected by IL-1a and IL-8 production in HaCaT and THP-1 cell lines, respectively. A key finding of our research was that the cationic charge position and the alkyl chain length of the surfactants determine the nanovesicles resulting toxicity. The charge on the a-amino group of lysine increased the depletion of cell metabolic activity, as determined by the MTT assay, while a higher hydrophobicity tends to enhance the toxic responses of the nanovesicles. The insights provided here using different cell lines and assays offer a comprehensive toxicological evaluation of this group of new nanomaterials.

Estimations of topographically correct regeneration to nerve branches and skin after peripheral nerve injury and repair.

Peripheral nerve injury is typically associated with long-term disturbances in sensory localization, despite nerve repair and regeneration. Here, we investigate the extent of correct reinnervation by back-labeling neuronal soma with fluorescent tracers applied in the target area before and after sciatic nerve injury and repair in the rat. The subpopulations of sensory or motor neurons that had regenerated their axons to either the tibial branch or the skin of the third hindlimb digit were calculated from the number of cell bodies labeled by the first and/or second tracer. Compared to the normal control side, 81% of the sensory and 66% of the motor tibial nerve cells regenerated their axons back to this nerve, while 22% of the afferent cells from the third digit reinnervated this digit. Corresponding percentages based on quantification of the surviving population on the experimental side showed 91%, 87%, and 56%, respectively. The results show that nerve injury followed by nerve repair by epineurial suture results in a high but variable amount of topographically correct regeneration, and that proportionally more neurons regenerate into the correct proximal nerve branch than into the correct innervation territory in the skin

Classification models for neurocognitive impairment in HIV infection based on demographic and clinical variables

Objective: We used demographic and clinical data to design practical classification models for prediction of neurocognitive impairment (NCI) in people with HIV infection. Methods: The study population comprised 331 HIV-infected patients with available demographic, clinical, and neurocognitive data collected using a comprehensive battery of neuropsychological tests. Classification and regression trees (CART) were developed to btain detailed and reliable models to predict NCI. Following a practical clinical approach, NCI was considered the main variable for study outcomes, and analyses were performed separately in treatment-naïve and treatment-experienced patients. Results: The study sample comprised 52 treatment-naïve and 279 experienced patients. In the first group, the variables identified as better predictors of NCI were CD4 cell count and age (correct classification [CC]: 79.6%, 3 final nodes). In treatment-experienced patients, the variables most closely related to NCI were years of education, nadir CD4 cell count, central nervous system penetration-effectiveness score, age, employment status, and confounding comorbidities (CC: 82.1%, 7 final nodes). In patients with an undetectable viral load and no comorbidities, we obtained a fairly accurate model in which the main variables were nadir CD4 cell count, current CD4 cell count, time on current treatment, and past highest viral load (CC: 88%, 6 final nodes). Conclusion: Practical classification models to predict NCI in HIV infection can be obtained using demographic and clinical variables. An approach based on CART analyses may facilitate screening for HIV-associated neurocognitive disorders and complement clinical information about risk and protective factors for NCI in HIV-infected patients.

Classification of textures seen from different distances and under varying illumination direction

Changes in the angle of illumination incident upon a 3D surface texture can significantly alter its appearance, implying variations in the image texture. These texture variations produce displacements of class members in the feature space, increasing the failure rates of texture classifiers. To avoid this problem, a model-based texture recognition system which classifies textures seen from different distances and under different illumination directions is presented in this paper. The system works on the basis of a surface model obtained by means of 4-source colour photometric stereo, used to generate 2D image textures under different illumination directions. The recognition system combines coocurrence matrices for feature extraction with a Nearest Neighbour classifier. Moreover, the recognition allows one to guess the approximate direction of the illumination used to capture the test image

A new approach to the classification of mammographic masses and normal breast tissue

A new approach to mammographic mass detection is presented in this paper. Although different algorithms have been proposed for such a task, most of them are application dependent. In contrast, our approach makes use of a kindred topic in computer vision adapted to our particular problem. In this sense, we translate the eigenfaces approach for face detection/classification problems to a mass detection. Two different databases were used to show the robustness of the approach. The first one consisted on a set of 160 regions of interest (RoIs) extracted from the MIAS database, being 40 of them with confirmed masses and the rest normal tissue. The second set of RoIs was extracted from the DDSM database, and contained 196 RoIs containing masses and 392 with normal, but suspicious regions. Initial results demonstrate the feasibility of using such approach with performances comparable to other algorithms, with the advantage of being a more general, simple and cost-effective approach

Using appearance and context for outdoor scene object classification

We propose a probabilistic object classifier for outdoor scene analysis as a first step in solving the problem of scene context generation. The method begins with a top-down control, which uses the previously learned models (appearance and absolute location) to obtain an initial pixel-level classification. This information provides us the core of objects, which is used to acquire a more accurate object model. Therefore, their growing by specific active regions allows us to obtain an accurate recognition of known regions. Next, a stage of general segmentation provides the segmentation of unknown regions by a bottom-strategy. Finally, the last stage tries to perform a region fusion of known and unknown segmented objects. The result is both a segmentation of the image and a recognition of each segment as a given object class or as an unknown segmented object. Furthermore, experimental results are shown and evaluated to prove the validity of our proposal

Influence of the single-particle structure on the nuclear surface and the neutron skin

We analyze the influence of the single-particle structure on the neutron density distribution and the neutron skin in Ca, Ni, Zr, Sn, and Pb isotopes. The nucleon density distributions are calculated in the Hartree-Fock+BCS approach with the SLy4 Skyrme force. A close correlation is found between the quantum numbers of the valence neutrons and the changes in the position and the diffuseness of the nuclear surface, which in turn affect the neutron skin thickness. Neutrons in the valence orbitals with low principal quantum number and high angular momentum mainly displace the position of the neutron surface outwards, while neutrons with high principal quantum number and low angular momentum basically increase the diffuseness of the neutron surface. The impact of the valence shell neutrons on the tail of the neutron density distribution is discussed.

A Method for Sky-Condition Classification from Ground-Based Solar Radiation Measurements

Identification of clouds from satellite images is now a routine task. Observation of clouds from the ground, however, is still needed to acquire a complete description of cloud conditions. Among the standard meteorologicalvariables, solar radiation is the most affected by cloud cover. In this note, a method for using global and diffuse solar radiation data to classify sky conditions into several classes is suggested. A classical maximum-likelihood method is applied for clustering data. The method is applied to a series of four years of solar radiation data and human cloud observations at a site in Catalonia, Spain. With these data, the accuracy of the solar radiation method as compared with human observations is 45% when nine classes of sky conditions are to be distinguished, and it grows significantly to almost 60% when samples are classified in only five different classes. Most errors are explained by limitations in the database; therefore, further work is under way with a more suitable database