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.

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.

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.

Fertilizing Methods and Nutrient Balance at the End of Traditional Organic Agriculture in the Mediterranean Bioregion: Catalonia (Spain) in the 1860s

By reconstructing the nutrient balance of a Catalan v illage circa 1861-65 we examine the sustainability of organic agricultural sy stems in the northwest Mediterranean bioregion prior to the green rev olution and the question of whether the nutrients extracted f rom the soil were replenished. With a population density of 59 inhabitants per square km, similar to other northern European rural areas at that time, and a lower liv estock density per cropland unit, this v illage experienced a manure shortage. The gap was f illed by other labour-intensiv e way s of transf erring nutrients f rom uncultiv ated areas into the cropland. Key elements in this agricultural sy stem were v iney ards because they hav e f ew nutrient requirements, and woodland and scrublands as sources of relev ant amounts of nutrients collected in sev eral ways.

Headspace needle-trap analysis of priority volatile organic compounds from aqueous samples: application to the analysis of natural and waste waters

Combining headspace (HS) sampling with a needle-trap device (NTD) to determine priority volatile organic compounds (VOCs) in water samples results in improved sensitivity and efficiency when compared to conventional static HS sampling. A 22 gauge stainless steel, 51-mm needle packed with Tenax TA and Carboxen 1000 particles is used as the NTD. Three different HS-NTD sampling methodologies are evaluated and all give limits of detection for the target VOCs in the ng L−1 range. Active (purge-and-trap) HS-NTD sampling is found to give the best sensitivity but requires exhaustive control of the sampling conditions. The use of the NTD to collect the headspace gas sample results in a combined adsorption/desorption mechanism. The testing of different temperatures for the HS thermostating reveals a greater desorption effect when the sample is allowed to diffuse, whether passively or actively, through the sorbent particles. The limits of detection obtained in the simplest sampling methodology, static HS-NTD (5 mL aqueous sample in 20 mL HS vials, thermostating at 50 °C for 30 min with agitation), are sufficiently low as to permit its application to the analysis of 18 priority VOCs in natural and waste waters. In all cases compounds were detected below regulated levels

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

A Headspace needle-trap method for the analysis of volatile organic compounds in whole blood

Needle trap devices (NTDs) are a relatively new and promising tool for headspace (HS) analysis. In this study, a dynamic HS sampling procedure is evaluated for the determination of volatile organic compounds (VOCs) in whole blood samples. A full factorial design was used to evaluate the influence of the number of cycles and incubation time and it is demonstrated that the controlling factor in the process is the number of cycles. A mathematical model can be used to determine the most appropriate number of cycles required to adsorb a prefixed amount of VOCs present in the HS phase whenever quantitative adsorption is reached in each cycle. Matrix effect is of great importance when complex biological samples, such as blood, are analyzed. The evaluation of the salting out effect showed a significant improvement in the volatilization of VOCs to the HS in this type of matrices. Moreover, a 1:4 (blood:water) dilution is required to obtain quantitative recoveries of the target analytes when external calibration is used. The method developed gives detection limits in the 0.020–0.080 μg L−1 range (0.1–0.4 μg L−1 range for undiluted blood samples) with appropriate repeatability values (RSD < 15% at high level and <23% at LOQ level). Figure of merits of the method can be improved by using a smaller phase ratio (i.e., an increase in the blood volume and a decrease in the HS volume), which lead to lower detection limits, better repeatability values and greater sensibility. Twenty-eight blood samples have been evaluated with the proposed method and the results agree with those indicated in other studies. Benzene was the only target compound that gave significant differences between blood levels detected in volunteer non-smokers and smokers

Organic chicken product authentication: state-of-the-art and future perspectives

Organic food products are highly susceptible to fraud. Currently, administrative controls are conducted to detect fraud, but having an analytical tool able to verify the organic identity of food would be very supportive. The state-of-the-art in food authentication relies on fingerprinting approaches that find characteristic analytical patterns to unequivocally identify authentic products. While wide research on authentication has been conducted for other commodities, the authentication of organic chicken products is still in its infancy. Challenges include finding fingerprints to discriminate organic from conventional products, and recruiting sample sets that cover natural variability. Future research might be oriented towards developing new authentication models for organic feed, eggs and chicken meat, keeping models updated and implementing them into regulations. Meanwhile, these models might be very supportive to the administrative controls directing inspections towards suspicious fraudulent samples.

The influence of substratum type and nutrient supply on biofilm organic matter utilization in streams

We investigated the effect of benthic substratum type (sand and rocks) and nutrient supply (N and P) on biofilm structure and heterotrophic metabolism in a field experiment in a forested Mediterranean stream (Fuirosos). Rock and sand colonization and biofilm formation was intensively studied for 44 d at two stream reaches: control and experimental (continuous addition of phosphate, ammonia, and nitrate). Structural (C, N, and polysaccharide content and bacterial and chlorophyll density) and metabolic biofilm parameters (b-glucosidase, peptidase, and phosphatase enzyme activities) were analyzed throughout the colonization process. The epilithic biofilm (grown on rocks) had a higher peptidase activity at the impacted reach, together with a higher algal and bacterial biomass. The positive relationship between the peptidase activity per cell and the N content of the epilithic biofilm suggested that heterotrophic utilization of proteinaceous compounds from within the biofilm was occurring. In contrast, nutrient addition caused the epipsammic biofilm (grown on sand) to exhibit lower b-glucosidase and phosphatase activities, without a significant increase in bacterial and algal biomass. The differential response to nutrient addition was related to different structural characteristics within each biofilm. The epipsammic biofilm had a constant and high C:N ratio (22.7) throughout the colonization. The epilithic biofilm had a higher C:N ratio at the beginning of the colonization (43.2) and evolved toward a more complex structure (high polysaccharide content and low C:N ratio) during later stages. The epipsammic biofilm was a site for the accumulation and degradation of organic matter: polysaccharides and organic phosphorus compounds had higher degradation activities

Hydrology, light and the use of organic and inorganic materials as structuring factors of biological communities in Mediterranean streams

Hydrological disturbances, light availability and nutrients are the most relevant factors determining the structure of the biological communities in Mediterranean rivers. While some hydrological disturbances are able to induce catastrophic effects, which may cause a complete reset in physical and biological conditions, continued enrichment or changes in light availability are factors leading to the progressive shift in the communities of autotrophs and heterotrophs in the systems. Primary production in Mediterranean streams shows relevant seasonal changes which mainly follows the variations in light availability. In most forested streams, the algal community is shade-adapted. Nutrient enrichment (especially phosphorus) leads to marked increases in primary production, but this increase is not lineal and there is a saturation of algal biomass even in the most enriched systems. The heterotrophs (bacteria, fungi) are related to the pattern of DOC availability (which most depends on the seasonal discharge and leaf fall dynamics) and to the available substrata in the stream. It has been repeatedly observed that shorttime increases of extracellular enzyme activities are related to the accumulation of autochthonous (algal) and/or allochthonous (leaves) organic matter on the streambed during spring and summer, this being more remarkable in dry than in wetter years. Flow reduction favours detritus concentration in pools, and the subsequent increase in the density and biomass of the macroinvertebrate community. In Mediterranean streams collectors are accounting for the highest density and biomass, this being more remarkable in the least permanent systems, in accordance with the effect of floods on the organic matter availability. Nutrients, through the effect on the primary producers, also affect the trophic food web in the streams by favouring the predominance of grazers

Organic carbon and nutrient (P, N) concentrations of water and sediment in several aquatic environment types of a Mediterranean coastal wetland (Empordà Wetlands, NE Iberian Peninsula)

Total sediment and water organic carbon and nutrient (nitrogen and phosphorus) concentrations of different environment types of a Mediterranean coastal wetland (temporary and brackish, temporary and freshwater, semi-permanent and brackish, and permanent and brackish basins) were analysed during two hydroperiods. A nitrogen limitation was found for both sediment and water. The total organic carbon concentration of the water was significantly related to the water level, which varies throughout the hydroperiods. In contrast, the total organic carbon concentration of the sediment was not related to water level. However, significant differences in total organic carbon of the sediment were found between hydroperiods. On the other hand, total organic carbon of the sediment varied spatially, being higher in temporary brackish basins with lower sand content, and lower in permanent and semi-permanent brackish basins with higher sand content

Distribution Patterns of Soil Properties in a Rural Mediterranean Area in Northeastern Spain

Soil properties on the Cap de Creus Peninsula, NE Spain depend primarily on scarce agricultural practices and early abandonment. In the study area, 90% of which is mainly covered by Cistus shrubs, 8 environments representing variations in land use/land cover and soil properties at different depths were identified. In each environment variously vegetated areas were selected and sampled. The soils, collected at different depths, were classified as Lithic Xerorthents according to the United States Department of Agriculture system of soil classification (USDA-NRCS 1975). Differences in soil properties were largely found according to the evolution of the plant canopy and the land use history. To identify underlying patterns in soil properties related to environmental evolution, factor analysis was performed and factor scores were used to determine how the factor patterns varied between soil variables, soil depths and selected environments. The three-factor model always accounted for 80% of the total variation in the data at the different soil depths. Organic matter was the more relevant soil property at 0–2 cm depth, whereas active minerals (silt and clay) were found to be the most relevant soil parameters controlling soil dynamics at the other depths investigated. Results showed that vineyards and olive tree soils are poorly developed and present worse conditions for mineral and organic compounds. Analysis of factor scores allowed independent assessment of soils, depth and plant cover and demonstrated that soils present the best physico-chemical characteristics under Erica arborea and meadows. In contrast, soils under Cistus monspeliensis were less nutrient rich and less well structured