Artificial neural networks applied for soil class prediction in mountainous landscape of the Serra do Mar¹

Soil information is needed for managing the agricultural environment. The aim of this study was to apply artificial neural networks (ANNs) for the prediction of soil classes using orbital remote sensing products, terrain attributes derived from a digital elevation model and local geology information as data sources. This approach to digital soil mapping was evaluated in an area with a high degree of lithologic diversity in the Serra do Mar. The neural network simulator used in this study was JavaNNS and the backpropagation learning algorithm. For soil class prediction, different combinations of the selected discriminant variables were tested: elevation, declivity, aspect, curvature, curvature plan, curvature profile, topographic index, solar radiation, LS topographic factor, local geology information, and clay mineral indices, iron oxides and the normalized difference vegetation index (NDVI) derived from an image of a Landsat-7 Enhanced Thematic Mapper Plus (ETM+) sensor. With the tested sets, best results were obtained when all discriminant variables were associated with geological information (overall accuracy 93.2 - 95.6 %, Kappa index 0.924 - 0.951, for set 13). Excluding the variable profile curvature (set 12), overall accuracy ranged from 93.9 to 95.4 % and the Kappa index from 0.932 to 0.948. The maps based on the neural network classifier were consistent and similar to conventional soil maps drawn for the study area, although with more spatial details. The results show the potential of ANNs for soil class prediction in mountainous areas with lithological diversity.

Imported Cattle Report, March 2012

The Imported Cattle report monthly by the Department of Agricultural.

Comparing the artificial neural network with parcial least squares for prediction of soil organic carbon and pH at different moisture content levels using visible and near-infrared spectroscopy

Visible and near infrared (vis-NIR) spectroscopy is widely used to detect soil properties. The objective of this study is to evaluate the combined effect of moisture content (MC) and the modeling algorithm on prediction of soil organic carbon (SOC) and pH. Partial least squares (PLS) and the Artificial neural network (ANN) for modeling of SOC and pH at different MC levels were compared in terms of efficiency in prediction of regression. A total of 270 soil samples were used. Before spectral measurement, dry soil samples were weighed to determine the amount of water to be added by weight to achieve the specified gravimetric MC levels of 5, 10, 15, 20, and 25 %. A fiber-optic vis-NIR spectrophotometer (350-2500 nm) was used to measure spectra of soil samples in the diffuse reflectance mode. Spectra preprocessing and PLS regression were carried using Unscrambler® software. Statistica® software was used for ANN modeling. The best prediction result for SOC was obtained using the ANN (RMSEP = 0.82 % and RPD = 4.23) for soil samples with 25 % MC. The best prediction results for pH were obtained with PLS for dry soil samples (RMSEP = 0.65 % and RPD = 1.68) and soil samples with 10 % MC (RMSEP = 0.61 % and RPD = 1.71). Whereas the ANN showed better performance for SOC prediction at all MC levels, PLS showed better predictive accuracy of pH at all MC levels except for 25 % MC. Therefore, based on the data set used in the current study, the ANN is recommended for the analyses of SOC at all MC levels, whereas PLS is recommended for the analysis of pH at MC levels below 20 %.

ORGANIC PHOSPHORUS FRACTIONS IN SOIL FERTILIZED WITH CATTLE MANURE

Inorganic phosphorus (Pi) usually controls the P availability in tropical soils, but the contribution of organic P (Po) should not be neglected, mainly in systems with low P input or management systems that promote organic matter accumulation. The aims of this study were to evaluate the changes in the Po fractions over time in soil fertilized and not fertilized with cattle manure and to correlate Po forms with available P extracted by anion exchange resin. The experiment was carried out under field conditions, in a sandy-clay loam Haplustox. The experimental design was a 2 × 9 randomized complete block factorial design, in which the first factor was manure application (20 t ha-1) or absence, and the second the soil sampling times (3, 7, 14, 21, 28, 49, 70, 91, and 112 days) after manure incorporation. Labile, moderately labile and non-labile Po fractions were determined in the soil material of each sampling. Manure fertilization increased the Po levels in the moderately labile and non-labile fractions and the total organic P, but did not affect the Po fraction proportions in relation to total organic P. On average, 5.1 % of total Po was in the labile, 44.4 % in the moderately labile and 50.5 % in the non-labile fractions. Available P (resin P) was more affected by the manure soluble Pi rather than by the labile Po forms. The labile and non-labile Po fractions varied randomly with no defined trend in relation to the samplings; for this reason, the data did not fit any mathematical model.

Guide Specification for Highway Construction Texturing Concrete Pavement for Reduced Tire/Pavement Noise using Artificial Turf Drag, March 1, 2011

This document provides language that can be used by an Owner-Agency to develop materials and construction specifications with the objective of reducing tire/pavement noise. While the practices described herein are largely prescriptive, they have been demonstrated to increase the likelihood of constructing a durable, quieter concrete surface. Guidance is provided herein for texturing the concrete surface since texture geometry has a paramount effect on tire/pavement noise. Guidance for curing is also provided to improve strength and durability of the surface mortar, and thus to improve texture durability.

Blood profile during and after hemoglobin substitute administration.

The in vivo effects of Diaspirin Crosslinked Hemoglobin (DCLHb, Baxter Healthcare Corp.) on hematology and biochemistry are unknown. This study includes 6 calves (71.2+/-1.3 kg). In each animal a total of 2 litres of blood was exchanged for the same amount of hydroxylethyl starch (Haes, Fresenius) (n=3) or DCLHb (n=3), which is equivalent to 28cc/kg of blood substitute, over a period of 5 hours. The animals were allowed to survive 7 days. Blood samples were taken hourly during the perfusion protocol, at postoperative day (POD) 1, 2 and 7. ANOVA test was used for repeated measurements. Blood cell profiles were similar in both groups. Peak methemoglobinemia was 4.2% in the DCLHb group. Osmolarity was significantly higher in the DCLHb group with the greatest difference at POD 1 and 2. Postmortem analysis of the major organs did not show any sign of hemoglobin deposit in the DCLHb group. In the given setup DCLHb can be administered in a large quantity with good hematological tolerance and without any deposits in major organs. A prolonged plasma expander effect was observed.

Artificial-Intelligence-Based Optimization of the Management of Snow Removal Assets and Resources Final Report, October 2002

Geographic information systems (GIS) and artificial intelligence (AI) techniques were used to develop an intelligent snow removal asset management system (SRAMS). The system has been evaluated through a case study examining snow removal from the roads in Black Hawk County, Iowa, for which the Iowa Department of Transportation (Iowa DOT) is responsible. The SRAMS is comprised of an expert system that contains the logical rules and expertise of the Iowa DOT’s snow removal experts in Black Hawk County, and a geographic information system to access and manage road data. The system is implemented on a mid-range PC by integrating MapObjects 2.1 (a GIS package), Visual Rule Studio 2.2 (an AI shell), and Visual Basic 6.0 (a programming tool). The system could efficiently be used to generate prioritized snowplowing routes in visual format, to optimize the allocation of assets for plowing, and to track materials (e.g., salt and sand). A test of the system reveals an improvement in snowplowing time by 1.9 percent for moderate snowfall and 9.7 percent for snowstorm conditions over the current manual system.

Imported Cattle Report, September 2012

The Imported Cattle report monthly by the Department of Agricultural.

Artificial muscle: the human chimera is the future.

Severe heart failure and cerebral stroke are broadly associated with the impairment of muscular function that conventional treatments struggle to restore. New technologies enable the construction of "smart" materials that could be of great help in treating diseases where the main problem is muscle weakness. These materials "behave" similarly to biological systems, because the material directly converts energy, for example electrical energy into movement. The extension and contraction occur silently like in natural muscles. The real challenge is to transfer this amazing technology into devices that restore or replace the mechanical function of failing muscle. Cardiac assist devices based on artificial muscle technology could envelope a weak heart and temporarily improve its systolic function, or, if placed on top of the atrium, restore the atrial kick in chronic atrial fibrillation. Artificial sphincters could be used to treat urinary incontinence after prostatectomy or faecal incontinence associated with stomas. Artificial muscles can restore the ability of patients with facial paralysis due to stroke or nerve injury to blink. Smart materials could be used to construct an artificial oesophagus including peristaltic movement and lower oesophageal sphincter function to replace the diseased oesophagus thereby avoiding the need for laparotomy to mobilise stomach or intestine. In conclusion, in the near future, smart devices will integrate with the human body to fill functional gaps due to organ failure, and so create a human chimera.

Enhanced polyhydroxyalkanoates accumulation by Halomonas spp. in artificial biofilms of alginate beads.

Microbial mats are complex but stable, multi-layered and multi-functional biofilms, which are the most frequent bacterial formations in nature. The functional strategies and physiological versatility of the bacterial populations growing in microbial mats allow bacteria to resist changing conditions within their environment. One of these strategies is the accumulation of carbon- and energy-rich polymers that permit the recovery of metabolic activities when favorable conditions are restored. In the present study, we systematically screened microbial mats for bacteria able to accumulate large amounts of the ester carbon polymers polyhydroxyalkanoates (PHA). Several of these strains were isolated from Ebro Delta microbial mats and their ability to accumulate PHA up to 40-60 % of their dry weight was confirmed. According to two identification approaches (16S rRNA and ropD genes), these strains were identified as Halomonas alkaliphila (MAT-7, -13, -16), H. neptunia (MAT-17), and H. venusta (MAT-28). To determine the mode of growth yielding maximum PHA accumulation, these three different species were cultured in an artificial biofilm in which the cells were immobilized on alginate beads. PHA accumulation by cells that had detached from the biofilm was compared with that of their planktonic counterparts. Experiments in different culture media showed that PHA accumulation, measured as the relative fluorescence intensity after 48 h of incubation at 30 °C, was higher in immobilized than in planktonic cells, with the exception of cells growing in 5 % NaCl, in which PHA accumulation was drastically lower in both. Therefore, for obtaining high PHA concentrations, the use of immobilized cells may be a good alternative to the PHA accumulation by bacteria growing in the classical, planktonic mode. From the ecological point of view, increased PHA accumulation in detached cells from biofilms would be a natural strategy to improve bacterial dispersion capacity and, consequently, to increase survival in stressed environments.

Enhanced polyhydroxyalkanoates accumulation by Halomonas spp. in artificial biofilms of alginate beads.

Microbial mats are complex but stable, multi-layered and multi-functional biofilms, which are the most frequent bacterial formations in nature. The functional strategies and physiological versatility of the bacterial populations growing in microbial mats allow bacteria to resist changing conditions within their environment. One of these strategies is the accumulation of carbon- and energy-rich polymers that permit the recovery of metabolic activities when favorable conditions are restored. In the present study, we systematically screened microbial mats for bacteria able to accumulate large amounts of the ester carbon polymers polyhydroxyalkanoates (PHA). Several of these strains were isolated from Ebro Delta microbial mats and their ability to accumulate PHA up to 40-60 % of their dry weight was confirmed. According to two identification approaches (16S rRNA and ropD genes), these strains were identified as Halomonas alkaliphila (MAT-7, -13, -16), H. neptunia (MAT-17), and H. venusta (MAT-28). To determine the mode of growth yielding maximum PHA accumulation, these three different species were cultured in an artificial biofilm in which the cells were immobilized on alginate beads. PHA accumulation by cells that had detached from the biofilm was compared with that of their planktonic counterparts. Experiments in different culture media showed that PHA accumulation, measured as the relative fluorescence intensity after 48 h of incubation at 30 °C, was higher in immobilized than in planktonic cells, with the exception of cells growing in 5 % NaCl, in which PHA accumulation was drastically lower in both. Therefore, for obtaining high PHA concentrations, the use of immobilized cells may be a good alternative to the PHA accumulation by bacteria growing in the classical, planktonic mode. From the ecological point of view, increased PHA accumulation in detached cells from biofilms would be a natural strategy to improve bacterial dispersion capacity and, consequently, to increase survival in stressed environments.

Imported Cattle Report, December 2012

The Imported Cattle report monthly by the Department of Agricultural.

Imported Cattle Report, October 2012

The Imported Cattle report monthly by the Department of Agricultural.

Imported Cattle Report, November 2012

The Imported Cattle report monthly by the Department of Agricultural.

INTELIGÊNCIA ARTIFICIAL: SISTEMAS ESPECIALISTAS NO GERENCIAMENTO DA INFORMAÇÃO

O principal objetivo deste artigo é propor um modelo para sistemas de gerenciamento da informação baseado em técnicas de inteligência artificial. O modelo propõe uma arquitetura de sistema especialista para gerenciamento da informação, sugerindo a utilização de um analisador semântico embutido na interface do usuário final. A abordagem enfatiza a dificuldade em se obter informações com precisão e qualidade, para apoiar tomadores de decisões, e a necessidade de prover os usuários finais com mecanismos, poderosos, capazes de analisar, selecionar e direcionar-lhes informações, de acordo com as necessidades e urgências de cada um