Comparison between artificial neural networks and maximum likelihood classification in digital soil mapping

Soil surveys are the main source of spatial information on soils and have a range of different applications, mainly in agriculture. The continuity of this activity has however been severely compromised, mainly due to a lack of governmental funding. The purpose of this study was to evaluate the feasibility of two different classifiers (artificial neural networks and a maximum likelihood algorithm) in the prediction of soil classes in the northwest of the state of Rio de Janeiro. Terrain attributes such as elevation, slope, aspect, plan curvature and compound topographic index (CTI) and indices of clay minerals, iron oxide and Normalized Difference Vegetation Index (NDVI), derived from Landsat 7 ETM+ sensor imagery, were used as discriminating variables. The two classifiers were trained and validated for each soil class using 300 and 150 samples respectively, representing the characteristics of these classes in terms of the discriminating variables. According to the statistical tests, the accuracy of the classifier based on artificial neural networks (ANNs) was greater than of the classic Maximum Likelihood Classifier (MLC). Comparing the results with 126 points of reference showed that the resulting ANN map (73.81 %) was superior to the MLC map (57.94 %). The main errors when using the two classifiers were caused by: a) the geological heterogeneity of the area coupled with problems related to the geological map; b) the depth of lithic contact and/or rock exposure, and c) problems with the environmental correlation model used due to the polygenetic nature of the soils. This study confirms that the use of terrain attributes together with remote sensing data by an ANN approach can be a tool to facilitate soil mapping in Brazil, primarily due to the availability of low-cost remote sensing data and the ease by which terrain attributes can be obtained.

Time-series forecasting of pollutant concentration levels using particle swarm optimization and artificial neural networks

This study evaluates the application of an intelligent hybrid system for time-series forecasting of atmospheric pollutant concentration levels. The proposed method consists of an artificial neural network combined with a particle swarm optimization algorithm. The method not only searches relevant time lags for the correct characterization of the time series, but also determines the best neural network architecture. An experimental analysis is performed using four real time series and the results are shown in terms of six performance measures. The experimental results demonstrate that the proposed methodology achieves a fair prediction of the presented pollutant time series by using compact networks.

Evaluation of follicular lymphoid depletion in the Bursa of Fabricius: an alternative methodology using digital image analysis and artificial neural networks

Fifty Bursa of Fabricius (BF) were examined by conventional optical microscopy and digital images were acquired and processed using Matlab® 6.5 software. The Artificial Neuronal Network (ANN) was generated using Neuroshell® Classifier software and the optical and digital data were compared. The ANN was able to make a comparable classification of digital and optical scores. The use of ANN was able to classify correctly the majority of the follicles, reaching sensibility and specificity of 89% and 96%, respectively. When the follicles were scored and grouped in a binary fashion the sensibility increased to 90% and obtained the maximum value for the specificity of 92%. These results demonstrate that the use of digital image analysis and ANN is a useful tool for the pathological classification of the BF lymphoid depletion. In addition it provides objective results that allow measuring the dimension of the error in the diagnosis and classification therefore making comparison between databases feasible.

Classification of antimicrobial resistance using artificial neural networks and the relationship of 38 genes associated with the virulence of Escherichia coli isolates from broilers

Avian pathogenic Escherichia coli (APEC) is responsible for various pathological processes in birds and is considered as one of the principal causes of morbidity and mortality, associated with economic losses to the poultry industry. The objective of this study was to demonstrate that it is possible to predict antimicrobial resistance of 256 samples (APEC) using 38 different genes responsible for virulence factors, through a computer program of artificial neural networks (ANNs). A second target was to find the relationship between (PI) pathogenicity index and resistance to 14 antibiotics by statistical analysis. The results showed that the RNAs were able to make the correct classification of the behavior of APEC samples with a range from 74.22 to 98.44%, and make it possible to predict antimicrobial resistance. The statistical analysis to assess the relationship between the pathogenic index (PI) and resistance against 14 antibiotics showed that these variables are independent, i.e. peaks in PI can happen without changing the antimicrobial resistance, or the opposite, changing the antimicrobial resistance without a change in PI.

Synergistic control of forearm based on accelerometer data and artificial neural networks

In the present study, we modeled a reaching task as a two-link mechanism. The upper arm and forearm motion trajectories during vertical arm movements were estimated from the measured angular accelerations with dual-axis accelerometers. A data set of reaching synergies from able-bodied individuals was used to train a radial basis function artificial neural network with upper arm/forearm tangential angular accelerations. The trained radial basis function artificial neural network for the specific movements predicted forearm motion from new upper arm trajectories with high correlation (mean, 0.9149-0.941). For all other movements, prediction was low (range, 0.0316-0.8302). Results suggest that the proposed algorithm is successful in generalization over similar motions and subjects. Such networks may be used as a high-level controller that could predict forearm kinematics from voluntary movements of the upper arm. This methodology is suitable for restoring the upper limb functions of individuals with motor disabilities of the forearm, but not of the upper arm. The developed control paradigm is applicable to upper-limb orthotic systems employing functional electrical stimulation. The proposed approach is of great significance particularly for humans with spinal cord injuries in a free-living environment. The implication of a measurement system with dual-axis accelerometers, developed for this study, is further seen in the evaluation of movement during the course of rehabilitation. For this purpose, training-related changes in synergies apparent from movement kinematics during rehabilitation would characterize the extent and the course of recovery. As such, a simple system using this methodology is of particular importance for stroke patients. The results underlie the important issue of upper-limb coordination.

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.

Description of epidemics of coffee rust with neural networks

The objective of this paper was to evaluate the potential of neural networks (NN) as an alternative method to the basic epidemiological approach to describe epidemics of coffee rust. The NN was developed from the intensities of coffee (Coffea arabica) rust along with the climatic variables collected in Lavras-MG between 13 February 1998 and 20 April 2001. The NN was built with climatic variables that were either selected in a stepwise regression analysis or by the Braincel® system, software for NN building. Fifty-nine networks and 26 regression models were tested. The best models were selected based on small values of the mean square deviation (MSD) and of the mean prediction error (MPE). For the regression models, the highest coefficients of determination (R²) were used. The best model developed with neural networks had an MSD of 4.36 and an MPE of 2.43%. This model used the variables of minimum temperature, production, relative humidity of the air, and irradiance 30 days before the evaluation of disease. The best regression model was developed from 29 selected climatic variables in the network. The summary statistics for this model were: MPE=6.58%, MSE=4.36, and R²=0.80. The elaborated neural networks from a time series also were evaluated to describe the epidemic. The incidence of coffee rust at four previous fortnights resulted in a model with MPE=4.72% and an MSD=3.95.

Application of artificial neural networks as an alternative to volumetric water balance in drip irrigation management in watermelon crop

Precision irrigation seeks to establish strategies which achieve an efficient ratio between the volume of water used (reduction in input) and the productivity obtained (increase in production). There are several studies in the literature on strategies for achieving this efficiency, such as those dealing with the method of volumetric water balance (VWB). However, it is also of great practical and economic interest to set up versatile implementations of irrigation strategies that: (i) maintain the performance obtained with other implementations, (ii) rely on few computational resources, (iii) adapt well to field conditions, and (iv) allow easy modification of the irrigation strategy. In this study, such characteristics are achieved when using an Artificial Neural Network (ANN) to determine the period of irrigation for a watermelon crop in the Irrigation Perimeter of the Lower Acaraú, in the state of Ceará, Brazil. The Volumetric Water Balance was taken as the standard for comparing the management carried out with the proposed implementation of ANN. The statistical analysis demonstrates the effectiveness of the proposed management, which is able to replace VWB as a strategy in automation.

Artificial neural networks (ANN): prediction of sensory measurements from instrumental data

The objective of this study was to predict by means of Artificial Neural Network (ANN), multilayer perceptrons, the texture attributes of light cheesecurds perceived by trained judges based on instrumental texture measurements. Inputs to the network were the instrumental texture measurements of light cheesecurd (imitative and fundamental parameters). Output variables were the sensory attributes consistency and spreadability. Nine light cheesecurd formulations composed of different combinations of fat and water were evaluated. The measurements obtained by the instrumental and sensory analyses of these formulations constituted the data set used for training and validation of the network. Network training was performed using a back-propagation algorithm. The network architecture selected was composed of 8-3-9-2 neurons in its layers, which quickly and accurately predicted the sensory texture attributes studied, showing a high correlation between the predicted and experimental values for the validation data set and excellent generalization ability, with a validation RMSE of 0.0506.

Dietary patterns and risk of oral cancer: a case-control study in São Paulo, Brazil

OBJECTIVE: To analyze the association between dietary patterns and oral cancer. METHODS: The study, part of a Latin American multicenter hospital-based case-control study, was conducted in São Paulo, Southeastern Brazil, between November 1998 and March 2002 and included 366 incident cases of oral cancer and 469 controls, frequency-matched with cases by sex and age. Dietary data were collected using a food frequency questionnaire. The risk associated with the intake of food groups defined a posteriori, through factor analysis (called factors), was assessed. The first factor, labeled "prudent," was characterized by the intake of vegetables, fruit, cheese, and poultry. The second factor, "traditional," consisted of the intake of rice, pasta, pulses, and meat. The third factor, "snacks," was characterized as the intake of bread, butter, salami, cheese, cakes, and desserts. The fourth, "monotonous," was inversely associated with the intake of fruit, vegetables and most other food items. Factor scores for each component retained were calculated for cases and controls. After categorization of factor scores into tertiles according to the distribution of controls, odds ratios and 95% confidence intervals were calculated using unconditional multiple logistic regression. RESULTS: "Traditional" factor showed an inverse association with cancer (OR=0.51; 95% CI: 0.32; 0.81, p-value for trend 0.14), whereas "monotonous" was positively associated with the outcome (OR=1.78; 95% CI: 1.78; 2.85, p-value for trend <0.001). CONCLUSIONS: The study data suggest that the traditional Brazilian diet, consisting of rice and beans plus moderate amounts of meat, may confer protection against oral cancer, independently of any other risk factors such as alcohol intake and smoking.

Water-contact patterns and schistosoma mansoni infection in a rural community in northeast Brazil

We evaluated the influence of water-related human activities, contaminative behaviour, house location, education and socio-economic status on endemic Schistosoma mansoni infection. The study was conducted in a hilry non-irrigated area of rural northeast Brazil amongst a defined population of subsistence farmers, of whom 93% were infected by age 20. The area was mapped, water bodies were surveyed, and a detailed questionnaire was performed on each household. Infection was assessed by duplicate stool examinations using the sensitive Bell technique to quantify egg excretion. For each household, and index of intensity of infection was computed by grouping individual log-transformed egg counts as an age-sex adjusted Z score. Few households had a sanitary installation or a domestic water supply. However, neither water-contact nor contaminative behavior were indiscriminate. The people made considerable effort to defaecate far from a water source, to obtain household drinking water from the cleanest source, and to bathe only at certain sites where privacy is assured. Land ownership and literacy correlated poorly with the household index of intensity of infection. The key influence on infection status was the relative location of the house and snail-free or snail colonized water sources. In this area, a safe domestic water supply is the critical input needed to achieve definitive control of endemic Schistosomiasis.

A multivariate analysis of socio-demographic factors, water contact patterns and Schistosoma mansoni infection in an endemic area in Brazil

Associations between socio-demographic factors, water contact patterns and Schistosoma mansoni infection were investigated in 506 individuals (87% of inhabitants over 1 year of age) in an endemic area in Brazil (Divino), aiming at determining priorities for public health measures to prevent the infection. Those who eliminated S. mansoni eggs (n = 198) were compared to those without eggs in the stools (n = 308). The following explanatory variables were considered: age, sex, color, previous treatment with schistosomicide, place of birth, quality of the houses, water supply for the household, distance from houses to stream, and frequency and reasons for water contact. Factors found to be independently associated with the infection were age (10-19 and > 20 yrs old), and water contact for agricultural activities, fishing, and swimming or bathing (Adjusted relative odds = 5.0, 2.4, 3.2, 2.1 and 2.0, respectively). This suggests the need for public health measures to prevent the infection, emphasizing water contact for leisure and agricultural activities in this endemic area.

Water-contact patterns and risk factors for Schistosoma mansoni infection in a rural village of Northeast Brazil

Schistosomiasis mansoni in the Serrano village, municipality of Cururupu, state of Maranhão, Brazil, is a widely spread disease. The PECE (Program for the Control of Schistosomiasis), undertaken since 1979 has reduced the prevalence of S. mansoni infection and the hepatosplenic form of the disease. Nevertheless piped water is available in 84% of the households, prevalence remains above 20%. In order to identify other risk factors responsible for the persistence of high prevalence levels, a cross-sectional survey was carried out in a systematic sample of 294 people of varying ages. Socioeconomic, environmental and demographic variables, and water contact patterns were investigated. Fecal samples were collected and analyzed by the Kato-Katz technique. Prevalence of S. mansoni infection was 24.1%, higher among males (35.5%) and between 10-19 years of age (36.6%). The risk factors identified in the univariable analysis were water contacts for vegetable extraction (Risk Ratio - RR = 2.92), crossing streams (RR = 2.55), bathing (RR = 2.35), fishing (RR = 2.19), hunting (RR = 2.17), cattle breeding (RR = 2.04), manioc culture (RR = 1.90) and leisure (RR = 1.56). After controlling for confounding variables by proportional hazards model the risks remained higher for males, vegetable extraction, bathing in rivers and water contact in rivers or in periodically inundated parts of riverine woodland (swamplands)

Clinical patterns and seasonal trends in respiratory syncytial virus hospitalizations in São Paulo, Brazil

The respiratory viruses are recognized as the most frequent lower respiratory tract pathogens for infants and young children in developed countries but less is known for developing populations. The authors conducted a prospective study to evaluate the occurrence, clinical patterns, and seasonal trends of viral infections among hospitalized children with lower respiratory tract disease (Group A). The presence of respiratory viruses in children's nasopharyngeal was assessed at admission in a pediatric ward. Cell cultures and immunofluorescence assays were used for viral identification. Complementary tests included blood and pleural cultures conducted for bacterial investigation. Clinical data and radiological exams were recorded at admission and throughout the hospitalization period. To better evaluate the results, a non- respiratory group of patients (Group B) was also constituted for comparison. Starting in February 1995, during a period of 18 months, 414 children were included- 239 in Group A and 175 in Group B. In Group A, 111 children (46.4%) had 114 viruses detected while only 5 children (2.9%) presented viruses in Group B. Respiratory Syncytial Virus was detected in 100 children from Group A (41.8%), Adenovirus in 11 (4.6%), Influenza A virus in 2 (0.8%), and Parainfluenza virus in one child (0.4%). In Group A, aerobic bacteria were found in 14 cases (5.8%). Respiratory Syncytial Virus was associated to other viruses and/or bacteria in six cases. There were two seasonal trends for Respiratory Syncytial Virus cases, which peaked in May and June. All children affected by the virus were younger than 3 years of age, mostly less than one year old. Episodic diffuse bronchial commitment and/or focal alveolar condensation were the clinical patterns more often associated to Respiratory Syncytial Virus cases. All children from Group A survived. In conclusion, it was observed that Respiratory Syncytial Virus was the most frequent pathogen found in hospitalized children admitted for severe respiratory diseases. Affected children were predominantly infants and boys presenting bronchiolitis and focal pneumonias. Similarly to what occurs in other subtropical regions, the virus outbreaks peak in the fall and their occurrence extends to the winter, which parallels an increase in hospital admissions due to respiratory diseases.

Electrophoretic protein patterns and numerical analysis of Candida albicans from the oral cavities of healthy children

The aim of this research was to evaluate the protein polymorphism degree among seventy-five C. albicans strains from healthy children oral cavities of five socioeconomic categories from eight schools (private and public) in Piracicaba city, São Paulo State, in order to identify C. albicans subspecies and their similarities in infantile population groups and to establish their possible dissemination route. Cell cultures were grown in YEPD medium, collected by centrifugation, and washed with cold saline solution. The whole-cell proteins were extracted by cell disruption, using glass beads and submitted to SDS-PAGE technique. After electrophoresis, the protein bands were stained with Coomassie-blue and analyzed by statistics package NTSYS-pc version 1.70 software. Similarity matrix and dendrogram were generated by using the Dice similarity coefficient and UPGMA algorithm, respectively, which made it possible to evaluate the similarity or intra-specific polymorphism degrees, based on whole-cell protein fingerprinting of C. albicans oral isolates. A total of 13 major phenons (clusters) were analyzed, according to their homogeneous (socioeconomic category and/or same school) and heterogeneous (distinct socioeconomic categories and/or schools) characteristics. Regarding to the social epidemiological aspect, the cluster composition showed higher similarities (0.788 < S D < 1.0) among C. albicans strains isolated from healthy children independent of their socioeconomic bases (high, medium, or low). Isolates of high similarity were not found in oral cavities from healthy children of social stratum A and D, B and D, or C and E. This may be explained by an absence of a dissemination route among these children. Geographically, some healthy children among identical and different schools (private and public) also are carriers of similar strains but such similarity was not found among other isolates from children from certain schools. These data may reflect a restricted dissemination route of these microorganisms in some groups of healthy scholars, which may be dependent of either socioeconomic categories or geographic site of each child. In contrast to the higher similarity, the lower similarity or higher polymorphism degree (0.499 < S D < 0.788) of protein profiles was shown in 23 (30.6%) C. albicans oral isolates. Considering the social epidemiological aspect, 42.1%, 41.7%, 26.6%, 23.5%, and 16.7% were isolates from children concerning to socioeconomic categories A, D, C, B, and E, respectively, and geographically, 63.6%, 50%, 33.3%, 33.3%, 30%, 25%, and 14.3% were isolates from children from schools LAE (Liceu Colégio Albert Einstein), MA (E.E.P.S.G. "Prof. Elias de Melo Ayres"), CS (E.E.P.G. "Prof. Carlos Sodero"), AV (Alphaville), HF (E.E.P.S.G. "Honorato Faustino), FMC (E.E.P.G. "Prof. Francisco Mariano da Costa"), and MEP (E.E.P.S.G. "Prof. Manasses Ephraim Pereira), respectively. Such results suggest a higher protein polymorphism degree among some strains isolated from healthy children independent of their socioeconomic strata or geographic sites. Complementary studies, involving healthy students and their families, teachers, servants, hygiene and nutritional habits must be done in order to establish the sources of such colonization patterns in population groups of healthy children. The whole-cell protein profile obtained by SDS-PAGE associated with computer-assisted numerical analysis may provide additional criteria for the taxonomic and epidemiological studies of C. albicans.