Video target tracking by using competitive neural networks

A target tracking algorithm able to identify the position and to pursuit moving targets in video digital sequences is proposed in this paper. The proposed approach aims to track moving targets inside the vision field of a digital camera. The position and trajectory of the target are identified by using a neural network presenting competitive learning technique. The winning neuron is trained to approximate to the target and, then, pursuit it. A digital camera provides a sequence of images and the algorithm process those frames in real time tracking the moving target. The algorithm is performed both with black and white and multi-colored images to simulate real world situations. Results show the effectiveness of the proposed algorithm, since the neurons tracked the moving targets even if there is no pre-processing image analysis. Single and multiple moving targets are followed in real time.

Short-term multinodal load forecasting in distribution systems using general regression neural networks

Multinodal load forecasting deals with the loads of several interest nodes in an electrical network system, which is also known as bus load forecasting. To perform this demand, it is necessary a technique that is precise, trustable and has a short-time processing. This paper proposes two methodologies based on general regression neural networks for short-term multinodal load forecasting. The first individually forecast the local loads and the second forecast the global load and individually forecast the load participation factors to estimate the local loads. To design the forecasters it wasn't necessary the previous study of the local loads. Tests were made using a New Zealand distribution subsystem and the results obtained are compatible with the ones founded in the specialized literature. © 2011 IEEE.

Monitoring in precision metal drilling process using multi-sensors and neural network

This paper presents a new method to estimate hole diameters and surface roughness in precision drilling processes, using coupons taken from a sandwich plate composed of a titanium alloy plate (Ti6Al4V) glued onto an aluminum alloy plate (AA 2024T3). The proposed method uses signals acquired during the cutting process by a multisensor system installed on the machine tool. These signals are mathematically treated and then used as input for an artificial neural network. After training, the neural network system is qualified to estimate the surface roughness and hole diameter based on the signals and cutting process parameters. To evaluate the system, the estimated data were compared with experimental measurements and the errors were calculated. The results proved the efficiency of the proposed method, which yielded very low or even negligible errors of the tolerances used in most industrial drilling processes. This pioneering method opens up a new field of research, showing a promising potential for development and application as an alternative monitoring method for drilling processes. © 2012 Springer-Verlag London Limited.

Speed estimation for induction motor using neural networks method

This work presents an alternative approach based on neural network method in order to estimate speed of induction motors, using the measurement of primary variables such as voltage and current. Induction motors are very common in many sectors of the industry and assume an important role in the national energy policy. The nowadays methodologies, which are used in diagnosis, condition monitoring and dimensioning of these motors, are based on measure of the speed variable. However, the direct measure of this variable compromises the system control and starting circuit of an electric machinery, reducing its robustness and increasing the implementation costs. Simulation results and experimental data are presented to validate the proposed approach. © 2003-2012 IEEE.

The bias in reversing the Box-Cox transformation in time series forecasting: An empirical study based on neural networks

The Box-Cox transformation is a technique mostly utilized to turn the probabilistic distribution of a time series data into approximately normal. And this helps statistical and neural models to perform more accurate forecastings. However, it introduces a bias when the reversion of the transformation is conducted with the predicted data. The statistical methods to perform a bias-free reversion require, necessarily, the assumption of Gaussianity of the transformed data distribution, which is a rare event in real-world time series. So, the aim of this study was to provide an effective method of removing the bias when the reversion of the Box-Cox transformation is executed. Thus, the developed method is based on a focused time lagged feedforward neural network, which does not require any assumption about the transformed data distribution. Therefore, to evaluate the performance of the proposed method, numerical simulations were conducted and the Mean Absolute Percentage Error, the Theil Inequality Index and the Signal-to-Noise ratio of 20-step-ahead forecasts of 40 time series were compared, and the results obtained indicate that the proposed reversion method is valid and justifies new studies. (C) 2014 Elsevier B.V. All rights reserved.

A method using artificial neural networks to morphologically assess mouse blastocyst quality

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Use of uniform designs in combination with neural networks for viral infection process development

This work aimed to compare the predictive capacity of empirical models, based on the uniform design utilization combined to artificial neural networks with respect to classical factorial designs in bioprocess, using as example the rabies virus replication in BHK-21 cells. The viral infection process parameters under study were temperature (34°C, 37°C), multiplicity of infection (0.04, 0.07, 0.1), times of infection, and harvest (24, 48, 72 hours) and the monitored output parameter was viral production. A multilevel factorial experimental design was performed for the study of this system. Fractions of this experimental approach (18, 24, 30, 36 and 42 runs), defined according uniform designs, were used as alternative for modelling through artificial neural network and thereafter an output variable optimization was carried out by means of genetic algorithm methodology. Model prediction capacities for all uniform design approaches under study were better than that found for classical factorial design approach. It was demonstrated that uniform design in combination with artificial neural network could be an efficient experimental approach for modelling complex bioprocess like viral production. For the present study case, 67% of experimental resources were saved when compared to a classical factorial design approach. In the near future, this strategy could replace the established factorial designs used in the bioprocess development activities performed within biopharmaceutical organizations because of the improvements gained in the economics of experimentation that do not sacrifice the quality of decisions.

The application of neural networks to the analysis of dissolved gases in insulating oil used in transformers

The state of insulating oils used in transformers is determined through the accomplishment of physical-chemical tests, which determine the state of the oil, as well as the chromatography test, which determines possible faults in the equipment. This article concentrate on determining, from a new methodology, a relationship among the variation of the indices obtained from the physical-chemical tests with those indices supplied by the chromatography tests.The determination of the relationship among the tests is accomplished through the application of neural networks. From the data obtained by physical-chemical tests, the network is capable to determine the relationship among the concentration of the main gases present in a certain sample, which were detected by the chromatography tests.More specifically, the proposed approach uses neural networks of perceptron type constituted of multiple layers. After the process of network training, it is possible to determine the existent relationship between the physical-chemical tests and the amount of gases present in the insulating oil.

Artificial neural networks applied to bandsawing process control

In the search for productivity increase, industry has invested on the development of intelligent, flexible and self-adjusting method, capable of controlling processes through the assistance of autonomous systems, independently whether they are hardware or software. Notwithstanding, simulating conventional computational techniques is rather challenging, regarding the complexity and non-linearity of the production systems. Compared to traditional models, the approach with Artificial Neural Networks (ANN) performs well as noise suppression and treatment of non-linear data. Therefore, the challenges in the wood industry justify the use of ANN as a tool for process improvement and, consequently, add value to the final product. Furthermore, Artificial Intelligence techniques such as Neuro-Fuzzy Networks (NFNs) have proven effective, since NFNs combine the ability to learn from previous examples and generalize the acquired information from the ANNs with the capacity of Fuzzy Logic to transform linguistic variables in rules.

The use of artificial neural networks in analysing the nutritional ecology of Chrysomya megacephala (F.) (Diptera: Calliphoridae), compared with a statistical model

Artificial neural networks (ANNs) have been widely applied to the resolution of complex biological problems. An important feature of neural models is that their implementation is not precluded by the theoretical distribution shape of the data used. Frequently, the performance of ANNs over linear or non-linear regression-based statistical methods is deemed to be significantly superior if suitable sample sizes are provided, especially in multidimensional and non-linear processes. The current work was aimed at utilising three well-known neural network methods in order to evaluate whether these models would be able to provide more accurate outcomes in relation to a conventional regression method in pupal weight predictions of Chrysomya megacephala, a species of blowfly (Diptera: Calliphoridae), using larval density (i.e. the initial number of larvae), amount of available food and pupal size as input data. It was possible to notice that the neural networks yielded more accurate performances in comparison with the statistical model (multiple regression). Assessing the three types of networks utilised (Multi-layer Perceptron, Radial Basis Function and Generalised Regression Neural Network), no considerable differences between these models were detected. The superiority of these neural models over a classical statistical method represents an important fact, because more accurate models may clarify several intricate aspects concerning the nutritional ecology of blowflies.

Associations between healthy eating patterns and indicators of metabolic risk in postmenopausal women

Background: Since human diets contain many components that may work synergistically to prevent or promote disease, assessing diet quality may be informative. The purpose of this study was to investigate the association between quality diet, by using Healthy Eating Index (HEI), and metabolic risk indicators in postmenopausal women.Methods: This cross-sectional study included a total of 173 Brazilian women, aged 45-75 years, seeking healthcare at a public outpatient center. Food consumption assessed by 24 h-recall food inquiry was used to calculate HEI scores: >80 implied diet good, 80-51 diet needed improvement, and <51 diet poor. Anthropometric data included: body mass index (BMI = weight/height(2)), waist-circumference (WC), body fat (%BF) and lean mass (%LM). Data on total cholesterol (TC), high density lipoprotein cholesterol (HDLC), low density lipoprotein cholesterol (LDLC), and triglycerides (TG) were also collected. Fisher's Exact test, and logistic regression method (to determine odds ratio, OR) were used in the statistical analysis.Results: Overweight and obesity were observed in 75.7% of the participants. Excessive %BF (> 35%) was observed in 56.1%, while %LM was reduced (<70%) in 78.1%. WC was elevated (= 88 cm) in 72.3%. Based on HEI values, diet quality was good in 3% (5/173), needed improvement in 48.5% (84/173), and was poor in 48.5% (84/173) of the cases. In this group, 75% of women had high intakes of lipids (> 35%), predominantly saturated and monounsaturated fat. on average, plasma TC, LDLC, and TG levels were higher than recommended in 57.2%, 79.2% and 45.1% of the women, respectively, while HDLC was low in 50.8%. There was association between HEI scores and the %BF that it was higher among women with HEI score < 80 (p = 0.021). There were not observed significant risk associations between HEI and lipid profile.Conclusion: Among the Brazilian postmenopausal women attending a public outpatient clinic, diet was considered to need improvement or to be of poor quality, attributed to high saturated fat ingestion, which probably caused a negative impact on metabolic risk indicators, namely body composition.

Effects of adding a spray-dried polyclonal antibody preparation on ruminal fermentation patterns and digestibility of cows fed high concentrate diets

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Effects of adding polyclonal antibody preparations on ruminal fermentation patterns and digestibility of cows fed different energy sources

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Effect of Progesterone and Ionomycin on Domestic Cat Sperm Motility Patterns and Acrosome Reaction

This study was aimed at assessing the changes in sperm motion patterns and the percentage of acrosome reaction (AR) in domestic cat semen after treatment with either ionomycin or progesterone (P(4)). Ten ejaculates were collected from five tomcats using an artificial vagina, and were diluted, centrifuged and resuspended in a capacitation medium. Samples were evaluated and divided into seven equal aliquots and, after 2 h at 25 degrees C, were incubated for 30 min at 38 degrees C in 5% CO(2) and then analyzed. Computer-assisted sperm analysis and a combination of three fluorescent probes were used to assess sperm plasma, acrosomal membrane integrity and mitochondrial transmembrane potential. Thirty minutes after the start of incubation, P(4) was added (10 mu g/ml) to the P1 group. Groups P2 and P3 were supplemented with P(4) (10 and 20 mu g/ml, respectively) only after 2 h of incubation, and groups I1 and I2 were supplemented with ionomycin (4 and 8 mu M, respectively) 2 h after incubation. Group E was supplemented with ethanol (0.6%) at 2 h after incubation and group C received no supplementation. Ionomycin and P(4) treatments led to a hyperactivation-like sperm motion and an increase (p < 0.05) in the percentage of AR. Although a higher (p < 0.05) percentage of AR was obtained in group I2 when compared with all P(4) groups, a decrease (p < 0.05) in total and progressive motility was observed in I2 group. As I1 group was similar to I2 to induce AR without diminishing sperm motility, we can conclude that ionomycin at 4 mu M seems to be more suitable to trigger AR in domestic cat sperm.

PCR primed with minisatellite core sequences yields species-specific patterns and assessment of population variability in fishes of the genus Brycon

Minisatellite core sequences were used as single primers in polymerase chain reaction (PCR) to amplify genomic DNA in a way similar to the random amplified polymorphic DNA methodology. This technique, known as Directed Amplification of Minisatellite-region DNA, was applied in order to differentiate three neotropical fish species (Brycon orbignyanus, B. microlepis and B. lundii ) and to detect possible genetic variations among samples of the threatened species, B. lundii , collected in two regions with distinct environmental conditions in the area of influence of a hydroelectric dam. Most primers generated species-specific banding patterns and high levels of intraspecific polymorphism. The genetic variation observed between the two sampling regions of B. lundii was also high enough to suggest the presence of distinct stocks of this species along the same river basin. The results demonstrated that minisatellite core sequences are potentially useful as single primers in PCR to assist in species and population identification. The observed genetic stock differentiation in B. lundii associated with ecological and demographic data constitute a crucial task to develop efficient conservation strategies in order to preserve the genetic diversity of this endangered fish species.