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.

The Effect of Serial Culture and Storage on the Protective Potential of a Competitive Exclusion Preparation

Cultura de fezes (Método de Exclusão Competitiva - EC) utilizada para prevenir a colonização cecal de aves por Salmonella enterica serovar Enteritidis (SE) foi submetida a cultivos seriados para evitar a presença de patógenos e, após o tratamento mais adequado, foi armazenada em temperatura de refrigeração antes do seu uso por até 63 dias. Os resultados mostraram que o cultivo repetido por 14 vezes não prejudica a ação protetora da cultura (CE), a qual continua inibindo a colonização cecal por SE. O produto submetido a 12 cultivos e armazenado durante 28 dias em temperatura de refrigeração também continua eficaz.

Environmental management in Brazil: is it a completely competitive priority?

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Competitive release and area effects

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Petroleum well drilling monitoring through cutting image analysis and artificial intelligence techniques

Petroleum well drilling monitoring has become an important tool for detecting and preventing problems during the well drilling process. In this paper, we propose to assist the drilling process by analyzing the cutting images at the vibrating shake shaker, in which different concentrations of cuttings can indicate possible problems, such as the collapse of the well borehole walls. In such a way, we present here an innovative computer vision system composed by a real time cutting volume estimator addressed by support vector regression. As far we know, we are the first to propose the petroleum well drilling monitoring by cutting image analysis. We also applied a collection of supervised classifiers for cutting volume classification. (C) 2010 Elsevier Ltd. All rights reserved.

APPLICATIONS OF ARTIFICIAL-INTELLIGENCE IN ORGANIC-CHEMISTRY .17. NEW PROGRAMS IN THE SISTEMAT PROJECT

This work describes the new improvements of the SISTEMAT project, one system for structural elucidation mainly in the field of Natural Products Chemistry. Some examples of the resolution of problems using C-13 Nuclear Magnetic Resonance and Mass Spectroscopy are given. Programs to discover new heuristic rules for structure generation are discussed. The data base contains about 10000 C-13 NMR spectra.

Combining artificial intelligence and human problem solving: Proposing a new architecture for ITS's

This paper shows a comparative study between the Artificial Intelligence Problem Solving and the Human Problem Solving. The study is based on the solution by many ways of problems proposed via multiple-choice questions. General techniques used by humans to solve this kind of problems are grouped in blocks and each block is divided in steps. A new architecture for ITS - Intelligent Tutoring System is proposed to support experts' knowledge representation and novices' activities. Problems are represented by a text and feasible answers with particular meaning and form, to be rigorously analyzed by the solver to find the right one. Paths through a conceptual space of states represent each right solution.

Stroking Parameters during Continuous and Intermittent Exercise in Regional-Level Competitive Swimmers

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Industrial Robotics Applied to Education

This work describes a ludic proposal for programming learning of industrial robots to be developed by groups of engineering students. Two projects are presented: Tic-tac-toe Opponent Robot and Environmentalist Robot. The first project use competitive search techniques of the Artificial Intelligence, computational vision, electronic and pneumatic concepts for ability decision making for a robotic agent on the tic-tae-toe game. The second project consists of a game that contains a questions and answers database about environmental themes. An algorithm selects the group of questions to be answered by the player, analyses the answers and sends the result to a industrial robot through serial port. According with the player performance, the robot makes congratulation movements and giving a gift to the winner player. Otherwise, the robot makes movements, disapproving the player performance.

Evidence of zinc deficiency in competitive swimmers

Objective: The aim of this study was to assess the nutritional zinc (Zn) status of elite swimmers during different training periods.Methods: A longitudinal paired study was performed at the University of São Paulo in eight male swimmers 18 to 25 y old who had been swimming competitively at the state and national levels for at least 5 y. The swimmers were evaluated over a total period of 14 wk: before the basic and specific preparatory period (BSPP-baseline), at the end of the basic and specific preparatory period (post-BSPP), and at the end of the polishing period (PP). Levels of Zn were determined in the plasma, erythrocyte, urine, and saliva by atomic absorption spectrophotometry. Anthropometric measurements and a 3-d food record were also evaluated.Results: The median plasma Zn concentration was below the reference value in all training periods (BSPP-baseline 59 mu g/dL, post-BSPP 55.9 mu g/dL, after PP 58.8 mu g/dL, P > 0.05), as were threshold values for erythrocytes (BSPP-baseline 36.5 mu g of Zn/g of hemoglobin, post-BSPP 42 mu g of Zn/g of hemoglobin, after PP 40.7 mu g of Zn/g of hemoglobin, P > 0.05), urinary Zn (BSPP-baseline 280 mu g/24 h, post-BSPP 337 mu g/24 h, after PP 284 mu g/24 h, P > 0.05), and salivary Zn (BSPP-baseline 66.1 mu g/L, post-BSPP 54.1 mu g/L, after PP 79.7 mu g/L, > 0.05). Salivary Zn did not correlate with plasma and erythrocyte Zn levels.Conclusion: The results suggest that the elite swimmers studied presented a possible Zn deficiency and that salivary Zn was not adequate to evaluate the Zn nutritional status. (C) 2012 Elsevier B.V. All rights reserved.

Fuzzy distributed artificial intelligence systems

In this paper, we introduce a DAI approach called hereinafter Fuzzy Distributed Artificial Intelligence (FDAI). Through the use of fuzzy logic, we have been able to develop mechanisms that we feel may effectively improve current DAI systems, giving much more flexibility and providing the subsidies which a formal theory can bring. The appropriateness of the FDAI approach is explored in an important application, a fuzzy distributed traffic-light control system, where we have been able to aggregate and study several issues concerned with fuzzy and distributed artificial intelligence. We also present a number of current research directions necessary to develop the FDAI approach more fully.

Detection of infectious bronchitis virus in experimentally infected chickens by an antigen-competitive ELISA

An antigen-competitive enzyme-linked immunosorbent assay (Ag-C-ELISA) was developed for the detection of infectious bronchitis virus (IBV) antigens, M41 strain, in tissues from experimentally infected chickens, or in allantoic fluid harvested from inoculated embryonated eggs. The detection limit of IBV in the Ag-C-ELISA was 104.1 median embryo infective doses (EID50)/well. Tracheal and lung samples from chickens vaccinated with 102.5 EID50 of live attenuated infectious bronchitis (H120) vaccine were negative in the direct detection Ag-C-ELISA. The results indicate that the Ag-C-ELISA has the potential to detect IBV, either directly in tissue samples or when combined with the passage of material in embryonated eggs, thereby constituting an alternative method for the diagnosis of IBV.

Using artificial intelligence for the control of medium voltage substations

This paper introduces a method for the supervision and control of devices in electric substations using fuzzy logic and artificial neural networks. An automatic knowledge acquisition process is included which allows the on-line processing of operator actions and the extraction of control rules to replace gradually the human operator. Some experimental results obtained by the application of the implemented software in a simulated environment with random signal generators are presented.