Classification and characterization of places for mapping of environment using hierarchical neural network and omnivision

Mobile robots need autonomy to fulfill their tasks. Such autonomy is related whith their capacity to explorer and to recognize their navigation environments. In this context, the present work considers techniques for the classification and extraction of features from images, using artificial neural networks. This images are used in the mapping and localization system of LACE (Automation and Evolutive Computing Laboratory) mobile robot. In this direction, the robot uses a sensorial system composed by ultrasound sensors and a catadioptric vision system equipped with a camera and a conical mirror. The mapping system is composed of three modules; two of them will be presented in this paper: the classifier and the characterizer modules. Results of these modules simulations are presented in this paper.

Environment mapping for mobile robots navigation using hierarchical neural network and omnivision

Autonomous robots must be able to learn and maintain models of their environments. In this context, the present work considers techniques for the classification and extraction of features from images in joined with artificial neural networks in order to use them in the system of mapping and localization of the mobile robot of Laboratory of Automation and Evolutive Computer (LACE). To do this, the robot uses a sensorial system composed for ultrasound sensors and a catadioptric vision system formed by a camera and a conical mirror. The mapping system is composed by three modules. Two of them will be presented in this paper: the classifier and the characterizer module. The first module uses a hierarchical neural network to do the classification; the second uses techiniques of extraction of attributes of images and recognition of invariant patterns extracted from the places images set. The neural network of the classifier module is structured in two layers, reason and intuition, and is trained to classify each place explored for the robot amongst four predefine classes. The final result of the exploration is the construction of a topological map of the explored environment. Results gotten through the simulation of the both modules of the mapping system will be presented in this paper. © 2008 IEEE.

Assessment of the ergonomic design of diagnostic ultrasound transducers through wrist movements and subjective evaluation

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

Real time B-mode ultrasound in pacas pregnancy (Agouti paca, Linnaeus, 1766)

O objetivo deste estudo foi estabelecer o tempo de prenhez da paca por meio de ultra-sonografia. Nove pacas prenhes foram periodicamente acompanhadas com um transdutor eletrônico setorial bi-frequencial de 5,0 e 7,5 MHz, em modo B, desde a detecção ultra-sonográfica da vesícula embrionária ou do feto até o nascimento dos filhotes. Os animais foram colocados em uma gaiola de ferro de prensagem lateral e permaneceram em posição quadrupedal durante as sessões. Um pano escuro foi usado para cobrir a gaiola e frutas foram oferecidas durante o exame ultra-sonográfico para evitar reações agressivas. Quanto mais precocemente ocorreu a detecção de prenhez, maior foi o período de acompanhamento ultra-sonográfico até o nascimento dos filhotes. Apenas um filhote nasceu por parto, com 796,5 ± 74,36 gramas (valor médio ± desvio padrão da amostra) e 33,46 ± 0,60 centímetros (valor médio ± desvio padrão da amostra) de comprimento (entre a borda rostral do focinho e a extremidade distal da cauda). O período de prenhez da paca abrange 135 a 139 dias.

Efficacy of linear and convex transducers for ultrasound-guided transvaginal follicle aspiration

A new device was developed to hold linear transducers for transvaginal follicle aspiration. Efficacy of follicle aspiration was compared using a linear 6 MHz and a convex 5 MHz transducer. Fifty-five cows were submitted to follicle aspiration at random days of the estrous cycle. Aspirations were conducted with linear (n = 28) and convex (n = 38) transducers with 18 G needles at a negative pressure corresponding to 13 ml H2O/min. A greater number of follicles were aspirated using convex than to linear probe (12.4 versus 7.8, respectively, P < 0.05). Mean number of oocytes and recovery rates were similar for convex (5.4 and 48.6%) and linear (4.6 and 59.3%) transducers. Limited space between the linear transducer and needle guide restricted access to some portions of the ovary, reducing the number of follicles aspirated using a linear transducer. The newly developed adaptor allowed greater stability, holding the ovaries firmly against the linear transducer. This diminished mobility permitted a similar number of oocytes to be recovered with both transducers. In conclusion, this new adaptor provided a low cost alternative for routine follicle aspiration and oocyte recovery in cattle. (C) 2002 Elsevier B.V. All rights reserved.

Relationship between follicle size and ultrasound-guided transvaginal oocyte recovery

We evaluated the relationship between follicle size and oocyte recovery (OR) using ultrasound-guided follicle aspiration. Thirty Holstein cows were subjected to OR without gonadotrophic therapy. Oocytes were recovered two to four times from each cow in a total of 67 aspiration sessions, Ovarian follicles with diameters less than or equal to4 mm and >4 mm were aspirated in separated groups. Recovered oocytes from each group were kept separate and submitted to in vitro maturation, fertilization, and culture to the blastocyst stage. A total of 430 follicles were aspirated, of which 154 (35.8%) were from follicles >4 mm and 276 (64.2%) were from follicles less than or equal to4 mm. Seventy-seven oocytes (50%) were recovered from follicles >4 mm and 200 (72.2%) were from follicles less than or equal to4 mm. Nineteen blastocysts were obtained from follicles >4 mm, whereas 45 blastocysts were obtained from follicles less than or equal to4 mm. Recovery rate was greater (P < 0.01) in follicles less than or equal to4 mm, Oocyte quality, cleavage rate and blastocyst development did not differ between different follicle sizes. Routine aspiration of small follicles (less than or equal to4 mm) could increase the number of oocytes available for in vitro development. (C) 2001 Elsevier B.V. B.V. All rights reserved.

Dominant follicle removal by ultrasound guided transvaginal aspiration and superovulatory response in Nellore cows

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

Genetic associations between carcass traits measured by real-time ultrasound and scrotal circumference and growth traits in Nelore cattle

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Genetic and environmental factors affecting ultrasound measures of longissimus muscle area and backfat thickness in Nelore cattle

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Genetic association between body composition measured by ultrasound and visual scores in Brazilian Nelore cattle

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Analysis of relative humidity sensors at the WMO Radiosonde intercomparison experiment in Brazil

The quality of the vertical distribution measurements of humidity in the atmosphere is very important in meteorology due to the crucial role that water vapor plays in the earth's energy budget. The radiosonde is the humidity measurement device that provides the best vertical resolution. Also, radiosondes are the operational devices that are used to measure the vertical profile of atmospheric water vapor. The World Meteorological Organization (WMO) has carried out several intercomparison experiments at different climatic zones in order to identify the differences between the available commercial sensors. This article presents the results of an experiment that was carried out in Brazil in 2001 in which major commercial radiosonde manufacturers [e.g., Graw Radiosondes GmbH & Co., KG (Germany); MODEM (France); InterMet Systems (United States); Sippican, Inc. (United States); and Vaisala (Finland)] were involved. One of the main goals of this experiment was to evaluate the performance of the different humidity sensors in a tropical region. This evaluation was performed for different atmospheric layers and distinct periods of the day. It also considers the computation of the integrated water vapor (IWV). The results showed that the humidity measurements achieved by the different sensors were quite similar in the low troposphere (the bias median value regarding the RS80 was around 1.8%) and were quite dispersed in the superior layers (the median rms regarding the RS80 was around 14.9%).

Wine classification by taste sensors made from ultra-thin films and using neural networks

This paper reports on a sensor array able to distinguish tastes and used to classify red wines. The array comprises sensing units made from Langmuir-Blodgett (LB) films of conducting polymers and lipids and layer-by-layer (LBL) films from chitosan deposited onto gold interdigitated electrodes. Using impedance spectroscopy as the principle of detection, we show that distinct clusters can be identified in principal component analysis (PCA) plots for six types of red wine. Distinction can be made with regard to vintage, vineyard and brands of the red wine. Furthermore, if the data are treated with artificial neural networks (ANNs), this artificial tongue can identify wine samples stored under different conditions. This is illustrated by considering 900 wine samples, obtained with 30 measurements for each of the five bottles of the six wines, which could be recognised with 100% accuracy using the algorithms Standard Backpropagation and Backpropagation momentum in the ANNs. (C) 2003 Elsevier B.V. All rights reserved.

Exploiting the versatility of taste sensors based on impedance spectroscopy

The versatility of sensor arrays made from nanostructured Langmuir-Blodgett (LB) and layer-by-layer (LBL) films is demonstrated in two ways. First, different combinations of sensing units are employed to distinguish the basic tastes, viz. sweet, sour, bitter, and salty tastes, produced, respectively, by small concentrations (down to 0.01 g/mol) of sucrose, HCl, quinine, and NaCl solutions. The sensing units are comprised of LB and/or LBL films from semiconducting polymers, a ruthenium complex, and sulfonated lignin. Then, sensor arrays were used to identify wines from different sources, with the high distinguishing ability being demonstrated in principal component analysis (PCA) plots. Particularly important was the fact that the sensing ability does not depend on specific interactions between analytes and the film materials, but a judicious choice of materials is, nevertheless, required for the materials to respond differently to a given sample. It is also shown that the interaction with the analyte may affect the morphology of the nanostructured films, as indicated with scanning electron microscopy. For instance, in wine analysis these changes are not irreversible and the original film morphology is retrieved if the sensing unit is washed with copious amounts of water, thus allowing the sensor unit to be reused.

Fabrication and characterization of chemical sensors made from nanostructured films of poly(o-ethoxyaniline) prepared with different doping acids

Chemical sensors made from nanostructured films of poly(o-ethoxyaniline) POEA and poly(sodium 4-styrene sulfonate) PSS are produced and used to detect and distinguish 4 chemicals in solution at 20 mM, including sucrose, NaCl, HCl, and caffeine. These substances are used in order to mimic the 4 basic tastes recognized by humans, namely sweet, salty, sour, and bitter, respectively. The sensors are produced by the deposition of POEA/PSS films at the top of interdigitated microelectrodes via the layer-by-layer technique, using POEA solutions containing different dopant acids. Besides the different characteristics of the POEA/PSS films investigated by UV-Vis and Raman spectroscopies, and by atomic force microscopy.. it is observed that their electrical response to the different chemicals in liquid media is very fast, in the order of seconds, systematical, reproducible, and extremely dependent on the type of acid used for film fabrication. The responses of the as-prepared sensors are reproducible and repetitive after many cycles of operation. Furthermore, the use of an "electronic tongue" composed by an array of these sensors and principal component analysis as pattern recognition tool allows one to reasonably distinguish test solutions according to their chemical composition. (c) 2007 Published by Elsevier B.V.