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.

Oriented texture classification based on self-organizing neural network and Hough transform

This paper presents a technique for oriented texture classification which is based on the Hough transform and Kohonen's neural network model. In this technique, oriented texture features are extracted from the Hough space by means of two distinct strategies. While the first operates on a non-uniformly sampled Hough space, the second concentrates on the peaks produced in the Hough space. The described technique gives good results for the classification of oriented textures, a common phenomenon in nature underlying an important class of images. Experimental results are presented to demonstrate the performance of the new technique in comparison, with an implemented technique based on Gabor filters.

Automation in fault detection using neural network and model updating

In this article, an implementation of structural health monitoring process automation based on vibration measurements is proposed. The work presents an alternative approach which intent is to exploit the capability of model updating techniques associated to neural networks to be used in a process of automation of fault detection. The updating procedure supplies a reliable model which permits to simulate any damage condition in order to establish direct correlation between faults and deviation in the response of the model. The ability of the neural networks to recognize, at known signature, changes in the actual data of a model in real time are explored to investigate changes of the actual operation conditions of the system. The learning of the network is performed using a compressed spectrum signal created for each specific type of fault. Different fault conditions for a frame structure are evaluated using simulated data as well as measured experimental data.

Periapical tissue healing after post space preparation with or without use of a protection plug and root canal exposure to the oral environment. Study in dogs

The purpose of this study was to evaluate the influence of coronal leakage on the healing of dogs' periapical tissues after root canal filling, post space preparation and protection or not with a temporary sealer plug. Forty root canals of dogs' teeth were instrumented and filled by the lateral condensation technique with gutta-percha points and Endomethasone or CRCS sealers. After post space preparation, the remaining filling material was protected or not with a plug of temporary Coltosol sealer and exposed to the oral environment for 90 days. Thereafter, the animals were sacrificed and the specimens were removed and prepared for histomorphological and histobacteriological analysis. The findings revealed 35% of microbial leakage in the groups without plugs and 15% of leakage in the groups with plugs. Statistical analysis showed that the use of a Coltosol plug improved significantly the histomorphological results regardless of the type of root canal sealer (p=0.05) and that CRCS and Endomethasone sealers showed similar results (p>0.05).

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.

Microhardness of glass ionomer cements indicated for the ART technique according to surface protection treatment and storage time

The aim of this study was to assess the microhardness of 5 glass ionomer cements (GIC) - Vidrion R (V, SS White), Fuji IX (F, GC Corp.), Magic Glass ART (MG, Vigodent), Maxxion R (MR, FGM) and ChemFlex (CF, Dentsply) - in the presence or absence of a surface protection treatment, and after different storage periods. For each GIC, 36 test specimens were made, divided into 3 groups according to the surface protection treatment applied - no protection, varnish or nail varnish. The specimens were stored in distilled water for 24 h, 7 and 30 days and the microhardness tests were performed at these times. The data obtained were submitted to the ANOVA for repeated measures and Tukey tests (α = 5%). The results revealed that the mean microhardness values of the GICs were, in decreasing order, as follows: F > CF = MR > MG > V; that surface protection was significant for MR, at 24 h, without protection (64.2 ± 3.6a), protected with GIC varnish (59.6 ± 3.4b) and protected with nail varnish (62.7 ± 2.8ab); for F, at 7 days, without protection (97.8 ± 3.7ab), protected with varnish (95.9 ± 3.2b) and protected with nail varnish (100.8 ± 3.4a); and at 30 days, for F, without protection (98.8 ± 2.6b), protected with varnish (103.3 ± 4.4a) and protected with nail varnish (101 ± 4.1ab) and, for V, without protection (46 ± 1.3b), protected with varnish (49.6 ± 1.7ab) and protected with nail varnish (51.1 ± 2.6a). The increase in storage time produced an increase in microhardness. It was concluded that the different GICs, surface protection treatments and storage times could alter the microhardness values.

Preprocessing data for short-term load forecasting with a general regression neural network and a moving average filter

This paper proposes a filter based on a general regression neural network and a moving average filter, for preprocessing half-hourly load data for short-term multinodal load forecasting, discussed in another paper. Tests made with half-hourly load data from nine New Zealand electrical substations demonstrate that this filter is able to handle noise, missing data and abnormal data. © 2011 IEEE.

Adolescent vulnerability to cardiovascular consequences of chronic social stress: Immediate and long-term effects of social isolation during adolescence

It has been demonstrated that disruption of social bonds and perceived isolation (loneliness) are associated with an increased risk of cardiovascular morbidity and mortality. Adolescence is proposed as a period of vulnerability to stress. Nevertheless, the impact of chronic social stress during this ontogenic period in cardiovascular function is poorly understood. Therefore, the purpose of this study was to compare the impact in cardiovascular function of social isolation for 3 weeks in adolescent and adult male rats. Also, the long-term effects of social isolation during adolescence were investigated longitudinally. Social isolation reduced body weight in adolescent, but not in adult animals. Disruption of social bonds during adolescence increased arterial pressure without affecting heart rate and pulse pressure (PP). Nevertheless, social isolation in adulthood reduced systolic arterial pressure and increased diastolic arterial pressure, which in turn decreased PP without affecting mean arterial pressure. Cardiovascular changes in adolescents, but not adults, were followed by facilitation of both baroreflex sensitivity and vascular reactivity to the vasodilator agent acetylcholine. Vascular responsiveness to either the vasodilator agent sodium nitroprusside or the vasoconstrictor agent phenylephrine was not affected by social isolation. Except for the changes in body weight and baroreflex sensitivity, all alterations evoked by social isolation during adolescence were reversed in adulthood after moving animals from isolated to collective housing. These findings suggest a vulnerability of adolescents to the effects of chronic social isolation in cardiovascular function. However, results indicate minimal cardiovascular consequences in adulthood of disruption of social bonds during adolescence. © 2015 Wiley Periodicals, Inc. Develop Neurobiol, 2015.

Explorando potencialidades para a criação de rede de apoio social a mulheres lusófonas que vivem com câncer de mama em Toronto, Canadá

Introduction: Health indicators tend to be altered due to the participation of people in social networks. Objective: To find out ideas of individuals belonging to Portuguese speaking communities in Toronto, Canada, about the possibility of creating a social support network for women experiencing breast cancer. Method: Nineteen participants of the present ethnographic and critical study answered to questions, providing their opinions regarding to the social support network and its positive and negative aspects. Also, the participants suggested other possible individuals who could participate and help in the creation of such network. Discussions were transcribed, analysed and coded using qualitative software called Atlas ti 6.0. Results: The main components for the creation of the social support network were: the demystification of breast cancer and its prevention, emphasis in health education, dissemination of the need of volunteers and a direct social support to those women. The positive aspects were the participation of oldest women as social leaders and the utilization of schools and religious institutions for publicity. Negative aspects that were perceived as barriers are: the belief that breast cancer is a disease lived by women, the lack of knowledge about its cure and rehabilitation, as well as a collective sensitiveness to it. Also, about the participation of community leaders, the suggestions were: diplomats, priests and pastors, schools directors and communication entrepreneurs. Conclusion: The creation of the social support network should consider the cultural sensitiveness and the inner diversity of the consulted Portuguese speaking communities. Due to the insufficient number of Angolan participants to sustain a major analysis, a special recommendation was that Angolan social leaders and professionals should be invited to design the structure of such network according to their specific cultural traits.

Comparative analysis of different meat traceability systems using multiple criteria and a social network approach

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)