Antonio C. de C. Lima

Web Environment for Programming and Control of a Mobile Robot in a Remote Laboratory

Remote robotics laboratories have been successfully used for engineering education. However, few of them use mobile robots to to teach computer science. This article describes a mobile robot Control and Programming Environment (CPE) and its pedagogical applications. The system comprises a remote laboratory for robotics, an online programming tool, and a virtual learning environment. It allows experiments with a mobile robot to be carried out, tested and validated remotely, using a simple graphic interface via web browser, without additional software installation on the users computer. Students can control and manipulate the robot with simple commands without worrying about hardware details or use C/C++ programming language to develop complex programs. The robot has been built with inexpensive components and has sensors that enable its use in several experiments. CPE can be used in contextualized teaching in various subjects of computer science, both in class and at distance. A practical application of the whole system using CPE, introducing programming concepts, is also described in this paper. The initial assessment of the environment as an educational tool shows high levels of interest among our students, an improvement in their academic scores, and potential for application in the context of computing education, when properly introduced as a learning tool.

METHOD THRESHOLDING AUTOMATIC FOR SOMATIC CELL COUNT IN MICROSCOPIC IMAGES

The objective of this work was to present a segmentation method and somatic cell count of bovine milk for images obtained directly from the optical microscope through a proposal for automatic threshold. For purposes of verifying efficiency of the technique, proposed thresholding method was compared with two thresholding methods known in the literature. The correlation between the manual reference counting and thresholding methods tested was 0.98, 0.71 and 0.12, respectively. The proposed method acceptable correlation demonstrating efficiency of this algorithm for thresholding and somatic cell count and other similar applications. Key-words: microscope; Rosin thresholding; Otsu thresholding.

Diagnóstico Automático de Reguladores de Tensão Utilizando Algoritmos Genéticos e Redes Neurais

On Load Tap Changers (OLTC) are widely used for voltage regulation in electricity networks. Non-invasive vibration methods for condition monitoring of internal electrical contacts have been recently proposed in the literature. The vibration signals emitted during the tap changes are usually recorded and post-processed using spectral analysis and some pattern classifier technique. To reduce the complexity of the Neural classifier, a new technique based on Genetic Algorithm is proposed in this paper. A description of the data acquisition system and the corresponding collected experimental data are presented. The proposed technique is detailed and preliminary experimental results are discussed.

Neural Equalizer Performance Evaluation Using Genetic Algorithm

Artificial Neural Networks (ANN) have been successfully applied to deal with linear or nonlinear problems. The best ANN architecture choice is not a trivial task to be performed and requires some a priori knowledge. In this work, we propose a Genetic Algorithm (GA) evaluation approach to determine the best combination of ANN and learning algorithm for equalization propose. A comparative analysis, using well known neural architectures, is presented in order to accomplish a 4-QAM equalization of signals submitted to Inter Symbol Interference (ISI), inherent in typical mobile communication channels. MLP, FLANN, PPN and three RNN based ANN structures, trained using backpropagation algorithm and others, have been evaluated.