Search

In this paper an explanation of the structure and how a self-organized neuro-fuzzy inference system (SONFIS) works, is given with detail. The study uses three classification problems (Fisher iris, Breast Cancer and Human Activities) to then compare the results with well-known universal classifiers such as artificial neural networks (ANN) and multiclass support vector machines (SVM). A brief description of each of these methods is presented. The results show that SONFIS has a similar, and sometimes better, performance than ANN and SVM with the advantage of generating a rule basis that helps understanding the inner structure of the problem. [ABSTRACT FROM AUTHOR]

The objective of this paper was the development of a content-based image retrieval system, using siamese and triplet convolutional neural networks. These networks were used to generate visual descriptors, extracting semantic information from two images (siamese) or three images (triplet) at the same time. Then, a similarity learning was done, encoding these two or three visual descriptors. In the proposed scheme the storage of descriptors is not required. The experimental results show that the schemes based on convolutional neural networks extract more semantic information. The siamese and triplet architectures, apart from extracting semantic information, improved the image retrieval rate. It is concluded that the proposed scheme solved three of the main challenges in these systems, such as, semantic gap, similarity learning and storage space, which have not been solved in the previous works. [ABSTRACT FROM AUTHOR]

In this paper, the creation and application of two Intelligent Virtual Environments (IVE) with Artificial Neural Networks (ANN) are presented. In one EVI, the diagnosis of vision problems like astigmatism, myopia and hyperopia is studied. The other one focuses to the perception and reasoning of warning signals in a work environment. For the development of this paper, the characterization of Artificial Neural Networks is done, followed by the simulation; according to the results one network architecture is selected (Multilayer Perceptron) and then implemented in the IVE. Finally the time constraints in ANN learning and in computational cost applied to IVE are discussed. [ABSTRACT FROM AUTHOR]

This paper presents a methodology for optimal Distributed Generation (DG) allocation using a hybrid genetic algorithm. In this case, the objective function is the minimization of power losses. The proposed algorithm involves an artificial neural network to evaluate the fitness function and a local search subroutine that allows the algorithm to explore a wider search space, and eventually, escape from local optimal solutions. The proposed approach was tested on a 34-bus system showing that the proper allocation of DG units allows the reduction of active power losses and the improvement of voltage profile. [ABSTRACT FROM AUTHOR]