No abstract

Minimal siphons in the class of S 4 P R nets have become a conceptual and practical central tool to deal with deadlocks caused by the sharing of resources in Flexible Manufacturing Systems. The availability of efficient algorithms to compute these structural objects is very important. In this paper we take advantage from the particular properties of the siphons in S 4 P R to obtain an efficient algorithm. These properties allow to compute the minimal siphons from a generating family of minimal siphons. This family is composed by the minimal siphons containing only one resource. The computation of the minimal siphons is based in the maximal strongly connected components of a graph representing the relations between the siphons of the generating family. The algorithm is very economic in memory in all intermediate steps with respect to the classical algorithms.

Skin lesions are one of the typical symptoms of many diseases in humans and indicative of many types of cancer worldwide. Increased risks caused by the effects of climate change and a high cost of treatment, highlight the importance of skin cancer prevention efforts like this. The methods used to detect these diseases vary from a visual inspection performed by dermatologists to computational methods, and the latter has widely used automatic image classification applying Convolutional Neural Networks (CNNs) in medical image analysis in the last few years. This article presents an approach that uses CNNs with a NASNet architecture to recognize in a more accurate way, without segmentation, eight skin diseases. The model was trained end-to-end on Keras with augmented skin diseases images from the International Skin Imaging Collaboration (ISIC). The CNN architectures were initialized with weight from ImageNet, fine-tuned in order to discriminate well among the different types of skin lesions, and then 10-fold cross-validation was applied. Finally, some evaluation metrics are calculated as accuracy, sensitivity, and specificity and compare with other CNN trained architectures. This comparison shows that the proposed system offers higher accuracy results, with a significant reduction on the training paraments. To the best of our knowledge and based in the state-of-art recompiling in this work, the application of the NASNet architecture training with skin image lesion from ISIC archive for multi-class classification and evaluated by cross-validation, represents a novel skin disease classification system.

No abstract

In recent years, the integration of new elements to the electric grid, such as electric vehicles and renewable energies, requires the evolution of the electric grid as we know it, making it necessary to optimize the processes of production, distribution, and storage of energy. This situation gives rise to introducing the so-called Smart Grids (SG), which would allow a balance between energy supply and demand, thus enabling a system in which the consumer will also become a producer of its surplus energy. Under this scenario, this work proposes an architecture whose technological components, such as the internet of things (IoT), artificial intelligence (AI), cloud computing, and mobile applications, allow users to address the problem of consumption and production of electricity. In the experiments conducted, results were obtained from the components that support the functionality of the proposed platform.