Abstract
In this paper we introduce a new conceptualization for the reduction of the number of support vectors (SVs) for an efficient design of support vector machines. The techniques here presented provide a good balance between SVs reduction and generalization capability. Our proposal explores concepts from classification with reject option. These methods output a third class (the rejected instances) for a binary problem when a prediction cannot be given with sufficient confidence. Rejected instances along with misclassified ones are discarded from the original data to give rise to a classification problem that can be linearly solved. Our experimental study on two benchmark datasets show significant gains in terms of SVs reduction with competitive performances.

Abstract
The signal of the wireless sensor network in grounding grid, owing to energy loss, network congestion, path constraints and other factors, is easy to delay even partially losing. In order to ensure that the signal can be transmitted effectively in grounding grids for the substation, this paper presents a method based on traffic model of back-off balanced multiple sensor network cooperation model. As we all know, cognitive radio (CR) technology is adopted in multi-channel wireless networks to provide enough channels for data transmission. The MAC protocols should enable the secondary users to maintain the accurate channel state information to identify and utilize the leftover frequency spectrum in a way that constrains the level of interference to the primary users. We proposed a novel cooperation spectrum sensing scheme in which the secondary users adopt backoff-based sensing policy based on the traffic model of the primary users to maximum the throughput of the network. To obtain the full accurate information of the spectrum is a difficult task so that we propose the backoff sensing as a sub-optimal strategy. Since the secondary users sense only a subset of the channels in our proposed scheme, less time is spent to get the channel state information as more time is saved for the data transmission. And while dealing the signal data, I combine the intensity transfer method instead of the priority method. This can effectively reduce the network congestion, to ensure that the main information can be transfer well. It is also very useful to signal transmission for the Multi-sensor in Substations Grounding Grid (SGG).

Abstract
The hospitalization of patients with Heart Failure represents an increasing burden for the healthcare system with more than 23 million worldwide suffering from this disease. In this paper we explore methods to detect fluid retention in the lungs by measuring the thoracic impedance, so that is possible to monitor Heart Failure patients, and physicians can early detect acute episodes. A small and portable device was developed to measure the thoracic impedance of the patient. From the measured thoracic impedance it can estimate the accumulation of fluid in the lungs. This device is a low cost, friendly to use equipment that can be operated by a big range of users: Moreover, it was designed for low power consumption with a rechargeable battery for portable use. The device empowers the patient to monitor his own body fluid at home, and a physician can follow him remotely. This procedure would help to drastically reduce the number of hospitalizations and, consequently, improve the quality of life of people diagnosed with Heart Failure.

Abstract

Abstract
Through the years, several CAD systems have been developed to help radiologists in the hard task of detecting signs of cancer in mammograms. In these CAD systems, mass segmentation plays a central role in the decision process. In the literature, mass segmentation has been typically evaluated in a intra-sensor scenario, where the methodology is designed and evaluated in similar data. However, in practice, acquisition systems and PACS from multiple vendors abound and current works fails to take into account the differences in mammogram data in the performance evaluation. In this work it is argued that a comprehensive assessment of the mass segmentation methods requires the design and evaluation in datasets with different properties. To provide a more realistic evaluation, this work proposes: a) improvements to a state of the art method based on tailored features and a graph model; b) a head-to-head comparison of the improved model with recently proposed methodologies based in deep learning and structured prediction on four reference databases, performing a cross-sensor evaluation. The results obtained support the assertion that the evaluation methods from the literature are optimistically biased when evaluated on data gathered from exactly the same sensor and/or acquisition protocol.

Abstract
Despite the existence of patterns able to discriminate between consensual and non-consensual intercourse, the relevance of genital lesions in the corroboration of a legal rape complaint is currently under debate in many countries. The testimony of the physicians when assessing these lesions has been questioned in court due to several factors (e.g., a lack of comprehensive knowledge of lesions, wide spectrum of background area, among others). Therefore, it is relevant to provide automated tools to support the decision process in an objective manner. In this work, we evaluate the performance of state-of-the-art deep learning architectures for the forensic assessment of sexual assault. We propose a deep architecture and learning strategy to tackle the class imbalance on deep learning using ranking. The proposed methodologies achieved the best results when compared with handcrafted feature engineering and with other deep architectures .