Abstract
Heart rate variability (HRV) analysis has been used as a quantitative marker of the autonomous nervous system activity to measure mental stress. Wearable sensors have been emerging as a solution to collect HRV data for stress assessment in a real context, however such studies raise additional requirements. The wearable system must be minimally obtrusive to allow the subjects to perform their tasks without interference, and inconspicuous to avoid the anxiety associated with wearing medical devices in public. The purpose of this study was to quantify the accuracy trade-off in the use of a chest band heart rate sensor that is less intrusive and less costly than a wearable electrocardiogram (ECG). The HRV metrics extracted from a chest band heart rate monitor, Zephyr HxM (TM) (Zph (TM)), were compared with those extracted from an ECG certified medical device, Vital Jacket (TM) (VJ (TM)). The two systems were worn simultaneously. under laboratory conditions by a population of 14 young and healthy subjects, aged 20 to 26 years, under the stress induced by the Trier Social Stress Test (TSST) procedure. The results showed a mean difference between RR intervals of 9 ms; a. root-mean square error. (RMSE) of less than 8% and. a Pearson's correlation higher than 0.946, considering all TSST phases. In the HRV analysis, the average of all normal intervals (AVNN) showed errors less than 2% between the two systems with a correlation higher than 0.99 for all TSST phases. We thus conclude that the used chest band sensor represents an alternative to the current wearable medical devices to monitor RR intervals, and could be used for mental stress monitoring similar to the TSST protocol.

Abstract
Cancer genome projects are characterizing the genome, epigenome and transcriptome of a large number of samples using the latest high-throughput sequencing assays. The generated data sets pose several challenges for traditional statistical and machine learning methods. In this work we are interested in the task of deriving the most informative genes from a cancer gene expression data set. For that goal we built denoising autoencoders (DAE) and stacked denoising autoencoders and we studied the influence of the input nodes on the final representation of the DAE. We have also compared these deep learning approaches with other existing approaches. Our study is divided into two main tasks. First, we built and compared the performance of several feature extraction methods as well as data sampling methods using classifiers that were able to distinguish the samples of thyroid cancer patients from samples of healthy persons. In the second task, we have investigated the possibility of building comprehensible descriptions of gene expression data by using Denoising Autoencoders and Stacked Denoising Autoencoders as feature extraction methods. After extracting information related to the description built by the network, namely the connection weights, we devised post-processing techniques to extract comprehensible and biologically meaningful descriptions out of the constructed models. We have been able to build high accuracy models to discriminate thyroid cancer from healthy patients but the extraction of comprehensible models is still very limited.

Abstract
Nowadays imbalanced learning represents one of the most vividly discussed challenges in machine learning. In these scenarios, one or some of the classes in the problem have a significantly lower a priori probability, usually leading to trivial or non-desirable classifiers. Because of this, imbalanced learning has been researched to a great extent by means of different approaches. Recently, the focus has switched from binary classification to other paradigms where imbalanced data also arise, such as ordinal classification. This paper tests the application of learning pairwise ranking with multiple granularity levels in an ordinal and imbalanced classification problem where the aim is to construct an accurate model for donor-recipient allocation in liver transplantation. Our experiments show that approaching the problem as ranking solves the imbalance issue and leads to a competitive performance.

Abstract
A fundamental question that often occurs in statistical tests is the normality of distributions. Countless distributions exist in science and life, but one distribution that is obtained via permutations, usually referred to as permutation distribution, is interesting. Although a permutation distribution should behave in accord with the central limit theorem, if both the independence condition and the identical distribution condition are fulfilled, no studies have corroborated this concurrence in functional magnetic resonance imaging data. In this work, we used Anderson-Darling test to evaluate the accordance level of permutation distributions of classification accuracies to normality expected under central limit theorem. A simulation study has been carried out using functional magnetic resonance imaging data collected, while human subjects responded to visual stimulation paradigms. Two scrambling schemes are evaluated: the first based on permuting both the training and the testing sets and the second on permuting only the testing set. The results showed that, while a normal distribution does not adequately fit to permutation distributions most of the times, it tends to be quite well acceptable when mean classification accuracies averaged over a set of different classifiers is considered. The results also showed that permutation distributions can be probabilistically affected by performing motion correction to functional magnetic resonance imaging data, and thus may weaken the approximation of permutation distributions to a normal law. Such findings, however, have no relation to univariate/univoxel analysis of functional magnetic resonance imaging data. Overall, the results revealed a strong dependence across the folds of cross-validation and across functional magnetic resonance imaging runs and that may hinder the reliability of using cross-validation. The obtained p-values and the drawn confidence level intervals exhibited beyond doubt that different permutation schemes may beget different permutation distributions as well as different levels of accord with central limit theorem. We also found that different permutation schemes can lead to different permutation distributions and that may lead to different assessment of the statistical significance of classification accuracy.

Abstract
Breast cancer is one of the main causes of cancer death worldwide. The diagnosis of biopsy tissue with hematoxylin and eosin stained images is non-trivial and specialists often disagree on the final diagnosis. Computer-aided Diagnosis systems contribute to reduce the cost and increase the efficiency of this process. Conventional classification approaches rely on feature extraction methods designed for a specific problem based on field-knowledge. To overcome the many difficulties of the feature-based approaches, deep learning methods are becoming important alternatives. A method for the classification of hematoxylin and eosin stained breast biopsy images using Convolutional Neural Networks (CNNs) is proposed. Images are classified in four classes, normal tissue, benign lesion, in situ carcinoma and invasive carcinoma, and in two classes, carcinoma and non-carcinoma. The architecture of the network is designed to retrieve information at different scales, including both nuclei and overall tissue organization. This design allows the extension of the proposed system to whole-slide histology images. The features extracted by the CNN are also used for training a Support Vector Machine classifier. Accuracies of 77.8% for four class and 83.3% for carcinoma/non-carcinoma are achieved. The sensitivity of our method for cancer cases is 95.6%.

Abstract
Image quality assessment has been a topic of intense research over the last decades. Although its application to other disciplines is growing tremendously, its use in retinal imaging is still immature and some fundamental challenges remain unsolved. Thus, we present a research methodology for the objective assessment of the quality in retinal images. The methodology can be used as a preliminary step in any computer-aided system, and is composed of four main steps: the location of the region-of-interest, the extraction of relevant image properties and their analysis by feature selection, and the final binary classification into two classes (good and poor quality). The experimental results demonstrate the adequacy of the proposed methodology in this context, being able to objectively assess the quality of retinal images with an accuracy over 99%.