Abstract
Alternative splicing is the mechanism by which different combinations of exons in the pre-mRNA give rise to distinct mature mRNAs. This process is mediated by splicing factors that bind the pre-mRNA and affect the recognition of its splicing signals. Saccharomyces species lack many of the regulatory factors present in metazoans. Accordingly, it is generally assumed that the amount of alternative splicing is limited. However, there is recent compelling evidence that yeast have functional alternative splicing, mainly in response to environmental conditions. We have previously shown that sequence and structure properties of the pre-mRNA could explain the selection of 3' splice sites (ss) in Saccharomyces cerevisiae. In this work, we extend our previous observations to build a computational classifier that explains most of the annotated 3'ss in the CDS and 5' UTR of this organism. Moreover, we show that the same rules can explain the selection of alternative 3'ss. Experimental validation of a number of predicted alternative 3'ss shows that their usage is low compared to annotated 3'ss. The majority of these alternative 3'ss introduce premature termination codons (PTCs), suggesting a role in expression regulation. Furthermore, a genome-wide analysis of the effect of temperature, followed by experimental validation, yields only a small number of changes, indicating that this type of regulation is not widespread. Our results are consistent with the presence of alternative 3'ss selection in yeast mediated by the pre-mRNA structure, which can be responsive to external cues, like temperature, and is possibly related to the control of gene expression.

Abstract
In spite of the growing interest verified in the field of technology-based interventions for Stroke rehabilitation, there is still no global solution that is both successful and suitable for a widespread use [1,2]. In this article, we present a novel tele-rehabilitation tool designed to be used for ambulatory patients, and developed towards the motor recovery of the patient's upper-limb. The SWORD system combines a movement quantification system that analyzes the quality of the motor task performed with a biofeedback console. The proposed structure defines the SWORD system as a complete tele-rehabilitation framework that enables a direct connection between clinical and ambulatory settings. Currently a randomized clinical trial is being designed in order to assess the effectiveness of the SWORD tele-rehabilitation system.

Abstract
Wearable technologies have been evolving towards daily usage and are a major player in the personalized health challenge. In this paper we present a personal view of their evolution, how one of them developed within our lab went to the international market and how this type of technology is being used in pHealth projects for first responder professionals and public transportation drivers.

Abstract
Depression is expected to be the disorder with the highest disease burden in high-income countries by the year 2030. ICT4Depression (ICT4D) is a European FP7 project, which aims to contribute to the alleviation of this burden by making use of depression treatment and ICT innovations. In this project we developed an ICT-based system for use in primary care that aims to improve access as well as actual care delivery for depressed adults. Innovative technologies within the ICT4D system include 1) flexible self-help treatments for depression, 2) automatic assessment of the patient using mobile phone and web-based communication 3) wearable biomedical sensor devices for monitoring activities and electrophysiological indicators, 4) computational methods for reasoning about the state of a patient and the risk of relapse (reasoning engine) and 5) a flexible system architecture for monitoring and supporting people using continuous observations and feedback via mobile phone and the web. The general objective of the ICT4D project is to test the feasibility and acceptability of the ICT4D system within a pilot study in the Netherlands and in Sweden during 2012 and 2013. © 2012 Interactive Media Institute and IOS Press.

Abstract
Permutation tests have extensively been used to estimate the significance of classification. Permutation tests usually use the test error as a dataset statistic to measure the difference between two or more populations. Then, to estimate the p-value(s), the test error is compared to a set of permuted test-error(s), which is usually obtained after permuting the labels of the populations. In this study, we investigate how several dataset factors, e.g., the number of samples, the number of classes, and the dimensionality size, may affect the p-value obtained via permutation tests. We performed the analysis using the standard permutation test procedure that uses the overall all test error dataset statistic and compared it to the permutation test procedure that uses per-class test error as a dataset statistic that we recently have proposed (doi:10.1016/j.neucom.2011.11.007). We found that permutation tests that use a per-class test error as a dataset statistic are not only more reliable in addressing the null hypothesis but also are highly sensitive to changes in the dataset factors that we investigated in this work. An important finding of this study is that when the dimensionality is low and the number of classes is up to several, say ten, highly above chance accuracy would be required to state the significance. For the same low dimensionality, however, slightly above chance accuracy would be adequate to state significance in a two-class problem.

Abstract
There has been increasing interest in pattern classification methods and neuroimaging studies using permutation tests to estimate the statistical significance of a classifier (p-value). Permutation tests usually use the test error as a dataset statistic to estimate the p-value(s) by measuring the dissimilarity between two or more populations. Using the test error as a dataset statistic; however, may camouflage the lowest recognizable classes, and the resulting p-value will be biased toward better values (usually lower values) because of the highly recognizable classes; thus, lower p-values could sometimes be the result of undercoverage. In this study, we investigate this problem and propose the implementation of permutation tests based on a per-class test error as a dataset statistic. We also propose a model that is based on partially scrambling the testing samples (in this model, the training samples are not scrambled) when computing the non-permuted statistic in order to judge the p-value's tolerance and to draw conclusions regarding, which permutation test procedures are more reliable. For the same purpose, we propose another model that is based on chance-level shifting of the permuted statistic. We tested these two proposed models on functional magnetic resonance imaging data that were collected while human subjects responded to visual stimulation paradigms, and our results showed that these models can aid in determining, which permutation test procedure is superior. We also found that permutation tests that use a per-class test error as a dataset statistic are more reliable in addressing the null hypothesis that all classes in the problem domain are drawn from the same distribution.