Abstract
Traditional machine learning systems learn from non-relational data but in fact most of the real world data is relational. Normally the learning task is done using a single flat file, which prevents the discovery of effective relations among records. Inductive logic programming and statistical relational learning partially solve this problem. In this work, we resource to another method to overcome this problem and propose the T-SPPA: Trended Statistical PreProcessing Algorithm, a preprocessing method that translates related records to one single record before learning. Using different kinds of data, we compare our results when learning with the transformed data with results produced when learning from the original data to demonstrate the efficacy of our method.

Abstract

Abstract
The amplitude modulations of musical instrument sounds and speech are important perceptual cues. Accurate estimation of the amplitude, or equivalently energy, envelope of a time-domain signal (waveform) is not a trivial task, though. Ideally, the amplitude envelope should outline the waveform connecting the main peaks and avoiding over fitting. In this work we propose a method to obtain a smooth function that approximately matches the main peaks of the waveform using true envelope estimation, dubbed true amplitude envelope. True envelope is a cepstral smoothing technique that has been shown to outperform traditional envelope estimation techniques both in accuracy of estimation and ease of order selection. True amplitude envelope gives a reliable estimation that follows closely sudden variations in amplitude and avoids ripples in more stable regions with near optimal order selection depending on the fundamental frequency of the signal.

Abstract
BioStories is the outcome of a four-year research project focused in uniting affective and ubiquitous computing with context aware multimedia environments real-time generation. Its initial premise was based in the possibility of performing real-time automatic emotion assessment trough online biometric channels monitoring and use this information to design on-the-fly dynamic multimedia storylines emotionally adapted, so that end users would unconsciously be determining the story graph. The emotion assessment process was based on biometric channels dynamic fusion such as EEG, GSR, respiration rate and volume, skin temperature and heart rate on top of Russell's circumplex model of affect. BioStories' broad scope also allowed for some spin-off projects namely mouse control through EMG that resulted in a tested technology for alternative/inclusive interfaces. Exhaustive experiments showed 86% of success rate for emotion assessment, IC(95%)(p)approximate to(0.81, 0.90), in a dynamic tridimensional virtual environment with an immersiveness user score of 4.3 out of 5. The success of the proposed approach allows the vision of its appliance in several domains such as virtual entertainment, videogames and cinema as well as direct marketing, digital TV and domotic appliances.

Abstract
This paper is a systematic study of verification conditions and their use in the context of program verification. We take Hoare logic as a starting point and study in detail how a verification conditions generator can be obtained from it. The notion of program annotation is essential in this process. Weakest preconditions and the use of updates are also studied as alternative approaches to verification conditions. Our study is carried on in the context of a While language. Important extensions to this language are considered toward the end of the paper. We also briefly survey modern program verification tools and their approaches to the generation of verification conditions. © 2011 Elsevier Inc.

Abstract
Breast screening is the regular examination of a woman's breasts to find breast cancer earlier. The sole exam approved for this purpose is mammography. Usually, findings are annotated through the Breast Imaging Reporting and Data System (BIRADS) created by the American College of Radiology. The BIRADS system determines a standard lexicon to be used by radiologists when studying each finding. Although the lexicon is standard, the annotation accuracy of the findings depends on the experience of the radiologist. Moreover, the accuracy of the classification of a mammography is also highly dependent on the expertise of the radiologist. A correct classification is paramount due to economical and humanitarian reasons. The main goal of this work is to produce machine learning models that predict the outcome of a mammography from a reduced set of annotated mammography findings. In the study we used a data set consisting of 348 consecutive breast masses that underwent image guided or surgical biopsy performed between October 2005 and December 2007 on 328 female subjects. The main conclusions are threefold: (1) automatic classification of a mammography, independent on information about mass density, can reach equal or better results than the classification performed by a physician; (2) mass density seems to be a good indicator of malignancy, as previous studies suggested; (3) a machine learning model can predict mass density with a quality as good as the specialist blind to biopsy, which is one of our main contributions. Our model can predict malignancy in the absence of the mass density attribute, since we can fill up this attribute using our mass density predictor.