Abstract
Through the years, several CAD systems have been developed to help radiologists in the hard task of detecting signs of cancer in the numerous screening mammograms. A more recent trend includes the development of pre-CAD systems aiming at identifying normal mammograms instead of detecting suspicious ones. Normal breasts are screened-out from the process, leaving radiologists more time to focus on more difficult cases. In this work, a new approach for the identification of normal breasts is presented. Considering that even breasts with malignant findings are mostly constituted by normal tissue, the breast area is divided into blocks which are then compared pairwise. If all blocks are very similar, the breast is labelled as normal, and as suspicious otherwise. Features characterizing the pairwise block similarity and characterizing the intra-block pixel distribution are used to design a predictive method based on machine learning techniques. The proposed solution was applied on a real world screening setting composed by nearly 18000 mammograms. Results are similar to the more complex state of the art approaches by correctly identifying more than 20% of the normal mammograms. These results suggest the usefulness of the relative comparison instead of the absolute classification. When properly used, simple statistics can suffice to distinguish the clearly normal breasts.

Abstract
In our daily life, we often have the feeling of being exhausted due to mental or physical work, and a sense of performance degradation in the execution of simple tasks. The maximum capacity of operation and performance of an individual, whether physical or mental, usually also decreases gradually as the day progresses. The loss of these resources is linked to the onset of fatigue, which is particularly noticeable in long and demanding tasks or repetitive jobs. However, good management of the working time and effort invested in each task, as well as the effect of breaks at work, can result in better performance and better mental health, delaying the effects of fatigue. This paper details a non-invasive approach on the monitoring of fatigue of a human being, based on the analysis of the performance of his interaction with the computer.

Abstract
This paper attempts to propose a fair solution in generation scheduling problem in the presence of inherent uncertainties in short-term power system operation. The proposed methodology incorporates probabilistic methodology in the uncertainties representation section, while harmony search algorithm is adopted as a fast and reliable soft computing algorithm to solve the proposed nonlinear, non-convex, large-scaled and combinatorial problem. As an indispensable step towards a more economical power system operation, the optimal generation scheduling strategy in the presence of mixed hydro-thermal generation mix, deemed to be the most techno-economically efficient scheme, comes to the play and is profoundly taken under concentration in this study. This paper devises a comprehensive hybrid optimisation approach by which all the crucial aspects of great influence in the generation scheduling process can be accounted for. Two-point estimation method is also adopted probabilistically approaching the involved uncertain criteria. In the light of the proposed methodology being implemented on an adopted test system, the anticipated efficiency of the proposed method is well verified. © 2014 Taylor & Francis.

Abstract
In previous work we proposed a performance analysis model for automatically identifying potential root causes of performance problems in personal software development. In this paper we present an approach for automatically ranking those potential root causes based on a cost-benefit estimate that takes into account historical data. The approach was applied for the Personal Software Process, taking advantage of a large data set referring to more than 30,000 projects, but can be replicated in other contexts.

Abstract

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.