Abstract
Reject option is a technique used to improve classifier's reliability in decision support systems. It consists on withholding the automatic classification of an item, if the decision is considered not sufficiently reliable. The rejected item is then handled by a different classifier or by a human expert. The vast majority of the works on this issue have been concerned with implementing a reject option by endowing a supervised learning scheme (e.g., Multilayer Perceptron, Learning Vector Quantization or Support Vector Machines) with a reject mechanism. In this paper we introduce variants of the Self-Organizing Map (SOM), originally an unsupervised learning scheme, to act as supervised classifiers with reject option, and compare their performances with that of the MLP classifier. © 2014 Springer International Publishing Switzerland.

Abstract
In recent years, periocular recognition has become a popular alternative to face and iris recognition in less ideal acquisition scenarios. An interesting example of such scenarios is the usage of mobile devices for recognition purposes. With the growing popularity and easy access to such devices, the development of robust biometric recognition algorithms to work under such conditions finds strong motivation. In the present work we assess the performance of extended versions of two state-of-the-art periocular recognition algorithms on the publicly available CSIP database, a recent dataset composed of images acquired under highly unconstrained and multi-sensor mobile scenarios. The achieved results show each algorithm is better fit to tackle different scenarios and applications of the biometric recognition problem.

Abstract
Breast cancer conservative treatment (BCCT) is now the preferred technique for breast cancer treatment. The limited reproducibility of standard aesthetic evaluation methods led to the development of objective methods, such as the software tool Breast Cancer Conservative Treatment.cosmetic results (BCCT.core). Although results are satisfying, there are still limitations concerning complete automation and the inability to measure volumetric information. With the fundamental premise of maintaining the system a low-cost tool, this work studies the incorporation of the Microsoft Kinect sensor in BCCT evaluations. The aim is to enable the automatic joint detection of prominent points, both on depth and RGB images. Afterwards, using those prominent points, it is possible to obtain two-dimensional and volumetric features. Finally, the aesthetic result is achieved using machine learning techniques converted automatically from the set of measures defined. Experimental results show that the proposed algorithm is accurate and robust for a wide number of patients. In addition, comparing with previous research, the procedure for detecting prominent points was automated. © 2013 © 2013 Taylor & Francis.

Abstract
We study the problem of learning lexicographic preferences on multiattribute domains, and propose Rankdom Forests as a compact way to express preferences in learning to rank scenarios. We start generalizing Conditional Lexicographic Preference Trees by introducing multiple kernels in order to handle non-categorical attributes. Then, we define a learning strategy for inferring lexicographic rankers from partial pairwise comparisons between options. Finally, a Lexicographic Ensemble is introduced to handle multiple weak partial rankers, being Rankdom Forests one of these ensembles. We tested the performance of the proposed method using several datasets and obtained competitive results when compared with other lexicographic rankers.

Abstract
Deep Transfer Learning (DTL) emerged as a new paradigm in machine learning in which a deep model is trained on a source task and the knowledge acquired is then totally or partially transferred to help in solving a target task. Even though DTL offers a greater flexibility in extracting high-level features and enabling feature transference from a source to a target task, the DTL solution might get stuck at local minima leading to performance degradation-negative transference-, similar to what happens in the classical machine learning approach. In this paper, we propose the Source-Target-Source (STS) methodology to reduce the impact of negative transference, by iteratively switching between source and target tasks in the training process. The results show the effectiveness of such approach.

Abstract