Abstract
In the predictive modeling tasks, a clear distinction is often made between learning problems that are supervised or unsupervised, the first involving only labeled data (training patterns with known category labels) while the latter involving only unlabeled data. There is a growing interest in a hybrid setting, called semi-supervised learning, in semi-supervised classification, the labels of only a small portion of the training data set are available. The unlabeled data, instead of being discarded, are also used in the learning process. Motivated by a breast cancer application, in this work we address a new learning task, in-between classification and semi-supervised classification. Each example is described using two different feature sets, not necessarily both observed for a given example. If a single view is observed, then the class is only due to that feature set, if both views are present the observed class label is the maximum of the two values corresponding to the individual views. We propose new learning methodologies adapted to this learning paradigm and experimentally compare them with baseline methods from the conventional supervised and unsupervised settings. The experimental results verify the usefulness of the proposed approaches. © 2011 IEEE.

Abstract

Abstract
Feature selection is a topic of growing interest mainly due to the increasing amount of information, being an essential task in many machine learning problems with high dimensional data. The selection of a subset of relevant features help to reduce the complexity of the problem and the building of robust learning models. This work presents an adaptation of a recent quadratic programming feature selection technique that identifies in one-fold the redundancy and relevance on data. Our approach introduces a non-probabilistic measure to capture the relevance based on Minimum Spanning Trees. Three different real datasets were used to assess the performance of the adaptation. The results are encouraging and reflect the utility of feature selection algorithms.

Abstract
This paper describes an approach based on the shortest path method for the detection and tracking of vibrating lines. The detection and tracking of vibrating structures, such as lines and cables, is of great importance in areas such as civil engineering, but the specificities of these scenarios make it a hard problem to tackle. We propose a two-step approach consisting of line detection and subsequent tracking. The automatic detection of the lines avoids manual initialization - a typical problem of these scenarios - and favors tracking. The additional information provided by the line detection enables the improvement of existing algorithms and extends their application to a larger set of scenarios.

Abstract
Background. To analyze the relationship of objective and subjective evaluation tools of breast aesthetics, we compare the results of the BCCT.core (breast cancer conservative treatment.cosmetic results) software, a semiautomated objective symmetry evaluation tool, with those of the Aesthetic Status of the BCTOS (Breast Cancer Treatment Outcome Scale) patient questionnaire. Materials and Methods. We included 128 patients with one-sided, primary breast cancer, treated conservatively in a prospective, exploratory study in order to assess the inter-rater reliability of the BCCT.core and the agreement between the BCCT.core and the BCTOS preoperatively, shortly and 1 year after surgery. Therefore, we use agreement rates, multiple (mk), and weighted (wk) kappa coefficients as statistical methods. Furthermore, we analyzed patient-, tumor-, and therapy-related variables as possible covariates to explain agreement. Results. The inter-rater reliability for the semiautomated BCCT.core is very good with agreement rates up to 84% (mk = 0.80). The agreement rates of the BCCT.core and the BCTOS Aesthetic Status range between 35 and 44% subject to the different times of assessment (wk = 0.34 at best). Moreover, the patients judge their aesthetic outcome more positively than the software. None of the considered patient-, tumor-, and therapy-related covariates turned out to explain agreement. Conclusion. The BCCT.core is a reliable instrument that shows fair agreement with patient's perspective.

Abstract
An algorithm and a software application for recombining in real time MIDI drum loops that makes use of a novel analysis of rhythmic patterns that sorts them in order of their complexity is presented. We measure rhythmic complexity by comparing each rhythmic pattern found in the loops to a metrical template characteristic of its time signature. The complexity measure is used to sort the MIDI loops prior to utilizing them in the recombination algorithm. This way, the user can effectively control the complexity and variation in the generated rhythm during performance. © 2011 International Society for Music Information Retrieval.