Abstract
Breast cancer treatments can have a negative impact on breast aesthetics, in case when surgery is intended to intersect tumor. For many years mastectomy was the only surgical option, but more recently breast conserving surgery (BCS) has been promoted as a liable alternative to treat cancer while preserving most part of the breast. However, there is still a significant number of BCS intervened patients who are unpleasant with the result of the treatment, which leads to self-image issues and emotional overloads. Surgeons recognize the value of a tool to predict the breast shape after BCS to facilitate surgeon/patient communication and allow more educated decisions; however, no such tool is available that is suited for clinical usage. These tools could serve as a way of visually sensing the aesthetic consequences of the treatment. In this research, it is intended to propose a methodology for predict the deformation after BCS by using machine learning techniques. Nonetheless, there is no appropriate dataset containing breast data before and after surgery in order to train a learning model. Therefore, an in-house semi-synthetic dataset is proposed to fulfill the requirement of this research. Using the proposed dataset, several learning methodologies were investigated, and promising outcomes are obtained.

Abstract
Social media platforms are having a profound impact on the so-called information ecosystem, specifically on how information is produced, distributed and consumed. Social media in particular has contributed to the rise of user generated content and consequently to a greater diversity in online content. On the other hand, social media networks, such as Twitter or Facebook, have become information management tools that allow users to setup and configure information sources to their particular interests. A Twitter user can handpick the sources he wishes to follow, thus creating a custom information channel. However, this opportunity to create personalized information channels effectively results in different consumption profiles? Is the information consumed by users through social media networks distinct from the information consumed though traditional mainstream media? In this work, we set out to investigate this question using Twitter as a case study. We prepare two samples of users, one based on a uniform random selection of user IDs, and another one based on a selection of mainstream media followers. We analyze the home timelines of the users in each sample, focusing on characterizing information consumption habits. We find that information consumption volume is higher, while diversity is consistently lower, for mainstream media followers when compared to random users. When analyzing daily behavior, however, the samples slightly approximate, while clearly maintaining a lower diversity for mainstream media followers and a higher diversity for random users. Copyright © 2018 for the individual papers by the papers’ authors.

Abstract
In multi-label classification tasks, instances are simultaneously associated with multiple labels, representing different and, possibly, related concepts from a domain. One characteristic of these tasks is a high class-label imbalance. In order to obtain improved predictive models, several algorithms either have explored the label dependencies or have dealt with the problem of imbalanced labels. This work proposes a label expansion approach which combines both alternatives. For such, some labels are expanded with data from a related class label, making the labels more balanced and representative. Preliminary experiments show the effectiveness of this approach to improve the Binary Relevance strategy. Particularly, it reduced the number of labels that were never predicted in the test instances. Although the results are preliminary, they are potentially attractive, considering the scale and consistency of the improvement obtained, as well as the broad scope of the proposed approach.

Abstract
Assistive systems which incorporate different technologies to provide simple and quick, yet informative, content, have recently been proposed to alleviate the mobility and accessibility constrains of users with visual impairment. Currently, technology has reached a maturation point that allows the development of systems based on video capturing, image recognition and geo-location referencing, which are key for providing features of artificial vision, assisted navigation and spatial perception. The miniaturization of electronics can be used to create devices, such as electronic canes equipped with sensors, that can provide contextual information to a blind user. In this paper, we describe the current work on assistive systems for the blind and propose a new perspective on using the base information of those systems to provide new services to the general public. By bridging the gap between the two groups, we expect to further advance the development of the current systems and contribute to their economic sustainability.

Abstract

Abstract
Visual coherence between virtual and real objects is a major issue in creating convincing augmented reality (AR) applications. To achieve this seamless integration, actual light conditions must be determined in real time to ensure that virtual objects are correctly illuminated and cast consistent shadows. In this paper, we propose a novel method to estimate daylight illumination and use this information in outdoor AR applications to render virtual objects with coherent shadows. The illumination parameters are acquired in real time from context-aware live sensor data. The method works under unprepared natural conditions. We also present a novel and rapid implementation of a state-of-the-art skylight model, from which the illumination parameters are derived. The Sun's position is calculated based on the user location and time of day, with the relative rotational differences estimated from a gyroscope, compass and accelerometer. The results illustrated that our method can generate visually credible AR scenes with consistent shadows rendered from recovered illumination.