Abstract
This paper describes the analysis and design of a tablet-based gaming platform for seniors that promotes their quality-of-life and well-being by incorporating cognitive training mechanisms. A literature review of age-related changes and games for seniors indicated 'casual games' have the characteristics necessary to provide an enjoyable user experience for the senior audience. Having concluded that these games should target cognitive stimulation, the authors analysed mechanisms to achieve this purpose and compiled them into a matrix to be used as a starting point for the games design process. In parallel, the authors also gathered seniors' preferences and requirements regarding games, through observations and a game book. Low-, medium-, and high-fidelity prototypes for a gaming cognitive platform were developed, evaluated with end-users, and iteratively improved. Results showed that seniors easily interacted with the platform and were willing to use it in the future. Results and experience led to the identification of 10 rules of thumb that can be beneficial if applied to related projects. This paper concludes by identifying exciting areas for future research and development. © 2012 ACM.

Abstract
Marsyas is a software framework for building efficient complex audio processing systems and applications. Although originally designed for Music Information Retrieval (MIR) tasks in the past few years it has been expanded to include any type of audio analysis or synthesis. Complex Audio processing systems are defined hierarchically through composition using implicit patching. Both the specification of the processing network and the control of it while data is flowing through can be performed at runtime without requiring recompilation. Compilation is required only when new processing objects need to be defined. Therefore the Marsyas runtime provides considerable functionality and flexibility. In this paper we demonstrate how the Marsyas runtime can be accessed using a variety of different ways allowing non-trivial interactions with common software frameworks and environments.

Abstract
In this paper, we study the use of audio and visual cues to perform speaker segmentation of audiovisual recordings of formal meetings such as interviews, lectures, or courtroom sessions. The sole use of audio cues for such recordings can be ineffective due to low recording quality and high level of background noise. We propose to use additional cues from the video stream by exploiting the relative static locations of speakers among the scene. The experiments show that the combination of those multiple cues helps to identify more robustly the transitions arriong speakers.

Abstract
The design and implementation of multimedia signal processing systems is challenging especially when efficiency and real-time performance is desired. In many modern applications, software systems must be able to handle multiple flows of various types of multimedia data such as audio and video. Researchers frequently have to rely on a combination of different software tools for each modality to assemble proof-of-concept systems that are inefficient, brittle and hard to maintain. Marsyas is a software framework originally developed to address these issues in the domain of audio processing. In this paper we describe MarsyasX, a new open-source cross-modal analysis framework that aims at a broader score of applications. It follows a data ow architecture where complex networks of processing objects can be assembled to form systems that can handle multiple and different types of multimedia flows with expressiveness and efficiency. Copyright 2008 ACM.

Abstract
Twelve expert observers from nine different countries convened in a workshop to evaluate the validity of the Breast Cancer Conservative Treatment. Cosmetic results (BCCT.core) software, an objective method for the aesthetic evaluation of breast cancer conservative treatment. Experts were initially asked to subjectively classify the aesthetic results of 30 photographed cases submitted to breast cancer conservative treatment according to the four-point Harris scale. It was pre-established that if at least two-thirds [Cardoso MJ, Cardoso J, Santos AC, Barros H, Oliveira MC. Interobserver agreement and consensus over the esthetic evaluation of conservative treatment for breast cancer. Breast 2005] of participants provided the same classification this would be considered a consensual evaluation for that case. For cases where such agreement was not reached, consensus was obtained using a nominal group technique. Experts then individually performed objective evaluation of the same set of photographs using the BCCT.core software. This provides an automatic rating of aesthetic results, once scale and reference points in the photograph have been chosen. Agreement between observers, between each observer and the consensus, for computer evaluation obtained by the different participants and between software and consensus was calculated using multiple kappa (k) and weighted kappa (wk) statistics. In the subjective assessment, first-round consensus was achived in 17 (57%) cases. Overall interobserver agreement was fair to moderate (k = 0.40, wk = 0.57). In the objective assessment there was a higher level of concordance between participants (k = 0.86, wk = 0.90). Agreement between software and consensus classification was fair (k = 0.34, wk = 0.53), but was higher in the 17 cases that reached first-round consensus (k = 0.60, wk = 0.73). Merging the two middle classes of the Harris scale, to form a three-point scale, led to an improvement of all non-weighted measures of agreement. These results show that the BCCT.core software provides consistent evaluation of cosmesis. It has the potential to become a gold standard method for assessment of breast cosmesis in clinical trials, as it can be used simultaneously by a panel of observers from different parts of the world to provide more reliable assessments than has been possible previously.

Abstract
Breast cancer conservative treatment (BCCT), due to its proven oncological safety, is considered, when feasible, the gold standard of breast cancer treatment. However, aesthetic results are heterogeneous and difficult to evaluate in a standardized way, due to the lack of reproducibility of the subjective methods usually applied. The objective assessment methods, considered in the past as being less capable of evaluating all aspects of BCCT, are nowadays being preferred to overcome the drawbacks of the subjective evaluation. A computer-aided medical system was recently developed to objectively and automatically evaluate the aesthetic result of BCCT. In this system, the detection of the breast contour on the patient's digital photograph is a necessary step to extract the features subsequently used in the evaluation process. In this paper an algorithm based on the shortest path oil a graph is proposed to detect automatically the breast contour. The proposed method extends an existing semi-automatic algorithm for the same purpose. A comprehensive comparison with manually-drawn contours reveals the strength of the proposed method.