Abstract
In developed societies populations are aging. Facing the global slump states are reducing expenses bringing crisis to health care systems. Solutions to decrease costs are needed. Within ICT, smartphones' features can help provide personalised health and care services that meet individual needs. There is a huge rise of applications that effectively help people but they act independently, each one for a certain purpose. In this paper we propose the HelpWave system, a cloud-centred architecture information system that integrates data from the users' smartphones APPs. Conceived as a social care network its aim is to reinforce connection between caregivers and carereceiver as for instance, older people. (C) 2015 Published by Elsevier B.V.

Abstract

Abstract
Machine learning processes consist in collecting data, obtaining a model and applying it to a given task. Given a new task, the standard approach is to restart the learning process and obtain a new model. However, previous learning experience can be exploited to assist the new learning process. The two most studied approaches for this are metalearning and transfer learning. Metalearning can be used for selecting the predictive model to use over a determined dataset. Transfer learning allows the reuse of knowledge from previous tasks. Our aim is to use metalearning to support transfer learning and reduce the computational cost without loss in terms of performance, as well as the user effort needed for the algorithm selection. In this paper we propose some methods for mapping the transfer of weights between neural networks to improve the performance of the target network, and describe some experiments performed in order to test our hypothesis.

Abstract
Malaria is one of the most severe public health problems worldwide. It is estimated that 3.3 billion people live in areas at risk of malaria transmission, and in 2010 caused around 655,000 deaths, 91% of them in the African Region. In this study we assess if the mHealth application “MalariaScope” developed by Fraunhofer Portugal AICOS (FhP AICOS) found to be usable and satisfactory by users from a European country, Portugal, can achieve similar positive results in an African country, Mozambique, which is one of its intended contexts of use. To this end, an academic partner from that African country conducted locally a usability evaluation of the application following the same procedure with participants with similar scientific backgrounds to the Portuguese counterparts. A comparison of the usability metrics of the two evaluations found no significant differences between the Portuguese and Mozambican set of users. © Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2015.

Abstract
With the emergence of new low-cost gestural interaction devices various studies have been developed on multi-modal human-computer interaction to improve user experience. We present an exploratory study which analysed the user experience with a multimodal interaction game prototype. As a result, we propose a set of preliminary recommendations for combined use of such devices and present implications for advancing the multimodal field in human-computer interaction.

Abstract
Breast cancer is the most frequently diagnosed cancer in women. Using historical patient information stored in clinical datasets, data mining and machine learning approaches can be applied to predict the survival of breast cancer patients. A common drawback is the absence of information, i.e., missing data, in certain clinical trials. However, most standard prediction methods are not able to handle incomplete samples and, then, missing data imputation is a widely applied approach for solving this inconvenience. Therefore, and taking into account the characteristics of each breast cancer dataset, it is required to perform a detailed analysis to determine the most appropriate imputation and prediction methods in each clinical environment This research work analyzes a real breast cancer dataset from Institute Portuguese of Oncology of Porto with a high percentage of unknown categorical information (most clinical data of the patients are incomplete), which is a challenge in terms of complexity. Four scenarios are evaluated: (I) 5-year survival prediction without imputation and 5-year survival prediction from cleaned dataset with (II) Mode imputation, (Ill) Expectation-Maximization imputation and (IV) K-Nearest Neighbors imputation. Prediction models for breast cancer survivability are constructed using four different methods: K-Nearest Neighbors, Classification Trees, Logistic Regression and Support Vector Machines. Experiments are performed in a nested ten-fold cross-validation procedure and, according to the obtained results, the best results are provided by the K-Nearest Neighbors algorithm: more than 81% of accuracy and more than 0.78 of area under the Receiver Operator Characteristic curve, which constitutes very good results in this complex scenario.