Abstract
In order to behave autonomously, it is desirable for robots to have the ability to use human supervision and learn from different input sources (perception, gestures, verbal and textual descriptions etc). In many machine learning tasks, the supervision is directed specifically towards machines and hence is straight forward clearly annotated examples. But this is not always very practical and recently it was found that the most preferred interface to robots is natural language. Also the supervision might only be available in a rather indirect form, which may be vague and incomplete. This is frequently the case when humans teach other humans since they may assume a particular context and existing world knowledge. We explore this idea here in the setting of conceptualizing objects and scene layouts. Initially the robot undergoes training from a human in recognizing some objects in the world and armed with this acquired knowledge it sets out in the world to explore and learn more higher level concepts like static scene layouts and environment activities. Here it has to exploit its learned knowledge and ground language into perception to use inputs from different sources that might have overlapping as well as novel information. When exploring, we assume that the robot is given visual input, without explicit type labels for objects, and also that it has access to more or less generic linguistic descriptions of scene layout. Thus our task here is to learn the spatial structure of a scene layout and simultaneously visual object models it was not trained on. In this paper, we present a cognitive architecture and learning framework for robot learning through natural human supervision and using multiple input sources by grounding language in perception. Copyright

Abstract
Over the past years, inverse perspective mapping has been successfully applied to several problems in the field of Intelligent Transportation Systems. In brief, the method consists of mapping images to a new coordinate system where perspective effects are removed. The removal of perspective associated effects facilitates road and obstacle detection and also assists in free space estimation. There is, however, a significant limitation in the inverse perspective mapping: the presence of obstacles on the road disrupts the effectiveness of the mapping. The current paper proposes a robust solution based on the use of multimodal sensor fusion. Data from a laser range finder is fused with images from the cameras, so that the mapping is not computed in the regions where obstacles are present. As shown in the results, this considerably improves the effectiveness of the algorithm and reduces computation time when compared with the classical inverse perspective mapping. Furthermore, the proposed approach is also able to cope with several cameras with different lenses or image resolutions, as well as dynamic viewpoints. © 2014 Elsevier B.V.

Abstract
Metabolomics aims at gathering the maximum amount of metabolic information for a total interpretation of biological systems. A process analytical technology pipeline, combining gas chromatography-mass spectrometry data preprocessing with multivariate analysis, was applied to a Port wine "forced ageing" process under different oxygen saturation regimes at 60 degrees C. It was found that extreme "forced ageing" conditions promote the occurrence of undesirable chemical reactions by production of dioxane and dioxolane isomers, furfural and 5-hydroxymethylfurfural, which affect the quality of the final product through the degradation of the wine aromatic profile, colour and taste. Also, were found high kinetical correlations between these key metabolites with benzaldehyde, sotolon, and many other metabolites that contribute for the final aromatic profile of the Port wine. The use of the kinetical correlations in time-dependent processes as wine ageing can further contribute to biological or chemical systems monitoring, new biomarkers discovery and metabolic network investigations.

Abstract
This paper proposes new clustering criteria for distinguishing Saccharomyces cerevisiae (yeast) strains using their spectrometric signature. These criteria are introduced in an agglomerative hierarchical clustering context, and consist of: (a) minimizing the total volume of clusters, as given by their respective convex hulls; and, (b) minimizing the global variance in cluster directionality. The method is deterministic and produces dendrograms, which are important features for microbiologists. A set of experiments, performed on yeast spectrometric data and on synthetic data, show the new approach outperforms several well-known clustering algorithms, including techniques commonly used for microorganism differentiation.

Abstract
The Darwinian Particle Swarm Optimization (DPSO) is an evolutionary algorithm that extends the Particle Swarm Optimization (PSO) using natural selection, or survival-of-the-fittest, to enhance the ability to escape from local optima. An extension of the DPSO to multi-robot applications has been recently proposed and denoted as Robotic Darwinian PSO (RDPSO), benefiting from the dynamical partitioning of the whole population of robots. Therefore, the RDPSO decreases the amount of required information exchange among robots, and is scalable to large populations of robots. This paper presents a stability analysis of the RDPSO to better understand the relationship between the algorithm parameters and the robot's convergence. Moreover, the analysis of the RDPSO is further extended for real robot constraints (e.g., robot dynamics, obstacles and communication constraints) and experimental assessment with physical robots. The optimal parameters are evaluated in groups of physical robots and a larger population of simulated mobile robots for different target distributions within larger scenarios. Experimental results show that robots are able to converge regardless of the RDPSO parameters within the defined attraction domain. However, a more conservative parametrization presents a significant influence on the convergence time. To further evaluate the herein proposed approach, the RDPSO is further compared with four state-of-the-art swarm robotic alternatives under simulation. It is observed that the RDPSO algorithm provably converges to the optimal solution faster and more accurately than the other approaches.

Abstract
In the end of a requirements elicitation phase, it is expectable that all information can be properly perceived by the implementation teams. In our work, we faced the problem of dealing with a large set of requirements that need to be implemented by different teams, to ensure on-time delivery. The teams are physically separated and with different working cultures and skills. The system requirements were (semi-) automatically derived from user requirements, are framed within a logical architecture (of the intended system) and the desired high-level execution scenarios are defined and included in the requirements description. Due to the large size of the architecture and to the nature of the working environment, the architecture must be divided before being delivered. In this paper, we present our approach for dividing the logical architecture of the intended system into modules to be delivered for implementation. The division in constructed upon requirement views that provide information about the modules, their interfaces, the intended execution scenarios, and the interfaces with other modules or systems. The approach is evaluated using the ISOFIN project.