Abstract
Writing scientific publications is usually a challenging and complex activity, involving several authors. Despite the different natures of their contributions, this activity is clearly collaborative and the collaboration is usually achieved through face-to-face meetings and using email to exchange the documents. More recently the availability of collaborative editors introduced a further step in the collaboration, but none of the existing solutions contemplate some specific issues like referencing and publishing adequately. This fact motivated us to conduct a study to evaluate the requirements for a platform that integrates in a single solution the three main functionalities required: a text editor, a reference manager and a connector to scientific digital repositories.

Abstract
This paper proposes a new framework to image segmentation which combines edge- and region-based information with spectral techniques through the morphological algorithm of watersheds. A pre-processing step is used to reduce the spatial resolution without losing important image information. An initial partitioning of the image into primitive regions is set by applying a rainfalling watershed algorithm on the image gradient magnitude. This initial partition is the input to a computationally efficient region segmentation process which produces the final segmentation. The latter process uses a region-based similarity graph representation of the image regions. The experimental results clearly demonstrate the effectiveness of the proposed approach to produce simpler segmentations and to compare favourably with state-of-the-art methods.

Abstract
Classification is a quite relevant task within data analysis field. This task is not a trivial task and different difficulties can arise depending on the nature of the problem. All these difficulties can become worse when the datasets are too large or when new information can arrive at any time. Incremental learning is an approach that can be used to deal with the classification task in these cases. It must alleviate, or solve, the problem of limited time and memory resources. One emergent approach uses concentration bounds to ensure that decisions are made when enough information supports them. IADEM is one of the most recent algorithms that use this approach. The aim of this paper is to improve the performance of this algorithm in different ways: simplifying the complexity of the induced models, adding the ability to deal with continuous data, improving the detection of noise, selecting new criteria for evolutionating the model, including the use of more powerful prediction techniques, etc. Besides these new properties, the new system, IADEM-2, preserves the ability to obtain a performance similar to standard learning algorithms independently of the datasets size and it can incorporate new information as the basic algorithm does: using short time per example.

Abstract
Intelligent surveillance is becoming increasingly important for the enhanced protection of facilities such as airports and power stations from various types of threats. We propose a surveillance system architecture based on multiple sources of information to apply on large scale surveillance networks. The main contribution of this paper is the definition of the requirements for a flexible and scalable architecture that supports intelligent surveillance using, alongside video, different sources of information, such as audio or other sensors.

Abstract
Patients visit multiple health institutions and leave a trail of information scattered around hospitals, healthcare centres and laboratories. Information availability is of major importance in healthcare delivery. Most of the Electronic Patient Record systems are unarticulated and usually address only the specificities of a single medical specialty. Virtual Electronic Patient Records such as MAID (Multi Agent system for the Integration of Data) system provide for the necessary means for intra-institutions departmental information integration. In this paper is presented a mobile agent based extension to the agent based MAID system in order to enable inter-institution patient data integration. This system was designed as a MAID extension with additional patient data integration features. In order to accomplish this, modules for external data discovery and collection where developed using mobile agents. Data collection activities are trigged by scheduled clinical events. The system is intended to enhance an existing institutional system taking it beyond the institutional barrier providing health professionals with a more complete patient clinical history.

Abstract
It is stated that a closer intervention of experts in knowledge discovery can complement and improve the effectiveness of results. Normally, in data mining, automated methods display final results through visualization methods. A more active intervention of experts on automated methods can bring enhancements to the analysis; No meanwhile that approach raises questions about what is a relevant stopping stage. In this work, efforts are made to couple automatic methods with visualization methods in the context of partitioning algorithms applied to spatial data. A data mining workflow is presented with the following concepts: data mining transaction, data mining save point and data mining snapshot. Moreover to display results, novel visual metaphors are changed allowing a better exploration of clustering. In knowledge discovery, experts validate final results; certainly it would be appropriate to them validate intermediate results, avoiding, for instance, losing time, when in disagreement, starting it with new hypnoses or allow data reduction by disable an intermediate cluster from the next stage.