Abstract
The correct estimation of the friction coefficient in automotive applications is of paramount importance in the design of effective vehicle safety systems. In this article a new parametrization for estimating the peak friction coefficient, in the tire-road interface, is presented. The proposed parametrization is based on a feedforward neural network (FFNN), trained by the Extreme Learning Machine (ELM) method. Unlike traditional learning techniques for FFNN, typically based on backpropagation and inappropriate for real time implementation, the ELM provides a learning process based on random assignment in the weights between input and the hidden layer. With this approach, the network training becomes much faster, and the unknown parameters can be identified through simple and robust regression methods, such as the Recursive Least Squares. Simulation results, obtained with the CarSim program, demonstrate a good performance of the proposed parametrization; compared with previous methods described in the literature, the proposed method reduces the estimation errors using a model with a lower number of parameters.

Abstract
The three-dimensional bin packing problem consists of packing a set of boxes into the minimum number of bins. In this paper we propose a new GRASP algorithm for solving three-dimensional bin packing problems which can also be directly applied to the two-dimensional case. The constructive phase is based on a maximal-space heuristic developed for the container loading problem. In the improvement phase, several new moves are designed and combined in a VND structure. The resulting hybrid GRASP/VND algorithm is simple and quite fast and the extensive computational results on test instances from the literature show that the quality of the solutions is equal to or better than that obtained by the best existing heuristic procedures.

Abstract
The challenge of managing large scale media assets has led to the development of metadata schemas that are expected to enable efficient search and retrieval of multimedia content. Those approaches propose schemas that can range from simple keyword based descriptions to complex hierarchical organization of information. However, effective media asset management requires more than content searching and retrieval: underlying infrastructures are usually complex, require the use of a number of different equipment and management decisions have to be done based on information available from the multimedia metadata layer as well as on data describing system resources and capabilities. In this paper we propose a new ontology that aggregates information from different sources and enables a top level business oriented view of multimedia archives.

Abstract
Dynamic, evolving systems pose new challenges from the point of view of Quality of Service (QoS) analysis, calling for techniques able to combine traditional offline methods with new ones applied at run-time. Tracking the evolution and updating the assessment consistently with such system evolution require not only advanced analysis methods, but also appropriate metrics well representative of QoS properties in the addressed context. The ongoing European project Connect addresses systems evolution, and aims at bridging technological gaps arising from heterogeneity of networked systems, by synthesising on-the-fly interoperability connectors. Moving from such ambitious goal, in this paper we present a metrics framework, whereby classical dependability/ QoS metrics can be refined and combined to characterise Connect applications and to support their monitoring and analysis.

Abstract
This paper presents an artificial immune system (AIS) based on Grossman's tunable activation threshold (TAT) for temporal anomaly detection. We describe the generic AIS framework and the TAT model adopted for simulating T Cells behaviour, emphasizing two novel important features: the temporal dynamic adjustment of T Cells clonal size and its associated homeostasis mechanism. We also present some promising results obtained with artificially generated data sets, aiming to test the appropriateness of using TAT in dynamic changing environments, to distinguish new unseen patterns as part of what should be detected as normal or as anomalous. We conclude by discussing results obtained thus far with artificially generated data sets.

Abstract
Technology has profoundly changed the way we learn and live. Indeed, such relationship appears to be quite complex, within IT contexts, and especially in socially and technologically rich learning environments, where related skills and learning are progressively required and fostered. Thus, if a satisfactory level of intellectual performance and social competence of a primary school pupil is indeed highly dependent on the type of participation that parents offer their children, IT, in general, and Internet, in particular, may well provide a new paradigm, setting forth that education and communication approach is truly more complex than ever before. It is on the basis of such paradigm that we therefore present a case study where a set of multimedia exercises were used in order to possibly improve the mathematical skills of pupils, one with mental retardation and another with cerebral palsy. Being part of a Web-based system to support students' learning, the referred set of multimedia exercises proved to be the children's favorite, rather than exercises in paper form, which also led the children to show a fair more positive attitude towards learning. Also, we observed that through the mentioned multimedia exercises, the children became far more autonomous, interested, persistent, happy, and able to easily absorb the material as well as more willingly to continue on working.