Abstract-Component ensembles are a promising way of building self-aware autonomic adaptive systems. This approach has been promoted by the EU project ASCENS, which develops the core idea of ensembles by providing rigorous semantics as well as models and methods for the whole development life cycle of an ensemble-based system. These methods specifically address adaptation, self-awareness, self-optimization, and continuous system evolution. In this paper, we demonstrate the key concepts and benefits of the ASCENS approach in the context of intelligent navigation of electric vehicles (e-Mobility), which itself is one of the three key case studies of the project.

Developing systems that support people in everyday life in a discrete and effective way is an ultimate goal of a new generation of technical systems. Physiological computing represents one means of creating a system to sense the user, analyse users' responses to system adaptation and respond dynamically. This process of adaptation is achieved by creating a biocybernetic loop that may operate on several, simultaneous timescales (minutes/hours/weeks/months/years). In terms of architecture, it is argued that a "sense-analyse-react" system requires middleware with closed-loop control consisting of. (1) a tangible layer concerned with sensors and actuators, (2) a reflective layer containing a flexible representation of the user to guide system adaptation, and (3) an application layer representing application scenarios and the context for adaptation and evolution

Pervasive adaptive systems are concerned with the construction of "smart" technologies capable of adapting to the needs of the individual in real time. In order to achieve this level of specificity, systems must be capable of monitoring the psychological status of the user and responding to these changes in real time and across multiple systems if necessary. This article describes a number of conceptual issues associated with this category of adaptive technology. The biocybernetic loop describes different approaches to monitoring the status of the user from physiological sensors to overt behavior. These data are used to drive real time system adaptation tailored to a specific user in a particular context. The rate at which the technology adapts to the individual user are described over three different phases of usage: awareness (short-term), adjustment (medium-term), and coevolution (long-term). An ontology is then proposed for the development of an adaptive software ar chitecture that embodies this approach and may be extended to encompass several distinct loops working in parallel. The feasibility of the approach is assessed through implemented case studies of their performance and functionality

Parallelism and distribution have been considered the key features of neural processing. The term parallel distributed processing is even used as a synonym for arti cial neural networks. Nevertheless, the actual implementations are still in search of the appropriate model to "naturally represent" neural computing. And thenal judgement is always given in performance gures { keeping the parallelization issue high on the neurosimulation agenda. Two approaches have yielded the best results: parallel simulations on general-purpose computers, and specially developed neurohardware. Programming neural networks on parallel machines requires high-level techniques re ecting both inherent features of neuromodels and characteristics of the underlying computers. On the other hand, emulation of the neuroparadigm requires that the functioning of neural operations be mimicked directly by the hardware. Both approaches are presented, and their advantages and shortcomings are outlined.