A methodology for example-based specification and design

There is an ever-increasing use of embedded systems; fast prototyping, time to market and severe implementation constraints must be faced to provide an effective - low cost - solution for a given application. To this end, several algorithmic formalisms are available to describe and validate complex systems at a behavioural level in order to minimise development costs and facilitate the integration of design and implementation constraints. Unfortunately, a soft-computing paradigm cannot be directly manipulated by conventional development environments for embedded systems unless an algorithmic description is available. In general, such a description is the result of a training procedure which, by following the selection of the most suitable soft-computing paradigm, configures it. The paper addresses the issues related to the integration of soft-computing paradigms within conventional development environments for embedded systems. The analysis is carried out at a behavioural abstraction level.