In many control applications, it is attractive to describe nonlinear (NL) and time-varying (TV) plants by linear parameter-varying (LPV) models and design controllers based on such representations to regulate the behavior of the system.
This paper shows how to construct multi-models that represent partially unknown nonlinear systems and also how to perform a control design based on such a representation.
Based on such multimodality representation, it is desirable to find useful patterns with rich semantics.
Based on such an ontological representation, a Knowledge-Based System (KBS) for EIP energy management named J-Park Simulator (JPS) is developed.
Based on such feature coding representation, a detailed process plan can be generated through a process optimization module that incorporates an object-based knowledge system for achieving enhancement in terms of resource allocation.
Based on such a local representation of the real world, misbehavior detection, in-network data aggregation and more general decisions are made.
A difficult aspect for signal subspace decomposition based on such a sparse representation is to define the most appropriate criterion to identify the principal components (called atoms) from the learned dictionary to build the principal subspace.
This classification was made based on such characteristics as immigration intensity, species representation in the metacommunity and the size of local communities.
A categorization scheme was developed based on representation criteria such as 2D vs 3D, static vs dynamic, with the application to time-series analysis.
Indeed, the postural body scheme is normally used to control posture according to a feed-forward process, based on internal representations such as the body geometry, the forces exerted on the ground and the orientation of the subject's body in relation to the vertical pull of gravity [4], [5].
