The evolutionary approach in the design optimisation of MEMS is a novel and promising research area. The problem is of a multi-objective nature; hence, multi-objective evolutionary algorithms (MOEA) are used. The literature shows that two main classes of MOEA have been used in MEMS evolutionary design Optimisation, NSGA-II and MOGA-II. However, no one has provided a justification for using eith...

.............................................................................................. I Acknowledgements ............................................................................ II ركشو ءادهآ .............................................................................................. IV List of Figures .................................................................................

This paper focuses on the geometrical design of active noise control (ANC) in freefield propagation medium. The development and performance assessment uses genetic optimisation techniques to arrange system components so as to satisfy several performance requirements, such as physical extent of cancellation, controller design restriction and system stability. The ANC system design can be effecti...

In this chapter recent research in the area of multi-objective optimisation of regression models is presented and combined. Evolutionary multi-objective optimisation techniques are described for training a population of regression models to optimise the recently defined Regression Error Characteristic Curves (REC). A method which meaningfully compares across regressors and against benchmark mod...

This paper presents models and algorithms for real-time 4-Dimensional Flight Trajectory (4DT) operations in next generation Communications, Navigation, Surveillance/Air Traffic Management (CNS/ATM) systems. In particular, the models are employed for multi-objective optimisation of 4DT intents in ground-based 4DT Planning, Negotiation and Validation (4-PNV) systems and in airborne Next Generatio...

An important issue in multi-objective optimisation is how to ensure that the obtained non-dominated set covers the Pareto front as widely as possible. A number of techniques (e.g. weight vectors, niching, clustering, cellular structures, etc.) have been proposed in the literature for this purpose. In this paper we propose a new approach to address this issue in multi-objective combinatorial opt...

The Ant Colony Optimisation Algorithm (ACO) supports the development of a system for a multi-objective network optimisation problem. The ACO system bases itself on an agent’s population and, in this case, uses a multi-level pheromone trail associated to a cost vector, which will be optimised.