This thesis studies a class of optimisation algorithms, namely Memetic Computing Structures, and proposes a novel set of promising algorithms that move the first step towards an implementation for the automatic generation of optimisation algorithms for continuous domains. This thesis after a thorough review of local search algorithms and popular meta-heuristics, focuses on Memetic Computing in terms of algorithm structures and design philosophy. In particular, most of the design carried out during my doctoral studies is inspired by the lex parsimoniae, aka Ockham’s Razor. It has been shown how simple algorithms, when well implemented can outperform complex implementations. In order to achieve this aim, the design is always carried out by attempting to identify the role of each algorithmic component/operator. In this thesis, on the basis of this logic, a set of variants of a recently proposed algorithms are presented. Subsequently a novel memetic structure, namely Parallel Memetic Structure is proposed and tested against modern algorithms representing the state of the art in optimisation. Furthermore, an initial prototype of an automatic design platform is also included. This prototype performs an analysis on separability of the optimisation problem and, on the basis of the analysis results, designs some parts of the parallel structure. Promising results are included. Finally, an investigation of the correlation among the variables and problem dimensionality has been performed. An extremely interesting finding of this thesis work is that the degree of correlation among the variables decreases when the dimensionality increases. As a direct consequence of this fact, large scale problems are to some extent easier to handle than problems in low dimensionality since, due to the lack of correlation among the variables, they can effectively be tackled by an algorithm that performs moves along the axes.

No description available.

The thesis presents research on multiobjective optimization based on memetic computing and its applications in engineering. We have introduced a framework for adaptive multiobjective memetic optimization algorithms (AMMOA) with an information theoretic criterion for guiding the selection, clustering, and local refinements. A robust stopping criterion for AMMOA has also been introduced to solve non-linear and large-scale optimization problems. The framework has been implemented for different benchmark test problems with remarkable results. This thesis also presents two applications of these algorithms. First, an optimal image data hiding technique has been formulated as a multiobjective optimization problem with conflicting objectives. In particular, trade-off factors in designing an optimal image data hiding are investigated to maximize the quality of watermarked images and the robustness of watermark. With the fixed size of a logo watermark, there is a conflict between these two objectives, thus a multiobjective optimization problem is introduced. We propose to use a hybrid between general regression neural networks (GRNN) and the adaptive multiobjective memetic optimization algorithm (AMMOA) to solve this challenging problem. This novel image data hiding approach has been implemented for many different test natural images with remarkable robustness and transparency of the embedded logo watermark. We also introduce a perceptual measure based on the relative Rényi information spectrum to evaluate the quality of watermarked images. The second application is the problem of joint spectrum sensing and power control optimization for a multichannel, multiple-user cognitive radio network. We investigated trade-off factors in designing efficient spectrum sensing techniques to maximize the throughput and minimize the interference. To maximize the throughput of secondary users and minimize the interference to primary users, we propose a joint determination of the sensing and transmission parameters of the secondary users, such as sensing times, decision threshold vectors, and power allocation vectors. There is a conflict between these two objectives, thus a multiobjective optimization problem is used again in the form of AMMOA. This algorithm learns to find optimal spectrum sensing times, decision threshold vectors, and power allocation vectors to maximize the averaged opportunistic throughput and minimize the averaged interference to the cognitive radio network. / February 2016