Choi-Hong Lai

Particle Swarm Optimisation: Classical and Quantum Perspectives

Although the particle swarm optimisation (PSO) algorithm requires relatively few parameters and is computationally simple and easy to implement, it is not a globally convergent algorithm. In Particle Swarm Optimisation: Classical and Quantum Perspectives, the authors introduce their concept of quantum-behaved particles inspired by quantum mechanics, which leads to the quantum-behaved particle swarm optimisation (QPSO) algorithm. This globally convergent algorithm has fewer parameters, a faster convergence rate, and stronger searchability for complex problems. The book presents the concepts of optimisation problems as well as random search methods for optimisation before discussing the principles of the PSO algorithm. Examples illustrate how the PSO algorithm solves optimisation problems. The authors also analyse the reasons behind the shortcomings of the PSO algorithm. Moving on to the QPSO algorithm, the authors give a thorough overview of the literature on QPSO, describe the fundamental model for the QPSO algorithm, and explore applications of the algorithm to solve typical optimisation problems. They also discuss some advanced theoretical topics, including the behaviour of individual particles, global convergence, computational complexity, convergence rate, and parameter selection. The text closes with coverage of several real-world applications, including inverse problems, optimal design of digital filters, economic dispatch problems, biological multiple sequence alignment, and image processing. MATLAB, Fortran, and C++ source codes for the main algorithms are provided on an accompanying CD-ROM. Helping you numerically solve optimisation problems, this book focuses on the fundamental principles and applications of PSO and QPSO algorithms. It not only explains how to use the algorithms, but also covers advanced topics that establish the groundwork for understanding state-of-the-art research in the field.

STAGGERED-MESH COMPUTATION FOR AERODYNAMIC SOUND

For the numerical solution of the linearized Euler equations, an optimized computational scheme is considered. It is based on fully staggered (in space and time) regular meshes and on a simple mirroring procedure at the stepwise solid walls. There is no need to define ghost points into the solid ohjects that reflect the sound waves. Test results demonstrate the accuracy of the method that may be used for aeroacoustic problems with complex geometries.

Diakoptics, Domain Decomposition and Parallel Computing

This paper gives a brief history or diakoptics and provides an insight into its connections with domain decomposition methods. The aim is to discuss some or the common grounds of the two methods and to relate these common grounds to parallel computing. Load balancing in an MIMD environment and implementation issues in an SIMD environment are discussed

Adaptive partition and hybrid method in fractal video compression

Fractal image compression is a relatively recent image compression method, which is simple to use and often leads to a high compression ratio. These advantages make it suitable for the situation of a single encoding and many decoding, as required in video on demand, archive compression, etc. There are two fundamental fractal compression methods, namely, the cube-based and the frame-based methods, being commonly studied. However, there are advantages and disadvantages in both methods. This paper gives an extension of the fundamental compression methods based on the concept of adaptive partition. Experimental results show that the algorithms based on adaptive partition may obtain a much higher compression ratio compared to algorithms based on fixed partition while maintaining the quality of decompressed images.

Parallel quantum-behaved particle swarm optimization

Quantum-behaved particle swarm optimization (QPSO), like other population-based algorithms, is intrinsically parallel. The master–slave (synchronous and asynchronous) and static subpopulation parallel QPSO models are investigated and applied to solve the inverse heat conduction problem of identifying the unknown boundary shape. The performance of all these parallel models is compared. The synchronous parallel QPSO can obtain better solutions, while the asynchronous parallel QPSO converges fast without idle waiting. The scalability of the static subpopulation parallel QPSO is not as good as the master–slave parallel model.

Solving the multi-stage portfolio optimization problem with a novel particle swarm optimization

Research highlights? We propose a drift particle swarm optimization (DPSO) algorithm. ? DPSO is applied to solve multi-stage portfolio optimization (MSPO) problems. ? MSPO problems with data from S&P 100 index are tested by DPSO and other algorithms. ? DPSO outperforms its competitors in solving the MSPO problems. Solving the multi-stage portfolio optimization (MSPO) problem is very challenging due to nonlinearity of the problem and its high consumption of computational time. Many heuristic methods have been employed to tackle the problem. In this paper, we propose a novel variant of particle swarm optimization (PSO), called drift particle swarm optimization (DPSO), and apply it to the MSPO problem solving. The classical return-variance function is employed as the objective function, and experiments on the problems with different numbers of stages are conducted by using sample data from various stocks in S&P 100 index. We compare performance and effectiveness of DPSO, particle swarm optimization (PSO), genetic algorithm (GA) and two classical optimization solvers (LOQO and CPLEX), in terms of efficient frontiers, fitness values, convergence rates and computational time consumption. The experiment results show that DPSO is more efficient and effective in MSPO problem solving than other tested optimization tools.

Quantum-Behaved Particle Swarm Optimization with Ring Topology and Its Application in Estimating Temperature-Dependent Thermal Conductivity

A quantum-behaved particle swarm optimization with ring topology is proposed to estimate the temperature-dependent thermal conductivity in transient heat conduction problems. No priori information is available on the functional form of the unknown thermal conductivity, so this inverse problem is classified as function estimation by inverse calculation. Considering the ill-posedness of the inverse problem, the Tikhonov regularization method is used to stabilize the solution. The numerical results indicate the validity and stability of the proposed method by using just boundary measurements. Comparison with the classic quantum-behaved particle swarm optimization and other stochastic intelligent algorithms such as particle swarm optimization, genetic algorithm, is also presented.

An improved quantum-behaved particle swarm optimization and its application to medical image registration

This paper investigates the quantum-behaved particle swarm optimization (QPSO) algorithm from the perspective of estimation of distribution algorithm (EDA) which reveals the reason of QPSOs superiority. A revised QPSO (RQPSO) technique with a novel iterative equation is also proposed. The modified technique is deduced from the distribution function of the sum of two random variables with exponential and normal distribution, respectively. We present a diversity-controlled RQPSO (DRQPSO) algorithm, which helps prevent the evolutionary algorithms’ tendency to be easily trapped into local optima as a result of rapid decline in diversity. Both the RQPSO and DRQPSO are tested on three benchmark functions, as well as in medical image registration for performance comparison with the particle swarm optimization and QPSO.

Construction and properties of multiwavelet packets with arbitrary scale and the related algorithms of decomposition and reconstruction

A more flexible method of constructing multiwavelet packets with the scale a ≥ 2 from the same set of multiwavelets is discussed in this paper. The properties of these packets are studied. The formulae for performing iterations and decomposition are given. L2(R) can be further decomposed by these multiwavelet packets and good bases of L2(R) are given. Finally, we provide the algorithms for the decomposition and reconstruction using these multiwavelet packets.

A defect equation approach for the coupling of subdomains in domain decomposition methods

A defect equation for the coupling of nonlinear subproblems defined in nonoverlapped subdomains arise in domain decomposition methods is presented. Numerical solutions of defect equations by means of quasi-Newton methods are considered.