Multi-Guide Particle Swarm Optimization for Large-Scale Multi-Objective Optimization Problems
Abstract
Multi-guide particle swarm optimization (MGPSO) is a novel metaheuristic for multi-objective optimization based on particle swarm optimization (PSO). MGPSO has been shown to be competitive when compared with other state-of-the-art multi-objective optimization algorithms for low-dimensional problems. However, to the best of the author’s knowledge, the suitability of MGPSO for high-dimensional multi-objective optimization problems has not been studied. One goal of this thesis is to provide a scalability study of MGPSO in order to evaluate its efficacy for high-dimensional multi-objective optimization problems. It is observed that while MGPSO has comparable performance to state-of-the-art multi-objective optimization algorithms, it experiences a performance drop with the increase in the problem dimensionality. Therefore, a main contribution of this work is a new scalable MGPSO-based algorithm, termed cooperative co-evolutionary multi-guide particle swarm optimization (CCMGPSO), that incorporates ideas from cooperative PSOs. A detailed empirical study on well-known benchmark problems comparing the proposed improved approach with various state-of-the-art multi-objective optimization algorithms is done. Results show that the proposed CCMGPSO is highly competitive for high-dimensional problems.Collections
Related items
Showing items related by title, author, creator and subject.
-
Comparative Study On Cooperative Particle Swarm Optimization Decomposition Methods for Large-scale OptimizationClark, Mitchell; Department of Computer ScienceThe vast majority of real-world optimization problems can be put into the class of large-scale global optimization (LSOP). Over the past few years, an abundance of cooperative coevolutionary (CC) algorithms has been proposed to combat the challenges of LSOP’s. When CC algorithms attempt to address large scale problems, the effects of interconnected variables, known as variable dependencies, causes extreme performance degradation. Literature has extensively reviewed approaches to decomposing problems with variable dependencies connected during optimization, many times with a wide range of base optimizers used. In this thesis, we use the cooperative particle swarm optimization (CPSO) algorithm as the base optimizer and perform an extensive scalability study with a range of decomposition methods to determine ideal divide-and-conquer approaches when using a CPSO. Experimental results demonstrate that a variety of dynamic regrouping of variables, seen in the merging CPSO (MCPSO) and decomposition CPSO (DCPSO), as well varying total fitness evaluations per dimension, resulted in high-quality solutions when compared to six state-of-the-art decomposition approaches.
-
THE OPTIMIZATION OF A TIME-RESOLVED, VESICLE-BASED FLUORESCENCE ASSAY FOR THE ACTIVITY OF THE LIPID KINASE PI4K-IIIBETA AND THE EFFECT OF LIPID TRANSFER PROTEINS ON ENZYME ACTIVITYMuniz Correa, Marcelo Victor; Centre for BiotechnologyHuman PI4K-IIIβ is an 89 kDa phosphatidylinositol (PI) kinase that phosphorylates its substrate headgroup at position C-4, thus producing PI(4)P. This phosphoinositide is the most abundant in the trans-Golgi network where it is essential for secretory vesicle formation, as well as the precursor for other phosphoinositides that are crucial for intracellular signalling. Among others, phosphoinositide homeostasis in eukaryotic membranes rely on PI kinases and PI transfer proteins (PITPs). In yeast, the PITP Sec14p is known to exchange PI and phosphatidylcholine between lipid bilayers in vitro and proposed to present PI to be phosphorylated by the PI4-kinase Pik1 in a heterotypic ligand exchange fashion. However, the precise mechanism by which this interaction occurs has yet to be elucidated. To explore how and if PITPs and PI4K-IIIβ work as hypothesized, we expressed and purified recombinant human PI4K-IIIβ in Escherichia coli and assayed lipid kinase activity using an optimized real-time, vesicle-based fluorescence assay. After comparing different affinity tags, deletion mutants and expressing cell lines, GST-tagged wild-type PI4K-IIIβ was chosen and expressed in Rosetta 2(DE3) cells with a 2.5-fold increase in the native protein yield when compared to other methods. Proteins were further purified by an addition heat shock protein removal wash. The resulting PI4K-IIIβ displayed activity comparable to the commercially available, insect cell expressed counterpart. Optimization of the activity assay afforded a robust assay that displayed protein concentration dependent response while using unilamellar liposomes as the substrate. Agreeing with previous reports, the activity of PI4K-IIIβ was greatly reduced by wortmannin and increased by Triton X-100. The activity of PI4K-IIIβ was tested in the presence of active human PITPα and PITPβ, as well as yeast Frequenin and Sec14p, but none of them elicited a reproducible enhancement on PI(4)P production by PI4K-IIIβ. A similar pattern was observed with the human PI3-kinase, PIK3C3. Our results demonstrate that a PI presentation model based on heterotypic exchange may not occur in vitro, suggesting either that PITPs’ role in phosphoinositide production could rely uniquely on maintaining sufficient PI pools in the Golgi membrane or that additional protein partners may be required for the regulation of PI4K-IIIβ by PITPs.
-
Histogram filtering as a tool in variational Monte Carlo optimizationÅ najdr, Martin.; Department of Physics (Brock University, 1999-07-09)Optimization of wave functions in quantum Monte Carlo is a difficult task because the statistical uncertainty inherent to the technique makes the absolute determination of the global minimum difficult. To optimize these wave functions we generate a large number of possible minima using many independently generated Monte Carlo ensembles and perform a conjugate gradient optimization. Then we construct histograms of the resulting nominally optimal parameter sets and "filter" them to identify which parameter sets "go together" to generate a local minimum. We follow with correlated-sampling verification runs to find the global minimum. We illustrate this technique for variance and variational energy optimization for a variety of wave functions for small systellls. For such optimized wave functions we calculate the variational energy and variance as well as various non-differential properties. The optimizations are either on par with or superior to determinations in the literature. Furthermore, we show that this technique is sufficiently robust that for molecules one may determine the optimal geometry at tIle same time as one optimizes the variational energy.