Multi-guide Particle Swarm Optimisation for Dynamic Multi-objective Optimisation Problems
Author
Jocko, PawelKeyword
Dynamic Multi-objective OptimisationMulti-guide Particle Swarm Optimisation
Archive Management
Quantum Particle Swarm Optimisation
Sensitivity Analysis
Metadata
Show full item recordAbstract
This study investigates the suitability of, and adapts, the multi-guide particle swarm optimisation (MGPSO) algorithm for dynamic multi-objective optimisation problems (DMOPs). The MGPSO is a multi-swarm approach, originally developed for static multi-objective optimisation problems (SMOPs), where each subswarm optimises one of the objectives. It uses a bounded archive that is based on a crowding distance archive implementation. Compared to static optimization problems, DMOPs pose a challenge for meta-heuristics because there is more than one objective to optimise, and the location of the Pareto-optimal set (POS) and the Pareto-optimal front (POF) can change over time. To efficiently track the changing POF in DMOPs using MGPSO, six archive management update approaches, eight archive balance coefficient initialization strategies, and six quantum particle swarm optimisation (QPSO) variants are proposed. To evaluate the adapted MGPSO for DMOPs, a total of twenty-nine well-known benchmark functions and six performance measures were implemented. Three experiments were run against five different environment types with varying temporal and spatial severities. The best strategies from each experiment were then compared with the other dynamic multi-objective optimisation algorithms (DMOAs). An extensive empirical analysis shows that the adapted MGPSO achieves very competitive, and often better, performance compared to existing DMOAs.Collections
Related items
Showing items related by title, author, creator and subject.
-
Characterisation and optimisation of the flavour of health-promoting, plantderived bitterants in functional beverages.Gaudette, Nicole J.; Applied Health Sciences Program (Brock University, 2012-07-30)Flavour is a combination of taste, odour, and chemesthetic sensations. Close associations exist between these sensory modalities, and thus, the overall flavour of a food or beverage product can change when the intensity of one or more of these sensations is altered. Strategies to modify flavour are often utilized by the food industry, and are central to the engineering of new and reformulated products. For functional food and beverages, flavour modification is particularly important, as fortifying agents can elicit high levels of less than desirable sensations, such as bitterness and astringency. The application of various flavour modifying strategies can decrease the perceived intensity of these sensations, and in tum, improve the sensory profile of the product. This collection of studies describes the sensory characteristics of experimental functional beverages fortified with trans-resveratrol, (+)-catechin, and/or caffeine, and examines the impact of novel flavour modifying strategies on the perceived flavour of these beverages. In the first study, results demonstrate that the flavour profile of Cabemet Sauvignon wines fortified with 20 mglL and 200 mg/L of trans-resveratrol is not perceived as different compared to control wine (0 mglL). However, Riesling wine fortified with 200 mg/L is perceived as significantly higher in bitterness compared to 20 mglL and control. For some functional food formulations, alternative strategies for flavour modification are needed. Traditional methods, such as the addition of sucrose and sodium chloride, may decrease the perceived 'healthiness' of a product, and thus, may be sub-optimal. In a second study, high and low concentrations of five different bitter inhibiting compounds - 'bitter blockers' - (B-cyclodextrin, homoeridictyol sodium salt, carboxymethylcellulose - low viscosity, zinc sulfate, magnesium sulfate) were tested for their efficacy towards decreasing the bitterness of high and low concentrations of caffeine and (+)catechin - two health-relevant, plant-derived bitterants. B-cyclodextrin and homoeridictyol sodium salt were the most effective blockers at decreasing (+ )-catechin and caffeine, respectively. In addition to bitter blockers, additional flavour modifying strategies, either alone or in combination - may also be successful in functional food formulations. Both sucrose and rebaudioside A - a plant-derived sweetener - were effective at decreasing the bitterness of (+)catechin. When added to (+)-catechin along with B-cyc1odextrin, both sweeteners provided the most effective decrease in bitterness compared to binary, ternary, or quaternary mixtures of (+)catechin together with bitter blockers, sweeteners, andlor odourants. The perceived intensity of sensations elicited by sweeteners and odourants was not affected by the addition of bitter blockers, and thus, their impact within these complex matrices is minimal. In addition, withinmodal (taste-taste) compared to cross-modal (taste-odour) sensory interactions were more effective at decreasing the bitterness of (+ )-catechin. Overall, results from these studies demonstrate that certain novel, alternative flavour modifying approaches may be successful towards lowering the bitterness and astringency elicited by (+ )-catechin and caffeine in aqueous solutions.