Massey Documents by Type

Permanent URI for this communityhttps://mro.massey.ac.nz/handle/10179/294

Browse

Subject: search.filters.subject.Decision science

Search Results

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Modular local search : a framework for self-adaptive metaheuristics : a thesis presented in partial fulfilment of the requirements for the degree of Doctor of Philosophy in Decision Science at Massey University
    (Massey University, 2010) Woods, David Colin
    This research develops Modular Local Search (MLS), a framework such that trajectory-based metaheuristics can be expressed as subsets of “modules” from a common library, with a common structure. The standardized modules and structure allow the easy formulation of common metaheuristic paradigms, as well as the easy creation of relatively complex hybrids by simply listing the modules that should be included. A new markup language called Modular Local Search Markup Language (MLSML) is developed so that new metaheuristics can be implemented declaratively, rather than programmatically. Some advanced ideas are introduced and explored, whereby metaheuristics are able to modify themselves during their execution, by varying parameters and swapping modules into and out of activation. This ability introduces the potential for semi-intelligent algorithms that are capable of a type of learning. Several demonstration methods are developed and these show promise on a small test set of problem instances. A new combinatorial optimization problem is developed to serve as the testing ground for the new heuristic ideas. The Arc Subset Routing Problem (ASRP) involves routing a vehicle on a graph, choosing a subset of the arcs, such that the reward collected by traversing these arcs is maximised subject to a constraint on the total distance travelled. This problem is first formulated and explored as a traditional Operations Research investigation; construction heuristics are developed, as well as some improvement routines for local search, and computational tournaments are performed to compare the methods. Some attention is given to developing methods to predict which of two heuristics is most suited to a given problem instance, based on an analysis of the characteristics of that problem. Initial results demonstrate the potential of such an approach. The MLS framework offers a powerful and flexible structure both for the easy and consistent implementation of existing metaheuristics, and also as a platform for the development of new, advanced metaheuristic ideas. Early results are encouraging, and a number of directions for future research are discussed, including some complex real-world problems for which the self-adaptive capabilities of MLS would be especially useful.
  • Thumbnail Image
    Item
    Supply chain collaboration : a thesis presented in partial fulfilment of the requirements for the degree of Doctor of Technology in Decision Science at Massey University
    (Massey University, 2004) Simatupang, Togar Mangihut
    There is general acceptance within the literature that supply chain collaboration will become a focus area for research in supply chain management. Although collaboration has been examined widely in a variety of different contexts, relatively little attention has been given to systematically drawing them together. This study is thus conducted to offer an integrative framework in the context of an interorganisational supply chain to define collaboration by identifying its different elements and provides empirical evidence to support the theoretical framework. This framework would further allow the participating members to understand and examine the strategic importance of these elements of collaboration and what needs to be done to gain the benefits of collaboration. The study includes a literature review, the discontent model, a theoretical framework for supply chain collaboration, measuring the level of supply chain collaboration, supporting the theory with empirical evidence, an innovative scheme for benchmarking, and an empirical study of benchmarking supply chain collaboration. The theoretical framework offered in the study incorporates the five elements of collaboration, namely, a collaborative performance system, information sharing, decision synchronisation, incentive alignment, and streamlined intercompany business processes. To provide empirical evidence, supply chain collaboration between retailers and suppliers was chosen as a unit of analysis and data were collected from a survey of New Zealand companies. Based on the survey results, the three empirical studies reported in this thesis provide the basis for testing a new measure for the extent of supply chain collaboration, testing the hypotheses on the relationship between supply chain collaboration and operational performance, and presenting the benchmarks for classifying high and low performing supply chains. Empirical evidence shows that collaboration between retailers and suppliers has a significant influence on operational performance.
  • Thumbnail Image
    Item
    Use of decision science to aid selection of genetically superior animals : a thesis presented in partial fulfilment of the requirements for the degree of Doctor of Philosophy in Animal Science at Massey University, Palmerston North, New Zealand
    (Massey University, 2010) Sherriff, Ryan Leith
    This thesis is concerned with a theoretical simulation model for pig breeding, as part of the ongoing search for the “perfect” genotype. The starting point is an additive model to investigate how accurately the classical, infinitesimal model predicts genetic gain for traits controlled by few loci and few alleles. This initial investigation demonstrates that the infinitesimal model is robust, providing that at least 15 loci are controlling a trait and there is symmetry in the allele distributions. A Genotype-Pig (GE-Pig) model is then developed to apply the additive effects of alleles on sub-phenotypic traits like maximum protein deposition, minimum lipid to protein content in the whole body, ad libitum digestible energy intake, energy for maintenance requirement and water content in the whole body. These parameters are then used in a nutrient partitioning simulation model to growth a pig and calculate traditional breeding traits such as average daily gain, feed conversion ratio, and backfat thickness for any combination of alleles. Three algorithms, Genetic Algorithm, Tabu Search, and Simulated Annealing, are used to investigate the GE-Pig model and find optimal combination of alleles for different dietary and selection objective situations. The two diets investigated were either of a low or high quality, and the three selection objectives used were, maximising average daily gain, minimizing feed conversion ratio, and minimizing back fat. A graphical method is developed for easy comparison of the genotypes. Of the algorithms, the Genetic Algorithm performed the best, followed by Tabu Search and finally Simulated Annealing. It is demonstrated that, in general, there is a different, single, optimum for any given selection objective and diet. However under the back fat selection objective, both diets produce the same optimal genotype. Also there are many similarities between the optima for the average daily gain and feed conversion ratio selection objectives. When the theoretical minimum number of generations of selection to the optima is considered, the feed conversion ratio selection objective is the quickest for a breeding program to achieve the optimal solutions, followed by back fat, then average daily gain. It is demonstrated that diet also has an effect on the theoretical number of generations. A Multiple selection objective, using relative economic values applied to the individual selection objectives, is also investigated. For both diets, the majority of the multiple selection objective solutions are in the vicinity of the feed conversion ratio optima, indicating that feed conversion ratio is the most prominent factor. It is also demonstrated that the optimal solution is most affected by the objective parameter weights under low diet conditions.