No description available.

In many industrial experiments, completely randomized designs (CRDs) are impractical due to restrictions on randomization, or the existence of one or more hard-to-change factors. Under these situations, split-plot experiments are more realistic. The two separate randomizations in split-plot experiments lead to different error structure from in CRDs, and hence this affects not only response modeling but also the choice of design. In this dissertation, two graphical tools, three-dimensional variance dispersion graphs (3-D VDGs) and fractions of design space (FDS) plots are adapted for split-plot designs (SPDs). They are used for examining and comparing different variations of central composite designs (CCDs) with standard, V- and G-optimal factorial levels. The graphical tools are shown to be informative for evaluating and developing strategies for improving the prediction performance of SPDs. The overall cost of a SPD involves two types of experiment units, and often each individual whole plot is more expensive than individual subplot and measurement. Therefore, considering only the total number of observations is likely not the best way to reflect the cost of split-plot experiments. In this dissertation, cost formulation involving the weighted sum of the number of whole plots and the total number of observations is discussed and the three cost adjusted optimality criteria are proposed. The effects of considering different cost scenarios on the choice of design are shown in two examples. Often in practice it is difficult for the experimenter to select only one aspect to find the optimal design. A realistic strategy is to select a design with good balance for multiple estimation and prediction criteria. Variations of the CCDs with the best cost-adjusted performance for estimation and prediction are studied for the combination of D-, G- and V-optimality criteria and each individual criterion. / Ph. D.

Yes / Food loss is one of the significant threats to sustainable development. Although various studies investigating food loss drivers disclosed that logistics is a significant reason for food loss, logistics-related food loss drivers have not been thoroughly studied. Thus, this paper aims to identify, classify and rank the logistics-related food loss drivers, having more influence on the amount of food loss in the fruit and vegetable supply chain, with the help of a mixed-method approach. First, a literature review was conducted to identify potential logistics-related food loss drivers. A total of 49 articles were analyzed. Second, 21 semi-structured interviews were conducted with industry experts to finalize the drivers. Third, the analytical hierarchy process was employed to rank the drivers having more influence on the amount of food loss. Five main drivers and nineteen sub-drivers were identified at the end of the literature review and interview process. Categorization of main drivers is based on the logistics activities. According to results, warehousing-related drivers and transportation-related drivers are the two most influential drivers on the amount of food loss, while lack of coordination and improper packaging material are the two most influential sub-drivers. Following the ranking of drivers and sub-drivers, mitigation strategies to diminish food loss are also discussed. The findings of this study are intended to guide fruit and vegetable supply chain actors in tackling food loss.

專家系統自1965年發展至今，其發展是與日遽增，在邁入二十一世紀這個新紀元，傳統的專家系統遭遇到不同以往的問題，不僅處理的問題複雜度提高之外，在建置系統的過程中需要更多專家提供其寶貴的意見，以期讓系統在處理問題的層面能更加寬廣及增進其彈性和效用。因此，多專家系統能夠解決傳統上單一專家先天上的限制。Gaines和Shaw於1989年在其論著中指出，利用一群專家的知識來發展專家系統其效益比單一專家來的更好。 然而，在多專家的專家系統中會產生案例選取的衝突，過去大都依賴人為的經驗法則判斷。如此一來，不僅在處理的時間成本上產生耗損，其選取案例的公信力亦容易令人產生存疑。此外在相關的研究上，絕大多數都未對於此一衝突提出另外一套較具公正性的解決辦法。 針對此一現象，本研究發現欲解決其中之案例衝突，可以藉由群體決策和多評準決策領域中尋求解決之辦法，透過本研究一連串的文獻蒐集與探討，得到Nemawashi決策模式可以加以導入應用，因此，本研究嘗試引用案例式推論（Case-Base Reasoning）、Nemawashi 決策模式，提出一個整合多專家的意見和解決其案例產生衝突的方法。 / Expert system has been in speeding development since 1965. With the advent of the 21st century, the traditional expert system is encountering problems different from the past. With the rising complexity of nowadays problems, it requires valuable opinions from more professionals in the construction of expert system. The multi-expert knowledge can not only broaden the scope in which the system handles problems, but also enhance the system’s flexibility and efficiency. Thus, multi-expert system outsmarts the conventional expert system which is restricted by the voice of a single expert. Gaines and Shaw in 1989 commented that the expert system was better quipped with a group of experts than with one single expert. Nevertheless, multi-expert system contains the problem of case conflict. To undermine the conflict, it is common for people to resort to experts’ judgments and their personal experiences. Consequently, the multi-expert system has the disadvantage of consuming time in the process of case selection. Moreover, the case selected out of this process may be unconvincing due to its overdependence on human decisions. As to the problem of case conflict, most of the researches related to multi-expert system do not propose other more objective solutions. Focus on the problem mentioned above, this study tends to solve case conflict through the use of Group Decision and Multiple Criteria Decision-Making (MCDM). After the collection and analysis of data, the study finds out that Nemawashi Decisions are effective in handling the problem of case conflict. Thus, this study attempts to apply Nemawashi Decisions in Case-Base Reasoning in order to combine opinions from different experts and to solve the case conflict in the multi-expert system.

In developing natural resources, decision makers are seeking to achieve different objectives, which cannot be reduced to a single objective such as economic efficiency, this covers only part of the problem. Tradeoffs between multiple objective of unequal importance is unavoidable in the process of selection or ranking of alternative developmental projects or plans. Multiobjective technique has the ability to deal with qualitative and quantitative objectives, also it enhances the planning process by involving broader segments of the society in the process of decision making. Compromise programming (CP) and utility worth analysis (UWA), two multiobjective methods were applied on Zarqa River Basin Project (ZRBP) in Jordan. Their appropriateness and suitability as decision aiding tools was examined in this study. For the purpose of the study, five criteria were developed to serve as a basis for the evaluation and 61 farmers and 15 technicians, planners and decision makers were interviewed. High consistency was observed among the results of ranking the six alternatives when both methods were applied, at the same time the ranking of the alternatives according to benefit/cost ratio and the internal rates of return as economic efficiency measures showed no agreement with the multiobjective ranking.

Decision making study has been the multi-disciplinary research involving operations researchers, management scientists, statisticians, mathematical psychologists and economists as well as others. This study aims to investigate the theory and methodology of decision making research and apply them to different contexts in real cases. The study has reviewed the literature of Multiple Criteria Decision Making (MCDM), Evidential Reasoning (ER) approach, Naturalistic Decision Making (NDM) movement, Social Judgment Theory (SJT), and Adaptive Toolbox (AT) program. On the basis of these literatures, two methods, Evidence-based Trade-Off (EBTO) and Judgment Analysis with Heuristic Modelling (JA-HM), have been proposed and developed to accomplish decision making problems under different conditions. In the EBTO method, we propose a novel framework to aid people s decision making under uncertainty and imprecise goal. Under the framework, the imprecise goal is objectively modelled through an analytical structure, and is independent of the task requirement; the task requirement is specified by the trade-off strategy among criteria of the analytical structure through an importance weighting process, and is subject to the requirement change of a particular decision making task; the evidence available, that could contribute to the evaluation of general performance of the decision alternatives, are formulated with belief structures which are capable of capturing various format of uncertainties that arise from the absence of data, incomplete information and subjective judgments. The EBTO method was further applied in a case study of Soldier system decision making. The application has demonstrated that EBTO, as a tool, is able to provide a holistic analysis regarding the requirements of Soldier missions, the physical conditions of Soldiers, and the capability of their equipment and weapon systems, which is critical in domain. By drawing the cross-disciplinary literature from NDM and AT, the JA-HM extended the traditional Judgment Analysis (JA) method, through a number of novel methodological procedures, to account for the unique features of decision making tasks under extreme time pressure and dynamic shifting situations. These novel methodological procedures include, the notion of decision point to deconstruct the dynamic shifting situations in a way that decision problem could be identified and formulated; the classification of routine and non-routine problems, and associated data alignment process to enable meaningful decision data analysis across different decision makers (DMs); the notion of composite cue to account for the DMs iterative process of information perception and comprehension in dynamic task environment; the application of computational models of heuristics to account for the time constraints and process dynamics of DMs decision making process; and the application of cross-validation process to enable the methodological principle of competitive testing of decision models. The JA-HM was further applied in a case study of fire emergency decision making. The application has been the first behavioural test of the validity of the computational models of heuristics, in predicting the DMs decision making during fire emergency response. It has also been the first behavioural test of the validity of the non-compensatory heuristics in predicting the DMs decisions on ranking task. The findings identified extend the literature of AT and NDM, and have implications for the fire emergency decision making.

O processo de tomada de decisão que envolve a priorização e a seleção de projetos de investimentos na indústria do petróleo está longe de ser uma tarefa trivial. Ao mesmo tempo em que a empresa deve buscar relações favoráveis entre risco e retorno econômico-financeiro também deve se alinhar cada vez mais aos princípios do desenvolvimento sustentável em seus negócios. Em se tratando do caso da indústria petrolífera brasileira, formada essencialmente por um monopólio estatal, esta tarefa se torna ainda mais difícil, já que uma série de interesses públicos relacionados ao investimento também devem ser considerados. Sendo assim, o objetivo principal desta pesquisa foi o desenvolvimento e a aplicação de um modelo original de análise usando múltiplos critérios que auxiliasse na priorização e na seleção de projetos de investimentos nas refinarias de petróleo brasileiras. Utilizou-se uma metodologia de pesquisa quantitativa com o uso de diversos artefatos de matemática aplicada capazes de lidar adequadamente com as avaliações muitas vezes incompletas e subjetivas que caracterizam o problema da análise de investimentos em refinarias de petróleo. Ao final do trabalho, conseguiu-se obter um modelo suficientemente simples, ao ponto de ser facilmente implementado em uma planilha eletrônica, robusto, ao ser capaz de lidar de maneira bastante adequada com as principais peculiaridades que envolvem o setor do refino de petróleo no Brasil e flexível, de maneira que os critérios de análise e as alternativas de decisão pudessem ser facilmente adicionados, removidos ou alterados de acordo com as necessidades específicas exigidas para cada caso. / The decision-making process involving the prioritization and selection of investment projects in the oil industry is far from being a trivial task. At the same time that the company must seek for a favorable relationship between risk and economic-financial return it must also be more and more aligned to the principles of sustainable development in their business. Regarding to the case of the Brazilian oil industry, essentially formed by a state monopoly, this task becomes even more difficult, since a number of public interests related to investment should also be considered. Thus, the main objective of this research was the development and application of an original analysis model using multiple criteria that help in the prioritization and selection of investment projects on the Brazilian oil refineries. We used a quantitative research methodology using various applied mathematical tools capable of dealing properly with often incomplete and subjective valuations of investment analysis in oil refineries. At the end, it was possible to obtain a sufficiently simple model, that could be easily implemented in a spreadsheet, robust, to deal in a properly way with the main peculiarities involving the oil refining sector in Brazil and sufficiently flexible so that the criteria for analysis and decision alternatives could be easily added, removed or modified in accordance with the specific needs required for each case.

Made available in DSpace on 2016-08-10T10:40:23Z (GMT). No. of bitstreams: 1 POLLYANA DE FREITAS ANDRADE.pdf: 1328160 bytes, checksum: b4ac49bc4d92a3d57210ee4d58a88f3b (MD5) Previous issue date: 2014-09-22 / Private social investments are presented as an important form of activity in the business sector which supports the mitigation of socio economic issues. Such investments are made through environmental and social projects of public interest. However, despite the importance of the topic, there are only few academic researches aimed at improving the allocation of business resources in private social investments. This research aims to contribute to this scenario through implementation and analysis of multi-criteria decision support method ELECTRE I, which separates the process of decision-making from the subjectivity and increases the potential for efficient selection of projects. / Os investimentos sociais privados apresentam-se como importante forma de atuação do setor empresarial junto à busca da mitigação de problemas sociais. Tais investimentos são realizados por meio de projetos sociais, ambientais e sociais de interesse público. Nota-se que, apesar da relevância do tema, existem poucos estudos voltados ao aprimoramento da alocação dos recursos empresariais nesta área. A pesquisa visa contribuir para este cenário por meio de aprofundamento e aplicação do método multicritério de apoio à decisão ELECTRE I, por meio do qual o processo de tomada de decisão distancia-se da subjetividade e amplia o potencial de seleção eficiente de projetos.

O serviço veterinário oficial é responsável por proteger a saúde pública e animal. Uma ferramenta que auxilia na busca desse objetivo é a análise de risco, que começou a ser utilizada na década de 1990 pelos serviços veterinários oficiais. Para a realização de uma análise de risco, inicialmente deve-se identificar o perigo, o qual na área da saúde animal, geralmente, é o agente patogênico causador de uma doença. A etapa subsequente é a avaliação de riscos, na qual devem ser ponderadas, com suporte de técnicas específicas, as formas de ocorrência do perigo, bem como a magnitude de suas consequências. Entre as técnicas utilizadas nessa etapa, a análise de decisão por múltiplos critérios tem tido um crescente uso. Essa metodologia consegue associar e analisar, conjuntamente, diversas variáveis e, quando integrada ao sistema de informação geográfica, incorpora a dimensão espacial, tornando a ferramenta mais potente. A terceira etapa da análise de risco refere-se ao manejo dos riscos, que visa a propor medidas que mitiguem o risco, bem como avaliar o custo/benefício de cada medida. A última fase é a comunicação dos riscos, que deve ser iniciada juntamente com a análise de risco em si, deixando aberto um canal permanente de comunicação com todos os atores sociais interessados no estudo. O presente trabalho, inicialmente, realizou uma revisão da literatura sobre análise de risco, objetivando expor sua definição e processo de elaboração, assim como verificar como ela está sendo utilizada, quais são as limitações e os desafios do uso dessa ferramenta pelo serviço veterinário oficial brasileiro. Posteriormente, realizou-se uma avaliação de riscos para determinar as áreas de risco para a ocorrência de febre aftosa no Rio Grande do Sul e, ainda, avaliar o desempenho do sistema de vigilância estadual para essa enfermidade. Como resultado, verificou-se que os desafios para o desenvolvimento de uma análise de risco pelo serviço veterinário oficial brasileiro ainda são grandes, destacando-se aqueles relacionados à falta de dados e de pessoal capacitado, o que, por sua vez, pode estar relacionado com a realização de poucas análises de risco no Brasil. Na avaliação de riscos realizada pela técnica de múltiplos critérios, identificou-se que as regiões de fronteira internacional, além da região de Estrela, foram aquelas que apresentaram as áreas de maior risco de ocorrência da febre aftosa no estado do Rio Grande do Sul. As variáveis “proximidade da fronteira internacional”, “densidade de ruminantes” e “densidade de propriedades com suínos de subsistência” foram as que mais influenciaram no modelo. A “presença da unidade veterinária local no município” e a “quantidade de notificações de suspeita de enfermidade animal” foram as variáveis de maior relevância no indicador criado para avaliar o desempenho do sistema de vigilância. As regiões sudeste e sudoeste apresentaram os melhores desempenhos quando comparados com outras regiões do estado. A avaliação de riscos tornou-se um importante instrumento utilizado pelos gestores dos serviços veterinários oficiais na tomada de decisões, contribuindo para a escolha de alternativas que confiram, cientificamente, o menor risco sanitário. Com base neste estudo, os gestores gaúchos poderão escolher as ações sanitárias específicas para cada região do Rio Grande do Sul, servindo, portanto, como uma ferramenta de auxílio, a fim de mitigar o risco de ocorrência da febre aftosa. / As the main responsibility of the Official Veterinary Service is protecting animal and public health, an important tool to achieve this goals is the risk analysis, which began to be used in the 1990s. In order to conduct a risk analysis, it is initially necessary to identify the hazard, which in animal health is generally the pathogen causing a disease. The next step is risk assessment, which consists in evaluating different forms where hazard occurs as well as the magnitude of its consequences. Among various techniques that could be employed in this stage, the multiple criteria decision analysis has been increasingly used nowadays. This methodology associates and analyses jointly many variables and, when integrated with geographic information system, incorporates the spatial dimension, making it a powerful tool. The third risk analysis step refers to risk management, which aims to propose measures to mitigate the risk and assess costs and benefits of each measure. The communication of the risk is the last stage. It should be initiated along with the risk analysis itself, allowing an open and permanent communication with all interested stakeholders in the study. This work commenced with a literature review of risk analysis, so as to expose its definition and development process, as well as checking how it is being used, what limitations exist and the challenges of this tool usage by the Brazilian Official Veterinary Service. Subsequently, there was conducted a risk assessment to determine the risk areas for Foot and Mouth Disease occurrence in Rio Grande do Sul and also evaluate the State performance on surveillance system for this disease. As a result, the challenges for a development of a risk analysis by the Brazilian Official Veterinary Service are still found large, especially those related to the lack of data and trained personnel, resulting in a small number of this type of studies in Brazil. In this risk assessment study it was observed that international border areas, in addition to Estrela/RS region, were the ones which presented the greatest risk of Foot and Mouth Disease occurrence. The most important variables in the model were “international border proximity”, “ruminant density” and “pig farming properties density”. The “presence of a local veterinary unit in the city” and “the amount of suspected animal disease notifications” were the most relevant variables in the indicator created to evaluate the surveillance system performance. The Southeast and Southwest mesoregions showed the best results when compared with other mesoregions of the State. The risk assessment has become an important tool utilized by Official Veterinary Service managers in decision-making, owing to its scientifically proved contribution, which results in a better sanitary risk judgment by them. Based on this study, local managers can select specific animal health actions for each Rio Grande do Sul mesoregion, providing a supportive tool in order to mitigate the risk of Foot and Mouth occurrence.

An organization’s information technology (IT) infrastructure capability is increasinglyrealized as a critical part to business effectiveness and efficiency. IT infrastructure servicesare particularly important for organizations looking to deploy business processes indeveloping markets. There has also been an interest from many small and medium sizedorganizations whose core business is not in IT to outsource and manage these servicesthrough third party service providers. However there is a need to create an understanding forthese organizations to deploy the right infrastructure services in order to enable easierimplementation or reengineering of the business process. There has been little researchfocusing on the patterns of the IT infrastructure capabilities in the small and medium sizedorganizations in the developing markets.The research aims for a comprehensive coverage by analyzing the requirements in thedeveloping markets and proposing a selection model for the organizations to choose ITservice provider in case they decide to outsource the infrastructure services. The effect of theIT infrastructure services on the business process implementation is presented with anemphasis on the boundary crossing services. Using empirical case study, the research analysesa firm in developing markets and compares it against four strategically similar organizationsfrom different industries. Data collection was primarily qualitative and ably supported bysecondary data.The requirements in developing markets reflect the same as in mature markets. The pricing isseen to play a major role in the selection of the service providers with service security notvery much organization’s priority. The number of boundary crossing services effectivelyenables information sharing and control. These services are the drivers in simplifying thebusiness process implementation. The findings have implications for both business andtechnical managers in regard to planning the IT strategy in the long term and developingappropriate infrastructure according to the process needs. / Program: Magisterutbildning i informatik