To manage an uncertain future relevant societal groups, such as government and corporate sectors, utilise economic forecasts to help plan future strategies. Many vital decisions are based on economic forecasts. Economists have traditionally been the professionals employed as economic forecasting experts. The dominant paradigm for present day forecasting is the "rational expectations theory", which assumes that a forecaster is capable of making optimal use all of the available information. The field of psychology offers a different, yet complementary, approach to the topic of economic forecasting. The aim of the current study was to research mental processes and behaviours of individuals participating in a forecasting task. The role of the following psychological variables within economic prediction behaviour was assessed: (1) task complexity, (2) decision making style, (3) the anchoring and adjustment heuristic, (4) the framing effect, and (5) personal feelings about the task content. All of these variables were hypothesised to have a direct influence on prediction behaviour. In addition, task complexity and decision making style were assumed to moderate the influence of the other psychological variables. A conceptual framework was designed to depict the assumed relationships. (For complete abstract open document)

Orientador: Carlos Alberto Bandeira Guimarães / Dissertação (mestrado) - Universidade Estadual de Campinas, Faculdade de Engenharia Elétrica e de Computação / Made available in DSpace on 2018-08-19T08:42:56Z (GMT). No. of bitstreams: 1 Vecchini_DaltonCherubim_M.pdf: 2675188 bytes, checksum: c6d42c6c743a4bf310db50ca2ef591df (MD5) Previous issue date: 2011 / Resumo: Os problemas dinâmicos de roteirização de veículos com janela de tempo (DVRPTW), derivados dos clássicos problemas de roteirização de veículos (VRP), são conhecidos e estudados há muito tempo. Devido ao barateamento das tecnologias de comunicação, de mapas digitais, a computadores mais rápidos e a sua relevância no dia a dia das empresas de transporte, o interesse da comunidade científica em solucioná-los vem ganhando maior importância e atenção.Este trabalho estuda as características dos DVRPTW e os tipos de abordagem para sua solução.Posteriormente é estabelecida uma estratégia de abordagem e aplicada uma heurística a um caso prático extraído do levantamento em campo em uma empresa de transporte de carga seca e fracionada na cidade de São Paulo, com o objetivo de reduzir o tempo de atendimento das coletas dinâmicas. Finalmente são realizados comparativos entre a prática e o simulado focando na avaliação do tempo de atendimento, distância percorrida e tempo de processamento / Abstract: The problems of dynamic vehicle routing with time window (DVRPTW), derived from the classic vehicle routing problem (VRP), are well known and studied for a long time. Due to cheapening of communication technologies, digital maps, faster computers and its relevance in everyday transport companies, the scientific community's interest in solve them is gaining greater importance and attention. This study shows the characteristics of DVRPTW and the types of approach to its solution. Later it is established a strategy and implemented an heuristic approach to a practical case taken from the field survey in a business of transporting dry cargo and fractionated in São Paulo, aiming to reduce the handling time of dynamics pickups. Finally comparisons are made between the practice and simulated focusing on the evaluation of service time, distance and time processing / Mestrado / Transportes / Mestre em Engenharia Civil

Context: In today's society virus makers have a large set of obfuscation tools to avoid classic signature detection used by antivirus software. Therefore there is a need to identify new and obfuscated viruses in a better way. One option is to look at the behaviour of a program by executing the program in a virtual environment to determine if it is malicious or benign. This approach is called dynamic heuristic analysis. Objectives: In this study a new heuristic dynamic analysis tool for detecting unknown malware is proposed. The proposed implementation is evaluated against state-of-the-art in terms of accuracy. Methods: The proposed implementation uses Cuckoo sandbox to collect the behavior of a software and a decision tree to classify the software as either malicious or benign. In addition, the implementation contains several custom programs to handle the interaction between the components. Results: The experiment evaluating the implementation shows that an accuracy of 90% has been reached which is higher than 2 out of 3 state-of-the-art software. Conclusions: We conclude that an implementation using Cuckoo and decision tree works well for classifying malware and that the proposed implementation has a high accuracy that could be increased in the future by including more samples in the training set.

Continuous optimization problems are optimization problems where all variables<p>have a domain that typically is a subset of the real numbers; mixed discrete-continuous<p>optimization problems have additionally other types of variables, so<p>that some variables are continuous and others are on an ordinal or categorical<p>scale. Continuous and mixed discrete-continuous problems have a wide range<p>of applications in disciplines such as computer science, mechanical or electrical<p>engineering, economics and bioinformatics. These problems are also often hard to<p>solve due to their inherent difficulties such as a large number of variables, many<p>local optima or other factors making problems hard. Therefore, in this thesis our<p>focus is on the design, engineering and configuration of high-performing heuristic<p>optimization algorithms.<p>We tackle continuous and mixed discrete-continuous optimization problems<p>with two classes of population-based heuristic algorithms, ant colony optimization<p>(ACO) algorithms and evolution strategies. In a nutshell, the main contributions<p>of this thesis are that (i) we advance the design and engineering of ACO algorithms to algorithms that are competitive or superior to recent state-of-the-art<p>algorithms for continuous and mixed discrete-continuous optimization problems,<p>(ii) we improve upon a specific state-of-the-art evolution strategy, the covariance<p>matrix adaptation evolution strategy (CMA-ES), and (iii) we extend CMA-ES to<p>tackle mixed discrete-continuous optimization problems.<p>More in detail, we propose a unified ant colony optimization (ACO) framework<p>for continuous optimization (UACOR). This framework synthesizes algorithmic<p>components of two ACO algorithms that have been proposed in the literature<p>and an incremental ACO algorithm with local search for continuous optimization,<p>which we have proposed during my doctoral research. The design of UACOR<p>allows the usage of automatic algorithm configuration techniques to automatically<p>derive new, high-performing ACO algorithms for continuous optimization. We also<p>propose iCMAES-ILS, a hybrid algorithm that loosely couples IPOP-CMA-ES, a<p>CMA-ES variant that uses a restart schema coupled with an increasing population<p>size, and a new iterated local search (ILS) algorithm for continuous optimization.<p>The hybrid algorithm consists of an initial competition phase, in which IPOP-CMA-ES and the ILS algorithm compete for further deployment during a second<p>phase. A cooperative aspect of the hybrid algorithm is implemented in the form<p>of some limited information exchange from IPOP-CMA-ES to the ILS algorithm<p>during the initial phase. Experimental studies on recent benchmark functions<p>suites show that UACOR and iCMAES-ILS are competitive or superior to other<p>state-of-the-art algorithms.<p>To tackle mixed discrete-continuous optimization problems, we extend ACOMV <p>and propose CESMV, an ant colony optimization algorithm and a covariance matrix adaptation evolution strategy, respectively. In ACOMV and CESMV ,the decision variables of an optimization problem can be declared as continuous, ordinal, or categorical, which allows the algorithm to treat them adequately. ACOMV and<p>CESMV include three solution generation mechanisms: a continuous optimization<p>mechanism, a continuous relaxation mechanism for ordinal variables, and a categorical optimization mechanism for categorical variables. Together, these mechanisms allow ACOMV and CESMV to tackle mixed variable optimization problems.<p>We also propose a set of artificial, mixed-variable benchmark functions, which can<p>simulate discrete variables as ordered or categorical. We use them to automatically tune ACOMV and CESMV's parameters and benchmark their performance.<p>Finally we test ACOMV and CESMV on various real-world continuous and mixed-variable engineering optimization problems. Comparisons with results from the<p>literature demonstrate the effectiveness and robustness of ACOMV and CESMV<p>on mixed-variable optimization problems.<p>Apart from these main contributions, during my doctoral research I have accomplished a number of additional contributions, which concern (i) a note on the<p>bound constraints handling for the CEC'05 benchmark set, (ii) computational results for an automatically tuned IPOP-CMA-ES on the CEC'05 benchmark set and<p>(iii) a study of artificial bee colonies for continuous optimization. These additional<p>contributions are to be found in the appendix to this thesis.<p> / Doctorat en Sciences de l'ingénieur / info:eu-repo/semantics/nonPublished

The planning of snow removal routes is complicated by the fact that the amount it snows, and thus the amount of resources, that is, vehicles, needed to clear it, varies from year to year. This variation has created a demand for a way to quickly generate efficient snow removal plans that take the resources that are available into account. In this report we describe the development of an ad hoc heuristic algorithm that improves already existing feasible solutions to the snow removal problem. It accomplishes this by reassigning tasks from the vehicles with the longest tours to those with the shortest tours, followed by reordering their tasks to ensure that the solution remains feasible. This algorithm is meant to be implemented in a larger piece of software and it is tested on a set of pre-generated solutions for a given network and number of vehicles, including the best known ones. Over half of the previously best known solutions were improved by this algorithm.

<p>I syfte att förbättra kunskapsläget kring människors beteenden vid bränder och utrymningar studerades fyra brandsituationer hämtade från ett flertal verkliga händelser ur ett beslutsfattande- och riskbedömningsperspektiv. Det teoretiska underlaget hämtades ur Kahnemans och Tverskys forskning kring heuristiker (Kahneman och Tversky, 1974; Kahneman, Slovic & Tversky, 1982; Gilovich, Griffin & Kahneman, 2002). För ändamålet användes tre heuristiska regler: tillgänglighet, representativitet och affekt. Dessa tre heuristiker möjliggör ögonblickssnabba riskbedömningar genom att allt utom en särskild variabel bortses från i beslutsprocessen. När människor blir stressade tenderar de att förlita sig mer på heuristiker i sina bedömningar. Analysen visar att det är rimligt att anta att de beteenden som observerats i samband med bränder i de fyra fallen beror på beslut huvudsakligen fattade med hjälp av någon av de tre heuristikerna. Denna kunskap kan öppna upp nya möjligheter för att förebygga dödsfall på grund av felaktiga beteenden i samband med bränder och utrymningar.</p>

I syfte att förbättra kunskapsläget kring människors beteenden vid bränder och utrymningar studerades fyra brandsituationer hämtade från ett flertal verkliga händelser ur ett beslutsfattande- och riskbedömningsperspektiv. Det teoretiska underlaget hämtades ur Kahnemans och Tverskys forskning kring heuristiker (Kahneman och Tversky, 1974; Kahneman, Slovic &amp; Tversky, 1982; Gilovich, Griffin &amp; Kahneman, 2002). För ändamålet användes tre heuristiska regler: tillgänglighet, representativitet och affekt. Dessa tre heuristiker möjliggör ögonblickssnabba riskbedömningar genom att allt utom en särskild variabel bortses från i beslutsprocessen. När människor blir stressade tenderar de att förlita sig mer på heuristiker i sina bedömningar. Analysen visar att det är rimligt att anta att de beteenden som observerats i samband med bränder i de fyra fallen beror på beslut huvudsakligen fattade med hjälp av någon av de tre heuristikerna. Denna kunskap kan öppna upp nya möjligheter för att förebygga dödsfall på grund av felaktiga beteenden i samband med bränder och utrymningar.

Published Article / Planning problems are frequently encountered in everyday situations. The brute force approach of evaluating every possible solution for any medium size planning problem is just not feasible. Drools Planner is an open source Java library developed to help solve planning problems by using meta-heuristic algorithms. Drools Planner uses the Drools Expert (rule engine) for score calculation to greatly reduce the complexity and effort required to write scalable constraints in a declarative manner. This paper presents an introduction to Drools Planner, how it can be used to solve problems and concludes with an example scenario.

This work considers the management in the short run of aircraft departures from their parking stands at major airports where traffic congestion is noticeable. At the ground level, congestion is patent when carefully designed departure time tables become unworkable, causing ever increasing delays which penalize heavily passengers, airlines and the airport surrounding community. The study is composed of two parts: First an overall analysis of the considered problem is performed to provide background knowledge and to display basic principles for the management of aircraft ground movements at modem airports. Physical components as well as current operational rules are discussed and their interdependence is revealed. A particular importance is given to new and foreseeable developments in communication and guidance technology which allow an improved prediction of runway occupancy times or gaps. Capacity issues are also discussed with respect to aircraft ground activities and the airfield capacity is analysed. This first part of the work ends with the description of levels of fuel consumption and of pollution emission by aircraft ground operations and thus shows the relevance of the problem considered in this study. The second part of this work is devoted to the design of a just-in-time clearance policy which should minimise environment, fuel and pollution levels and made possible a delay-free ground traffic for departing aircraft A mathematical formulation of the considered decision problem, characterized as a real time scheduling problem, is built up. Then possible solution strategies are appraised and an "ad hoc" heuristic solution algorithm is designed. This solution is first compared in theoretical terms with a First Come First Served policy showing that in an error-free situation the proposed solution cannot be worse than its competitor. Then a simulation study is performed which confirms in practical terms the above result The influence of the main design parameters of the solution algorithm on its performance are also examined giving some insights in relation to necessary communication and prediction aids. Finally, possible extensions of the proposed method and its integration in a global aircraft traffic management system are discussed.

Portfolio selection is an example of decision making under conditions of uncertainty. In the face of an unknown future, fund managers make complex financial choices based on the investors perceptions and preferences towards risk and return. Since the seminal work of Markowitz, many studies have been published using his mean-variance (MV) model as a basis. These mathematical models of investor attitudes and asset return dynamics aid in the portfolio selection process. In this thesis we extend the MV model to include the cardinality constraints which limit the number of assets held in the portfolio and bounds on the proportion of an asset held (if any is held). We present our formulation based on the Markowitz MV model for rebalancing an existing portfolio subject to both fixed and variable transaction cost (the fee associated with trading). We determine and demonstrate the differences that arise in the shape of the trading portfolio and efficient frontiers when subject to non-cardinality and cardinality constrained transaction cost models. We apply our flexible heuristic algorithms of genetic algorithm, tabu search and simulated annealing to both the cardinality constrained and transaction cost models to solve problems using data from seven real world market indices. We show that by incorporating optimization into the generation of valid portfolios leads to good quality solutions in acceptable computational time. We illustrate this on problems from literature as well as on our own larger data sets.