abstract: The activity-based approach to travel demand analysis and modeling, which has been developed over the past 30 years, has received tremendous success in transportation planning and policy analysis issues, capturing the multi-way joint relationships among socio-demographic, economic, land use characteristics, activity participation, and travel behavior. The development of synthesizing population with an array of socio-demographic and socio-economic attributes has drawn remarkable attention due to privacy and cost constraints in collecting and disclosing full scale data. Although, there has been enormous progress in producing synthetic population, there has been less progress in the development of population evolution modeling arena to forecast future year population. The objective of this dissertation is to develop a well-structured full-fledged demographic evolution modeling system, capturing migration dynamics and evolution of person level attributes, introducing the concept of new household formations and apprehending the dynamics of household level long-term choices over time. A comprehensive study has been conducted on demography, sociology, anthropology, economics and transportation engineering area to better understand the dynamics of evolutionary activities over time and their impacts in travel behavior. This dissertation describes the methodology and the conceptual framework, and the development of model components. Demographic, socio-economic, and land use data from American Community Survey, National Household Travel Survey, Census PUMS, United States Time Series Economic Dynamic data and United States Center for Disease Control and Prevention have been used in this research. The entire modeling system has been implemented and coded using programming language to develop the population evolution module named `PopEvol' into a computer simulation environment. The module then has been demonstrated for a portion of Maricopa County area in Arizona to predict the milestone year population to check the accuracy of forecasting. The module has also been used to evolve the base year population for next 15 years and the evolutionary trend has been investigated. / Dissertation/Thesis / Ph.D. Civil and Environmental Engineering 2014

The time to treatment plays a major factor in recovery for stroke patients, and simulation techniques can be valuable tools for testing healthcare policies and improving the situation for stroke patients. However, simulation requires individual-level data about stroke patients which cannot be acquired due to patient’s privacy rules. This thesis presents a hybrid simulation model for generating a synthetic population of stroke patients by combining Agent-based and microsimulation modeling. Subsequently, Agent-based simulation is used to estimate the locations where strokes happen. The simulation model is built by conducting the Design Science research method, where the simulation model is built by following a set of steps including data preparation, conceptual model formulation, implementation, and finally running the simulation model. The generated synthetic population size is based on the number of stroke events in a year from a Poisson Point Process and consists of stroke patients along with essential attributes such as age, stroke status, home location, and current location. The simulation output shows that nearly all patients had their stroke while being home, where the traveling factor is insignificant to the stroke locations based on the travel survey data used in this thesis and the assumption that all patients return home at midnight.

A estimativa de viagens por domicílio é fundamental para a tomada de decisões relativas ao planejamento urbano e de transportes. Em geral, a obtenção destas informações é por meio de modelos tradicionais como o modelo clássico de quatro etapas, e a primeira etapa do modelo é a geração de viagens. Entretanto, modelos clássicos apresentam inúmeras falhas, muitas delas relacionadas a suposições prévias matemáticas (normalidade ou continuidade da variável dependente). Desta forma, surge a necessidade de testar outras técnicas de modo a minimizar as falhas apresentadas pelos modelos clássicos e utilizá-las como uma ferramenta auxiliar, como por exemplo, as Redes Neurais Artificiais (RNAs), que podem ser aplicáveis na modelagem de problemas complexos e não lineares na área de engenharia de transportes, pois apresentam capacidade de aprendizagem, adaptação e generalização. Assim, para estimar viagens por domicílio, seja pela modelagem tradicional ou pela modelagem RNA são necessários dados desagregados dos domicílios, incluindo dados dos indivíduos, como as atividades diárias que exerce me dados sócio demográficos, etc. Esses dados são geralmente obtidos por uma Pesquisa O/D, que fornece um banco de dados detalhado sobre o comportamento de viagem da população de uma cidade. No entanto, a maioria das cidades enfrenta problemas para a aquisição desses dados, uma vez que este tipo de pesquisa possui alto custo de preparação, execução, processamento e análise. Portanto, percebe-se a necessidade de novos métodos que forneçam dados confiáveis e com baixo custo, para estimar a demanda por viagens, capazes de gerar resultados com rapidez, qualidade e acurácia e sem a necessidade dos dados provenientes de uma Pesquisa O/D. Devido a dificuldade de aquisição de dados desagregados, foi proposto neste trabalho, a geração da população sintética com dados agregados a partir da aplicação do Método Monte Carlo. Este trabalho tem por objetivo gerar uma população sintética baseada em dados censitários agregados e testar a adequabilidade das RNAs para estimar viagens por domicílio. Neste estudo, a modelagem tradicional foi utilizada para comparar nos resultados obtidos com a modelagem RNA, pois o objetivo não foi checar minuciosamente a qualidade dos modelos lineares, e sim, testar a adequabilidade das RNAs para estimar viagens por domicílio. A abordagem tradicional se baseou em um modelo de regressão linear enquanto que a abordagem de redes neurais consistiu da rede perceptron multi camadas. Na execução do trabalho foram calibrados quatro modelos (dois de cada abordagem) com os dados desagregados da Pesquisa O/D e foram comparados os resultados obtidos de cada abordagem. Ao final do trabalho, foi possível escolher o modelo mais adequados de cada abordagem e em seguida, foram utilizados para prever viagens por domicílio com os dados obtidos pela população sintética. Os resultados indicaram que 70% das variáveis obtidas na população sintética foram consideradas aptas para o estudo e que a estimativa de viagens por domicílio da população sintética obtida em ambos os modelos (Modelo 3-RNA) e (Modelo 4-RLM) obtiveram uma boa previsão, ou seja, mais de 70% das viagens por domicílio da população sintética foram consideradas válidas. Isso demonstrou que, o uso de da modelagem RNA é uma técnica alternativa eficiente e promissora na área de planejamento de transportes, especificamente para a previsão de viagens por domicílio. / The estimated number of household travels is essential in the decision-making process related to urban and transportation planning. Usually, this information is obtained through traditional models, such as four-step classic model, for example, which has trip generation as a first step. However, classic models feature numerous failures. Many of these failures are related to mathematical prior assumptions (normality or continuity of the dependent variable). Thus, it is important to test other techniques in order to reduce the failures and use these techniques as an auxiliary tool, i.e. Artificial Neural Networks (ANN). ANN are applicable in the modeling of complex and nonlinear transportation problems, due to its learning, adaptation and generalization capacities. Thus, to estimate the number of household travel, either by traditional or by ANN models, it is required disaggregated data of the households. It might include information of individuals, as daily activities and sociodemographic information. Usually, these data are obtained by a O/D survey, which provides a detailed database of the population travel behavior of the city. However, the obtainment of this information leads to high costs of preparation, execution, processing and analysis of the data. Thus, most cities have faced problems to attain this information. Therefore, new methods of estimation providing reliable data and low cost, are required. It will enable to estimate the demand of travel, rapidly with quality and accuracy, without the need of data provided through an O/D survey. Due to the difficulty of acquiring disaggregated data, this study proposes the generation of synthetic population through aggregated data by applying the method of Monte Carlo. This study aims to generate a synthetic population based on aggregated census data, and test the suitability of ANN to estimate the number of household travels. Since the aim was not thoroughly check the quality of linear models, instead, test the suitability of ANN to estimate the number of household travels, obtained results of traditional and ANN models were compared. The traditional approach was based on a linear regression while the neural network consisted of Multilayer Perceptron network. Four models (two of each approach) were proposed and calibrated with disaggregated data of an O/D Survey. Then, the results were compared. It enabled to choose the most appropriate model of each approach. Hence, these models were used to forecast the number of household travels, using the data obtained by the synthetic population proposed. The results indicated that 70% of the variables obtained through the synthetic population, were considered suitable for the study. Besides, the estimated number of household travels of the synthetic population obtained for both models (Model 3-RNA and 4-MLR model) presented a good forecast, indicating that more than 70% of household travels of the synthetic population were considered valid. Finally, it is concluded that the use of ANN modeling is an effective and promising alternative technique in the transportation-planning field, specifically to forecast the number of household travels.

A estimativa de viagens por domicílio é fundamental para a tomada de decisões relativas ao planejamento urbano e de transportes. Em geral, a obtenção destas informações é por meio de modelos tradicionais como o modelo clássico de quatro etapas, e a primeira etapa do modelo é a geração de viagens. Entretanto, modelos clássicos apresentam inúmeras falhas, muitas delas relacionadas a suposições prévias matemáticas (normalidade ou continuidade da variável dependente). Desta forma, surge a necessidade de testar outras técnicas de modo a minimizar as falhas apresentadas pelos modelos clássicos e utilizá-las como uma ferramenta auxiliar, como por exemplo, as Redes Neurais Artificiais (RNAs), que podem ser aplicáveis na modelagem de problemas complexos e não lineares na área de engenharia de transportes, pois apresentam capacidade de aprendizagem, adaptação e generalização. Assim, para estimar viagens por domicílio, seja pela modelagem tradicional ou pela modelagem RNA são necessários dados desagregados dos domicílios, incluindo dados dos indivíduos, como as atividades diárias que exerce me dados sócio demográficos, etc. Esses dados são geralmente obtidos por uma Pesquisa O/D, que fornece um banco de dados detalhado sobre o comportamento de viagem da população de uma cidade. No entanto, a maioria das cidades enfrenta problemas para a aquisição desses dados, uma vez que este tipo de pesquisa possui alto custo de preparação, execução, processamento e análise. Portanto, percebe-se a necessidade de novos métodos que forneçam dados confiáveis e com baixo custo, para estimar a demanda por viagens, capazes de gerar resultados com rapidez, qualidade e acurácia e sem a necessidade dos dados provenientes de uma Pesquisa O/D. Devido a dificuldade de aquisição de dados desagregados, foi proposto neste trabalho, a geração da população sintética com dados agregados a partir da aplicação do Método Monte Carlo. Este trabalho tem por objetivo gerar uma população sintética baseada em dados censitários agregados e testar a adequabilidade das RNAs para estimar viagens por domicílio. Neste estudo, a modelagem tradicional foi utilizada para comparar nos resultados obtidos com a modelagem RNA, pois o objetivo não foi checar minuciosamente a qualidade dos modelos lineares, e sim, testar a adequabilidade das RNAs para estimar viagens por domicílio. A abordagem tradicional se baseou em um modelo de regressão linear enquanto que a abordagem de redes neurais consistiu da rede perceptron multi camadas. Na execução do trabalho foram calibrados quatro modelos (dois de cada abordagem) com os dados desagregados da Pesquisa O/D e foram comparados os resultados obtidos de cada abordagem. Ao final do trabalho, foi possível escolher o modelo mais adequados de cada abordagem e em seguida, foram utilizados para prever viagens por domicílio com os dados obtidos pela população sintética. Os resultados indicaram que 70% das variáveis obtidas na população sintética foram consideradas aptas para o estudo e que a estimativa de viagens por domicílio da população sintética obtida em ambos os modelos (Modelo 3-RNA) e (Modelo 4-RLM) obtiveram uma boa previsão, ou seja, mais de 70% das viagens por domicílio da população sintética foram consideradas válidas. Isso demonstrou que, o uso de da modelagem RNA é uma técnica alternativa eficiente e promissora na área de planejamento de transportes, especificamente para a previsão de viagens por domicílio. / The estimated number of household travels is essential in the decision-making process related to urban and transportation planning. Usually, this information is obtained through traditional models, such as four-step classic model, for example, which has trip generation as a first step. However, classic models feature numerous failures. Many of these failures are related to mathematical prior assumptions (normality or continuity of the dependent variable). Thus, it is important to test other techniques in order to reduce the failures and use these techniques as an auxiliary tool, i.e. Artificial Neural Networks (ANN). ANN are applicable in the modeling of complex and nonlinear transportation problems, due to its learning, adaptation and generalization capacities. Thus, to estimate the number of household travel, either by traditional or by ANN models, it is required disaggregated data of the households. It might include information of individuals, as daily activities and sociodemographic information. Usually, these data are obtained by a O/D survey, which provides a detailed database of the population travel behavior of the city. However, the obtainment of this information leads to high costs of preparation, execution, processing and analysis of the data. Thus, most cities have faced problems to attain this information. Therefore, new methods of estimation providing reliable data and low cost, are required. It will enable to estimate the demand of travel, rapidly with quality and accuracy, without the need of data provided through an O/D survey. Due to the difficulty of acquiring disaggregated data, this study proposes the generation of synthetic population through aggregated data by applying the method of Monte Carlo. This study aims to generate a synthetic population based on aggregated census data, and test the suitability of ANN to estimate the number of household travels. Since the aim was not thoroughly check the quality of linear models, instead, test the suitability of ANN to estimate the number of household travels, obtained results of traditional and ANN models were compared. The traditional approach was based on a linear regression while the neural network consisted of Multilayer Perceptron network. Four models (two of each approach) were proposed and calibrated with disaggregated data of an O/D Survey. Then, the results were compared. It enabled to choose the most appropriate model of each approach. Hence, these models were used to forecast the number of household travels, using the data obtained by the synthetic population proposed. The results indicated that 70% of the variables obtained through the synthetic population, were considered suitable for the study. Besides, the estimated number of household travels of the synthetic population obtained for both models (Model 3-RNA and 4-MLR model) presented a good forecast, indicating that more than 70% of household travels of the synthetic population were considered valid. Finally, it is concluded that the use of ANN modeling is an effective and promising alternative technique in the transportation-planning field, specifically to forecast the number of household travels.

Le but de cette thèse est de développer des outils statistiques permettant d'initialiser et de calibrer les modèles de microsimulation dynamique stochastique, en partant de l'exemple du modèle SimVillages (développé dans le cadre du projet Européen PRIMA). Ce modèle couple des dynamiques démographiques et économiques appliquées à une population de municipalités rurales. Chaque individu de la population, représenté explicitement dans un ménage au sein d'une commune, travaille éventuellement dans une autre, et possède sa propre trajectoire de vie. Ainsi, le modèle inclut-il des dynamiques de choix de vie, d'étude, de carrière, d'union, de naissance, de divorce, de migration et de décès. Nous avons développé, implémenté et testé les modèles et méthodes suivants: * un modèle permettant de générer une population synthétique à partir de données agrégées, où chaque individu est membre d'un ménage, vit dans une commune et possède un statut au regard de l'emploi. Cette population synthétique est l'état initial du modèle. * un modèle permettant de simuler une table d'origine-destination des déplacements domicile-travail à partir de données agrégées. * un modèle permettant d'estimer le nombre d'emplois dans les services de proximité dans une commune donnée en fonction de son nombre d'habitants et de son voisinage en termes de service. * une méthode de calibration des paramètres inconnus du modèle SimVillages de manière à satisfaire un ensemble de critères d'erreurs définis sur des sources de données hétérogènes. Cette méthode est fondée sur un nouvel algorithme d'échantillonnage séquentiel de type Approximate Bayesian Computation.

Le but de cette thèse est de développer des outils statistiques permettant d'initialiser et de calibrer les modèles de microsimulation dynamique stochastique, en partant de l’exemple du modèle SimVillages (développé dans le cadre du projet Européen PRIMA). Ce modèle couple des dynamiques démographiques et économiques appliquées à une population de municipalités rurales. Chaque individu de la population, représenté explicitement dans un ménage au sein d’une commune, travaille éventuellement dans une autre, et possède sa propre trajectoire de vie. Ainsi, le modèle inclut-il des dynamiques de choix de vie, d’étude, de carrière, d’union, de naissance, de divorce, de migration et de décès. Nous avons développé, implémenté et testé les modèles et méthodes suivants : 1 / un modèle permettant de générer une population synthétique à partir de données agrégées, où chaque individu est membre d’un ménage, vit dans une commune et possède un statut au regard de l’emploi. Cette population synthétique est l’état initial du modèle. 2 / un modèle permettant de simuler une table d’origine-destination des déplacements domicile-travail à partir de données agrégées. 3 / un modèle permettant d’estimer le nombre d’emplois dans les services de proximité dans une commune donnée en fonction de son nombre d’habitants et de son voisinage en termes de service. 4 / une méthode de calibration des paramètres inconnus du modèle SimVillages de manière à satisfaire un ensemble de critères d'erreurs définis sur des sources de données hétérogènes. Cette méthode est fondée sur un nouvel algorithme d’échantillonnage séquentiel de type Approximate Bayesian Computation. / The purpose of this thesis is to develop statistical tools to initialize and to calibrate dynamic stochastic microsimulation models, starting from their application to the SimVillages model (developed within the European PRIMA project). This model includes demographic and economic dynamics applied to the population of a set of rural municipalities. Each individual, represented explicitly in a household living in a municipality, possibly working in another, has its own life trajectory. Thus, model includes rules for the choice of study, career, marriage, birth children, divorce, migration, and death. We developed, implemented and tested the following models : • a model to generate a synthetic population from aggregate data, where each individual lives in a household in a municipality and has a status with regard to employment. The synthetic population is the initial state of the model. • a model to simulate a table of origin-destination commuting from aggregate data in order to assign a place of work for each individual working outside his municipality of residence. • a sub-model to estimate the number of jobs in local services in a given municipality in terms of its number of inhabitants and its neighbors in terms of service. • a method to calibrate the unknown SimVillages model parameters in order to satisfy a set of criteria. This method is based on a new Approximate Bayesian Computation algorithm using importance sampling. When applied to a toy example and to the SimVillages model, our algorithm is 2 to 8 times faster than the three main sequential ABC algorithms currently available.