Today bike sharing systems exists in many cities around the globe after a recent growth and popularity in the last decades. It is attractive for cities and users who wants to promote healthier lifestyles; to reduce air pollution and gas emission as well as improve traffic. One major challenge to docked bike sharing system is redistributing bikes and balancing dock stations. There are studies that propose models that can help forecasting bike usage; strategies for rebalancing bike distribution; establish patterns or how to identify patterns. Some of these studies proposes to extend the approach by including weather data. Some had limitations and did not include weather data. This study aims to extend upon these proposals and opportunities to explore on how and in what magnitude weather impacts bike usage. Bike usage data and weather data are gathered for the city of Washington D.C. and are analyzed by using a clustering algorithm called k-means. K-means is suitable for discovering patterns within the data by grouping (clustering) similar instances, which literature review also advocated. In this project, the k-means algorithm managed to identify three clusters that corresponds to bike usage depending on weather. The results show that weather impact on bike usage was noticeable between clusters. It showed that temperature followed by precipitation weighted the most, out of five weather variables. Results also supported that the use of k-means was appropriate for this type of study.

Sistemas de Bicicletas Compartilhadas (SBCs) têm sido implantados e aprimorados nos últimos anos nas principais cidades do mundo. Neste tipo de sistema, usuários podem retirar e devolver bicicletas em qualquer estação da rede, desde que haja bicicleta e vaga disponível, respectivamente. Porém, devido às características de ocupação do solo em grandes centros urbanos, existe uma tendência natural de desbalanceamento nos fluxos dos usuários, fazendo com que em determinados horários certas estações fiquem lotadas de bicicletas enquanto outras estações estão vazias. Para mitigar este problema, gestores de SBCs utilizam veículos de carga para rebalancear o sistema (reposicionar as bicicletas entre as estações). Entretanto, usualmente, esse processo na prática não é realizado com auxílio de ferramentas quantitativas que tornem o processo racional ou maximizem sua eficácia. Nesse sentido, no presente trabalho é proposto um modelo híbrido de simulação com otimização, aplicado ao rebalanceamento de um SBC brasileiro e com potencial para utilização em sistemas reais com o objetivo de melhorar seus níveis de serviço. Além disso, apresenta-se uma análise de dados e a caracterização de uso deste SBC, um histórico de evolução de SBCs ao redor do mundo e sua bibliografia pertinente, a fim de registrá-los na literatura e de se obter maior compreensão deste tipo de sistema. / Bike Sharing Systems (BSSs) have been implemented and enhanced in several major cities around the world, during the past few years. In such systems, users can take off a bike and return it at any network\'s station, provided that there is a bike and a dock available, respectively. However, these systems face an operational problem, caused by the fact that users\' flows are not balanced, bringing on that, at some point in time, some stations will be completely full while others will be empty. To tackle this issue, cargo vehicles are used by BSS\'s operators to rebalance the system (relocate bicycles through the stations). However, in most cases this process is not supported by quantitative tools that make the process rational or maximize its effectiveness. In this sense, this work proposes a hybrid model of simulation with optimization, applied to the rebalance of a Brazilian BSS and with potential for use in real systems with the aim of improving their service levels. In addition, is presented a data analysis and a usage study of this specific BSS, a BSSs evolutionary study and its relevant literature with the purpose of registering them in the literature and achieving a superior understanding of the problem.

Sistemas de Bicicletas Compartilhadas (SBCs) têm sido implantados e aprimorados nos últimos anos nas principais cidades do mundo. Neste tipo de sistema, usuários podem retirar e devolver bicicletas em qualquer estação da rede, desde que haja bicicleta e vaga disponível, respectivamente. Porém, devido às características de ocupação do solo em grandes centros urbanos, existe uma tendência natural de desbalanceamento nos fluxos dos usuários, fazendo com que em determinados horários certas estações fiquem lotadas de bicicletas enquanto outras estações estão vazias. Para mitigar este problema, gestores de SBCs utilizam veículos de carga para rebalancear o sistema (reposicionar as bicicletas entre as estações). Entretanto, usualmente, esse processo na prática não é realizado com auxílio de ferramentas quantitativas que tornem o processo racional ou maximizem sua eficácia. Nesse sentido, no presente trabalho é proposto um modelo híbrido de simulação com otimização, aplicado ao rebalanceamento de um SBC brasileiro e com potencial para utilização em sistemas reais com o objetivo de melhorar seus níveis de serviço. Além disso, apresenta-se uma análise de dados e a caracterização de uso deste SBC, um histórico de evolução de SBCs ao redor do mundo e sua bibliografia pertinente, a fim de registrá-los na literatura e de se obter maior compreensão deste tipo de sistema. / Bike Sharing Systems (BSSs) have been implemented and enhanced in several major cities around the world, during the past few years. In such systems, users can take off a bike and return it at any network\'s station, provided that there is a bike and a dock available, respectively. However, these systems face an operational problem, caused by the fact that users\' flows are not balanced, bringing on that, at some point in time, some stations will be completely full while others will be empty. To tackle this issue, cargo vehicles are used by BSS\'s operators to rebalance the system (relocate bicycles through the stations). However, in most cases this process is not supported by quantitative tools that make the process rational or maximize its effectiveness. In this sense, this work proposes a hybrid model of simulation with optimization, applied to the rebalance of a Brazilian BSS and with potential for use in real systems with the aim of improving their service levels. In addition, is presented a data analysis and a usage study of this specific BSS, a BSSs evolutionary study and its relevant literature with the purpose of registering them in the literature and achieving a superior understanding of the problem.

Le développement du vélo en ville constitue aujourd’hui un impératif pour les élus, notamment au regard des injonctions en faveur du développement durable. Dans les années 2000, les dispositifs de vélos en libre service se sont imposés dans la majorité des villes européennes. Si leur développement a été guidé par des considérations écologiques, ces dispositifs valorisent plus généralement l’innovation politico-institutionnelle et le dynamisme économique des villes. Ces dispositifs se sont imposés grâce à des réseaux transnationaux structurés autour de la thématique du vélo. Ces réseaux invitent à considérer les échanges transnationaux comme vecteurs de transformations dans l’action publique urbaine. Les préoccupations pour le développement du vélo ont une histoire qui s’inscrit dans une série d’interactions entre les villes depuis les années 1970. L’analyse de la formation et des effets des réseaux transnationaux du vélo permet de définir des périodes et des régularités dans ces recompositions qui affectent à la fois les politiques du vélo en ville et l’organisation des pouvoirs politiques urbains. Une première période structurée par l’activité transnationale des associations de défense du vélo invite à comprendre le rôle des échanges dans la définition d’un problème public puis sa mise à l’agenda dans l’ensemble des villes européennes au cours des années 1970. Le traitement des problèmes pousse les élus et les agents administratifs à s’investir dans les échanges transnationaux pour construire une nouvelle compétence municipale fondée sur les expertises associatives. Cet investissement des municipalités caractérise la deuxième période, dans laquelle les municipalités s’affirment dans la mise en œuvre des politiques publiques du vélo en institutionnalisant des réseaux de collectivités au cours des années 1980-1990. Enfin, une troisième période s’engage à partir des années 2000 avec l’arrivée des entreprises du mobilier urbain et de l’affichage publicitaire dans les échanges transnationaux. Cet investissement des entreprises engendre une intense circulation des systèmes de vélos en libre service et confronte les élus urbains à l’exercice d’une régulation des relations avec ces grandes firmes, autant dans les interactions transnationales que dans celles qui se déroulent sur les territoires pour la gestion des services urbains. Ces réseaux transnationaux du vélo sont un moyen d’organiser les pouvoirs locaux et de légitimer les élus municipaux dans la conduite de l’action publique urbaine. / Today, development of urban cycling is a must for politicians, particularly considering injunctions in favor of sustainable development. In the 2000s, bike sharing systems emerged in most European cities. If development was guided by ecological considerations, more generally, these services add value to political and institutional innovation and to the economic vitality of cities. Bike sharing systems were imposed thanks to transnational networks around the theme of the bike. These networks invite us to consider transnational exchanges as vectors of change in urban policies. The development of cycling has a history which is the result of many interactions between cities since the 1970s. The analysis of the creation and the effects of bicycle transnational networks allows us to define time periods and patterns in the evolutions that affect both urban cycling policies and organization of urban political power. A first period, structured by transnational activity of urban cyclist associations, helps us to understand the role of these interactions in the definition of a public issue, and of the inclusion of these questions in the agenda of many European cities during the 1970s. Problem solving encourages decision makers to engage in transnational exchanges to build a new municipal jurisdiction based on associative expertise. This municipal investment characterizes the second period, in which municipalities intensify the implementation of cyclist public policies by institutionalizing city networks in the years 1980-1990. Finally, a third period begins in the 2000s, with the appearance of companies in the area of urban furniture and outdoor advertising in transnational exchanges. These firms generate a heavy circulation of bike sharing systems, and pose the question for decision makers how to manage their relationships with these large companies, both on a transnational level and as far as the management of urban services is concerned. These bicycle transnational networks are a way to organize local authorities and to legitimate decision makers in the management of urban public policies.

A Bicycle-sharing system (BSS) is a popular service scheme deployed in cities of different sizes around the world. Although docked bike systems are its most popular model used, it still experiences a number of weaknesses that could be optimized by investigating bike sharing network properties and evolution of obtained patterns.Efficiently keeping bicycle-sharing system as balanced as possible is the main problem and thus, predicting or minimizing the manual transportation of bikes across the city is the prime objective in order to save logistic costs for operating companies.The purpose of this thesis is two-fold; Firstly, it is to visualize bike flow using data exploration methods and statistical analysis to better understand mobility characteristics with respect to distance, duration, time of the day, spatial distribution, weather circumstances, and other attributes. Secondly, by obtaining flow visualizations, it is possible to focus on specific directed sub-graphs containing only those pairs of stations whose mutual flow difference is the most asymmetric. By doing so, we are able to use graph mining and machine learning techniques on these unbalanced stations.Identification of spatial structures and their structural change can be captured using Convolutional neural network (CNN) that takes adjacency matrix snapshots of unbalanced sub-graphs. A generated structure from the previous method is then used in the Long short-term memory artificial recurrent neural network (RNN LSTM) in order to find and predict its dynamic patterns.As a result, we are predicting bike flows for each node in the possible future sub-graph configuration, which in turn informs bicycle-sharing system owners in advance to plan accordingly. This combination of methods notifies them which prospective areas they should focus on more and how many bike relocation phases are to be expected. Methods are evaluated using Cross validation (CV), Root mean square error (RMSE) and Mean average error (MAE) metrics. Benefits are identified both for urban city planning and for bike sharing companies by saving time and minimizing their cost. / Lånecykel avser ett system för uthyrning eller utlåning av cyklar. Systemet används främst i större städer och bekostas huvudsakligen genom tecknande av ett abonnemang.Effektivt hålla cykel andelssystem som balanseras som möjligt huvud problemand därmed förutsäga eller minimera manuell transport av cyklar över staden isthe främsta mål för att spara logistikkostnaderna för drift companies.Syftet med denna avhandling är tvåfaldigt.För det första är det att visualisera cykelflödet med hjälp av datautforskningsmetoder och statistisk analys för att bättre förstå rörlighetskarakteristika med avseende på avstånd, varaktighet, tid på dagen, rumsfördelning, väderförhållanden och andra attribut.För det andra är det vid möjliga flödesvisualiseringar möjligt att fokusera på specifika riktade grafer som endast innehåller de par eller stationer vars ömsesidiga flödesskillnad är den mest asymmetriska.Genom att göra det kan vi anvnda grafmining och maskininlärningsteknik på dessa obalanserade stationer, och använda konjunktionsnurala nätverk (CNN) som tar adjacency matrix snapshots eller obalanserade subgrafer.En genererad struktur från den tidigare metoden används i det långa kortvariga minnet artificiella återkommande neurala nätverket (RNN LSTM) för att hitta och förutsäga dess dynamiska mönster.Som ett resultat förutsäger vi cykelflden för varje nod i den eventuella framtida underkonfigurationen, vilket i sin tur informerar cykeldelningsägare om att planera i enlighet med detta.Denna kombination av metoder meddelar dem vilka framtida områden som bör inriktas på mer och hur många cykelflyttningsfaser som kan förväntas.Metoder utvärderas med hjälp av cross validation (CV), Root mean square error (RMSE) och Mean average error (MAE) metrics.Fördelar identifieras både för stadsplanering och för cykeldelningsföretag genom att spara tid och minimera kostnaderna.

Many metropolitan cities motivate people to exploit public bike-sharing programs as alternative transportation for many reasons. Due to its’ popularity, multiple types of research on optimizing public bike-sharing systems is conducted on city-level, neighborhood-level, station-level, or user-level to predict the public bike demand. Previously, the research on the public bike demand prediction primarily focused on discovering a relationship with weather as an external factor that possibly impacted the bike usage or analyzing the bike user trend in one aspect. This work hypothesizes two external factors that are likely to affect public bike demand: weather and air pollution. This study uses a public bike data set, daily temperature, precipitation data, and air condition data to discover the trend of bike usage using multiple machine learning techniques such as Decision Tree, Naïve Bayes, and Random Forest. After conducting the research, each algorithm’s output is evaluated with performance comparisons such as accuracy, precision, or sensitivity. As a result, Random Forest is an efficient classifier for the bike demand prediction by weather and precipitation, and Decision Tree performs best for the bike demand prediction by air pollutants. Also, the three class labelings in the daily bike demand has high specificity, and is easy to trace the trend of the public bike system.