The increasing number of travelers in urban areas has led to new opportunities for local government and private mobility providers to offer new travel modes besides and in addition to traditional ones. Multimodal travel provides an especially promising opportunity. However, until now the underlying reasons why consumers choose specific alternatives have not been fully understood. Hence, the design of new travel modes is mainly driven by obvious criteria such as environmental friendliness and convenience but might not consider consumers’ real or latent needs. To close this research gap, sixty in-depth interviews with urban travelers were conducted. To identify the perceptual differences of customers among different travel modes, the repertory grid technique as an innovative, structured interview method was applied. Our data show that urban travelers distinguish and select travel alternatives based on 28 perceptual determinants. While some determinants associated with private cars such as privacy, flexibility and autonomy are key indicators of travel mode choice, costs and time efficiency also play a major role. Furthermore, by comparing travel modes to an ideal category, we reveal that some perceptual determinants do not need to be maximized in order to fulfill customer needs optimally. A comparison of consumers’ perceptual assessments of alternative travel modes identifies specific advantages and disadvantages of all alternatives, and provides fruitful implications for government and private mobility providers.

Today’s sparse cities with for example workplaces located outside the city centre has led to increased travel levels for the inhabitants. The long distance between different attribute has resulted in a car dependency. To achieve the climate goals and a sustainable development it’s important to have a transition to more sustainable travel modes. This essay focus on socially and environmentally sustainable travels to workplaces outside the city centre. The aim of the study is the understand how the geographical location of the workplace affects the travel mode choice. The ambition is to examine the possibilities for environmentally sustainable travel at the same time as the travel also must be socially sustainable and feasible in the individual’s everyday life. This study is conducted in Umeå with a workplace located outside the city centre. The empirical material has been collected through interviews with employees in purpose the understand the individual conditions and travel patterns. The results are then discussed and analysed using, theories and previous research, time-geography, aspects of accessibility and travel mode choice to create an understanding of sustainable travel to workplaces with an external localisation. The results identified challenges linked to long distance, lack of accessibility to use other travel modes and individual constraints. The results shows that individuals have different constraints and opportunities to change their travel mode, but that it is also bound to how much an individual is willing, and able, to sacrifice.

Identification of travelers' transportation modes is a fundamental step for various problems that arise in the domain of transportation such as travel demand analysis, transport planning, and traffic management. This thesis aims to identify travelers' transportation modes purely based on their GPS trajectories. First, a segmentation process is developed to partition a user's trip into GPS segments with only one transportation mode. A majority of studies have proposed mode inference models based on hand-crafted features, which might be vulnerable to traffic and environmental conditions. Furthermore, the classification task in almost all models have been performed in a supervised fashion while a large amount of unlabeled GPS trajectories has remained unused. Accordingly, a deep SEmi-Supervised Convolutional Autoencoder (SECA) architecture is proposed to not only automatically extract relevant features from GPS segments but also exploit useful information in unlabeled data. The SECA integrates a convolutional-deconvolutional autoencoder and a convolutional neural network into a unified framework to concurrently perform supervised and unsupervised learning. The two components are simultaneously trained using both labeled and unlabeled GPS segments, which have already been converted into an efficient representation for the convolutional operation. An optimum schedule for varying the balancing parameters between reconstruction and classification errors are also implemented. The performance of the proposed SECA model, trip segmentation, the method for converting a raw trajectory into a new representation, the hyperparameter schedule, and the model configuration are evaluated by comparing to several baselines and alternatives for various amounts of labeled and unlabeled data. The experimental results demonstrate the superiority of the proposed model over the state-of-the-art semi-supervised and supervised methods with respect to metrics such as accuracy and F-measure. / Master of Science / Identifying users' transportation modes (e.g., bike, bus, train, and car) is a key step towards many transportation related problems including (but not limited to) transport planning, transit demand analysis, auto ownership, and transportation emissions analysis. Traditionally, the information for analyzing travelers' behavior for choosing transport mode(s) was obtained through travel surveys. High cost, low-response rate, time-consuming manual data collection, and misreporting are the main demerits of the survey-based approaches. With the rapid growth of ubiquitous GPS-enabled devices (e.g., smartphones), a constant stream of users' trajectory data can be recorded. A user's GPS trajectory is a sequence of GPS points, recorded by means of a GPS-enabled device, in which a GPS point contains the information of the device geographic location at a particular moment. In this research, users' GPS trajectories, rather than traditional resources, are harnessed to predict their transportation mode by means of statistical models. With respect to the statistical models, a wide range of studies have developed travel mode detection models using on hand-designed attributes and classical learning techniques. Nonetheless, hand-crafted features cause some main shortcomings including vulnerability to traffic uncertainties and biased engineering justification in generating effective features. A potential solution to address these issues is by leveraging deep learning frameworks that are capable of capturing abstract features from the raw input in an automated fashion. Thus, in this thesis, deep learning architectures are exploited in order to identify transport modes based on only raw GPS tracks. It is worth noting that a significant portion of trajectories in GPS data might not be annotated by a transport mode and the acquisition of labeled data is a more expensive and labor-intensive task in comparison with collecting unlabeled data. Thus, utilizing the unlabeled GPS trajectory (i.e., the GPS trajectories that have not been annotated by a transport mode) is a cost-effective approach for improving the prediction quality of the travel mode detection model. Therefore, the unlabeled GPS data are also leveraged by developing a novel deep-learning architecture that is capable of extracting information from both labeled and unlabeled data. The experimental results demonstrate the superiority of the proposed models over the state-of-the-art methods in literature with respect to several performance metrics.

Informações desagregadas de demanda por transportes são recursos essenciais ao correto planejamento urbano, especialmente no que se refere ao transporte público. Contudo, o acesso a estes dados é limitado, devido ao alto custo para coleta de pesquisas domiciliares e à confidencialidade de informações individuais. A presente tese de doutorado aborda esta problemática ao propor dois métodos heurísticos de desagregação de dados, através de simulação geoestatística. Propõe-se empregar, como um input aos procedimentos, informações com alta disponibilidade, como, por exemplo, os microdados, coletados pelo censo demográfico. A diferença principal entre os métodos é que o primeiro não necessita de valores de dados provenientes de Pesquisa Origem/Destino do município de São Paulo, área de estudo deste trabalho. Ambas as abordagens, que podem ser aplicadas a outros diferentes estudos de caso, compreendem um procedimento alternativo para deconvolução de semivariogramas, Simulação Sequencial Gaussiana e validação, considerando malhas regulares de diferentes suportes. Os mapas e métricas estatísticas gerados comprovam que é possível desagregar dados, associados a Áreas de Ponderação de Setores Censitários (Método Proposto 1 – MP1) e a Zonas de Tráfego (Método Proposto 2 – MP2), através dos procedimentos aplicados. Além disso, este trabalho apresenta contribuições metodológicas ao viabilizar: a geração de diversos cenários que reproduzam o comportamento espacial da variável; e o estudo da incerteza associada às simulações. / Disaggregated data for travel demand are essential resources towards good urban planning, especially with regard to public transportation. However, the access to such data is limited due to high costs of collecting household data and due to individual information confidentiality. The present PhD dissertation addresses this issue by introducing two heuristic methods to disaggregate data using geostatistical simulation. It is proposed to employ, as input to the procedures, information with high availability, such as census microdata. The main difference between both methods rely on the fact that the first does not require data values of any Origin/Destination Survey of the São Paulo city, study area of this research. Both approaches, which can be applied to other different study cases, comprise an alternative procedure for semivariogram deconvolution, Sequential Gaussian Simulation and validation, using regular grids of various spatial scales. The resulting maps and statistical metrics corroborate that is possible to disaggregate data associated with a set of Census Tracts (Proposed Method 1 – MP1) and Traffic Analysis Zones (Proposed Method 2 – MP2). Besides, this dissertation presents relevant contributions as it enables: creating different scenarios to reproduce the spatial behavior of the study variable; and assessing the associated uncertainty.

The purpose of this thesis is twofold: Firstly, it explores the reasons parents state for choosing the car to take their children to school; Secondly, it investigates how the characteristics of the journey relate to children’s wellbeing, mood, and cognitive performance. This thesis consists of three papers (Papers I, II, and III). Participating in Paper I were 245 parents of schoolchildren aged between 10 and 15 in Värmland County, Sweden. These parents answered a questionnaire wherein they stated to what degree certain statements correlated with their decision to choose the car. In Paper II, 237 children in grade 4 (aged 10-11), in the City of Staffanstorp, Sweden, recorded all their journeys in a diary over one school week, also reporting on their travel mode, current mood while travelling, activities on arrival, and experiences vis-à-vis those activities. Participating in Paper III was a sample of 345 children aged between 10 and 15 attending five public schools in Värmland County, Sweden. These children rated their current mood, filled out the Satisfaction with Travel Scale (capturing the travel experience), reported details about their journeys, and took a word fluency test. Parents’ wish to accompany their children to school, and the convenience of the car, both impact upon the travel mode decision. In addition, parents also seem to choose the car regardless of the distance between home and school. The findings further reveal that the mood children are in varies with how they travel and where they go, and that there is a difference between boys’ and girls’ experiences. Children who travel by car experience the lowest degree of quality and activation, something which is maintained throughout the school day (especially for girls). Social activities during travel bring a higher degree of quality and excitement, while solitary activities bring more stress. The findings further show that using a smartphone, or doing a combination of activities during the journey, results in better cognitive performance. Thus, it is concluded that the mode choice that parents make for their children correlates with those children’s mood and experience. Specifically, where and how children travel, what they do when they travel, and how long they travel for affect their experiences, mood, and/or cognitive performance. / The aim of this thesis is twofold. Firstly, it explores parents’ stated reasons for choosing the car for their children’s school journeys. Secondly, it investigates the relationship between the characteristics of a journey (i.e. travel mode, travel time, and activities conducted while travelling) and children’s wellbeing (through domain-specific satisfaction), current mood, and cognitive performance. The overall findings show that parents value the car both for its convenience and for the possibility of accompanying their children. Parents also use the car regardless of the distance between home and school. Travel affects children in various ways; for instance, doing certain activities while traveling can help boost cognitive performance and make children feel happy and excited. Notably, being passive during the journey makes children feel stressed and those who travel to school by car are the most tired during the school day. This implies that parents’ travel mode choice affects children’s wellbeing and cognitive performance. These insights are important when it comes to addressing current challenges relating to children’s day-to-day travel: How they experience their day-to-day travel may contribute toward how children travel in the future. / Den här avhandlingen har två delsyften. Först undersöks vilka skäl föräldrar anger för varför deväljer att skjutsa sina barn till skolan med bil. Ett andra syfte är att undersöka hur detta val påverkarbarns mentala hälsa via självskattad upplevelse av skolresan och hur de känner sig vid ankomst(humör). Ytterligare ett syfte är att undersöka hur upplevelsen av skolresan påverkar hur barnenpresterar när de kommer till skolan. Avhandlingen innehåller tre artiklar. I Artikel I deltog 245föräldrar till barn i årskurs 4, 6 och 8 i värmländska skolor. Föräldrarna angav i vilken utsträckningolika skäl påverkar deras val att skjutsa barnen till skolan med bil. I artikel II deltog 237 barn (varav101 flickor) från årskurs 4 i Staffanstorp, Skåne. Barnen förde resdagbok över alla resor de gjordeunder en vecka. I dagboken beskrev de vart de reste, vilka färdmedel de använt, deras humör underresan (som skattades som ledsen-glad och trött-pigg), vilka aktiviteter de ägnat sig åt vidslutdestinationen samt deras upplevelser av dessa aktiviteter. I Artikel III deltog 345 barn frånårskurs 4, 6 och 8 i Värmland. Istället för resdagbok skattade barnen sitt humör, hur nöjda de varmed resan genom att fylla i Satisfaction with Travel Scale adapted for Children (STS-C), resedetaljersamt gjorde ett ordflödestest direkt vid ankomst i skolan. Resultaten visar bland annat att föräldrars önskan att spendera tid med sina barn och praktiskaaspekter med bil ligger till grund för valet av bil. Huruvida det är ett långt eller kort avstånd tillskolan påverkar inte valet att använda bil. Barns humör varierar beroende på hur de reser(färdmedel) och vart de reser (destination). En skillnad observerades också mellan flickor ochpojkar och mellan olika årskurser där t.ex. fickor påverkades mer negativt av att resa med bil änpojkar. Barn som reser med bil till skolan är minst nöjda (upplevde en lägre grad av kvalitet) ochpå sämre humör (är känslomässigt mindre aktiva) vilket också håller i sig under skoldagen. Att ägnasig åt sociala aktiviteter (konversera med vänner och familj) under resan bidrar till en högre upplevdkvalitet och mer upprymdhet medan barn som ägnat sig åt aktiviteter utan sällskap upplever enhögre grad av stress. Resultaten visar också att barn som använder sin smartphone eller kombinerarolika aktiviteter under resan presterar bättre på kognitivt test.

Den här uppsatsen diskuterar hållbart resande, ett vanligt förekommande begrepp i och med det högaktuella begreppet hållbar utveckling. Hållbart resande undersöks i två mindre kommuner i Östergötland för att undersöka vilka uppfattningar och förutsättningar som medborgare och tjänstemän har. Uppsatsen studerar även vilka faktorer som påverkar vid val av färdmedel. Uppsatsen inkluderar intervjuer tillsammans med tjänstemän och medborgare i kommunerna Boxholm och Ödeshög. För att analysera det insamlade materialet tillämpas teorin social praktik, där begreppen kompetens, material och mening står i fokus. Resultatet visar på en gemensam syn gällande avsaknaden av tillgänglighet i kommunerna, framför allt till kollektivtrafik.  Det finns även en förändringsvilja i handlingsmönstret hos medborgarna till att resa mer hållbart men då kompetens och material saknas är det inte möjligt idag. Från kommunens sida finns det också en pågående förändringsvilja med visioner och ambitioner för att erbjuda medborgarna hållbara resalternativ. / This essay discusses sustainable travel which is a common concept in connection with sustainable development. Two small municipalities have been studied in Östergötland, Sweden to assess what individuals and planners think about sustainable travel in their communities. The method used in this essay was to interview with citizens and planners in the municipalities Ödeshög and Boxholm. To analyse the data collection, we apply the theory social practice which focuses on the three elements: materials, competences, meanings. The results show a lack of accessibility in the municipalities, especially in public transport. Furthermore, the result shows that the citizens have a will towards changing their behaviour to transport in a more sustainable way. From the citizens perspectives there was a lack of competences and materials which prevented them from traveling in a more sustainable way. We also saw a will from the planners to change behaviour in their ambitions towards more sustainable travel options.

The rapid growth of population and the permanent increase in the number of vehicles engender several issues in transportation systems, which in turn call for an intelligent and cost-effective approach to resolve the problems in an efficient manner. A cost-effective approach for improving and optimizing transportation-related problems is to unlock hidden knowledge in ever-increasing spatiotemporal and crowdsourced information collected from various sources such as mobile phone sensors (e.g., GPS sensors) and social media networks (e.g., Twitter). Data mining and machine learning techniques are the major tools for analyzing the collected data and extracting useful knowledge on traffic conditions and mobility behaviors. Deep learning is an advanced branch of machine learning that has enjoyed a lot of success in computer vision and natural language processing fields in recent years. However, deep learning techniques have been applied to only a small number of transportation applications such as traffic flow and speed prediction. Accordingly, my main objective in this dissertation is to develop state-of-the-art deep learning architectures for resolving the transport-related applications that have not been treated by deep learning architectures in much detail, including (1) travel mode detection, (2) vehicle classification, and (3) traffic information system. To this end, an efficient representation for spatiotemporal and crowdsourced data (e.g., GPS trajectories) is also required to be designed in such a way that not only be adaptable with deep learning architectures but also contains efficient information for solving the task-at-hand. Furthermore, since the good performance of a deep learning algorithm is primarily contingent on access to a large volume of training samples, efficient data collection and labeling strategies are developed for different data types and applications. Finally, the performance of the proposed representations and models are evaluated by comparing to several state-of-the-art techniques in literature. The experimental results clearly and consistently demonstrate the superiority of the proposed deep-learning based framework for each application. / PHD / The rapid growth of population and the permanent increase in the number of vehicles engender several issues in transportation systems, which in turn call for an intelligent and cost-effective approach to resolve the problems in an efficient manner. Furthermore, the recent advances in positioning tools (e.g., GPS sensors) and ever-popularity of social media networks have enabled generation of massive spatiotemporal and crowdsourced data. This dissertation aims to leverage the advances in artificial intelligence so as to unlock the rick knowledge in the recorded data and in turn, optimizing the transportation systems in a cost-effective way. In particular, this dissertation seeks for proposing end-to-end frameworks based on deep learning models, as an advanced branch of artificial intelligence, as well as spatiotemporal and crowdsourced datasets (e.g., GPS trajectory and social media) for improving three transportation problems. (1) Travel Mode Detection, which is defined as identifying users’ transportation mode(s) (e.g., walk, bike, bus, car, and train) when traveling around the traffic network. (2) Vehicle Classification, which is defined as identifying the vehicle’s type (e.g., passenger car and truck) while moving in a traffic network. (3) traffic information system based on social media networks, which is defined as detecting traffic events (e.g., crash) and capturing traffic information (e.g., traffic congestion) on a real-time basis from users’ tweets. The experimental results clearly and consistently demonstrate the superiority of the proposed deep-learning based framework for each application.

With a foundation in social sustainability, and with the theoretical framework of transport justice and transport poverty, the aim of this thesis is to create a profile picture of the future potential travelers on the North Bothnia Line in Sävar, Robertsfors and Bureå. Both a quantitative and a qualitative analysis are performed. The quantitative analysis describes the population structures concerning age, gender, educational level, employment, household type, income and cars per 1000 inhabitants. The qualitative analysis consists of an interview study, conducted in Robertsfors, with 47 informants. The interview answers are analyzed through content analysis, and presented in personas for each age group. The three areas differ in population structure, which could have different implications on the future travel. In the planning for a socially sustainable travel with the North Bothnia Line, focus needs to be directed to the young travelers, in particular the high school youths. Families with children are facing constraints when trying to manage sustainable travel, therefore, how to create a socially sustainable travel for this group is important to consider in the planning. Young adults, as well as individuals that are unemployed are vulnerable groups, important to consider. The senior travelers have another travel behavior, compared to the population of working age, but still have their needs connected to travel. The informants are positive about the North Bothnia Line, positive about train as travel mode, and intend to use the future train. They expect that the train will lead to easier and faster transportation and work commuting, increased access to schools and jobs, population growth, open up for more opportunities, and that people do not have to own a car. The greatest needs are; a good timetable, with many departures, matching the work schedule. The train has to be on time, and the ticket price not too high. Both the train and the station have to be easily accessible, supplied with good car parking facilities with engine heaters, and the train has to go fast. Both the train and the station have to be clean and controlled, and there has to be clear, and digital information. / Norrbotniabanans noder 2