The amount of useful information that can be extracted from travel diaries is matched by the difficulty of obtaining travel diaries in a modern era where the response rate to traditional travel diary collection methods has seen a decrease in most countries. Prompted by this, a body of research has been dedicated to study how travel diaries can be collected via new methods, namely location enabled devices such as smartphones, that have a higher penetration rate (in terms of device ownerships and user attachment) and are both easier and cheaper to manage compared to traditional data collection method, e.g. paper-and-pencil, phone, or web-based questionnaires. This paper offers an overview of the current state of travel diary collection, a potential future state and a practical checklist for travel diary collection case studies. A thorough discussion on different pros and cons of travel diary collection methods and efforts needed for the convergence of methods to collect travel diaries for all demographics are provided. The practical checklist to aid researchers to organise case studies is based on the authors' experience and it is meant to raise awareness of difficulties that can be encountered while collecting travel surveys with automated and semi-automated systems, and how to overcome them.

The amount of useful information that can be extracted from travel diaries is matched by the difficulty of obtaining travel diariesin a modern era where the response rate to traditional travel diary collection methods has seen a decrease in most countries.Prompted by this, a body of research has been dedicated to study how travel diaries can be collected via new methods, namelylocation enabled devices such as smartphones, that have a higher penetration rate (in terms of device ownerships and userattachment) and are both easier and cheaper to manage compared to traditional data collection method, e.g. paper-and-pencil,phone, or web-based questionnaires. This paper offers an overview of the current state of travel diary collection, a potentialfuture state and a practical checklist for travel diary collection case studies. A thorough discussion on different pros and cons oftravel diary collection methods and efforts needed for the convergence of methods to collect travel diaries for all demographicsare provided. The practical checklist to aid researchers to organise case studies is based on the authors’ experience and it is meantto raise awareness of difficulties that can be encountered while collecting travel surveys with automated and semi-automatedsystems, and how to overcome them.

The increased interest in the automation of travel diary collection, together with the ease of access to new artificial intelligence methods led scientists to explore the prerequisites to the automatic generation of travel diaries. One of the most promising methods for this automation relies on collecting GPS traces of multiple users over a period of time, followed by asking the users to annotate their collected data by specifying the base entities for a travel diary, i.e., trips and triplegs. This led scientist on one of two paths: either develop an in-house solution for data collection and annotation, which is usually an undocumented prototype implementation limited to few users, or contract an external provider for the development, which results in additional costs. This paper provides a third path: an open-source highly modular system for the collection and annotation of travel diaries of multiple users, named MEILI. The paper discusses the architecture of MEILI with an emphasis on the data model, which allows scientists to implement and evaluate their methods of choice for the detection of the following entities: trip start/end, trip destination, trip purpose, tripleg start/end, and tripleg mode. Furthermore, the open source nature of MEILI allows scientists to modify the MEILI solution in compliance with their legal and ethical specifications. MEILI was successfully trialed in multiple case studies in Stockholm and Gothenburg, Sweden between 2014 and 2017.

Researchers' pursuit for the better understanding of the dynamics of travel and travel behaviour led to a constant advance in data collection methods. One such data collection method, the travel diary, is a common proxy for travel behaviour and its use has a long history in the transportation research community. These diaries summarize information about when, where, why and how people travel by collecting information about trips, and their destination and purpose, and triplegs, and their travel mode. Whereas collecting travel diaries for short periods of time of one day was commonplace due to the high cost of conducting travel surveys, visionary researchers have tried to better understand whether travel and travel behaviour is stable or if, and how, it changes over time by collecting multiple day travel diaries from the same users. While the initial results of these researchers were promising, the high cost of travel surveys and the fill in burden of the survey participants limited the research contribution to the scientific community. Before identifying travel diary collection methods that can be used for long periods of time, an interesting phenomenon started to occur: a steady decrease in the response rate to travel diaries. This meant that the pursuit of understanding the evolution of travel behaviour over time stayed in the scientific community and did not evolve to be used by policy makers and industrial partners.

However, with the development of technologies that can collect trajectory data that describe how people travel, researchers have investigated ways to complement and replace the traditional travel diary collection methods. While the initial efforts were only partially successful because scientists had to convince people to carry devices that they were not used to, the wide adoption of smartphones opened up the possibility of wide-scale trajectory-based travel diary collection and, potentially, for long periods of time. This thesis contributes among the same direction by proposing MEILI, a travel diary collection system, and describes the trajectory collection outlet (Paper I) and the system architecture (Paper II). Furthermore, the process of transforming a trajectory into travel diaries by using machine learning is thoroughly documented (Papers III and IV), together with a robust and objective methodology for comparing different travel diary collection system (Papers V and VI). MEILI is presented in the context of current state of the art (Paper VIII) and the researchers' common interest (Paper IX), and has been used in various case studies for collecting travel diaries (Papers I, V, VI, VII). Finally, since MEILI has been successfully used for collecting travel diaries for a period of one week, a new method for understanding the stability and variability of travel patterns over time has been proposed (Paper X).

This workshop examined the state of the art of existing travel diary collection systems that make use of GPS data in relationshipto the needs of the practitioners that collect and analyze travel diaries. While the new data collection methods are a promisingalternative that can collect both data on previously ignored demographic segments as well as short trips that are usually forgottenby respondents, they do not solve all the issues the traditional methods are prone to, and also introduce new issues on their own.The workshop participants have identified, discussed and summarized the most pressing concerns regarding the use of new traveldiary collection systems based on smartphones and GPS receivers.

The growing need of acquiring data that is useful for travel behaviour analysis led scientists topursue new ways of obtaining travel diaries from large groups of people. The most promising al-ternative to traditional (declarative) travel diary collection methods are those that rely on collectingtrajectories from individuals and then extract travel diary semantics from the trajectories. However,most studies report on routines specific to the post-processing of data, and seldom focus on datacollection. Even the few studies that deal explicitly with data collection describe the final state ofthe collection system, but do not go at the lengths that are required to describe the decision thatwere taken to bring the system to its current state. This leads to a considerable amount of work thatis needed for designing collection systems that are often undocumented, which impedes the reuseof the aforementioned systems. In light of the aforementioned problems, this paper presents a series of three case studies behind the continuous development of MEILI, a travel diary collection,annotation and automation system, in an effort to: 1) illustrate the utility of the developed systemto collect travel diaries, 2) identify how MEILI and other semi-automatic travel diaries collectionsystems can be improved, and 3) propose MEILI as an open source system that has the potentialof being improved into a widely available semi-automated travel diary collection system.

The wide adoption of location-enabled devices, together with the acceptance of services that leverage (personal) data as payment, allows scientists to push through some of the previous barriers imposed by data insufficiency, ethics and privacy skepticism. The research problems whose study require hard-to-obtain data (e.g. transportation mode detection, service contextualisation, etc.) have now become more accessible to scientists because of the availability of data collecting outlets. One such problem is the detection of a user's transportation mode. Different fields have approached the problem of transportation mode detection with different aims: Location-Based Services (LBS) is a field that focuses on understanding the transportation mode in real-time, Transportation Science is a field that focuses on measuring the daily travel patterns of individuals or groups of individuals, and Human Geography is a field that focuses on enriching a trajectory by adding domain-specific semantics. While different fields providing solutions to the same problem could be viewed as a positive outcome, it is difficult to compare these solutions because the reported performance indicators depend on the type of approach and its aim (e.g. the real-time availability of LBS requires the performance to be computed on each classified location). The contributions of this paper are three fold. First, the paper reviews the critical aspects desired by each research field when providing solutions to the transportation mode detection problem. Second, it proposes three dimensions that separate three branches of science based on their main interest. Finally, it identifies important gaps in research and future directions, that is, proposing: widely accepted error measures meaningful for all disciplines, methods robust to new data sets and a benchmark data set for performance validation.

The increase in population, accompanied by an increase in the availability of travel opportunities have kindled the interest in understanding how people make use of the space around them and their opportunities. Understanding the travel behaviour of individuals and groups is difficult because of two main factors: the travel behaviour's wide coverage, which encompasses different research areas, all of which model different aspects of travel behaviour, and the difficulty of obtaining travel diaries from large groups of respondents, which is imperative for analysing travel behaviour and patterns.

A travel diary allows an individual to describe how she performed her activities by specifying the destinations, purposes and travel modes occurring during a predefined period of time. Travel diaries are usually collected during a large-scale survey, but recent developments show that travel diaries have important drawbacks such as the collection bias and the decreasing response rate. This led to a surge of studies that try to complement or replace the traditional declaration-based travel diary collection with methods that extract travel diary specific information from trajectories and auxiliary datasets.

With the automation of travel diary generation in sight, this thesis presents a suitable method for collecting data for travel diary automation (Paper I), a framework to compare multiple travel diary collection systems (Paper II), a set of relevant metrics for measuring the performance of travel mode segmentation methods (Paper III), and applies these concepts during different case studies (Paper IV).

Rooted in the philosophy of point- and segment-based approaches for transportation mode segmentation of trajectories, the measures that researchers have adopted to evaluate the quality of the results (1) are incomparable across approaches, hence slowing the progress in the field and (2) do not provide insight about the quality of the continuous transportation mode segmentation. To address these problems, this paper proposes new error measures that can be applied to measure how well a continuous transportation mode segmentation model performs. The error measures introduced are based on aligning multiple inferred continuous intervals to ground truth intervals, and measure the cardinality of the alignment and the spatial and temporal discrepancy between the corresponding aligned segments. The utility of this new way of computing errors is shown by evaluating the segmentation of three generic transportation mode segmentation approaches (implicit, explicit–holistic, and explicit–consensus-based transport mode segmentation), which can be implemented in a thick client architecture. Empirical evaluations on a large real-word data set reveal the superiority of explicit–consensus-based transport mode segmentation, which can be attributed to the explicit modeling of segments and transitions, which allows for a meaningful decomposition of the complex learning task.

Many modern mobile communication devices are equipped with a global positioning systems (GPS) receiver and a navigation tool. These devices are useful when a user seeks to reach a specified destination as soon as possible, but may not be so when he/she only needs to arrive at the destination in time and wants to focus on some activities on the way. To deal with this latter situation, a method and device called “Space Time Alarm” is presented for helping the user reach the destination by a specified deadline. It does so by continuously and efficiently computing how much more time the user may stay at his/her current location without failing to reach the destination by the deadline. Advantage of this approach is that it works completely in the background so that the user’s en route activities will not be interfered with.