Despite the availability of mobile positioning technologies and scientists' interests in tracking, modelling and predicting the movements of individuals and populations, these technologies are seldom efficiently used. The continuous changes in mobile positioning and other sensor technologies overburden scientists who are interested in data collection with the task of developing, implementing and testing tracking algorithms and their efficiency in terms of battery consumption. To this extent, this article proposes an adaptive, battery conscious tracking algorithm that collects trajectory data fused with accelerometer data and presents Mobility Collector, which is a prototype platform that, using the tracking algorithm, can produce highly configurable, off-the-shelf, multi-user tracking systems suitable for research purposes. The applicability of the tracking system is tested within the transport science domain by collecting labelled movement traces and related motion data, i.e. accelerometer data and derived information (number of steps and other useful movement features based on temporal aggregates of the raw readings) to develop and evaluate a method that automatically classifies the transportation mode of users with a 90.8% prediction accuracy.

The needs for cheaper and less intrusive ways to collect activity-travel diaries led scientist to pursue new technologies, e.g., positioning technologies like GPS. While a fully, reliable and widely accepted automatic activity-travel diary collection system is yet to be developed, scientists have presented systems that automate parts of an activity-travel diary collection. In the advent of automated systems, it is important to discuss how to analyse the potential of such systems and how to compare different activity-travel diary collection systems. To achieve this objective, this paper introduces a parallel survey design and a comparison framework for collection systems. The framework can be used as a development tool to optimise system design, to report and monitor progress of different system designs, to objectively weigh benefits in decision making, and to automate systematic analysis. In particular, the framework can be used as a comparison tool to reveal the qualitative difference in the data gathered using different collection systems. To achieve this, the framework defines: 1) a number of activity-travel diary measurement entities (trips and triplegs), entity attributes (e.g., trip purpose, origin / destination, etc.), 2) similarity functions between instances of the same entities, and 3) spatial and temporal quality indices to establish a notion of ground truth. The utility of the proposed framework is demonstrated by analysing the results of a trial survey where data is collected via two activity-travel collection systems: a web-based system (PP) and a smartphone-app-based system (MEILI). PP was collected for one day period and MEILI was used for one week period (with one day overlapping). The results show that half of the trips are captured by both systems, while each system roughly captures the same number of trips as the other. The strengths and weaknesses of MEILI are analysed using the framework on the entire week dataset.

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.

This paper describes the lessons learned from the trial of MEILI, a smartphone based semi-automatic activity-travel diarycollection system, in Stockholm city, Sweden. The design of the system, together with state-of-the-art improvements of different elements of the tool, are presented before and after the trial to better illustrate the improvements based on the lessons learned. During the trial, both MEILI and a paper-based diary captured about 65% of the total number of detected trips, but only about half of the trips were captured by both systems. The unmatchable trips are partly due to different activity declaration and system specific destination specification, i.e., a verbose specification of address in the paper-and-pencil survey and a point of interest selection / declaration in MEILI. In terms of subjective appreciation, the user experiences vary greatly between the different participants in the pilot. Presumably, this is mainly due to different level of IT-knowledge of the respondents, but also due to the occasionally non-uniform behaviour of the location collection service caused by hardware and / or software difficulties. Based on these inputs, further web and support system improvements have been implemented for future trials.