<p> Inefficient port drayage causes high costs in addition to congestion and pollution. To identify the causes of inefficiency in port drayage, we developed a mobile application, which utilizes a Global Point System (GPS), Bluetooth and some driver inputs to track the manner in which the drays move, such as picking up a loaded container or delivering an empty one. A web application is used to receive data from the mobile devices, interprets the data to determine whether or not the data points are in or out of range of port terminals, stores the data in a database and provides visualization of point locations on Google Maps. The collected data are then analyzed in order to pinpoint any trouble areas, find the cause, and recommend solutions where appropriate. In this work, we describe the software development process in both the mobile and the web applications and report results of our analysis based on the collected data.</p>

<p> Large physical systems are increasingly prevalent, and designing estimation strategies for them has become both a practical necessity and a complicated problem. Their sensing infrastructure is usually ad-hoc, and the estimate of interest is often a complex function of the data. At the same time, computing power is rapidly becoming a commodity. We show with the study of two estimation tasks in urban transportation how the proper design of algorithms can lead to significant gains in scalability compared to existing solutions. </p><p> A common problem in trip planning is to make a given deadline such as arriving at the airport within an hour. Existing routing services optimize for the expected time of arrival, but do not provide the most <i>reliable </i> route, which accounts for the variability in travel times. Providing statistical information is even harder for trips in cities which undergo a lot of variability. This thesis aims at building scalable algorithms for inferring statistical distributions of travel time over very large road networks, using GPS points from vehicles in real-time. We consider two complementary algorithms that differ in the characteristics of the GPS data input, and in the complexity of the model: a simpler streaming Expectation-Maximization algorithm that leverages very large volumes of extremely noisy data, and a novel Markov Model-Gaussian Markov Random Field that extracts global statistical correlations from high-frequency, privacy-preserving trajectories. </p><p> These two algorithms have been implemented and deployed in a pipeline that takes streams of GPS data as input, and produces distributions of travel times accessible as output. This pipeline is shown to scale on a large cluster of machines and can process tens of millions of GPS observations from an area that comprises hundreds of thousands of road segments. This is to our knowledge the first research framework that considers in an integrated fashion the problem of statistical estimation of traffic at a very large scale from streams of GPS data.</p>

<p> This work introduces signature-based data mining of pavement distress data. The goal is to understand the factors that influence pavement distress. The presented approach maintains multiple types of flexible pavement distress scores throughout the analysis and considers them as signatures. The signatures are used to establish the relationship between distress score increases and overweight truck characteristics. Hierarchical clustering of pavement distress signatures provides insights into similarities among road segments. The use of signatures, rather than composite distress scores, is consistent with a data mining approach to the pavement distress problem. One set of experiments showed a relationship between the discovered signature groups and a difference between overweight truck traffic. Group validation has been implemented with Fisher's exact test. Future work related to algorithm improvements have been identified and considered.</p>