Abstract: The wide propagation of devices, such as mobile phones, that include a global positioning system (GPS) sensor has popularised the storing of geographic information for different kind of activities, many of them recreational, such as sport. Extracting and learning knowledge from GPS data can provide useful geographic information that can be used for the design of novel applications. In this paper we address the problem of identifying the sport from a GPS track that is recorded during a sport session. For that purpose, we store 8500 GPS tracks from ten different kind of sports. We extract twelve features that are able to represent the activity that was recorded in a GPS track. From these features several models are induced by diverse machine learning classification techniques. We study the problem from two different perspectives: flat classification, i.e, models classify the track in one of the ten possible sport types; and hierarchical classification, i.e. given the high number of classes and the structure of the problem, we induce a hierarchy in the classes and we address the problem as a hierarchical classification problem. For this second framework, we analyse three different approaches. According to our results, multiclassifier systems based on decision trees obtain the better performance in both scenarios.

Abstract: People living in urban areas are exposed to outdoor air pollution. Air contamination is linked to numerous premature and pre-native deaths each year. Urban air pollution is estimated to cost approximately 2% of GDP in developed countries and 5% in developing countries. Some works reckon that vehicle emissions produce over 90% of air pollution in cities in these countries. This paper presents some results in predicting and interpolating real-time urban air pollution forecasts for the city of Valencia in Spain. Although many cities provide air quality data, in many cases, this information is presented with significant delays (three hours for the city of Valencia) and it is limited to the area where the measurement stations are located. We compare several regression models able to predict the levels of four different pollutants (NO, NO2, SO2, O3) in six different locations of the city. Wind strength and direction is a key feature in the propagation of pollutants around the city, in this sense we study different techniques to incorporate this factor in the regression models. Finally, we also analyse how to interpolate forecasts all around the city. Here, we propose an interpolation method that takes wind direction into account. We compare this proposal with respect to well-known interpolation methods. By using these contamination estimates, we are able to generate a real-time pollution map of the city of Valencia.

Abstract: Demand Response (DR) is a widely used technique to minimize the peak to average consumption ratio during high demand periods. We consider the DR problem of achieving a given curtailment target for a set of consumers equipped with a set of discrete curtailment strategies over a given duration. An effective DR scheduling algorithm should minimize the curtailment error - the difference between the targeted and achieved curtailment values - to minimize costs to the utility provider and maintain system reliability. The availability of smart meters with fine-grained customer control capability can be leveraged to offer customers a dynamic range of curtailment strategies that are feasible for small durations within the overall DR event. Both the availability and achievable curtailment values of these strategies can vary dynamically through the DR event and thus the problem of achieving a target curtailment over the entire DR interval can be modeled as a dynamic strategy selection problem over multiple discrete sub-intervals. We argue that DR curtailment error minimizing algorithms should not be oblivious to customer curtailment behavior during sub-intervals as (expensive) demand peaks can be concentrated in a few sub-intervals while consumption is heavily curtailed during others in order to achieve the given target, which makes such solutions expensive for the utility. Thus in this paper, we formally develop the notion of Sustainable DR (SDR) as a solution that attempts to distribute the curtailment evenly across sub-intervals in the DR event. We formulate the SDR problem as an Integer Linear Program and provide a very fast $\sqrt{2}$-factor approximation algorithm. We then propose a Polynomial Time Approximation Scheme (PTAS) for approximating the SDR curtailment error to within an arbitrarily small factor of the optimal. We then develop a novel ILP formulation that solves the SDR problem while explicitly accounting for customer strategy switching overhead as a constraint. We perform experiments using real data acquired from the University of Southern California’s smart grid and show that our sustainable DR model achieves results with a very low absolute error of 0.001-0.05 kWh range.

Abstract: Electric Vehicles (EVs) are set to play a crucial role in making transportation systems more sustainable. However, charging infrastructure needs to be built up before EV adoption can increase. A crucial factor that is ignored in most existing studies of optimal charging station (CS) deployment is the role played by the charging behaviour of drivers. In this study, through an agent-based traffic simulation, we analyse the impact of different driver charging behaviour under the assumption that CSs are placed at existing petrol stations and residential car park locations in Singapore. Three models are implemented: a simple model with a charging threshold and two more sophisticated models where the driver takes the current trip distance and existing CS locations into account. We analyse the performance of these three charging behaviours with respect to a number of different measures. Results suggest that charging behaviours do indeed have a significant impact on the simulation outcome. We also discover that the sensitivity of model parameters in each charging behaviour is an important factor to consider as variations in model parameter can lead to significant different results.

Abstract: We investigate techniques for earth dam and levee health monitoring and automatic detection of anomalous events in passive seismic data. We have developed a novel data-driven workflow that uses machine learning and geophysical data collected from sensors located on the surface of the levee to identify internal erosion events. In this paper, we describe our research experiments with binary and one-class Support Vector Machines (SVMs). We used experimental data from a laboratory earth embankment (80% normal and 20% anomalies) and extracted nine spectral features from decomposed segments of the time series data. The two-class SVM with 10-fold cross validation achieved over 97% accuracy. Experiments with the one-class SVM use the top two features selected by the ReliefF algorithm and our results show that we can successfully separate normal from anomalous data observations with over 83% accuracy.