Nowadays, large amounts of tracking data are generated via GPS-enabled devices and other advanced tracking technologies. These constitute a rich source for inferring the structure of transportation networks. In this work, we present a novel methodology for revealing a road network map from vehicle trajectories. Specifically, we propose an enhanced and robust map construction algorithm that is based on segmenting the original tracking data according to different types of movement and then constructing the topology of the road network hierarchically. The segmentation produces separate road network layers, which are then fused into a single network. This provides a more efficient way to addresses the challenges imposed by noisy and low sampling rate trajectories. It also allows for a mechanism to accommodate automatic map maintenance on updates. Thus, the proposed approach overcomes the limitations of existing methods and introduces a map construction algorithm that is robust against heterogeneous and sparse data and capable to incorporate changes and improvements. An experimental evaluation extensively assesses the quality of the proposed methodology by constructing large parts of the road networks of four major cities, namely Athens, Berlin, Vienna, and Chicago, using as input GPS tracking data of utility vehicles and taxi fleets. Our results show significant improvements concerning the spatial accuracy and the quality of the constructed road network over the current state of the art.

The conceptual design of the Extract -- Transform -- Load (ETL) processes is a crucial, burdensome, and challenging procedure that takes places at the early phases of a Data Warehouse project. Several models have been proposed for the conceptual design and representation of ETL processes, but all share two inconveniences: they require intensive human effort from the designers to create them, as well as technical knowledge from the business people to understand them. In a previous work, we have relaxed the former difficulty by working on the automation of the conceptual design leveraging Semantic Web technology. In this paper, we built upon our previous results and we tackle the second issue by investigating the application of natural language generation techniques to the ETL environment. In particular, we provide a method for the representation of a conceptual ETL design as a narrative, which is the most natural means of communication and does not require knowledge of any specific model. We discuss how linguistic techniques can be used for the establishment of a common application vocabulary. Finally, we present a flexible and customizable template-based mechanism for generating natural language representations for the ETL process requirements and operations.

Heterogeneous information networks (HINs) represent different types of entities and relationships between them. Exploring and mining HINs relies on metapath queries that identify pairs of entities connected by relationships of diverse semantics. While the real-time evaluation of metapath query workloads on large, web-scale HINs is highly demanding in computational cost, current approaches do not exploit interrelationships among the queries. In this paper, we present Atrapos, a new approach for the real-time evaluation of metapath query workloads that leverages a combination of efficient sparse matrix multiplication and intermediate result caching. Atrapos selects intermediate results to cache and reuse by detecting frequent sub-metapaths among workload queries in real time, using a tailor-made data structure, the Overlap Tree, and an associated caching policy. Our experimental study on real data shows that Atrapos accelerates exploratory data analysis and mining on HINs, outperforming off-the-shelf caching approaches and state-of-the-art research prototypes in all examined scenarios.

The analysis and modeling of parameters influencing parents’ decisions regarding school travel mode choice have perennially been a subject of interest. Concurrently, the evolution of artificial intelligence (AI) can effectively contribute to generating reliable predictions across various topics. This paper begins with a comprehensive literature review on classical models for predicting school travel mode choice, as well as the diverse applications of AI methods, with a particular focus on transportation. Building upon a published questionnaire survey in the city of Thessaloniki (Greece) and the conducted analysis and exploration of factors shaping the parental framework for school travel mode choice, this study takes a step further: the authors evaluate and propose a machine learning (ML) classification model, utilizing the pre-recorded parental perceptions, beliefs, and attitudes as inputs to predict the choice between motorized or non-motorized school travel. The impact of potential changes in the input values of the ML classification model is also assessed. Therefore, the enhancement of the sense of safety and security in the school route, the adoption of a more active lifestyle by parents, the widening of acceptance of public transportation, etc., are simulated and the impact on the parental choice ratio between non-motorized and motorized school commuting is quantified.