The overwhelming increase of parcel transports has prompted the need for effective and scalable intelligent logistics systems. In parallel, with the advent of Industry 4.0, a tight integration of Internet of Things technologies and Big Data analytics solution has become necessary to effectively manage industrial processes and to early predict product faults or service disruptions. In the context of good transports, the development of smart monitoring tools is particularly useful for couriers to ensure effective and efficient parcel deliveries. However, the existing predictive maintenance frameworks are not tailored to parcel delivery services. We present REDTag Service, an integrated framework to track and monitor the shipped packages. It relies on a network of IoT-enabled devices, called REDTags, allowing courier employees to easily collect the status of the package at each delivery step. The framework provides back-end functionalities for smart data transmission, management, storage, and analytics. A machine-learning process is included to promptly analyze the features describing event-related data to predict potential breaks of the goods in the packages. The framework provides also a dynamic view on the integrated data tailored to the different stakeholders, as well as on the prediction outcomes, enabling immediate feedback and model improvements. We analyze a real-world dataset including event-related data about parcel transports. To validate the hypothesis that the acquired data contains information relevant to predict the package status (i.e., broken or safe), we empirically analyze the performance of different, scalable classifiers. The experimental results confirm, in good approximation, the predictive power of the models extracted from the event-related features. To the best of the authors' knowledge, this work is the first attempt to address predictive maintenance in smart good transport logistics to predict package breaks from real-world data.

Digital technologies allow teachers and students to experience new pedagogical approaches leveraging on interactivity and collaboration. Among the available techniques, digital storytelling (DST) has been usually regarded as an activity that can both enrich the teaching practices and foster students’ active behaviour. This paper aims at analysing to what extent a DST platform proposing the collaborative writing of a fictional story and leveraging on an active learning technique such as role-play can affect a variety of dimensions, namely students’ performance, commitment, creativity and social skills. Combining the analysis of the data-log automatically collected by the system with the evaluations given by teachers before and after the activity, this article shows that the use of a DST tool in the teaching practice can have positive effects on students, including the ones that usually manifest moderate scores for the previously mentioned dimensions. Additionally, semi-structured interviews and direct observations provide an insight on how the benefits stemming from the use of a DST tool in the classroom can especially lie on the collaborative process that is activated.

In recent years there has been a growing interest in the use of multimedia mobile guides in museum environments. Mobile devices have the capabilities to detect the user context and to provide pieces of information suitable to help visitors discover and follow the logical and emotional connections that develop during the visit. In this scenario, location based services (LBS) currently represent an asset, and the choice of the technology to determine users’ position, combined with the definition of methods that can effectively convey information, become key issues in the design process. In this work, we present Museum Assistant (MusA), a general framework for the development of multimedia interactive guides for mobile devices. Its main feature is a vision-based indoor positioning system that allows the provision of several LBS, from way-finding to the contextualized communication of cultural contents, aimed at providing a meaningful exploration of exhibits according to visitors’ personal interest and curiosity. Starting from the thorough description of the system architecture, the article presents the implementation of two mobile guides, developed to respectively address adults and children, and discusses the evaluation of the user experience and the visitors’ appreciation of these applications.

The pervasive and increasing deployment of smart meters allows collecting a huge amount of fine-grained energy data in different urban scenarios. The analysis of such data is challenging and opening up a variety of interesting and new research issues across energy and computer science research areas. The key role of computer scientists is providing energy researchers and practitioners with cutting-edge and scalable analytics engines to effectively support their daily research activities, hence fostering and leveraging data-driven approaches. This paper presents SPEC, a scalable and distributed engine to predict building-specific power consumption. SPEC addresses the full analytic stack and exploits a data stream approach over sliding time windows to train a prediction model tailored to each building. The model allows us to predict the upcoming power consumption at a time instant in the near future. SPEC integrates different machine learning approaches, specifically ridge regression, artificial neural networks, and random forest regression, to predict fine-grained values of power consumption, and a classification model, the random forest classifier, to forecast a coarse consumption level. SPEC exploits state-of-the-art distributed computing frameworks to address the big data challenges in harvesting energy data: the current implementation runs on Apache Spark, the most widespread high-performance data-processing platform, and can natively scale to huge datasets. As a case study, SPEC has been tested on real data of an heating distribution network and power consumption data collected in a major Italian city. Experimental results demonstrate the effectiveness of SPEC to forecast both fine-grained values and coarse levels of power consumption of buildings.

The use of theory-based knowledge in machine learning models has a major impact on many engineering and physics problems. The growth of deep learning algorithms is closely related to an increasing demand for data that is not acceptable or available in many use cases. In this context, the incorporation of physical knowledge or a priori constraints has proven beneficial in many tasks. On the other hand, this collection of approaches is context-specific, and it is difficult to generalize them to new problems. In this paper, we experimentally compare some of the most commonly used theory-injection strategies to perform a systematic analysis of their advantages. Selected state-of-the-art algorithms were reproduced for different use cases to evaluate their effectiveness with smaller training data and to discuss how the underlined strategies can fit into new application contexts.

The availability of infotainment contents to be accessed while driving constitutes an added value to both drivers and passengers, improving their travel experience. These contents can be already on-board, diffused through broadcast networks (e.g., FM radio) or delivered on demand by servers as data streams. Vehicular ad-hoc networks (VANET) allow envisaging a new way to access contents based on epidemic data dissemination, tearing down the costs for both the user and the content publisher, and increasing system scalability. In this paper, we present the design and the evaluation of a collaborative system for content diffusion and retrieval among traveling vehicles. This system relies on multicast epidemic dissemination of messages and exploits vehicles mobility and their local storage capabilities. In order to assess its performance, several simulations have been carried out, using real-world maps and realistic mobility models, and varying intrinsic system parameters. Experimental results suggest that the system is feasible, produces reliable results, almost independent of the mobility scenario, and can be used as a peer-to-peer download accelerator for improving client-server access.