Raffaele Ianniello

Crowdsensing in Urban Areas for City-Scale Mass Gathering Management: Geofencing and Activity Recognition

The widespread availability of smartphones today equipped with several physical and virtual sensors allows to directly collect various information about surrounding physical and logical context for different purposes that range from detecting users current physical activity and also user presence in a designated area, often referred to as geofencing, to determining current social pulse of individuals and entire communities. Mobile crowdsensing seems a promising solution for enabling the design/development and deployment of a wide range of advanced applications in various fields. In particular, public safety, transportation, and energy monitoring and management in urban environments can benefit from mobile crowdsensing in terms of advanced provisioned applications as well as savings of investments in the urban sensing infrastructure. However, enabling those advanced smart urban applications requires complex signal processing, machine learning, and resource management algorithms that are often beyond the skills of many mobile app developers. This paper describes the pivotal relevance of these facilities for mobile crowdsensing applications and presents our open-source solution, called Mobile Sensing Technology (MoST), for activity detection and geofencing, comparing it with the reference implementations provided by Google as part of the Google Play Services library. Experimental results within the testbed framework of a crowd-management application scenario validate MoST design guidelines and demonstrate the general-purpose, unintrusive, and power-efficient characteristics of MoST sensing capabilities.

ParticipAct: A Large-Scale Crowdsensing Platform

In recent years, the widespread availability of sensor-provided smartphones has enabled the possibility of harvesting large quantities of data in urban areas exploiting user devices, so enabling the so-called crowdsensing that allows to realize complex applications impossible without the involvement of the research community. While many efforts have been made to improve specific techniques - spanning from signal processing to the assignment of data collection campaigns to users, and to the entire data processing - to the best of our knowledge, there are no active experiments aimed to explore the challenging issues raised by the management of large-scale crowdsensing campaigns as real-world experiments. This paper presents the ParticipAct platform and its ParticipAct living lab, an ongoing experiment at the University of Bologna that involves 170 students for one year in several crowdsensing campaigns that can access passively smartphone sensors and also prompt for user active collaboration. In this paper, we describe the guidelines behind the design of ParticipAct, its features, its architecture, and report quantitative results that assess and confirm the feasibility, obtained via intelligent coordination and management of crowdsensing campaigns.

Scalable and Cost-Effective Assignment of Mobile Crowdsensing Tasks Based on Profiling Trends and Prediction: The ParticipAct Living Lab Experience.

Nowadays, sensor-rich smartphones potentially enable the harvesting of huge amounts of valuable sensing data in urban environments, by opportunistically involving citizens to play the role of mobile virtual sensors to cover Smart City areas of interest. This paper proposes an in-depth study of the challenging technical issues related to the efficient assignment of Mobile Crowd Sensing (MCS) data collection tasks to volunteers in a crowdsensing campaign. In particular, the paper originally describes how to increase the effectiveness of the proposed sensing campaigns through the inclusion of several new facilities, including accurate participant selection algorithms able to profile and predict user mobility patterns, gaming techniques, and timely geo-notification. The reported results show the feasibility of exploiting profiling trends/prediction techniques from volunteers’ behavior; moreover, they quantitatively compare different MCS task assignment strategies based on large-scale and real MCS data campaigns run in the ParticipAct living lab, an ongoing MCS real-world experiment that involved more than 170 students of the University of Bologna for more than one year.

Mobile crowd sensing management with the ParticipAct living lab

Abstract The widespread availability of smartphones have enabled the blossom of Mobile Crowd Sensing (MCS) projects, whose goal is to involve users in participatory tasks aimed at building large real-world datasets. In this framework, we present the large-scale experience of the ParticipAct Living Lab, an ongoing experiment at the University of Bologna, which involves about 170 students in MCS campaigns. Specifically, we originally present the analysis of the large set of ParticipAct collected results against some primary datasets in the literature; we present the evaluation and assessment of the original participatory sensing campaign management aspects of ParticipAct; and we report the lessons learned from this wide-scale deployment experience.

Smartphones as smart cities sensors: MCS scheduling in the ParticipAct project

Novel sensor-equipped smartphones have enabled the possibility of harvesting large quantities of data in urban areas by opportunistically involving citizens and their portable devices, as mobile sensors widely available and distributed over Smart Cities areas, typically defined as Mobile Crowd Sensing (MCS). Although some existing efforts have already tackled some of the several MCS issues, to the best of our knowledge, active experiments addressing the challenging issue of the assignment of MCS data collection campaigns to users, namely, MCS scheduling, in a large-scale crowdsensing real-world experiment are still missing. This paper presents the ParticipAct platform and living lab, an ongoing crowdsensing experiment at University of Bologna that involves 300 students for one year. In particular, this article focus on ParticipAct intelligent MCS scheduling of future crowdsensing campaigns based on user mobility history and powered by NoSQL technologies for fast processing of the large amount of mobility traces in the ParticipAct backend. Showed results confirm the feasibility of the proposed approach and quantify its cost.

Automatic extraction of POIs in smart cities: Big data processing in ParticipAct

Recent advances in sensor-equipped smartphones are opening brand new opportunities, such as automatically extracting Points Of Interest (POIs) and mobility habits of citizens in Smart Cities from the large amount of harvested data hotspots. At the same time, the high dynamicity and unpredictability of Smart Cities crowds, opportunistically collaborating toward these common crowdsensing tasks, introduces challenging issues due to the need for fast and continuous processing of these Big Data Streams in the backend of next generation crowdsensing platforms. This paper presents our practical experiences and lessons learnt in deploying the ParticipAct platform and living lab, an ongoing experiment at University of Bologna that involves 300 students for one year. Among all management issues addressed in ParticipAct, this article shows the integration of MongoDB in the ParticipAct backend, as a powerful NoSQL storage and processing engine to fasten the identification of POIs; the reported performance results confirm the feasibility of the approach by quantifying its advantages for city managers.

Smart City Platform Specification: A Modular Approach to Achieve Interoperability in Smart Cities

The development of our cities towards the Smart City paradigm is one of the challenges facing today’s society. This means, among other things, continuously developing and adopting ICT technologies in order to create platforms on which governments, businesses and citizens can communicate and work together and providing the necessary connections between the networks (of people, businesses, technologies, infrastructures, energy and spaces) that are the base for the services of the city. The incredible vastness and diversity of applications that are emerging in this context generates an enormous amount of data of different types and from heterogeneous sources to be shared and exchanged. In this article we propose an approach and describe a methodology and a modular and scalable multi-layered ICT platform to address the problem of cross-domain interoperability in the context of Smart City applications.

Leveraging Communities to Boost Participation and Data Collection in Mobile Crowd Sensing

Mobile Crowd Sensing (MCS) is a technique that aims to obtain the participation of volunteers willing to use their smartphones to harvest large quantities of data as they move in urban areas. Those volunteers typically move inside a limited area and can encounter other volunteers during their day activity. From the number and duration of their encounters, it is possible to categorize relations between volunteers. From this knowledge, we classified volunteers in communities that will cooperate to complete a data collection. The main idea is that users inside a cooperation group are more willing to participate in a sensing campaign. The paper presents results of an implementation of our solution in a real testbed, an ongoing experiment that involves more than 170 students from Bologna University campus. In particular, this article focuses on community identification and cooperative task execution. Shown results confirm the feasibility of the proposed approach and report how user activity can be increased leveraging cooperation among them.

Linked data for Open Government: The case of Bologna

Open Data initiatives push public administrations to publish an increasing number of raw datasets, achieving a more transparent and open governance. The availability of new data raises opportunities for the development of new services, but also open new challenging issues such as the increasing volume of datasets publication available and their integration in large-scale public data ecosystems. The last decade has witnessed the spreading and the consolidation of the Semantic Web technologies that have been proposed as an opportunity to ease data integration through new semantic representation and interrogation languages. By using these technologies, we propose an analysis of the different phases that bring from raw data to mashups over these data through a deployment of standard Linked Data inside a triplestore and by exploiting a Geografic Information System tool for creating mashups with cartographic data, focusing on the real case of Bologna Open Data. We also report experimental results that point out the performances of different triplestores with the goal of supporting informed choices in this emerging new area.