Social Sensing Applications in Edge Computing Systems

Dear Colleagues,

Social sensing applications are spreading in many different domains. Basically, such applications exploit the social sensing paradigm, a promising sensing approach where humans and devices acting on their behalf collect data, process information, and extract knowledge from the physical world, improving the quality of our lives. This enables an accurate and efficient way to perceive the human being (health checking and reporting using everyday wearable devices and smartphones, contact tracing, etc.) and the surrounding environment (self-reporting of traffic conditions, public safety, etc.). To fulfill their objectives, social sensing applications usually rely on cloud “backends” to perform the heaviest computations, hence neglecting the day-by-day increase of computing power available on our personal devices (AI chips, GPUs, multi-processors, etc.). Indeed, the social sensing paradigm could be mixed with the edge computing paradigm, to push heavy tasks towards the edge of the network and along the cloud-to-thing continuum. This would bring many technological advantages, for instance in terms of a better quality of service, higher privacy, higher reliability, and user engagement.

However, for the successful integration of these computation paradigms, several research challenges need to be tackled, the most urgent being related to resource management (resource sharing among different devices, local resource usage vs. quality of service), heterogeneity (different hardware platforms, runtimes, and networking), privacy and security, robustness and reliability (adaptation to dynamic environments), and cooperativeness (some devices may be more selfish and not want to share resources). This Special Issue welcomes both original papers and thorough surveys witnessing the advantages of empowering social sensing applications with edge computing processes and core functionalities. Envisioned application domains include (but are not limited to) the following:

• Human-centric and human-in-the-loop applications;
• Wearables and eHealth;
• Collaborative smart-city scenarios;
• Emergency and disaster management;
• Media streaming and sharing;
• AI-as-a-service and edge intelligence for social sensing;
• Networking-as-a-service for social sensing

Prof. Dr. Massimo Vecchio
Prof. Pietro Ducange
Dr. Charith Perera
Dr. Mattia Antonini
Dr. Jacek Wodecki
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• edge computing
• social sensing
• computing paradigm
• explainable artificial intelligence
• crowdsensing
• distributed sensing