Mobile Crowd Sensing and Computing

Mobile Crowd Sensing and Computing: When Participatory Sensing Meets Participatory Social Media

[pdf-embedder url=”http://wellapets.com/wp-content/uploads/2019/06/Mobile-Crowd-Sensing-and-Computing.pdf” title=”Mobile Crowd Sensing and Computing”]

Abstract
With the development of mobile sensing and mobile social networking techniques, mobile crowd sensing and computing (MCSC), which leverages heterogeneous crowdsourced data for large-scale sensing, has become a leading paradigm. Built on top of the participatory sensing vision, MCSC has two characteristic features: it leverages heterogeneous crowdsourced data from two data sources: participatory sensing and participatory social media; and it presents the fusion of human and machine intelligence in both the sensing and computing processes. This article characterizes the unique features and challenges of MCSC. We further present early efforts on MCSC to demonstrate the benefits of aggregating heterogeneous crowdsourced data. 

The effective use of the incredible and continuous production of data coming from different sources (e.g., enterprises, the Internet of Things, online systems) will transform our life and work.
Within this context, people are not only data consumers, but participate in different ways (e.g., smartphone sensing, online posting) in the data production process. In this article, we discuss the opportunities that heterogeneous human participation offer to systems and services that rely on large-scale sensing.
It is essential to first clarify the motivation of taking the human in the loop for large-scale sensing. In the past few years, researchers have studied the benefits of understanding urban/ community dynamics [1]. However, traditional stationary wireless sensor network deployments often fail to capture such dynamics because they either do not have enough sensing capabilities or are limited in terms of scalability (e.g., high deployment and maintenance cost).
Mobile crowd sensing and computing (MCSC) offers a new method of large-scale sensing and computing. On one hand, the sheer number of mobile devices (e.g., smartphones, tablets, wearable devices) and their inherent mobility provide the ability to sense and infer people’s context (e.g., ambient noise) in an unprecedented manner. On the other hand, highly scalable sensing with mobile devices in combination with cloud computing support gives MCSC systems the scalability and versatility properties that are often lacking in static deployments. Although it is quite difficult to attempt a formal definition of the MCSC paradigm, we could state that MCSC is a new sensing paradigm that empowers ordinary people to contribute data sensed or generated from their mobile devices, and aggregates and processes heterogeneous crowdsourced data in the cloud for intelligent service provision.
From the artificial intelligence (AI) perspective, MCSC is founded on a distributed problem solving model where crowds are engaged in complex problem solving procedures through open calls. The concept of crowd-powered problem solving has been explored in several research areas. The term “crowdsourcing” was coined in 2005 by Wired. The definition of the term crowdsourcing is as follows:1 the practice of obtaining needed services or content by soliciting contributions from a large group of people, and especially from an online community. Wikipedia,2 where thousands of contributors from across the globe have collectively created the world’s largest encyclopedia, is a typical example. MCSC extends this concept by going beyond the boundaries of online communities and reaching out to the mobile device user population for sensing participation. With participatory sensing, first proposed by Burke et al. [2], we see for the first time solutions that require explicit human involvement in accomplishing sensing tasks. MCSC broadens the concept of participatory sensing from two aspects. First,
it takes advantage of various forms of human participation in the mobile Internet era. Generally speaking, MCSC sensing modalities can be obtained from specific hardware sensors (e.g., accelerometers, cameras) available on mobile devices and from the information trail (e.g., social media posts) directly generated by users. Second, MCSC presents the fusion of human and machine intelligence in both the sensing and computing processes. The usage of heterogeneous crowdsourced data as well as the integration of human and machine intelligence opens up new and unexpected opportunities.
We use the following trip planning scenario to showcase the characteristics of MCSC.

Categories