Ubiquitous Crowdsourcing Research Articles

A location-based ubiquitous crowdsourcing approach for the emergency supply of oxygen cylinders

Many people with chronic obstructive pulmonary diseases (COPD) are subjected to emergencies triggered by breathing difficulties. Oxygen therapy, administered from medical oxygen cylinders, can be used to relieve respiratory airways, and restore the supply of oxygen to the body’s vital organs. In this paper, we present a location-based ubiquitous crowdsourcing solution to enable COPD patients to request an emergency supply of oxygen cylinders. At the heart of the solution is a trusted platform that acts as a mediator for the ambient social interaction among a virtual and socially engaged community of requestors and suppliers. The geo-temporal data generated by this social interaction can be analyzed to uncover meaningful ambient environmental patterns. Our approach also uses image processing and computer vision techniques to help validate crowd responses. We discuss the details of the human-centric computer interaction design and its key features. We also elaborate on the challenges faced in the design and development of the solution and summarize the actions taken to address them.

CrowdPickUp

We develop and evaluate a new ubiquitous crowdsourcing platform called CrowdPickUp, that combines the advantages of mobile and situated crowdsourcing to overcome their respective limitations. In a 19-day long field study with 70 participants, we evaluate the quality of work that CrowdPickUp produces. In particular, we measure quality in terms of worker performance in a variety of tasks (requiring local knowledge, location-based, general) while using a number of different quality control mechanisms, and also capture workers’ perceptions of the platform. Our findings show that workers of CrowdPickUp contributed data of comparable quality to previously presented crowdsourcing deployments while at the same time allowing for a wide breadth of tasks to be deployed. Finally, we offer insights towards the continued exploration of this research agenda.

Ubiquitous Crowdsourcing Model for Fuzzy Information Enrichment of Tourist Spot Recommender System

The proposed research aims to integrate contextual information with tourist spot recommender system. Ubiquitous crowdsourcing model has been used for collecting the contextual information using fuzzy linguistic values in current time. The existing tourist spot recommender systems give list tourist spots along with their ratings. Proposed model takes this list as an input and the current fuzzy contextual information collected from crowd present at the spot and computes a new score for each spot/location. This new score not only conveys the popularity of a spot in vicinity but also advices whether this spot is worth visiting at given point in time. A prototype system has been implemented using java and MATLAB and is evaluated by 104 real users.

Ubiquitous crowdsourcing model for fuzzy information enrichment of tourist spot recommender system

The proposed research aims to integrate contextual information with tourist spot recommender system. Ubiquitous crowdsourcing model has been used for collecting the contextual information using fuzzy linguistic values in current time. The existing tourist spot recommender systems give list tourist spots along with their ratings. Proposed model takes this list as an input and the current fuzzy contextual information collected from crowd present at the spot and computes a new score for each spot/location. This new score not only conveys the popularity of a spot in vicinity but also advices whether this spot is worth visiting at given point in time. A prototype system has been implemented using java and MATLAB and is evaluated by 104 real users.

Motivating participation and improving quality of contribution in ubiquitous crowdsourcing

Ubiquitous crowdsourcing, or the crowdsourcing of tasks in settings beyond the desktop, is attracting interest due to the increasing maturity of mobile and ubiquitous technology, such as smartphones and public displays. In this paper we attempt to address a fundamental challenge in ubiquitous crowdsourcing: if people can contribute to crowdsourcing anytime and anyplace, why would they choose to do so? We highlight the role of motivation in ubiquitous crowdsourcing, and its effect on participation and performance. Through a series of field studies we empirically validate various motivational approaches in the context of ubiquitous crowdsourcing, and assess the comparable advantages of ubiquitous technologies' affordances. We show that through motivation ubiquitous crowdsourcing becomes comparable to online crowdsourcing in terms of participation and task performance, and that through motivation we can elicit better quality contributions and increased participation from workers. We also show that ubiquitous technologies' contextual capabilities can increase participation through increasing workers' intrinsic motivation, and that the in-situ nature of ubiquitous technologies can increase both participation and engagement of workers. Combined, our findings provide empirically validated recommendations on the design and implementation of ubiquitous crowdsourcing.

From sensing to controlling: the state of the art in ubiquitous crowdsourcing

Crowdsourcing systems aim to solve complex tasks by engaging a multitude of humans through mobile and social media and by harnessing their ability to perform specific subtasks and to report the results. Given the rapid increase in the number, size and diversity of ubiquitous crowdsourcing applications across a wide spectrum of domains all around the world, there is a need for a principled way of conceptualising such systems. The first step is the development of a crowdsourcing typology to create a baseline for comparing, evaluating and advancing efforts in this field. For example, crowdsourcing systems need to address a common set of issues to ensure their effectiveness, such as quality control and incentive design. In this paper, we present a thematic overview of the emerging ubiquitous crowdsourcing systems by grouping them based on the task complexity that they support and along key challenges in successfully harvesting expertise of large human networks.