Multicriteria‐Based Crowd Selection Using Ant Colony Optimization

Abstract

Internet-enabled technologies have provided a way for people to communicate and collaborate with each other. The collaboration and communication made crowdsourcing an efficient and effective activity. Crowdsourcing is a modern paradigm that employs cheap labors (crowd) for accomplishing different types of tasks. The task is usually posted online as an open call, and members of the crowd self-select a task to be carried out. Crowdsourcing involves initiators or crowdsourcers (an entity usually a person or an organization who initiate the crowdsourcing process and seek out the ability of crowd for a task), the crowd (online participant who is a having a particular background, qualification, and experience for accomplishing task in crowdsourcing activity), crowdsourcing task (the activity in which the crowd contribute), the process (how the activity is carried out), and the crowdsourcing platform (software or market place) where requesters offer various tasks and crowd workers complete these tasks. As the crowdsourcing is carried out in the online environment, it gives rise to certain challenges. The major problem is the selection of crowd that is becoming a challenging issue with the growth in crowdsourcing popularity. Crowd selection has been significantly investigated in crowdsourcing processes. Nonetheless, it has observed that the selection is based only on a single feature of the crowd worker which was not sufficient for appropriate crowd selection. For addressing the problem of crowd selection, a novel “ant colony optimization-based crowd selection method” (ACO-CS) is presented in this paper that selects a crowd worker based on multicriteria features. By utilizing the proposed model, the efficiency and effectiveness of crowdsourcing activity will be increased.

RETRACTED ARTICLE: Decision support system for effective action recognition of track and field sports using ant colony optimization

“…The relevant features are then fed into the proposed system to enhance the learning process of machine and to provide accurate results. [32,33], device selection [34], shape optimization, and gene identi cation [35] are some examples of practical optimization challenges. ACO is a feasible approach for improving prediction.…”