Mobile Crowdsensing (MCS), an important component of the Internet of Things (IoT), is a paradigm which utilizes people carrying smart devices, referred to as “workers”, to perform various sensing tasks. A type of such tasks is localization, where the location of a certain target or event is to be found. The recruitment of the right set of workers to perform a localization task plays a paramount role in the outcome quality in terms of localization time, energy, cost, and accuracy. The stability of workers in MCS, which is defined as their spatio-temporal availability, makes the problem of localization more complex, since such tasks are continuous. In this work, a novel Stable Data-based Recruitment System (SDRS) for localization tasks is proposed, which-a) integrates a new data-based recruitment parameter that dynamically exploits data readings to guide the recruitment system into selecting informative workers, while considering their mobility; b) presents a stable coverage assessment method that considers range-free sensors and the mobility of workers; and c) integrates a two-phase recruitment approach that is optimized using greedy and genetic methods. The testing and evaluation of the proposed approach is conducted using datasets of MCS workers and compared with existing benchmarks. The results demonstrate that the proposed approach efficiently and reliably leads to a speedy localization, with high outcome quality.

移动人群感知（MCS）是物联网（IoT）的重要组成部分，它是一种利用携带智能设备（称为“工人”）的人来执行各种传感任务的范例。这种任务的一种类型是本地化，即在其中找到特定目标或事件的位置。就本地化时间，精力，成本和准确性而言，招聘合适的工人来执行本地化任务对结果质量至关重要。MCS中的工人稳定性（定义为他们的时空可用性）使本地化问题变得更加复杂，因为此类任务是连续的。在这项工作中，针对本地化任务，提出了一种新颖的基于数据的稳定招聘系统（SDRS），（a）集成了一个新的基于数据的招聘参数，该参数动态地利用数据读数来指导招聘系统选择信息丰富的工人，同时考虑其流动性；b）提出了一种稳定的覆盖范围评估方法，该方法考虑了无范围传感器和工人的流动性；c）整合了两阶段招聘方法，该方法使用贪婪和遗传方法进行了优化。使用MCS工人的数据集对提议的方法进行测试和评估，并与现有基准进行比较。结果表明，所提出的方法有效且可靠地导致了快速的本地化，并具有较高的结果质量。b）提出了一种稳定的覆盖范围评估方法，该方法考虑了无范围传感器和工人的流动性；c）整合了两阶段招聘方法，该方法使用贪婪和遗传方法进行了优化。使用MCS工人的数据集对提议的方法进行测试和评估，并与现有基准进行比较。结果表明，所提出的方法有效且可靠地导致了快速的本地化，并具有较高的结果质量。b）提出了一种稳定的覆盖范围评估方法，该方法考虑了无范围传感器和工人的流动性；c）整合了两阶段招聘方法，该方法使用贪婪和遗传方法进行了优化。使用MCS工人的数据集对提议的方法进行测试和评估，并与现有基准进行比较。结果表明，所提出的方法有效且可靠地导致了快速的本地化，并具有较高的结果质量。