A Self-Adaptive Behavior-Aware Recruitment Scheme for Participatory Sensing.

Area of Science:

• Computer Science
• Ubiquitous Computing
• Data Science

Background:

• Participatory sensing leverages widespread smart devices for data collection.
• Effective participant recruitment is a key challenge, requiring integration with daily activities.
• Existing methods often lack adaptiveness to real-world application scenarios.

Purpose of the Study:

• To propose a self-adaptive, behavior-aware recruitment scheme for participatory sensing.
• To optimize participant selection by modeling spatio-temporal behavior and data quality.
• To address the challenge of recruiting participants who align with realistic application needs.

Main Methods:

• Developed a scheme to model participants' spatio-temporal behavior and rate data quality.
• Formulated participant recruitment as a linear programming problem.
• Incorporated factors such as spatio-temporal coverage, data quality, and budget constraints.

Main Results:

• The proposed scheme demonstrated efficient sensing performance.
• Evaluations confirmed stability, low cost, and strong spatio-temporal correlation.
• The system exhibited significant self-adaptiveness to different application scenarios.

Conclusions:

• The behavior-aware recruitment scheme effectively addresses participant recruitment challenges in participatory sensing.
• The approach offers a flexible and adaptive solution for optimizing sensing campaigns.
• This methodology enhances the overall efficiency and cost-effectiveness of participatory sensing.