Adaptive Sampling for Urban Air Quality through Participatory Sensing

Area of Science:

• Environmental Science
• Computer Science
• Data Science

Background:

• Air pollution is a significant global challenge.
• Smartphone applications facilitate urban sensing for air quality awareness.
• Effective data sampling is crucial for accurate sensing performance.

Purpose of the Study:

• To propose an Adaptive Sampling Scheme for Urban Air Quality (AS-air) using participatory sensing.
• To enhance the efficiency and adaptivity of urban air quality monitoring.
• To develop an energy-efficient data sampling strategy.

Main Methods:

• Utilizing the Apriori algorithm to identify historical air quality patterns.
• Predicting real-time air quality based on identified patterns.
• Employing Q-learning to adapt sampling parameters for optimized performance.

Main Results:

• AS-air demonstrates an energy-efficient sampling strategy.
• The scheme is adaptive to dynamic outdoor air environments.
• AS-air achieves good sampling efficiency in urban air quality sensing.

Conclusions:

• The proposed AS-air scheme effectively addresses data sampling challenges in urban air quality monitoring.
• Participatory sensing combined with adaptive algorithms offers a viable solution for real-time air quality assessment.
• This approach contributes to more sustainable and efficient environmental sensing networks.