Enhancing Urban Sensing Utility with Sensor-enabled Vehicles and Easily Accessible Data

TL;DR

This work tackles the challenge of optimizing sensing utility for sensor-enabled vehicles in urban environments under budget constraints. It proposes an adaptive framework that combines maximum-entropy-based vehicle selection with spatiotemporal weights learned from open data, culminating in the Improved OptiFleet algorithm to reduce redundancy while preserving coverage. Validation on two months of Guangzhou air-quality data with 320 vehicles demonstrates up to 5% gains in sensing utility using fewer vehicles and maintains sub-5% MAPE with around 200 vehicles, underscoring the pivotal role of temporal dynamics. The study highlights that dynamic urban signals, particularly traffic flow, are crucial for effective mobile sensing and points to opportunities for applying the framework to other cities with available data.

Abstract

Urban sensing is essential for the development of smart cities, enabling monitoring, computing, and decision-making for urban management.Thanks to the advent of vehicle technologies, modern vehicles are transforming from solely mobility tools to valuable sensors for urban data collection, and hold the potential of improving traffic congestion, transport sustainability, and infrastructure inspection.Vehicle-based sensing is increasingly recognized as a promising technology due to its flexibility, cost-effectiveness, and extensive spatiotemporal coverage. However, optimizing sensing strategies to balance spatial and temporal coverage, minimize redundancy, and address budget constraints remains a key challenge.This study proposes an adaptive framework for enhancing the sensing utility of sensor-equipped vehicles.By integrating heterogeneous open-source data, the framework leverages spatiotemporal weighting to optimize vehicle selection and sensing coverage across various urban contexts.An entropy-based vehicle selection strategy, \texttt{Improved OptiFleet}, is developed to maximize sensing utility while minimizing redundancy.The framework is validated using real-world air quality data from 320 sensor-equipped vehicles operating in Guangzhou, China, over two months.Key findings show that the proposed method outperforms baseline strategies, providing up to 5\% higher sensing utility with reduced fleet sizes, and also highlights the critical role of dynamic urban data in optimizing mobile sensing strategies.

Figures (4)

• Figure 1: Framework for calculating adaptive spatiotemporal sensing weights based on Mask2Former algorithm.
• Figure 2: Estimation errors of the selected vehicle fleets with the increase in fleet size.
• Figure 3: Spatial distribution of MAPE errors for PM2.5 estimation under different models (200 vehicles).
• Figure 4: Ablation study on the contribution of spatial and temporal weighting to sensing utility.