Urban traffic monitoring through Distributed Acoustic Sensing: Trial analysis of a potent monitoring tool

Distributed Acoustic Sensing (DAS) is a state-of-the-art sensing technology that transforms pre-existing fiber optic cables in cities into high-density arrays of sensors. It thus provides massive sensing capacity with high spatial and temporal resolution, becoming a potential attractive tool for urban traffic monitoring. This work presents a real uncontrolled urban-traffic monitoring experiment deployed in the city of Granada (Spain). The first analysis of the experiment reveals several categories of mobile events described in detail, proposing knowledge-based feature vectors to understand their characteristics and underlying discriminative information. A comprehensive exploratory data analysis is complemented with several state-of-the-art clustering techniques to address design foundational questions for data analysis like optimal frequency band, data separability, discriminative features selection, and identification of relevant spatial points. As a result, this study provides a working methodology for DAS technology pointing at challenges and future work paths using this potent urban monitoring tool.