FADACS: A Few-shot Adversarial Domain Adaptation Architecture for Context-Aware Parking Availability Sensing

TL;DR

This paper introduces FADACS, a transfer learning framework using adversarial domain adaptation to predict parking occupancy with limited data, leveraging heterogeneous external information across different urban contexts.

Contribution

It presents a novel few-shot adversarial domain adaptation architecture for parking sensing, addressing data scarcity and heterogeneity challenges in urban environments.

Findings

Comparable to state-of-the-art methods in accuracy

Effective with limited sensor data from different cities

Utilizes external contextual information like weather and POIs

Abstract

Existing research on parking availability sensing mainly relies on extensive contextual and historical information. In practice, the availability of such information is a challenge as it requires continuous collection of sensory signals. In this study, we design an end-to-end transfer learning framework for parking availability sensing to predict parking occupancy in areas in which the parking data is insufficient to feed into data-hungry models. This framework overcomes two main challenges: 1) many real-world cases cannot provide enough data for most existing data-driven models, and 2) it is difficult to merge sensor data and heterogeneous contextual information due to the differing urban fabric and spatial characteristics. Our work adopts a widely-used concept, adversarial domain adaptation, to predict the parking occupancy in an area without abundant sensor data by leveraging data from other areas with similar features. In this paper, we utilise more than 35 million parking data records from sensors placed in two different cities, one a city centre and the other a coastal tourist town. We also utilise heterogeneous spatio-temporal contextual information from external resources, including weather and points of interest. We quantify the strength of our proposed framework in different cases and compare it to the existing data-driven approaches. The results show that the proposed framework is comparable to existing state-of-the-art methods and also provide some valuable insights on parking availability prediction.