Mobility‐related information systems, such as on‐street parking information (OSPI) systems have become more popular in the original equipment manufacturer (OEM) industry over the last decade. However, there is a lack of methods to assess their quality at a large scale. This paper introduces a data‐driven methodology to measure the true quality by fleet data prioritization‐based subsampling strategies (PSSs). It is applied to the use case of OSPI using parking events (PE), but is applicable to other mobility‐related information systems utilizing their respective fleet data. PSSs are defined based on neighbourhoods and time periods. Each PSS generates a unique set of spatio‐temporally important areas at different quadkey zoom levels over 168 week‐hours, called slices. The importance weight in each slice depends on the volume of PE within them. The algorithm for each PSS automatically selects important areas and time frames that are vital to be observed. Sample prediction models are used for the benefits assessment of the methodology by comparing it against non‐prioritized randomized selection of ground truth. It is proven that the methodology can lessen the effort of ground truth collection, while maintaining the amount of information necessary to assess the true quality of a prediction model.
On-street parking information (OSPI) systems help reduce congestion in the city by lessening parking search time. However, current systems use features mainly relying on costly manual observations to maintain a high quality. In this paper, on top of traditional location-based features based on spatial, temporal and capacity attributes, vehicle parked-in and parked-out events are employed to fill the quality assurance gap. The parking events (PEs) are used to develop dynamic features to make the system adaptive to changes that impact on-street parking availability. Additionally, a parking behavior change detection (PBCD) model is developed as an OSPI supplementary component to trigger potential parking map updates. The evaluation shows that the developed OSPI availability prediction model is on par with state-of-the-art models, despite having simpler but more enhanced and adaptive features. The foundational temporal and aggregated spatial parking capacity features help the most, while the PE-based features capture variances better and enable adaptivity to disruptions. The PE-based features are advantageous as data are automatically gathered daily. For the PBCD model, impacts by construction events can be detected as validation. The methodology proves that it is possible to create a reliable OSPI system with predominantly PE-based features and aggregated parking capacity features.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.