Academia
QA of VGI: An Investigation into the Ottawa-Gatineau OSM Database
Abstract
Within the realm of Volunteered Geographic Information (VGI), reliability and quality of the geographic information continues to be a pressing concern. Many VGI projects do not have standard geospatial data quality assurance procedures and the reliability of such contributors remains in question. This study investigates the quality of VGI by analysing OpenStreetMap (OSM) data in Ottawa-Gatineau. First, a review of past publications into quality assessment of OSM data is examined. Next, a comparative analysis of OSM data is conducted relative to an authoritative dataset. The OSM historical information of map features and contributors is inspected to gain an understanding of how users are contributing to the database and their ability to do so accurately. Overall, OSM data in the context of Ottawa-Gatineau is comparable to or surpasses authoritative dataset quality and clustering contributors based on historical information can help identify tendencies within a contributor base.
Download CloseOSM quality assessment using unsupervised machine learning methods
Abstract
The reliability and quality of volunteered geographic information (VGI) continue to be pressing concerns. Many VGI projects lack standard geospatial data quality assurance procedures, and the reliability of contributors remains in question. Traditional approaches rely on comparing VGI to an “authoritative” or “gold standard” dataset to assess quality. This study investigates VGI quality by analysing the OpenStreetMap (OSM) database in Ottawa-Gatineau, focusing on historical map features and contributor data to gain an understanding of how users are contributing to the database, and their ability to do so accurately. Unsupervised machine learning analyses expose a cluster of experienced contributors classified as “OSM validators/experts”, which are then further used to attribute data quality. They are identified through a combination of strong contribution loadings associated with the use and experience of advanced OSM editors, and weaker loadings associated with feature creation and frequency of contributions leading to further correction. Limitations are discussed with implications for future work.
Request CloseDriving Behaviour Analytics for Monitoring Changes in Behaviour
Abstract
The existing methods of screening medically unfit older drivers in Canada (i.e., cognitive and physically impaired) needs to be improved by providing more evidence-based, objective measures of driving ability. As older drivers often rely on driving for independence (e.g., visit friends, grandchildren or social clubs), revoking their driver’s license can negatively impact their quality of life. By analyzing the driving history from sensor data on real- world driving, two methods were developed to monitor the changes in driving behaviour to detect a decline in driving ability. Our methods were developed from a dataset that included thousands of trips from 28 older drivers over a few recent years from the Candrive research study. The first method includes the development of total driving area and primary “mean” locations for the further proposal of a real-time GIS monitoring application. For the second method, a detection algorithm was created to track the proportion of unusual trips per month and provides an alert when a consistently high proportion of unusual trips were observed, which may indicate that the older driver is losing the sense of direction and have decline in memory. The methods in this study can improve the screening process for medically unfit older drivers and contribute to reducing healthcare costs and improve physician-patient relationship for older adults.
Download Close
