Data Story
Information from Data.SA indicates that there were 1875 disability-related complaints in South Australia in past years, with about 34% concerning services (Government of South Australia, 2022). This compelling insight fuelled our drive to advocate for accessible experiences.
We sourced information from open data sources, curating data on geography specifics, user reviews, and points of interest specifically relevant to people with disabilities.
The algorithm is adjustable based on the accessibility needs of a user.
In case of users with mobility issues, the algorithm starts by gathering park boundary data and Digital Elevation Models (DEM) data, which contains elevation values. These datasets are integrated to create a 2D array where each cell holds elevation information for a specific geographic point within tourist destination boundaries. This array is treated conceptually like an image.
Applying edge detection algorithms to this "elevation image" highlights abrupt elevation changes, indicating steep terrain. A quantitative measure of elevation irregularity is computed from these detected changes, assessing the terrain's roughness. A higher measure signifies greater elevation variations.
The algorithm interprets this metric to gauge the mobile accessibility of parks. For individuals with disabilities, particularly those using wheelchairs, navigating constantly ascending and descending terrains can transform a pleasant trip into a challenging ordeal. Parks with lower elevation irregularity metrics are deemed more wheelchair-accessible due to smoother terrain. Conversely, parks with higher metrics may present difficulties, potentially rendering them unsuitable for wheelchair users.
Ultimately, the algorithm categorizes places based on their accessibility, aiding in decision-making for outdoor activities. This multi-step process, from data integration and edge detection to elevation metric calculation and mobile accessibility assessment, provides insights into the terrain's impact on mobile device use within each park's boundaries.
Then, this measure becomes one of dimensions for k-nearest-neighbor algorithm next to other accessibility provisions such as priority parking, vision impairment hints.
If the place has previously been rated, the result that aligns well with user needs emerges at the top of recommendation list.
The project was prototyped using Figma:
* https://www.figma.com/proto/V2aSGgCEoXrtyGJ0MNfpWI/Gov-Hack2023?type=design&node-id=150-992&t=jCh1RLGQ3VXRoyIQ-1&scaling=scale-down&page-id=0%3A1&starting-point-node-id=144%3A682&show-proto-sidebar=1
Then, partially implemented as a web application available online (see our Homepage
).
* http://accessibletourism.pythonanywhere.com/
References
Government of South Australia, 2022. SATC Public Complaints 2019-20 to 2021-22. [Online]
Available at: https://data.sa.gov.au/data/dataset/public-complaints-reporting-south-australian-tourism-commission/resource/807725ba-e8fa-4859-bd81-2a932e5ed6d3