IncluVisit SA

Project Info

Team Name


Team Members

Fiona , Pavel and 2 other members with unpublished profiles.

Project Description

  • Promotion of SA tourism through advocation of accessibility practices.
  • Using Geospacial data to calculate difference in elevation. Using it to difirintiate accessibility of tourist destinations.
  • Using text, and numerical data to difirintiate accessibility of tourist destinations.
  • Content-based recommendation system based on k-nearest-neighbour cluster analysis algorithm.
  • AI text generation and procedural voice generation
  • UI wireframe prototype
  • Web Application with partial functionality is already online

IncluVisit SA aims to encourage more visitors to explore South Australia.

We do it by helping people with sensory and mobility impairments to find current and relevant to them information about popular tourist destinations in SA.

We gather information about appropriate accessibility facilities present at tourist attractions. The web application we have developed can recommend places based on user preferences and on accessibility facilities.

The solution itself was also developed with accessibility in mind. It includes provisions for people with vision and hearing difficulties. Our user interface can easily change shape to adapt for users with eyesight impairments. It also includes voice narration that can be triggered to describe presented information.

The project leverages data analytics for organising its content and making recommendations to users. Open data sources are used to pull-in and organise content delivery. The summaries for tourist destinations are auto generated using ChatGPT based on the data we have pulled.

Our hope is that by supporting tourists with accessibility needs we can incentivise them to explore more of South Australia and stay here longer.

#tourism disability accessibility inclusion deversity

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:

Then, partially implemented as a web application available online (see our Homepage).

Government of South Australia, 2022. SATC Public Complaints 2019-20 to 2021-22. [Online]
Available at:

Evidence of Work



Team DataSets

SRTM-derived 1 Second Digital Elevation Models Version 1.0

Description of Use Used to calculate the 'very_steep' metric for the recommendation system and accessibility parks segmentation.

Data Set

Conservation Reserve Boundaries

Description of Use We use it to get parc boundaries coordinates

Data Set

Australian Tourism Data Warehouse

Description of Use Used to summarise available accessibility facilities at tourist attractions. Contributed to most of the metrics in our web application

Data Set

SATC Public Complaints 2019-20 to 2021-22

Description of Use The dataset has 'Access to services' service delivery section, which contributes to `accessibility_information` attribute in our web application.

Data Set

Challenge Entries

Increase visitor expenditure through Smart Tourism

How can we use digital technology to "upsell" to visitors to South Australia by uncovering additional attractions and experiences and/or extending their stay?

Go to Challenge | 16 teams have entered this challenge.

Generative AI: Unleashing the Power of Open Data

Explore the potential of Generative AI in conjunction with Open Data to empower communities and foster positive social impact. This challenge invites participants to leverage Generative AI models to analyse and derive insights from Open Data sourced from government datasets. By combining the power of Generative AI with the wealth of Open Data available, participants can create innovative solutions that address real-world challenges and benefit communities.

Eligibility: Ethical use of a generative AI in your project and at least one Australian or New Zealand data set.

Go to Challenge | 29 teams have entered this challenge.