The latest award-winning science at CSIRO’s Data61
A data privacy measurement tool, enabling robots to ‘talk’, human-centric phishing detection, and visualising uncertainty in spatial data – CSIRO’s Data61’s science excellence is taking centre stage as this year’s award season kicks off.
Vizumap, winner of the Venables Award for New Developers of Open Source Software for Data Analytics
No data is almost as important as data in spatial and spatio-temporal mapping, with Vizumap the key to understanding uncertainty when little information is available.
An online mapping platform that visualises, measures and communicates data (or the lack thereof), Vizumap’s impact has been cemented after winning a Venables Award in June.
It’s four approaches to visualising uncertainty (bivariate maps, map pixelation, glyph rotation and exceedance probability maps) set the platform apart from the competition.
“Bivariate choropleth maps explore the ‘blending’ of two colour schemes, one representing the estimate and a second representing the margin of error,” explained team member Dr Petra Kuhnert.
“The second approach uses map pixelation to convey uncertainty. The third approach uses a glyph to represent uncertainty and is what we refer to as glyph rotation. The final map based exploration of uncertainty is through exceedance probabilities.”
“Vizumap’s ability to visualise data uncertainty also helps decision-makers identify regions where remediation efforts and further investment are required, making it ideal for statisticians, scientists, government departments and more.”
Take a tour of Vizumap’s interactive visualisation app here and the details of its R package on Github.
Multi-Robot Navigation Stack, winner of the QLD iAward Government & Public Sector Solution of the Year category
Designed in response to the DARPA Subterranean Challenge, the Navigation Stack enables a robotic team to navigate challenging environments outside of communications range.
The technology combines Wildcat SLAM with the robot’s hardware abstraction layer. Wildcat’s mapping and localisation capabilities are inputted and shared amongst the fleet, while the navigation subsystem builds a traversability graph and performs path planning.
The subsystem provides a traversability risk measurement, path planning, collision avoidance, narrow gaps planning, negative obstacle avoidance, and features a stair traversal mode.
Suitable for any type of robot (legged, tracked, wheeled, etc), the Navigation Stack enables a single operator to control different types of robots using the same interface, alleviating the need for specialised training for each version.
“These sorts of systems have been developed in a much smaller scale than what we have done recently,” explained Senior Robotics Software Engineer Fletcher Talbot.
“I think our system is the most mature system of a multi-agent robot fleet being operated by minimal crew to do the sort of things we do in an autonomous manner. This is Australian technology that is world class. There are very few systems around the world that can do what our system can do at the maturity level our system is.”
To find out more about the Navigation Stack and if it can solve your challenge, contact firstname.lastname@example.org
Smart Sheild, winner of the NSW iAward Technology Platform Solution category
A machine learning-powered anti-phishing tool, Smart Sheild’s human-centric artificial intelligence (AI) approach set it apart from competitors at the NSW iAwards.
The system grades email severity according to a traffic light colour system, explaining what triggered the warning and its severity in a banner popup.
Smart Shield’s advanced machine learning algorithms analyse and learn from malicious emails and websites to enable greater detection of advanced phishing attempts. Over 38,000 emails and 20 million phishing and benign URLs relevant to Australia were used to train the system.
Funded by the Cyber Security CRC and the Government of Western Australia with R&D undertaken by CSIRO’s Data61, Smart Sheild is in the final testing phase.
“Being a winner of an iAward positions Smart Shield on the map as a leading institution in cybersecurity innovation,” said CSIRO project lead Dr Sharif Abuadbba.
Smart Shield will compete against other state winners at the national iAwards in October.
PIF, merit winner of the NSW iAward Technology Platform Solution category
Known as Personal Information Factor (PIF) tool, PIF assesses the risks to an individual’s data within any dataset, allowing targeted and effective protection mechanisms to be put in place.
The software uses a sophisticated data analytics algorithm to identify the risks that sensitive, de-identified and personal information within a dataset can be re-identified and matched to its owner.
The early version of the tool was used by the NSW Government to analyse datasets tracking the spread of COVID-19 in the state since March 2020 and apply appropriate levels of protection before this data is released as open data.
Developed as a collaboration between CSIRO’s Data61, the digital specialist arm of Australia’s national science agency, the NSW Government, the Australian Computer Society (ACS) and several other groups, CSIRO has explored ways of enhancing the tool in collaboration with the Cyber Security Cooperative Research Centre (CSCRC) since 2020.
“Privacy is foundational to Australia’s cyber and national security,” explained CSIRO’s research lead Dr M.A.P. Chamikara.
“PIF drives trust in data management and data sharing infrastructure and is a critical tool for data custodians, as evidenced in its adoption by the NSW Government.”