Brisbane SIGCHI

Human-Centred AI

Data science is fundamental to our society today. From all areas, people are managing and processing data to extract information. Please join us for an afternoon on the topic of data science and human-centred AI.

This event is hosted by the QUT Centre for Data Science.

Program

  • 4pm: Welcome and introduction to the Centre for Data Science, Centre Director Kerrie Mengersen
  • 4.10pm: Three speakers
    • Designing Human-centred AI
      • Professor Margot Brereton, School of Computer Science
    • Towards Human-Centred AI: What Can Machines Learn from Eye-Tracking Data?
      • Dr Catarina Pinto Moreira, School of Information Science
  • Industry 5.0 and Augmented workforce
    • Dr Vitor Botazzi, R&D Manager/Robotics Engineer, Holovision
  • 5.30pm: Networking with coffee and tea

Designing Human-centred AI

Professor Margot Brereton, School of Computer Science, QUT

Abstract: AI design has historically been led by a technical push approach exploring techniques to operate over data, with less consideration given to human capabilities, use context, needs, interaction and creativity. The Human-centred AI program in the Centre for Data Science looks instead to design from the perspective of human use and values. In this talk I will offer a brief overview of the landscape of research in human-centred AI. I will then discuss our program of research which examines how people interact with AI technologies,  and how AI technologies can be designed to foster human values and learning as well as machine learning, by expanding the design frame.  

Towards Human-Centred AI: What Can Machines Learn from Eye-Tracking Data?

Dr Catarina Pinto Moreira, School of Information Science, QUT

Abstract: Artificial Intelligence (AI) and Deep Learning (DL) technologies have made great strides in equalling and even surpassing human performance in many tasks, particularly in healthcare. Although DL cannot replace clinicians in medical diagnosis, it can support expert radiologists in performing time-consuming tasks, such as examining chest X-rays for signs of pneumonia or COVID-19. Despite this success, the internal mechanisms of these technologies are an enigma because humans cannot scrutinize how these systems do what they do. This uncertainty poses a significant concern in adopting AI-based technologies in healthcare because they are highly susceptible to biases due to the computation of spurious correlations during the prediction process which can put human lives in danger. This talk will present an ongoing project and its preliminary results. The project aims to make DL models understandable to radiologists by investigating how eye-tracking data can be used to teach a machine how radiologists read and classify chest X-ray images. By using multimodal data containing chest X-ray images, radiologists’ eye patterns, and their respective audio recordings, this project aims to devise new methods to extract radiologists’ cognitive maps. We will pioneer the construction of new multimodal DL architectures that learn to identify abnormalities and regions of interest using the radiologists’ cognitive maps and X-ray images to teach machines how radiologists diagnose X-ray images. We will use that knowledge to generate explanations and promote trust in the adoption of AI-based systems, leading to a more accurate, augmented, and enhanced decision-making process in clinical practice. One important byproduct of this project will be novel computer-assisted training for young radiologists and imagiology students by designing an Explainable User Interface to facilitate the learning and training of radiologists.

Industry 5.0 and Augmented workforce

Dr Vitor Botazzi, R&D Manager/Robotics Engineer, Holovision

Vitor has 20+ years of experience working on challenging technology solutions internationally supporting engineering, steel fabrication, financial services, government, renewable energy, and the education sector. Vitor joined Watkins Group in 2020 as a Robotics engineer moving to the position of Research and Development (R&D) manager early in 2021 with the responsibility of researching automation and optimisation paths translating the latest technologies in robotics and advanced visualisations into manufacturing. Vitor’s skills include the integration of computer-aided design and computer-aided manufacturing standards with extended reality (XR), the internet of things (IoT) and enterprise software among other technologies supporting interoperability in industrial automation processes.

Jared Donovan