É«ÇéÍøÕ¾

Bushfires are getting more severe and destructive. Due to their fast-spreading nature, bushfires are often detected when already beyond control and consequently cause large-scale effects in a very short time. In this project, we aim to build an autonomous and intelligent system to detect active wildfires by applying deep learning methods on satellite data for timely alerts and adaptivity to unseen environmental events. In particular, we deploy a streaming data visualisation dashboard to support wildfire mitigation specialists in monitoring, identifying, and pro-acting to wildfires. ,

Our modern society is struggling with an unprecedented amount of online fake news, which do harm to democracy, economics, and national security. Creators of fake news optimise their chance to manipulate public opinion and maximise their financial and political gains through sophisticated pollution of our information diffusion channels. This project aims to build a human-powered real-time warning system for helping media fight fake news and restore public’s trust with cost-effective, scalable, robust and streaming techniques on top of large-scale dynamic social networks. Human experts are also employed to validate these emerging stories, guiding algorithmic models to train themselves to become smarter and adaptive to new traits of fake news formation.

The Hub combines world-leading capabilities in machine vision, machine learning, software quality control, engineering, biology, and farming industries to invent and adopt technologies to build more intelligent systems that can automatically determine what goal to achieve in a dynamic environment and the most efficient plan to achieve it.

The outcomes of this Hub will enable higher farming efficiency, lower production costs and disease risks, giving the É«ÇéÍøÕ¾n industry a great advantage in global competition, and creating new business opportunities. ARC Hub

This project aims to investigate structural, coloured textural, and hyperspectral analysis approaches to achieve automated lobster molt-cycle staging and classification to the level required for commercial production. High labour cost, water contamination, and disease transmission are major barriers in É«ÇéÍøÕ¾n bay lobster aquaculture inhibiting its large scale production. Automation of the production process and reducing the human contact with animals are of high priority in the development of this É«ÇéÍøÕ¾n-led emerging industry. The project aims to develop technology to bring this world- first aquaculture factory to large scale production, and create new export opportunities for lobsters and production systems.

This project aims to develop novel and efficient heuristic-based algorithms leading to near accurate protein tertiary structure models. Knowledge about protein structures is fundamental to our understanding of living systems. The progress on experimental determination of these structures has been extremely limited and remains an open challenge in molecular biology. Computational prediction of protein structures from sequences is emerging as a promising approach, but its accuracy is far from satisfactory. The software systems developed in this project will be used in structural identification of target proteins in drug design. This will make drug design process more efficient, saving time and cost, potentially saving lives.

This project aims to study the major technical barrier in plant disease image retrieval to build a pervasive rapid plant disease identification system. The techniques are designed to function on one or very few sample images, thus enabling on-line in field disease identification linked to authoritative plant disease image libraries. The success of this project will not only make significant contributions to fundamental theory in single model image retrieval, but also create a revolution in plant disease early detection for effective and efficient crop protection.

This project aims to improve the robustness and accuracy of automatic speech and speaker recognition systems. Though these systems work reasonably well in noise-free environments, their performance deteriorates drastically even in the presence of a small amount of noise. To overcome this problem, this project proposes a missing-feature approach for robust speech and speaker recognition. This approach is expected to make the speech and speaker recognition systems less sensitive to additive background noise and make them more useful in telecommunications and business.

This project applies Big Data analysis techniques on social media and other data and analyzes how people have been influenced and react to pandemics situation and introduces measures as well as captures different perspectives from multiple stakeholders. Specific attention is given to the four pillars under the State Disaster Management Themes of Prevention, Preparation, Response and eventually Recovery.

The aim of the project is to explore how innovative technologies such as Big Data analytics can be used to allow for appropriate interaction between freight vehicles and the transport network to create mutual benefits to state government agencies, municipal governments and the freight industry. 

Shaanxi Transport and Logistic Information Service Platform is a large and complex software intensive system. It will provide service for thousands of transport and logistic companies in Shaanxi Province, China.  To build it successfully, advanced software engineering techniques must be applied. This project is to investigate the customer’s requirements, apply state of art software engineering technology Behaviour Engineering in the design of implementation of the platform. We will introduce Behaviour Engineering in the area of Software Acquisition to improve its efficiency. It’s expected to produce two high quality papers and might create further collaboration opportunities.

For trust to emerge between humans and intelligent embodied systems, machines need to engage appropriately with both people and the real world. Whether the domain is autonomous vehicles, robotics or synthetic environments, there is a common need for models which can support social and dynamic interactions. Desirable capabilities include socially attuned communication, coping with novelty and an awareness of emerging trust. Unfortunately, current formal models struggle to represent these qualities. When left to our own devices, humans use narrative forms of information to describe and interact in changing situations. By leveraging some features of narrative reasoning, this project models human-machine collaboration in an open world using semantic and graphical grammars, which in turn can lead to new modeling abstractions and platforms.