AI-driven Effective Query Formulation for Better Systematic Reviews. This project aims to develop novel AI-based search engine methods to make the creation of systematic reviews cheaper, faster and unbiased. Systematic reviews are the cornerstone for evidence-based decisions in clinical practice and government policy making. Given the pace new research is published at, it is unsustainable to manually conduct systematic reviews in the traditional manner, taking on average 2 years and $350K and be ....AI-driven Effective Query Formulation for Better Systematic Reviews. This project aims to develop novel AI-based search engine methods to make the creation of systematic reviews cheaper, faster and unbiased. Systematic reviews are the cornerstone for evidence-based decisions in clinical practice and government policy making. Given the pace new research is published at, it is unsustainable to manually conduct systematic reviews in the traditional manner, taking on average 2 years and $350K and becoming already outdated when published. The outcomes of this project will lead to systematic reviews of higher quality, while reducing their financial and temporal costs, providing significant benefits to organisations performing reviews and their funders, and to people impacted by decisions made from the reviews.Read moreRead less
Single model irregular-region retrieval for rapid plant disease detection. 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 th ....Single model irregular-region retrieval for rapid plant disease detection. 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.Read moreRead less